@inproceedings{Rokach13c, author={Lior Rokach, Meir Kalech, Gregory Provan, Alexander Feldman}, year={2013}, booktitle={IJCAI}, title={Machine-Learning-Based Circuit Synthesis}, keywords = {Anomaly detection, Malware detection, Cyber security, Information security}, } @inproceedings{Lena13ce, author={Lena Tenenboim-Chekina, Oren Barad, Asaf Shabtai, Dudu Mimran, Lior Rokach, Bracha Shapira, Yuval Elovici}, year={2013}, booktitle={INFOCOM}, title={Detecting Application Update Attack on Mobile Devices through Network Features}, keywords = {Anomaly detection, Malware detection, Cyber security, Information security}, } @inproceedings{Ofek13b, author={Nir Ofek, Sandor Daranyi, Lior Rokach}, year={2013}, booktitle={Workshop on Computational Models of Narrative}, title={Linking Motif Sequences to Tale Type Families by Machine Learning}, keywords = {Information retrieval, Text mining}, } @inproceedings{Ofek13a, author={Nir Ofek, Cornelia Caragea, Prakhar Biyani, John Yen, Lior Rokach, Prasenjit Mitra}, year={2013}, booktitle={First International Workshop on Public Health in the Digital Age: Social Media, Crowdsourcing and Participatory Systems, WWW, 2013.}, title={Improving Sentiment Analysis in an Online Cancer Survivor Community Using Dynamic Sentiment Lexicon}, keywords = {Information retrieval, Sentiment analysis, Text mining}, } @inproceedings{Sagnik13, author={Sagnik Ray Choudhury, Suppawong Tuarob, Prasenjit Mitra, Lior Rokach, C. Lee Giles}, year={2013}, booktitle={JCDL '13: 13th ACM/IEEE-CS Joint Conference on Digital Libraries Proceedings.}, title={ChemXSeer Figure Search: A Chemical Literature Figure Search Engine}, keywords = {Information retrieval, Information extraction}, } @inproceedings{Rokach13ab, author={Lior Rokach, Prasenjit Mitra, Saurabh Kataria, Wenyi Huang, Lee Giles}, year={2013}, booktitle={The 10th Workshop on Large-Scale Distributed Systems for Information Retrieval, LSDS-IR 2013, Co-located with ACM WSDM 2013}, title={A Supervised Learning Method for Context-Aware Citation Recommendation in a Large Corpus}, ee={http://www.lsdsir.org/wp-content/uploads/2013/02/LSDS-IR-2013-Proceedings.pdf#page=17}, keywords = {Recommender systems, Information retrieval, Scientometrics, Text mining}, } @inproceedings{Lena13b, author={Tenenboim-Chekina, Lena and Rokach, Lior and Shapira, Bracha}, year={2013}, isbn={978-3-642-38066-2}, booktitle={Multiple Classifier Systems}, volume={7872}, series={Lecture Notes in Computer Science}, editor={Zhou, Zhi-Hua and Roli, Fabio and Kittler, Josef}, doi={10.1007/978-3-642-38067-9_26}, title={Ensemble of Feature Chains for Anomaly Detection}, ee={http://dx.doi.org/10.1007/978-3-642-38067-9_26}, publisher={Springer Berlin Heidelberg}, keywords={Ensemble learning, Anomaly detection, Malware detection, Cyber security, Information security}, pages={295-306} } @inproceedings{ArielBar, year={2013}, isbn={978-3-642-38066-2}, booktitle={Multiple Classifier Systems}, volume={7872}, series={Lecture Notes in Computer Science}, editor={Zhou, Zhi-Hua and Roli, Fabio and Kittler, Josef}, doi={10.1007/978-3-642-38067-9_1}, title={Improving Simple Collaborative Filtering Models Using Ensemble Methods}, ee={http://dx.doi.org/10.1007/978-3-642-38067-9_1}, publisher={Springer Berlin Heidelberg}, author={Bar, Ariel and Rokach, Lior and Shani, Guy and Shapira, Bracha and Schclar, Alon}, pages={1-12}, url = {http://arxiv.org/pdf/1211.2891v1}, keywords= {Recommender systems, Collaborative filtering, Ensemble learning} } @inproceedings{DBLP:conf/sac/RokachSSCS13, author = {Lior Rokach and Guy Shani and Bracha Shapira and Eyal Chapnik and Gali Siboni}, title = {Recommending insurance riders}, booktitle = {ACM SAC}, year = {2013}, pages = {253-260}, ee = {http://doi.acm.org/10.1145/2480362.2480417}, isbn = {978-1-4503-1656-9}, crossref = {DBLP:conf/sac/2013}, bibsource = {DBLP, http://dblp.uni-trier.de}, url = {http://www.bgu.ac.il/~shanigu/Publications/insurance.SAC.1.pdf}, keywords = {Recommender systems, Collaborative filtering} } @article{2013_j_2, journal = {Inf. Sci.}, author = {Yael Weiss and Yuval Elovici and Lior Rokach}, title = {The CASH algorithm-cost-sensitive attribute selection using histograms}, ee = {http://dx.doi.org/10.1016/j.ins.2011.01.035}, url = {http://www.ise.bgu.ac.il/faculty/liorr/INFO1.pdf}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {247-268}, volume = {222}, year = {2013}, keywords = {Feature selection, Decision trees, Cost-sensitive learning} } @article{2013_j_5, journal = {ACM Transactions on Intelligent Systems and Technology}, author = {Michael Fire, Lena Tenenboim, Ofrit Lesser, Rami Puzis, Lior Rokach, Yuval Elovici}, title = {Computationally Efficient Link Prediction in Variety of Social Networks}, year = {2013}, keywords = {Link prediction, Social networks, Ensemble learning} } @article{2013_j_4, journal = {JASIST}, author = {Lior Rokach and Prasenjit Mitra}, title = {Parsimonious Citer-Based Measures: Artificial Intelligence Domain as a Case Study}, year = {2013}, keywords = {Scientometrics} } @article{2013_j_3, title = "A GIS-based decision support system for hotel room rate estimation and temporal price prediction: The hotel brokers' context", journal = "Decision Support Systems", volume = "54", number = "2", pages = "1119 - 1133", year = "2013", note = "", issn = "0167-9236", doi = "10.1016/j.dss.2012.10.038", ee = "http://www.sciencedirect.com/science/article/pii/S0167923612003120", author = "Slava Kisilevich and Daniel Keim and Lior Rokach", keywords = {Prediction, Spatial mining, Geospatial} } @article{2013_j_6, journal = {JASIST}, author = {Guy Shani and Lior Rokach and Bracha Shapira and Sarit Hadash and Moran Tangi}, title = {Investigating Confidence Displays for Top-N Recommendations}, year = {2013}, keywords = {Recommender systems, Human computer interaction} } @article{2013_j_1, author = {Maayan Dror and Asaf Shabtai and Lior Rokach and Yuval Elovici}, title = {OCCT: A One-Class Clustering Tree for Implementing One-to-Many Data Linkage}, year = {2013}, journal = {IEEE Trans. Knowl. Data Eng.}, keywords = {Clustering, Decision trees, Data linkage}, } @inproceedings{khal2013, author = {Eliahu Khalastchi and Meir Kalech and Lior Rokach}, title = {Sensor fault detection and diagnosis for autonomous systems}, year = {2013}, booktitle = {The 12th International Conference on Autonomous Agents and Multiagent Systems (AAMAS2013)}, keywords = {Anomaly detection, Diagnosis}, } @inproceedings{DBLP:journals/corr/abs-1212-3540, author = {Yehonatan Bitton and Michael Fire and Dima Kagan and Bracha Shapira and Lior Rokach and Judit Bar-Ilan}, title = {Social Network Based Search for Experts}, year = {2012}, ee = {http://arxiv.org/abs/1212.3540}, booktitle = {Symposium on Human-Computer Interaction and Information Retrieval}, bibsource = {DBLP, http://dblp.uni-trier.de}, keywords = {Scientometrics, Text mining, Information retrieval} } @INPROCEEDINGS{6413889, author={Katz, Gilad and Shabtai, Asaf and Rokach, Lior and Ofek, Nir}, booktitle={Data Mining (ICDM), 2012 IEEE 12th International Conference on}, title={ConfDTree: Improving Decision Trees Using Confidence Intervals}, year={2012}, month={dec.}, volume={}, number={}, pages={339 -348}, abstract={Decision trees have three main disadvantages: reduced performance when the training set is small, rigid decision criteria and the fact that a single #x0022;uncharacteristic #x0022; attribute might #x0022;derail #x0022; the classification process. In this paper we present ConfDTree - a post-processing method which enables decision trees to better classify outlier instances. This method, which can be applied on any decision trees algorithm, uses confidence intervals in order to identify these hard-to-classify instances and proposes alternative routes. The experimental study indicates that the proposed post-processing method consistently and significantly improves the predictive performance of decision trees, particularly for small, imbalanced or multi-class datasets in which an average improvement of 5%-9% in the AUC performance is reported.}, doi={10.1109/ICDM.2012.19}, ee = {http://dx.doi.org/10.1109/ICDM.2012.19}, url = {http://www.ise.bgu.ac.il/faculty/liorr/confdtree.pdf}, keywords= {Decision trees}, ISSN={1550-4786}} @article{2012_rokachinitial, journal = {IEEE Transactions on Systems, Man, and Cybernetics, Part C}, author = {Rokach, L. and Kisilevich, S.}, title = {Initial Profile Generation in Recommender Systems Using Pairwise Comparison}, doi = {10.1109/TSMCC.2012.2197679}, ee = {http://dx.doi.org/10.1109/TSMCC.2012.2197679}, url = {http://www.ise.bgu.ac.il/faculty/liorr/pairwise2.pdf}, year={2012}, month={nov.}, volume={42}, number={6}, pages={1854-1859}, publisher = {IEEE}, abstract={Most recommender systems, such as collaborative filtering, cannot provide personalized recommendations until a user profile has been created. This is known as the new user cold-start problem. Several systems try to learn the new users #x2019; profiles as part of the sign up process by asking them to provide feedback regarding several items. We present a new, anytime preferences elicitation method that uses the idea of pairwise comparison between items. Our method uses a lazy decision tree, with pairwise comparisons at the decision nodes. Based on the user #x2019;s response to a certain comparison, we select on-the-fly what pairwise comparison should next be asked. A comparative field study has been conducted to examine the suitability of the proposed method for eliciting the user #x2019;s initial profile. The results indicate that the proposed pairwise approach provides more accurate recommendations than existing methods and requires less effort when signing up newcomers.}, keywords = {Preferences elicitation, Recommender systems, Cold-start, Collaborative filtering} } @article{2012_6392468, author={Schclar, A. and Rokach, L. and Abramson, A. and Elovici, Y.}, journal={IEEE Transactions on Systems, Man, and Cybernetics, Part C}, title={User Authentication Based on Representative Users}, year={2012}, month={nov. }, volume={42}, number={6}, pages={1669-1678}, ee = {http://dx.doi.org/10.1109/TSMCC.2012.2215850}, url = {http://www.ise.bgu.ac.il/faculty/liorr/userauth2.pdf}, keywords={Information security, Cyber security, Authentication, Clustering, Feature extraction, Behavioral biometrics, Keystroke dynamics}, abstract={User authentication based on username and password is the most common means to enforce access control. This form of access restriction is prone to hacking since stolen usernames and passwords can be exploited to impersonate legitimate users in order to commit malicious activity. Biometric authentication incorporates additional user characteristics such as the manner by which the keyboard is used in order to identify users. We introduce a novel approach for user authentication based on the keystroke dynamics of the password entry. A classifier is tailored to each user and the novelty lies in the manner by which the training set is constructed. Specifically, only the keystroke dynamics of a small subset of users, which we refer to as representatives, is used along with the password entry keystroke dynamics of the examined user. The contribution of this approach is twofold: it reduces the possibility of overfitting, while allowing scalability to a high volume of users. We propose two strategies to construct the subset for each user. The first selects the users whose keystroke profiles govern the profiles of all the users, while the second strategy chooses the users whose profiles are the most similar to the profile of the user for whom the classifier is constructed. Results are promising reaching in some cases 90 #x0025; area under the curve. In many cases, a higher number of representatives deteriorate the accuracy which may imply overfitting. An extensive evaluation was performed using a dataset containing over 780 users.}, doi={10.1109/TSMCC.2012.2215850}, ISSN={1094-6977} } @InCollection{DBLP:books/igi/Erickson09/RokachE09, author = {Lior Rokach and Yuval Elovici}, title = {An Overview of IDS Using Anomaly Detection}, ee = {http://www.igi-global.com/Bookstore/Chapter.aspx?TitleId=7922}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {384-394}, booktitle = {Database Technologies: Concepts, Methodologies, Tools, and Applications}, year = {2009}, keywords={Information security, Cyber security, Anomaly detection, Intrusion detection} } @InCollection{DBLP:books/sp/datamining2005/MaimonR05, author = {Oded Maimon and Lior Rokach}, title = {Introduction to Knowledge Discovery in Databases}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {1-17}, booktitle = {The Data Mining and Knowledge Discovery Handbook}, url = {http://www.ise.bgu.ac.il/faculty/liorr/hbchap1.pdf}, year = {2005}, keywords = {Data mining} } @InCollection{DBLP:books/sp/datamining2005/MaimonR05a, author = {Oded Maimon and Lior Rokach}, title = {Introduction to Supervised Methods}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {149-164}, booktitle = {The Data Mining and Knowledge Discovery Handbook}, url = {http://www.ise.bgu.ac.il/faculty/liorr/hbchap8.pdf}, year = {2005}, keywords = {Supervised learning} } @InCollection{DBLP:books/sp/datamining2005/MaimonR05b, author = {Oded Maimon and Lior Rokach}, title = {Decomposition Methodology for Knowledge Discovery and Data Mining}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {981-1003}, booktitle = {The Data Mining and Knowledge Discovery Handbook}, url = {http://www.ise.bgu.ac.il/faculty/liorr/hbchap46.pdf}, year = {2005}, keywords = {Ensemble learning, Decomposition} } @InCollection{DBLP:books/sp/datamining2005/Rokach05, author = {Lior Rokach}, title = {Ensemble Methods for Classifiers}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {957-980}, booktitle = {The Data Mining and Knowledge Discovery Handbook}, url = {http://www.ise.bgu.ac.il/faculty/liorr/hbchap45.pdf}, year = {2005}, keywords = {Ensemble learning} } @InCollection{DBLP:books/sp/datamining2005/RokachM05, author = {Lior Rokach and Oded Maimon}, title = {Decision Trees}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {165-192}, url = {http://www.ise.bgu.ac.il/faculty/liorr/hbchap9.pdf}, booktitle = {The Data Mining and Knowledge Discovery Handbook}, year = {2005}, keywords = {Decision trees} } @InCollection{DBLP:books/sp/datamining2005/RokachM05a, author = {Lior Rokach and Oded Maimon}, title = {Clustering Methods}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {321-352}, booktitle = {The Data Mining and Knowledge Discovery Handbook}, url = {http://www.ise.bgu.ac.il/faculty/liorr/hbchap15.pdf}, year = {2005}, keywords = {Clustering} } @book{DBLP:books/sp/DM2005, editor = {Oded Maimon and Lior Rokach}, title = {The Data Mining and Knowledge Discovery Handbook}, bibsource = {DBLP, http://dblp.uni-trier.de}, isbn = {0-387-24435-2}, year = {2005}, publisher = {Springer}, keywords = {Data mining} } @book{dlpbook, author = {Asaf Shabtai and Yuval Elovici and Lior Rokach}, title = {A Survey of Data Leakage Detection and Prevention Solutions}, isbn = {978-1-4614-2053-8}, year = {2012}, publisher = {Springer}, keywords = {Information security, Data leakage, Cyber security} } @inproceedings{DBLP:conf/amt/FireKESR12, author = {Michael Fire and Gilad Katz and Yuval Elovici and Bracha Shapira and Lior Rokach}, title = {Predicting Student Exams Scores by Analyzing Social Network Data}, ee = {http://dx.doi.org/10.1007/978-3-642-35236-2_59}, url = {http://www.ise.bgu.ac.il/faculty/liorr/fire2012predicting.pdf}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {584-595}, booktitle = {Active Media Technology - 8th International Conference, AMT 2012, Macau, China, December 4-7, 2012. Proceedings}, year = {2012}, keywords = {Social networks, Supervised learning, Prediction} } @InProceedings{DBLP:conf/awic/Ben-ShimonTRMSN07, author = {David Ben-Shimon and Alexander Tsikinovsky and Lior Rokach and Amnon Meisels and Guy Shani and Lihi Naamani}, title = {Recommender System from Personal Social Networks}, ee = {http://dx.doi.org/10.1007/978-3-540-72575-6_8}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {47-55}, booktitle = {Advances in Intelligent Web Mastering, Proceedings of the 5th Atlantic Web Intelligence Conference - AWIC 2007, Fontainebleau, France, June 25 - 27, 2007}, year = {2007}, keywords = {Social networks, Recommender systems} } @InProceedings{DBLP:conf/ccs/GafnySRE11, author = {Ma'ayan Gafny and Asaf Shabtai and Lior Rokach and Yuval Elovici}, title = {Poster: applying unsupervised context-based analysis for detecting unauthorized data disclosure}, ee = {http://doi.acm.org/10.1145/2093476.2093488}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {765-768}, booktitle = {Proceedings of the 18th ACM Conference on Computer and Communications Security, CCS 2011, Chicago, Illinois, USA, October 17-21, 2011}, year = {2011}, keywords = {Information security, Cyber security, Access control, Unsupervised learning, Clustering} } @InProceedings{DBLP:conf/cidm/ShaniRMNPB07, author = {Guy Shani and Lior Rokach and Amnon Meisels and Lihi Naamani and Nischal M. Piratla and David Ben-Shimon}, title = {Establishing User Profiles in the MediaScout Recommender System}, ee = {http://doi.ieeecomputersociety.org/10.1109/CIDM.2007.368912}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {470-476}, booktitle = {Proceedings of the IEEE Symposium on Computational Intelligence and Data Mining, CIDM 2007, part of the IEEE Symposium Series on Computational Intelligence 2007, Honolulu, Hawaii, USA, 1-5 April 2007}, year = {2007}, abstract={The MediaScout system is envisioned to function as personalized media (audio, video, print) service within mobile phones, online media portals, sling boxes, etc. The MediaScout recommender engine uses a novel stereotype-based recommendation engine. Upon the registration of new users the system must decide how to classify the new users to existing stereotypes. In this paper we present a method to achieve this classification through an anytime, interactive questionnaire, created automatically upon the generation of new stereotypes. A comparative study performed on the IMDB database illustrates the advantages of the new system}, doi={10.1109/CIDM.2007.368912}, keywords = {Recommender systems, Preferences elicitation, Cold-start, Collaborative filtering} } @InProceedings{DBLP:conf/cikm/HuangKCMGR12, author = {Wenyi Huang and Saurabh Kataria and Cornelia Caragea and Prasenjit Mitra and C. Lee Giles and Lior Rokach}, title = {Recommending citations: translating papers into references}, ee = {http://doi.acm.org/10.1145/2396761.2398542}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {1910-1914}, booktitle = {21st ACM International Conference on Information and Knowledge Management, CIKM'12, Maui, HI, USA, October 29 - November 02, 2012}, year = {2012}, keywords = {Recommender systems, Information retrieval} } @InProceedings{DBLP:conf/cikm/MorenoSRS12, author = {Orly Moreno and Bracha Shapira and Lior Rokach and Guy Shani}, title = {TALMUD: transfer learning for multiple domains}, ee = {http://doi.acm.org/10.1145/2396761.2396817}, url = {http://www.ise.bgu.ac.il/faculty/liorr/moreno2012talmud.pdf}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {425-434}, booktitle = {21st ACM International Conference on Information and Knowledge Management, CIKM'12, Maui, HI, USA, October 29 - November 02, 2012}, year = {2012}, keywords = {Recommender systems, Transfer learning, Collaborative filtering} } @InProceedings{DBLP:conf/cis/ShimshonMRE10, author = {Tomer Shimshon and Robert Moskovitch and Lior Rokach and Yuval Elovici}, title = {Continuous Verification Using Keystroke Dynamics}, ee = {http://doi.ieeecomputersociety.org/10.1109/CIS.2010.95}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {411-415}, booktitle = {2010 International Conference on Computational Intelligence and Security, CIS 2010, Nanning, Guangxi Zhuang Autonomous Region, China, December 11-14, 2010}, year = {2010}, abstract={Traditionally user authentication is based on a username and password. However, a logged station is still vulnerable to imposters when the user leaves her computer without logging-off. Keystroke dynamics methods can be useful for continuously verifying a user once the authentication process has successfully ended. However, current methods require long sessions and significant amounts of keystrokes to reliably verify users. We propose a new method that compactly represents the keystroke patterns by joining similar pairs of consecutive keystrokes. This automatically created representation reduces the session size required for inducing the user's verification model. The proposed method was evaluated on 21 legitimate users and 165 attackers. The results were encouraging and suggest that the detection performance of the proposed method is better than that of existing methods. Specifically we attained a false acceptance rate (FAR) of 3.47% and false rejection rate (FRR) of 0% using only 250 keystrokes.}, doi={10.1109/CIS.2010.95}, keywords = {Information security, Cyber security, Keystroke dynamics, Authentication, Behavioral biometrics} } @InProceedings{DBLP:conf/foiks/MaimonR02, author = {Oded Maimon and Lior Rokach}, title = {Improving Supervised Learning by Feature Decomposition}, ee = {http://dx.doi.org/10.1007/3-540-45758-5_12}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {178-196}, booktitle = {Foundations of Information and Knowledge Systems, Second International Symposium, FoIKS 2002 Salzau Castle, Germany, February 20-23, 2002, Proceedings}, year = {2002}, keywords = {Ensemble learning, Decomposition, Feature selection} } @InProceedings{DBLP:conf/fqas/RokachMA04, author = {Lior Rokach and Oded Maimon and Mordechai Averbuch}, title = {Information Retrieval System for Medical Narrative Reports}, ee = {http://dx.doi.org/10.1007/978-3-540-25957-2_18}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {217-228}, booktitle = {Flexible Query Answering Systems, 6th International Conference, FQAS 2004, Lyon, France, June 24-26, 2004, Proceedings}, year = {2004}, keywords = {Information retrieval, Medical informatics, Text mining} } @InProceedings{DBLP:conf/grc/RokachM05, author = {Lior Rokach and Oded Maimon}, title = {Decomposition methodology for classification tasks}, ee = {http://doi.ieeecomputersociety.org/10.1109/GRC.2005.1547369}, url = {http://www.ise.bgu.ac.il/faculty/liorr/PAA.pdf}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {636-641}, booktitle = {2005 IEEE International Conference on Granular Computing, Beijing, China, July 25-27, 2005}, year = {2005}, abstract={ The idea of decomposition methodology is to break down a complex data mining task into several smaller, less complex and more manageable, sub-tasks that are solvable by using existing tools, then joining their solutions together in order to solve the original problem. In this paper we provide an overview of decomposition methods in classification tasks with emphasis on elementary decomposition methods. We present the main properties that characterize various decomposition frameworks and the advantages of using these framework. Finally we discuss the uniqueness of decomposition methodology as opposed to other closely related fields, such as ensemble methods and distributed data mining.}, doi={10.1109/GRC.2005.1547369}, keywords = {Ensemble learning, Decomposition, Meta-learning} } @article{2012_DBLP:journals/ijgcrsis/RokachS12, author = {Lior Rokach and Alon Schclar}, title = {k-anonymised reducts}, journal = {IJGCRSIS}, volume = {2}, number = {3}, year = {2012}, pages = {196-210}, ee = {http://dx.doi.org/10.1504/IJGCRSIS.2012.047015}, url = {http://www.ise.bgu.ac.il/faculty/liorr/XROKACH.pdf}, bibsource = {DBLP, http://dblp.uni-trier.de}, keywords = {Privacy, Anonymization, Information security} } @inproceedings{DBLP:conf/grc/RokachS10, author = {Lior Rokach and Alon Schclar}, title = {k-Anonymized Reducts}, ee = {http://dx.doi.org/10.1109/GrC.2010.162}, url = {http://www.ise.bgu.ac.il/faculty/liorr/XROKACH.pdf}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {392-395}, booktitle = {2010 IEEE International Conference on Granular Computing, GrC 2010, San Jose, California, USA, 14-16 August 2010}, year = {2010}, pages={392 -395}, abstract={Privacy preserving data mining aims to prevent the violation of privacy that might result from mining of sensitive data. This is commonly achieved by data anonymization. One way to anonymize data is adherence to the k-anonymity concept which requires that the probability to identify an individual by linking databases not to exceed 1/k. In this paper we propose an algorithm which utilizes rough set theory to achieve k-anonymity. The basic idea is to partition the original dataset into several disjoint reducts such that each one of them adheres to k-anonymity. We show that it is easier to make each reduct comply with k-anonymity if it does not contain all quasi-identifier attributes. Moreover, our procedure ensures that even if the attacker attempts to rejoin the reducts, the k-anonymity is still preserved.}, doi={10.1109/GrC.2010.162}, keywords = {Privacy, Anonymization, Information security} } @InProceedings{DBLP:conf/icdm/ChekinaRS11, author = {Lena Chekina and Lior Rokach and Bracha Shapira}, title = {Meta-learning for Selecting a Multi-label Classification Algorithm}, ee = {http://doi.ieeecomputersociety.org/10.1109/ICDMW.2011.118}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {220-227}, booktitle = {Data Mining Workshops (ICDMW), 2011 IEEE 11th International Conference on, Vancouver, BC, Canada, December 11, 2011}, year = {2011}, abstract={Although various algorithms for multi-label classification have been developed in recent years, there is little, if any, information as to when each method is beneficial. The main goal of this paper is to compare the classification performance of several multi-label algorithms and to develop a set of rules or tools that will help in selecting the optimal algorithm according to a specific dataset and target evaluation measure. We utilize a meta-learning approach allowing fast automatic selection of the most appropriate algorithm for an unseen dataset based on its descriptive characteristics. We also define a list of characteristics specific for multi-label datasets. The experimental results indicate the applicability and usefulness of the meta-learning approach.}, doi={10.1109/ICDMW.2011.118}, keywords = {Meta-learning, Multi-label classification, Ensemble learning} } @InProceedings{DBLP:conf/icdm/RokachM01, author = {Lior Rokach and Oded Maimon}, title = {Theory and Applications of Attribute Decomposition}, ee = {http://doi.ieeecomputersociety.org/10.1109/ICDM.2001.989554}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {473-480}, booktitle = {Proceedings of the 2001 IEEE International Conference on Data Mining, 29 November - 2 December 2001, San Jose, California, USA}, year = {2001}, abstract={This paper examines the attribute decomposition approach with simple Bayesian combination for dealing with classification problems that contain high number of attributes and moderate numbers of records. According to the attribute decomposition approach, the set of input attributes is automatically decomposed into several subsets. A classification model is built for each subset, then all the models are combined using simple Bayesian combination. This paper presents theoretical and practical foundation for the attribute decomposition approach. A greedy procedure, called D-IFN, is developed to decompose the input attributes set into subsets and build a classification model for each subset separately. The results achieved in the empirical compart. son testing with well-known classification methods (like C4.5) indicate the superiority of the decomposition approach}, doi={10.1109/ICDM.2001.989554}, keywords = {Decomposition, Ensemble learning} } @InProceedings{DBLP:conf/icdm/RomanoRM06, author = {Roni Romano and Lior Rokach and Oded Maimon}, title = {Cascaded Data Mining Methods for Text Understanding, with medical case study}, ee = {http://doi.ieeecomputersociety.org/10.1109/ICDMW.2006.38}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {458-462}, booktitle = {Workshops Proceedings of the 6th IEEE International Conference on Data Mining (ICDM 2006), 18-22 December 2006, Hong Kong, China}, year = {2006}, abstract={Substantial electronically stored textual data such as clinical narratives reports often need to be retrieved to find relevant information for clinical and research purposes. The context of negation, a negative finding, is of special importance, since many of the most frequently described findings are such. Hence, when searching free-text narratives for patients with a certain medical condition, if negation is not taken into account, many of the documents retrieved were irrelevant. We present a new cascaded pattern learning method for automatic identification of negative context in clinical narratives reports. Studying the training corpuses, the classification errors and patterns selected by the classifier, we noticed that it is possible to create a more powerful ensemble structure than the structure obtained from general-purpose ensemble method (such as Adaboost). We compare the new algorithm to previous methods proposed for the same task of similar medical narratives, and show its advantages: accuracy improvement compared to other machine learning methods, and much faster than manual knowledge engineering techniques with matching accuracy}, doi={10.1109/ICDMW.2006.38}, keywords = {Information retrieval, Medical informatics, Ensemble learning, Text mining, Sequence mining} } @InProceedings{DBLP:conf/iceis/KisilevichKBTR11, author = {Slava Kisilevich and Daniel A. Keim and Roman Byshko and Michael Tsibelman and Lior Rokach}, title = {Developing a Price Management Decision Support System for Hotel Brokers using Free and Open Source Tools}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {147-156}, booktitle = {ICEIS 2011 - Proceedings of the 13th International Conference on Enterprise Information Systems, Volume 2, Beijing, China, 8-11 June, 2011}, url = {http://bib.dbvis.de/uploadedFiles/360.pdf}, year = {2011}, keywords = {Prediction, Spatial mining, Geospatial} } @incollection{DBLP:conf/iceis/KisilevichKLBR10, author = {Slava Kisilevich and Daniel A. Keim and Amit Lasry and Leon Bam and Lior Rokach}, title = {Developing Analytical GIS Applications with GEO-SPADE: Three Success Case Studies}, ee = {http://dx.doi.org/10.1007/978-3-642-19802-1_34}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {495-511}, booktitle = {Enterprise Information Systems}, year = {2011}, series = {Lecture Notes in Business Information Processing}, editor = {Filipe, J. and Cordeiro, J.}, volume = {73}, keywords = {Spatial mining, Geospatial} } @inproceedings{DBLP:conf/iceis/KisilevichKR10, author = {Slava Kisilevich and Daniel A. Keim and Lior Rokach}, title = {GEO-SPADE - A Generic Google Earth-based Framework for Analyzing and Exploring Spatio-temporal Data}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {13-20}, booktitle = {ICEIS 2010 - Proceedings of the 12th International Conference on Enterprise Information Systems, Volume 5, HCI, Funchal, Madeira, Portugal, June 8 - 12, 2010}, year = {2010}, keywords = {Spatial mining, Geospatial} } @inproceedings{DBLP:conf/iceis/OssmyTPRIE11, author = {Ori Ossmy and Ofir Tam and Rami Puzis and Lior Rokach and Ohad Inbar and Yuval Elovici}, title = {MindDesktop - Computer Accessibility for Severely Handicapped}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {316-320}, booktitle = {ICEIS 2011 - Proceedings of the 13th International Conference on Enterprise Information Systems, Volume 4, Beijing, China, 8-11 June, 2011}, year = {2011}, url = {http://www.ise.bgu.ac.il/faculty/liorr/MindDesktop2.pdf}, keywords = {Human computer interaction} } @inproceedings{DBLP:conf/iceis/RokachMS08, author = {Lior Rokach and Amnon Meisels and Alon Schclar}, title = {Anytime AHP Method for Preferences Elicitation in Stereotype-Based Recommender System}, bibsource = {DBLP, http://dblp.uni-trier.de}, url = {http://www.ise.bgu.ac.il/faculty/liorr/AHPShort.pdf}, pages = {268-275}, booktitle = {ICEIS 2008 - Proceedings of the Tenth International Conference on Enterprise Information Systems, Volume AIDSS, Barcelona, Spain, June 12-16, 2008}, year = {2008}, keywords = {Preferences elicitation, Recommender systems, Cold-start} } @inproceedings{DBLP:conf/iceis/RokachRM06, author = {Lior Rokach and Roni Romano and Oded Maimon}, title = {Automatic Identification of Negated Concepts in Narrative Clinical Reports}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {257-262}, booktitle = {ICEIS 2006 - Proceedings of the Eighth International Conference on Enterprise Information Systems: Databases and Information Systems Integration, Paphos, Cyprus, May 23-27, 2006}, year = {2006}, keywords = {Information retrieval, Medical informatics, Text mining, Sequence mining} } @InProceedings{DBLP:conf/iceis/SchclarR09, author = {Alon Schclar and Lior Rokach}, title = {Random Projection Ensemble Classifiers}, ee = {http://dx.doi.org/10.1007/978-3-642-01347-8_26}, url = {http://www.ise.bgu.ac.il/faculty/liorr/randproj.pdf}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {309-316}, booktitle = {Enterprise Information Systems, 11th International Conference, ICEIS 2009, Milan, Italy, May 6-10, 2009. Proceedings}, year = {2009}, keywords = {Ensemble learning} } @InProceedings{DBLP:conf/iics/GershmanMLRSS10, author = {Amir Gershman and Amnon Meisels and Karl-Heinz Luke and Lior Rokach and Alon Schclar and Arnon Sturm}, title = {A Decision Tree Based Recommender System}, ee = {http://subs.emis.de/LNI/Proceedings/Proceedings165/article5634.html}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {170-179}, booktitle = {10th International Conference on Innovative Internet Community Services (I$^{\mbox{2}}$CS), Jubilee Edition 2010, June 3-5, 2010, Bangkok, Thailand}, year = {2010}, keywords = {Recommender systems, Decision trees} } @InProceedings{DBLP:conf/iics/RokachLAS11, author = {Lior Rokach and Karl-Heinz Luke and Aykan Aydin and Roland Schwaiger}, title = {Recommenders Benchmark Framework}, ee = {http://subs.emis.de/LNI/Proceedings/Proceedings186/article6352.html}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {115-126}, booktitle = {11th International Conference on Innovative Internet Community Services (I$^{\mbox{2}}$CS 2011), June 15-17, 2011, Deutsche Telekom Laboratories, Berlin, Germany}, year = {2011}, keywords = {Recommender systems, Evaluation} } @inproceedings{DBLP:conf/ijcci/SchclarRA12, author = {Alon Schclar and Lior Rokach and Amir Amit}, title = {Diffusion Ensemble Classifiers}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {443-450}, booktitle = {IJCCI 2012 - Proceedings of the 4th International Joint Conference on Computational Intelligence, Barcelona, Spain, 5 - 7 October, 2012}, year = {2012}, keywords = {Ensemble learning} } @InProceedings{DBLP:conf/isi/BercovitchRHSRE11, author = {Maya Bercovitch and Meir Renford and Lior Hasson and Asaf Shabtai and Lior Rokach and Yuval Elovici}, title = {HoneyGen: An automated honeytokens generator}, ee = {http://dx.doi.org/10.1109/ISI.2011.5984063}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {131-136}, booktitle = {2011 IEEE International Conference on Intelligence and Security Informatics, ISI 2011, Beijing, China, 10-12 July, 2011}, year = {2011}, abstract={Honeytokens are artificial digital data items planted deliberately into a genuine system resource in order to detect unauthorized attempts to use information. The honeytokens are characterized by properties which make them appear as genuine data items. Honeytokens are also accessible to potential attackers who intend to violate an organization's security in an attempt to mine information in a malicious manner. One of the main challenges in generating honeytokens is creating data items that appear as real and that are difficult to distinguish from real tokens. In this paper we present #x201C;HoneyGen #x201D; - a novel method for generating honeytokens automatically. HoneyGen creates honeytokens that are similar to the real data by extrapolating the characteristics and properties of real data items. The honeytoken generation process consists of three main phases: rule mining in which various types of rules that characterize the real data are extracted from the production database; honeytoken generation in which an artificial relational database is generated based on the extracted rules; and the likelihood rating in which a score is calculated for each honeytoken based on its similarity to the real data. A Turing-like test was performed in order to evaluate the ability of the method to generate honeytokens that cannot be detected by humans as honeytokens. The results indicate that participants were unable to distinguish honeytokens having a high likelihood score from real tokens.}, doi={10.1109/ISI.2011.5984063}, keywords = {Cyber security, Information security} } @InProceedings{DBLP:conf/isi/HarelSRE11, author = {Amir Harel and Asaf Shabtai and Lior Rokach and Yuval Elovici}, title = {Dynamic Sensitivity-Based Access Control}, ee = {http://dx.doi.org/10.1109/ISI.2011.5984080}, url = {http://www.ise.bgu.ac.il/faculty/liorr/CONF1.pdf}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {201-203}, booktitle = {2011 IEEE International Conference on Intelligence and Security Informatics, ISI 2011, Beijing, China, 10-12 July, 2011}, year = {2011}, abstract={In this paper we propose a new access control mechanism, Dynamic Sensitivity-Based Access Control (DSBAC), designed to regulate users' access to sensitive data stored in relational databases. The DSBAC is an extension of the basic mandatory access control (MAC) mechanism, and it uses the M-score (Misuseability score) measure in order to assign, dynamically, an access class to each set of tuples.}, doi={10.1109/ISI.2011.5984080}, keywords = {Cyber security, Information security, Access control} } @InProceedings{DBLP:conf/isi/MoskovitchFMKMCLHMRE09, author = {Robert Moskovitch and Clint Feher and Arik Messerman and Niklas Kirschnick and Tarik Mustafic and Seyit Ahmet \c{C}amtepe and Bernhard L{\"o}hlein and Ulrich Heister and Sebastian M{\"o}ller and Lior Rokach and Yuval Elovici}, title = {Identity theft, computers and behavioral biometrics}, ee = {http://dx.doi.org/10.1109/ISI.2009.5137288}, doi={10.1109/ISI.2009.5137288}, url = {http://www.ise.bgu.ac.il/faculty/liorr/idth.pdf}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {155-160}, booktitle = {IEEE International Conference on Intelligence and Security Informatics, ISI 2009, Dallas, Texas, USA, June 8-11, 2009, Proceedings}, year = {2009}, abstract={The increase of online services, such as eBanks, WebMails, in which users are verified by a username and password, is increasingly exploited by identity theft procedures. Identity Theft is a fraud, in which someone pretends to be someone else is order to steal money or get other benefits. To overcome the problem of identity Theft an additional security layer is required. Within the last decades the option of verifying users based on their keystroke dynamics was proposed during login verification. Thus, the imposter has to be able to type in a similar way to the real user in addition to having the username and password. However, verifying users upon login is not enough, since a logged station/mobile is vulnerable for imposters when the user leaves her machine. Thus, verifying users continuously based on their activities is required. Within the last decade there is a growing interest and use of biometrics tools, however, these are often costly and require additional hardware. Behavioral biometrics, in which users are verified, based on their keyboard and mouse activities, present potentially a good solution. In this paper we discuss the problem of identity theft and propose behavioral biometrics as a solution. We survey existing studies and list the challenges and propose solutions.}, keywords = {Information security, Cyber security, Keystroke dynamics, Authentication, Behavioral biometrics} } @InProceedings{DBLP:conf/isips/KisilevichESR08, author = {Slava Kisilevich and Yuval Elovici and Bracha Shapira and Lior Rokach}, title = {kACTUS 2: Privacy Preserving in Classification Tasks Using k-Anonymity}, ee = {http://dx.doi.org/10.1007/978-3-642-10233-2_7}, url = {http://www.ise.bgu.ac.il/faculty/liorr/kactus2.pdf}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {63-81}, booktitle = {Protecting Persons While Protecting the People, Second Annual Workshop on Information Privacy and National Security, ISIPS 2008, New Brunswick, NJ, USA, May 12, 2008. Revised Selected Papers}, year = {2008}, keywords = {Privacy, Anonymization, Information security} } @InProceedings{DBLP:conf/ismis/RokachML03, author = {Lior Rokach and Oded Maimon and Inbal Lavi}, series = {Lecture Notes in Artificial Intelligence}, title = {Space Decomposition in Data Mining: A Clustering Approach}, ee = {http://dx.doi.org/10.1007/978-3-540-39592-8_5}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {24-31}, volume = {2871}, booktitle = {Foundations of Intelligent Systems, 14th International Symposium, ISMIS 2003, Maebashi City, Japan, October 28-31, 2003, Proceedings}, year = {2003}, keywords = {Ensemble learning, Decomposition} } @InProceedings{DBLP:conf/kcap/HarelSRE11, author = {Amir Harel and Asaf Shabtai and Lior Rokach and Yuval Elovici}, title = {Eliciting domain expert misuseability conceptions}, ee = {http://doi.acm.org/10.1145/1999676.1999721}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {193-194}, booktitle = {Proceedings of the 6th International Conference on Knowledge Capture (K-CAP 2011), June 26-29, 2011, Banff, Alberta, Canada}, year = {2011}, keywords = {Preferences elicitation, Information security, Data misuse, Cyber security, Data leakage} } @InProceedings{DBLP:conf/mobicase/WeissFER10, author = {Yael Weiss and Yuval Fledel and Yuval Elovici and Lior Rokach}, title = {Cost-Sensitive Detection of Malicious Applications in Mobile Devices}, ee = {http://dx.doi.org/10.1007/978-3-642-29336-8_27}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {382-395}, booktitle = {Mobile Computing, Applications, and Services - Second International ICST Conference, MobiCASE 2010, Santa Clara, CA, USA, October 25-28, 2010, Revised Selected Papers}, year = {2010}, keywords = {Feature selection, Malware detection, Cyber security, Information security} } @InProceedings{DBLP:conf/ngits/RomanoRM06, author = {Roni Romano and Lior Rokach and Oded Maimon}, title = {Automatic Discovery of Regular Expression Patterns Representing Negated Findings in Medical Narrative Reports}, ee = {http://dx.doi.org/10.1007/11780991_26}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {300-311}, booktitle = {Next Generation Information Technologies and Systems, 6th International Workshop, NGITS 2006, Kibbutz Shefayim, Israel, July 4-6, 2006, Proceedings}, year = {2006}, keywords = {Information retrieval, Medical informatics, Text mining, Sequence mining} } @InProceedings{DBLP:conf/recsys/DayanKBRSASF11, author = {Aviram Dayan and Guy Katz and Naseem Biasdi and Lior Rokach and Bracha Shapira and Aykan Aydin and Roland Schwaiger and Radmila Fishel}, title = {Recommenders benchmark framework}, ee = {http://doi.acm.org/10.1145/2043932.2044003}, url = {http://www.ise.bgu.ac.il/faculty/liorr/CONF4.pdf}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {353-354}, booktitle = {Proceedings of the 2011 ACM Conference on Recommender Systems, RecSys 2011, Chicago, IL, USA, October 23-27, 2011}, year = {2011}, keywords = {Recommender systems} } @InProceedings{DBLP:conf/recsys/DeryKRS10, author = {Lihi Naamani Dery and Meir Kalech and Lior Rokach and Bracha Shapira}, title = {Iterative voting under uncertainty for group recommender systems}, ee = {http://doi.acm.org/10.1145/1864708.1864763}, url = {http://www.ise.bgu.ac.il/faculty/liorr/CONF6.pdf}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {265-268}, booktitle = {Proceedings of the 2010 ACM Conference on Recommender Systems, RecSys 2010, Barcelona, Spain, September 26-30, 2010}, year = {2010}, keywords = {Recommender systems, Voting, Active learning} } @InProceedings{DBLP:conf/recsys/KatzOSRS11, author = {Gilad Katz and Nir Ofek and Bracha Shapira and Lior Rokach and Guy Shani}, title = {Using Wikipedia to boost collaborative filtering techniques}, ee = {http://doi.acm.org/10.1145/2043932.2043984}, url = {http://www.ise.bgu.ac.il/faculty/liorr/CONF3.pdf}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {285-288}, booktitle = {Proceedings of the 2011 ACM Conference on Recommender Systems, RecSys 2011, Chicago, IL, USA, October 23-27, 2011}, year = {2011}, keywords = {Recommender systems, Collaborative filtering} } @InProceedings{DBLP:conf/recsys/SchclarTRMA09, author = {Alon Schclar and Alexander Tsikinovsky and Lior Rokach and Amnon Meisels and Liat Antwarg}, title = {Ensemble methods for improving the performance of neighborhood-based collaborative filtering}, ee = {http://doi.acm.org/10.1145/1639714.1639763}, url = {http://www.ise.bgu.ac.il/faculty/liorr/sp142-schclar.pdf}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {261-264}, booktitle = {Proceedings of the 2009 ACM Conference on Recommender Systems, RecSys 2009, New York, NY, USA, October 23-25, 2009}, year = {2009}, keywords = {Recommender systems, Collaborative filtering, Ensemble learning} } @InProceedings{DBLP:conf/socialcom/FireTLPRE11, author = {Michael Fire and Lena Tenenboim and Ofrit Lesser and Rami Puzis and Lior Rokach and Yuval Elovici}, title = {Link Prediction in Social Networks Using Computationally Efficient Topological Features}, ee = {http://doi.ieeecomputersociety.org/10.1109/PASSAT/SocialCom.2011.20}, url = {http://www.ise.bgu.ac.il/faculty/liorr/CONF5.pdf}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {73-80}, booktitle = {PASSAT/SocialCom 2011, Privacy, Security, Risk and Trust (PASSAT), 2011 IEEE Third International Conference on and 2011 IEEE Third International Confernece on Social Computing (SocialCom), Boston, MA, USA, 9-11 Oct., 2011}, year = {2011}, abstract={Online social networking sites have become increasingly popular over the last few years. As a result, new interdisciplinary research directions have emerged in which social network analysis methods are applied to networks containing hundreds millions of users. Unfortunately, links between individuals may be missing due to imperfect acquirement processes or because they are not yet reflected in the online network (i.e., friends in real world did not form a virtual connection.) Existing link prediction techniques lack the scalability required for full application on a continuously growing social network which may be adding everyday users with thousands of connections. The primary bottleneck in link prediction techniques is extracting structural features required for classifying links. In this paper we propose a set of simple, easy-to-compute structural features that can be analyzed to identify missing links. We show that a machine learning classifier trained using the proposed simple structural features can successfully identify missing links even when applied to a hard problem of classifying links between individuals who have at least one common friend. A new friends measure that we developed is shown to be a good predictor for missing links and an evaluation experiment was performed on five large social networks datasets: Face book, Flickr, You Tube, Academia and The Marker. Our methods can provide social network site operators with the capability of helping users to find known, offline contacts and to discover new friends online. They may also be used for exposing hidden links in an online social network.}, doi={10.1109/PASSAT/SocialCom.2011.20}, keywords = {Link prediction, Social networks} } @article{2010_DBLP:journals/air/Rokach10, journal = {Artif. Intell. Rev.}, author = {Lior Rokach}, title = {Ensemble-based classifiers}, ee = {http://dx.doi.org/10.1007/s10462-009-9124-7}, url = {http://www.ise.bgu.ac.il/faculty/liorr/AI.pdf}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {1-39}, volume = {33}, number = {1-2}, year = {2010}, keywords = {Ensemble learning} } @article{2009_DBLP:journals/control/RokachNS09, journal = {Control and Cybernetics}, author = {Lior Rokach and Lihi Naamani and Armin Shmilovici}, title = {Active learning using pessimistic expectation estimators}, ee = {http://control.ibspan.waw.pl:3000/contents/export?filename=Rokach-Naamani-Shmilovici.pdf}, url = {http://www.ise.bgu.ac.il/faculty/liorr/ACT18.pdf}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {261-280}, volume = {38}, number = {1}, year = {2009}, keywords = {Active learning, Cost-sensitive learning, Decision trees} } @techreport{DBLP:journals/corr/abs-1112-5246, journal = {CoRR}, author = {Eitan Menahem and Lior Rokach and Yuval Elovici}, title = {Combining One-Class Classifiers via Meta-Learning}, ee = {http://arxiv.org/abs/1112.5246}, bibsource = {DBLP, http://dblp.uni-trier.de}, volume = {abs/1112.5246}, year = {2011}, keywords = {Ensemble learning, Anomaly detection} } @techreport{DBLP:journals/corr/abs-1208-0564, journal = {CoRR}, author = {Lena Chekina and Duku Mimran and Lior Rokach and Yuval Elovici and Bracha Shapira}, title = {Detection of Deviations in Mobile Applications Network Behavior}, ee = {http://arxiv.org/abs/1208.0564}, bibsource = {DBLP, http://dblp.uni-trier.de}, volume = {abs/1208.0564}, year = {2012}, keywords = {Malware detection, Cyber security, Information security, Anomaly detection} } @techreport{DBLP:journals/corr/abs-1209-1797, journal = {CoRR}, author = {Eitan Menahem and Alon Schclar and Lior Rokach and Yuval Elovici}, title = {Securing Your Transactions: Detecting Anomalous Patterns In XML Documents}, ee = {http://arxiv.org/abs/1209.1797}, bibsource = {DBLP, http://dblp.uni-trier.de}, volume = {abs/1209.1797}, keywords = {Cyber security, Information security, Anomaly detection}, year = {2012} } @techreport{DBLP:journals/corr/abs-1209-5038, journal = {CoRR}, author = {Daniel Gordon and Danny Hendler and Lior Rokach}, title = {Fast Randomized Model Generation for Shapelet-Based Time Series Classification}, ee = {http://arxiv.org/abs/1209.5038}, bibsource = {DBLP, http://dblp.uni-trier.de}, volume = {abs/1209.5038}, keywords = {Time-series}, year = {2012} } @techreport{DBLP:journals/corr/abs-1211-2891, journal = {CoRR}, author = {Ariel Bar and Lior Rokach and Guy Shani and Bracha Shapira and Alon Schclar}, title = {Boosting Simple Collaborative Filtering Models Using Ensemble Methods}, ee = {http://arxiv.org/abs/1211.2891}, bibsource = {DBLP, http://dblp.uni-trier.de}, volume = {abs/1211.2891}, year = {2012}, keywords = {Recommender systems, Ensemble learning, Collaborative filtering} } @article{2009_DBLP:journals/csda/MenahemSRE09, journal = {Computational Statistics {\&} Data Analysis}, author = {Eitan Menahem and Asaf Shabtai and Lior Rokach and Yuval Elovici}, title = {Improving malware detection by applying multi-inducer ensemble}, ee = {http://dx.doi.org/10.1016/j.csda.2008.10.015}, url = {http://www.ise.bgu.ac.il/faculty/liorr/malens.pdf}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {1483-1494}, volume = {53}, number = {4}, year = {2009}, keywords = {Malware detection, Cyber security, Information security, Ensemble learning} } @article{2008_DBLP:journals/csda/MoskovitchER08, journal = {Computational Statistics {\&} Data Analysis}, author = {Robert Moskovitch and Yuval Elovici and Lior Rokach}, title = {Detection of unknown computer worms based on behavioral classification of the host}, ee = {http://dx.doi.org/10.1016/j.csda.2008.01.028}, url = {http://www.ise.bgu.ac.il/faculty/liorr/worm.pdf}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {4544-4566}, volume = {52}, number = {9}, year = {2008}, keywords = {Malware detection, Cyber security, Information security, Ensemble learning, Feature selection} } @article{2009_DBLP:journals/csda/Rokach09, journal = {Computational Statistics {\&} Data Analysis}, author = {Lior Rokach}, title = {Collective-agreement-based pruning of ensembles}, ee = {http://dx.doi.org/10.1016/j.csda.2008.12.001}, url = {http://www.ise.bgu.ac.il/faculty/liorr/colagr.pdf}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {1015-1026}, volume = {53}, number = {4}, year = {2009}, keywords = {Ensemble learning} } @article{DBLP:journals/csda/Rokach09a, journal = {Computational Statistics {\&} Data Analysis}, author = {Lior Rokach}, title = {Taxonomy for characterizing ensemble methods in classification tasks: A review and annotated bibliography}, ee = {http://dx.doi.org/10.1016/j.csda.2009.07.017}, url = {http://www.ise.bgu.ac.il/faculty/liorr/tax.pdf}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {4046-4072}, volume = {53}, number = {12}, year = {2009}, keywords = {Ensemble learning} } @article{DBLP:journals/datamine/RokachNS08, journal = {Data Min. Knowl. Discov.}, author = {Lior Rokach and Lihi Naamani and Armin Shmilovici}, title = {Pessimistic cost-sensitive active learning of decision trees for profit maximizing targeting campaigns}, ee = {http://dx.doi.org/10.1007/s10618-008-0105-2}, url = {http://www.ise.bgu.ac.il/faculty/liorr/PALV5.pdf}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {283-316}, volume = {17}, number = {2}, year = {2008}, keywords = {Active learning, Decision trees, Cost-sensitive learning} } @article{DBLP:journals/ida/RokachM05, journal = {Intell. Data Anal.}, author = {Lior Rokach and Oded Maimon}, title = {Feature set decomposition for decision trees}, ee = {http://iospress.metapress.com/content/t489v7c9dn0dg6ml/}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {131-158}, volume = {9}, number = {2}, year = {2005}, keywords = {Ensemble learning, Decomposition, Decision trees} } @article{DBLP:journals/ijcia/RokachMA05, journal = {International Journal of Computational Intelligence and Applications}, author = {Lior Rokach and Oded Maimon and Omri Arad}, title = {Improving Supervised Learning by Sample Decomposition}, ee = {http://dx.doi.org/10.1142/S146902680500143X}, url = {}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {37-54}, volume = {5}, number = {1}, year = {2005}, keywords = {Ensemble learning, Decomposition} } @article{DBLP:journals/ijis/Rokach08, journal = {Int. J. Intell. Syst.}, author = {Lior Rokach}, title = {An evolutionary algorithm for constructing a decision forest: Combining the classification of disjoints decision trees}, ee = {http://dx.doi.org/10.1002/int.20277}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {455-482}, volume = {23}, number = {4}, year = {2008}, keywords = {Ensemble learning, Decomposition, Decision trees, Genetic algorithms} } @article{DBLP:journals/ijista/Rokach08, journal = {IJISTA}, author = {Lior Rokach}, title = {Mining manufacturing data using genetic algorithm-based feature set decomposition}, ee = {http://dx.doi.org/10.1504/IJISTA.2008.016359}, url = {http://www.ise.bgu.ac.il/faculty/liorr/LRGA2.pdf}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {57-78}, volume = {4}, number = {1/2}, year = {2008}, keywords = {Ensemble learning, Decomposition, Decision trees, Genetic algorithms, Manufacturing} } @article{DBLP:journals/ijprai/RokachCM07, journal = {International Journal of Pattern Recognition and Artificial Intelligence}, author = {Lior Rokach and Barak Chizi and Oded Maimon}, title = {A Methodology for Improving the Performance of Non-Ranker Feature Selection Filters}, ee = {http://dx.doi.org/10.1142/S0218001407005727}, url = {http://www.ise.bgu.ac.il/faculty/liorr/fse.pdf}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {809-830}, volume = {21}, number = {5}, year = {2007}, keywords = {Ensemble learning, Feature selection} } @article{DBLP:journals/ijprai/RokachMA06, journal = {International Journal of Pattern Recognition and Artificial Intelligence}, author = {Lior Rokach and Oded Maimon and Reuven Arbel}, title = {Selective Voting -- Getting More for Less in Sensor Fusion}, ee = {http://dx.doi.org/10.1142/S0218001406004739}, doi = {10.1142/S0218001406004739}, url = {}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {329-350}, volume = {20}, number = {3}, year = {2006}, keywords = {Ensemble learning, Feature selection} } @article{DBLP:journals/ir/RokachRM08, journal = {Inf. Retr.}, author = {Lior Rokach and Roni Romano and Oded Maimon}, title = {Negation recognition in medical narrative reports}, ee = {http://dx.doi.org/10.1007/s10791-008-9061-0}, url = {http://www.ise.bgu.ac.il/faculty/liorr/RV2.pdf}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {499-538}, volume = {11}, number = {6}, year = {2008}, keywords = {Information retrieval, Medical informatics, Text mining, Sequence mining} } @article{DBLP:journals/isci/CohenRM07, journal = {Inf. Sci.}, author = {Shahar Cohen and Lior Rokach and Oded Maimon}, title = {Decision-tree instance-space decomposition with grouped gain-ratio}, ee = {http://dx.doi.org/10.1016/j.ins.2007.01.016}, url = {http://www.ise.bgu.ac.il/faculty/liorr/scohen.pdf}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {3592-3612}, volume = {177}, number = {17}, year = {2007}, keywords = {Decision trees} } @article{DBLP:journals/isci/FeherEMRS12, journal = {Inf. Sci.}, author = {Clint Feher and Yuval Elovici and Robert Moskovitch and Lior Rokach and Alon Schclar}, title = {User identity verification via mouse dynamics}, ee = {http://dx.doi.org/10.1016/j.ins.2012.02.066}, doi = {10.1016/j.ins.2012.02.066}, url = {http://www.ise.bgu.ac.il/faculty/liorr/Clint1.pdf}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {19-36}, volume = {201}, year = {2012}, keywords = {Information security, Cyber security, Authentication, Behavioral biometrics} } @article{DBLP:journals/isci/MatatovRM10, journal = {Inf. Sci.}, author = {Nissim Matatov and Lior Rokach and Oded Maimon}, title = {Privacy-preserving data mining: A feature set partitioning approach}, ee = {http://dx.doi.org/10.1016/j.ins.2010.03.011}, url = {http://www.ise.bgu.ac.il/faculty/liorr/INFO2.pdf}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {2696-2720}, volume = {180}, number = {14}, year = {2010}, keywords = {Privacy, Anonymization, Information security} } @article{DBLP:journals/isci/MenahemRE09, journal = {Inf. Sci.}, author = {Eitan Menahem and Lior Rokach and Yuval Elovici}, title = {Troika - An improved stacking schema for classification tasks}, ee = {http://dx.doi.org/10.1016/j.ins.2009.08.025}, url = {http://www.ise.bgu.ac.il/faculty/liorr/troika.pdf}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {4097-4122}, volume = {179}, number = {24}, year = {2009}, keywords = {Ensemble learning} } @article{DBLP:journals/isci/ShmueliTWSR12, journal = {Inf. Sci.}, author = {Erez Shmueli and Tamir Tassa and Raz Wasserstein and Bracha Shapira and Lior Rokach}, title = {Limiting disclosure of sensitive data in sequential releases of databases}, ee = {http://dx.doi.org/10.1016/j.ins.2011.12.020}, url = {http://www.openu.ac.il/Personal_sites/tamirtassa/Download/Journals/asr.pdf}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {98-127}, volume = {191}, year = {2012}, keywords = {Privacy, Anonymization, Information security} } @article{DBLP:journals/jasis/Rokach12, journal = {JASIST}, author = {Lior Rokach}, title = {Applying the Publication Power Approach to Artificial Intelligence Journals}, ee = {http://dx.doi.org/10.1002/asi.22616}, url = {http://www.ise.bgu.ac.il/faculty/liorr/JASIST2.pdf}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {1270-1277}, volume = {63}, number = {6}, year = {2012}, keywords = {Scientometrics} } @article{DBLP:journals/jasis/RokachKBS11, journal = {JASIST}, author = {Lior Rokach and Meir Kalech and Ido Blank and Rami Stern}, title = {Who is going to win the next Association for the Advancement of Artificial Intelligence Fellowship Award? Evaluating researchers by mining bibliographic data}, ee = {http://dx.doi.org/10.1002/asi.21638}, url = {http://www.ise.bgu.ac.il/faculty/liorr/JASIST.pdf}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {2456-2470}, volume = {62}, number = {12}, year = {2011}, keywords = {Scientometrics} } @article{DBLP:journals/paa/NissimMRE12, journal = {Pattern Anal. Appl.}, author = {Nir Nissim and Robert Moskovitch and Lior Rokach and Yuval Elovici}, title = {Detecting unknown computer worm activity via support vector machines and active learning}, ee = {http://dx.doi.org/10.1007/s10044-012-0296-4}, url = {http://www.ise.bgu.ac.il/faculty/liorr/nissim2012detecting.pdf}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {459-475}, volume = {15}, number = {4}, year = {2012}, keywords = {Active learning, Malware detection, Cyber security, Information security} } @article{DBLP:journals/paa/Rokach06, journal = {Pattern Anal. Appl.}, author = {Lior Rokach}, title = {Decomposition methodology for classification tasks: a meta decomposer framework}, ee = {http://dx.doi.org/10.1007/s10044-006-0041-y}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {257-271}, volume = {9}, number = {2-3}, year = {2006}, keywords = {Ensemble learning, Meta-learning, Decomposition} } @article{DBLP:journals/pr/Rokach08, journal = {Pattern Recognition}, author = {Lior Rokach}, title = {Genetic algorithm-based feature set partitioning for classification problems}, ee = {http://dx.doi.org/10.1016/j.patcog.2007.10.013}, url = {http://www.ise.bgu.ac.il/faculty/liorr/PRLRGARV7.pdf}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {1676-1700}, volume = {41}, number = {5}, year = {2008}, keywords = {Ensemble learning, Decomposition, Decision trees, Genetic algorithms} } @article{DBLP:journals/prl/ArbelR06, journal = {Pattern Recognition Letters}, author = {Reuven Arbel and Lior Rokach}, title = {Classifier evaluation under limited resources}, ee = {http://dx.doi.org/10.1016/j.patrec.2006.03.008}, url = {http://www.ise.bgu.ac.il/faculty/liorr/prl.pdf}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {1619-1631}, volume = {27}, number = {14}, year = {2006}, keywords = {Ensemble learning, Evaluation} } @article{DBLP:journals/tdsc/HarelSRE12, journal = {IEEE Trans. Dependable Sec. Comput.}, author = {Amir Harel and Asaf Shabtai and Lior Rokach and Yuval Elovici}, title = {M-Score: A Misuseability Weight Measure}, ee = {http://doi.ieeecomputersociety.org/10.1109/TDSC.2012.17}, url = {http://www.ise.bgu.ac.il/faculty/liorr/MSCORE.pdf}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {414-428}, volume = {9}, number = {3}, year = {2012}, abstract={Detecting and preventing data leakage and data misuse poses a serious challenge for organizations, especially when dealing with insiders with legitimate permissions to access the organization's systems and its critical data. In this paper, we present a new concept, Misuseability Weight, for estimating the risk emanating from data exposed to insiders. This concept focuses on assigning a score that represents the sensitivity level of the data exposed to the user and by that predicts the ability of the user to maliciously exploit this data. Then, we propose a new measure, the M-score, which assigns a misuseability weight to tabular data, discuss some of its properties, and demonstrate its usefulness in several leakage scenarios. One of the main challenges in applying the M-score measure is in acquiring the required knowledge from a domain expert. Therefore, we present and evaluate two approaches toward eliciting misuseability conceptions from the domain expert.}, doi={10.1109/TDSC.2012.17}, keywords = {Information security, Cyber security, Data misuse, Data leakage} } @article{DBLP:journals/tkde/KisilevichRES10, journal = {IEEE Trans. Knowl. Data Eng.}, author = {Slava Kisilevich and Lior Rokach and Yuval Elovici and Bracha Shapira}, title = {Efficient Multidimensional Suppression for K-Anonymity}, ee = {http://dx.doi.org/10.1109/TKDE.2009.91}, url = {http://www.ise.bgu.ac.il/faculty/liorr/TKDESlava.pdf}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {334-347}, volume = {22}, number = {3}, year = {2010}, abstract={Many applications that employ data mining techniques involve mining data that include private and sensitive information about the subjects. One way to enable effective data mining while preserving privacy is to anonymize the data set that includes private information about subjects before being released for data mining. One way to anonymize data set is to manipulate its content so that the records adhere to k-anonymity. Two common manipulation techniques used to achieve k-anonymity of a data set are generalization and suppression. Generalization refers to replacing a value with a less specific but semantically consistent value, while suppression refers to not releasing a value at all. Generalization is more commonly applied in this domain since suppression may dramatically reduce the quality of the data mining results if not properly used. However, generalization presents a major drawback as it requires a manually generated domain hierarchy taxonomy for every quasi-identifier in the data set on which k-anonymity has to be performed. In this paper, we propose a new method for achieving k-anonymity named K-anonymity of Classification Trees Using Suppression (kACTUS). In kACTUS, efficient multidimensional suppression is performed, i.e., values are suppressed only on certain records depending on other attribute values, without the need for manually produced domain hierarchy trees. Thus, in kACTUS, we identify attributes that have less influence on the classification of the data records and suppress them if needed in order to comply with k-anonymity. The kACTUS method was evaluated on 10 separate data sets to evaluate its accuracy as compared to other k-anonymity generalization- and suppression-based methods. Encouraging results suggest that kACTUS' predictive performance is better than that of existing k-anonymity algorithms. Specifically, on average, the accuracies of TDS, TDR, and kADET are lower than kACTUS in 3.5, 3.3, and 1.9 percent, respectively, despite their u- - sage of manually defined domain trees. The accuracy gap is increased to 5.3, 4.3, and 3.1 percent, respectively, when no domain trees are used.}, doi={10.1109/TKDE.2009.91}, keywords = {Privacy, Anonymization, Information security} } @article{DBLP:journals/tsmc/AntwargRS12, journal = {IEEE Transactions on Systems, Man, and Cybernetics, Part C}, author = {Liat Antwarg and Lior Rokach and Bracha Shapira}, title = {Attribute-Driven Hidden Markov Model Trees for Intention Prediction}, ee = {http://dx.doi.org/10.1109/TSMCC.2012.2198212}, url = {http://www.ise.bgu.ac.il/faculty/liorr/antwargattribute.pdf}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {1103-1119}, volume = {42}, number = {6}, year = {2012}, abstract={In this paper, we introduce a novel approach to generate an intention prediction model of user interactions with systems. As part of this new approach, we include personal aspects, such as user characteristics, that can increase prediction accuracy. The model is automatically trained according to the user's fixed attributes (e.g., demographic data such as age and gender) and the user's sequences of actions in the system. The generated model has a tree structure. The building blocks of each node can be any probabilistic sequence model [such as hidden Markov models (HMMs) and conditional random fields (CRFs)] and each node is split according to user attributes. Thus, we refer to this algorithm as an attribute-driven model tree. The new model was first tested on simulated data in which users with different attributes (such as age and gender) behave differently when trying to accomplish various tasks. We then validated the ability of the algorithm to discover the relevant attributes. We tested our algorithm on two real datasets: from a web application and a mobile application dataset. The results were encouraging and indicate the capability of the proposed method to discover the correct user intention model and increasing intention prediction accuracy compared with single HMM or CRF models.}, doi={10.1109/TSMCC.2012.2198212}, keywords = {Sequence mining, Decision trees} } @article{DBLP:journals/tsmc/RokachM05, journal = {IEEE Transactions on Systems, Man, and Cybernetics, Part C}, author = {Lior Rokach and Oded Maimon}, title = {Top-down induction of decision trees classifiers - a survey}, ee = {http://dx.doi.org/10.1109/TSMCC.2004.843247}, url = {http://www.ise.bgu.ac.il/faculty/liorr/DT.pdf}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {476-487}, volume = {35}, number = {4}, year = {2005}, abstract={ Decision trees are considered to be one of the most popular approaches for representing classifiers. Researchers from various disciplines such as statistics, machine learning, pattern recognition, and data mining considered the issue of growing a decision tree from available data. This paper presents an updated survey of current methods for constructing decision tree classifiers in a top-down manner. The paper suggests a unified algorithmic framework for presenting these algorithms and describes the various splitting criteria and pruning methodologies.}, doi={10.1109/TSMCC.2004.843247}, keywords = {Decision trees} } @article{DBLP:journals/virology/TahanGER10, journal = {Journal in Computer Virology}, author = {Gil Tahan and Chanan Glezer and Yuval Elovici and Lior Rokach}, title = {Auto-Sign: an automatic signature generator for high-speed malware filtering devices}, ee = {http://dx.doi.org/10.1007/s11416-009-0119-3}, url = {http://www.ise.bgu.ac.il/faculty/liorr/AutoSign.pdf}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {91-103}, volume = {6}, number = {2}, year = {2010}, keywords = {Feature extraction, Malware detection, Cyber security, Information security} } @InCollection{DBLP:reference/ai/Rokach09, author = {Lior Rokach}, title = {Incorporating Fuzzy Logic in Data Mining Tasks}, ee = {http://www.igi-global.com/Bookstore/Chapter.aspx?TitleId=10348}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {884-891}, booktitle = {Encyclopedia of Artificial Intelligence (3 Volumes)}, year = {2009}, keywords = {Fuzzy logic} } @InCollection{DBLP:reference/dataware/ChiziRM09, author = {Barak Chizi and Lior Rokach and Oded Maimon}, title = {A Survey of Feature Selection Techniques}, ee = {http://www.igi-global.com/Bookstore/Chapter.aspx?TitleId=11077}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {1888-1895}, booktitle = {Encyclopedia of Data Warehousing and Mining, Second Edition (4 Volumes)}, year = {2009}, keywords = {Feature selection} } @InCollection{DBLP:reference/dataware/Rokach09, author = {Lior Rokach}, title = {Data Mining for Improving Manufacturing Processes}, ee = {http://www.igi-global.com/Bookstore/Chapter.aspx?TitleId=10854}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {417-423}, booktitle = {Encyclopedia of Data Warehousing and Mining, Second Edition (4 Volumes)}, year = {2009}, keywords = {Manufacturing} } @book{DBLP:reference/dmkdh/2010, editor = {Oded Maimon and Lior Rokach}, title = {Data Mining and Knowledge Discovery Handbook, 2nd ed}, ee = {http://www.springerlink.com/content/978-0-387-09822-7}, bibsource = {DBLP, http://dblp.uni-trier.de}, isbn = {978-0-387-09822-7}, booktitle = {Data Mining and Knowledge Discovery Handbook, 2nd ed.}, year = {2010}, publisher = {Springer}, keywords = {Data mining} } @InCollection{DBLP:reference/dmkdh/MaimonR10, author = {Oded Maimon and Lior Rokach}, title = {Introduction to Knowledge Discovery and Data Mining}, ee = {http://dx.doi.org/10.1007/978-0-387-09823-4_1}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {1-15}, booktitle = {Data Mining and Knowledge Discovery Handbook, 2nd ed}, year = {2010}, keywords = {Data mining} } @InCollection{DBLP:reference/dmkdh/Rokach10, author = {Lior Rokach}, title = {A survey of Clustering Algorithms}, ee = {http://dx.doi.org/10.1007/978-0-387-09823-4_14}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {269-298}, booktitle = {Data Mining and Knowledge Discovery Handbook, 2nd ed}, year = {2010}, keywords = {Clustering} } @InCollection{DBLP:reference/dmkdh/Rokach10a, author = {Lior Rokach}, title = {Using Fuzzy Logic in Data Mining}, ee = {http://dx.doi.org/10.1007/978-0-387-09823-4_24}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {505-520}, booktitle = {Data Mining and Knowledge Discovery Handbook, 2nd ed}, year = {2010}, keywords = {Fuzzy logic} } @InCollection{DBLP:reference/dmkdh/Rokach10b, author = {Lior Rokach}, title = {Ensemble Methods in Supervised Learning}, ee = {http://dx.doi.org/10.1007/978-0-387-09823-4_50}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {959-979}, booktitle = {Data Mining and Knowledge Discovery Handbook, 2nd ed}, year = {2010}, keywords = {Ensemble learning} } @InCollection{DBLP:reference/dmkdh/RokachM10, author = {Lior Rokach and Oded Maimon}, title = {Supervised Learning}, ee = {http://dx.doi.org/10.1007/978-0-387-09823-4_8}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {133-147}, booktitle = {Data Mining and Knowledge Discovery Handbook, 2nd ed}, year = {2010}, keywords = {Supervised learning} } @InCollection{DBLP:reference/dmkdh/RokachM10a, author = {Lior Rokach and Oded Maimon}, title = {Classification Trees}, ee = {http://dx.doi.org/10.1007/978-0-387-09823-4_9}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {149-174}, booktitle = {Data Mining and Knowledge Discovery Handbook, 2nd ed}, year = {2010}, keywords = {Decision trees} } @InCollection{DBLP:reference/dmkdh/RokachM10b, author = {Lior Rokach and Oded Maimon}, title = {Data Mining using Decomposition Methods}, ee = {http://dx.doi.org/10.1007/978-0-387-09823-4_51}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {981-998}, booktitle = {Data Mining and Knowledge Discovery Handbook, 2nd ed}, year = {2010}, keywords = {Ensemble learning, Decomposition} } @Book{DBLP:reference/rsh/2011, editor = {Francesco Ricci and Lior Rokach and Bracha Shapira and Paul B. Kantor}, title = {Recommender Systems Handbook}, ee = {http://www.springerlink.com/content/978-0-387-85819-7}, bibsource = {DBLP, http://dblp.uni-trier.de}, isbn = {978-0-387-85819-7}, booktitle = {Recommender Systems Handbook}, year = {2011}, publisher = {Springer}, keywords = {Recommender systems} } @InCollection{DBLP:reference/rsh/RicciRS11, author = {Francesco Ricci and Lior Rokach and Bracha Shapira}, title = {Introduction to Recommender Systems Handbook}, ee = {http://dx.doi.org/10.1007/978-0-387-85820-3_1}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {1-35}, booktitle = {Recommender Systems Handbook}, year = {2011}, keywords = {Recommender systems} } @InCollection{DBLP:series/sci/CohenRM06, author = {Shahar Cohen and Lior Rokach and Oded Maimon}, title = {A Decision-Tree Framework for Instance-space Decomposition}, ee = {http://dx.doi.org/10.1007/3-540-33880-2_27}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {265-274}, booktitle = {Advances in Web Intelligence and Data Mining}, year = {2006}, keywords = {Decision trees, Decomposition} } @InCollection{DBLP:series/sci/RokachCM06, author = {Lior Rokach and Barak Chizi and Oded Maimon}, title = {Feature Selection by Combining Multiple Methods}, ee = {http://dx.doi.org/10.1007/3-540-33880-2_30}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {295-304}, booktitle = {Advances in Web Intelligence and Data Mining}, year = {2006}, keywords = {Ensemble learning, Feature selection} } @InCollection{DBLP:series/sci/RokachRCM06, author = {Lior Rokach and Roni Romano and Barak Chizi and Oded Maimon}, title = {A Decision Tree Framework for Semi-Automatic Extraction of Product Attributes from the Web}, ee = {http://dx.doi.org/10.1007/3-540-33880-2_21}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {201-210}, booktitle = {Advances in Web Intelligence and Data Mining}, year = {2006}, keywords = {Information retrieval, Information extraction, Text mining, Decision trees} } @Book{DBLP:series/springer/2008MaimonR, editor = {Oded Maimon and Lior Rokach}, title = {Soft Computing for Knowledge Discovery and Data Mining}, ee = {http://dx.doi.org/10.1007/978-0-387-69935-6}, bibsource = {DBLP, http://dblp.uni-trier.de}, isbn = {978-0-387-69934-9}, year = {2008}, publisher = {Springer}, keywords = {Data mining} } @InCollection{DBLP:series/springer/MaimonR08, author = {Oded Maimon and Lior Rokach}, title = {Introduction to Soft Computing for Knowledge Discovery and Data Mining}, ee = {http://dx.doi.org/10.1007/978-0-387-69935-6_1}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {1-13}, booktitle = {Soft Computing for Knowledge Discovery and Data Mining}, year = {2008}, keywords = {Data mining} } @InCollection{DBLP:series/springer/Rokach08, author = {Lior Rokach}, title = {The Role of Fuzzy Sets in Data Mining}, ee = {http://dx.doi.org/10.1007/978-0-387-69935-6_8}, bibsource = {DBLP, http://dblp.uni-trier.de}, pages = {187-203}, booktitle = {Soft Computing for Knowledge Discovery and Data Mining}, year = {2008}, keywords = {Fuzzy logic} } @inproceedings{dery2010multicamp, author = {Dery, L.N. and Shapira, B. and Rokach, L.}, organization = {IEEE}, title = {MultiCamp Cost sensitive active learning algorithm for multiple parallel campaigns}, pages = {000982--000985}, year = {2010}, booktitle = {Electrical and Electronics Engineers in Israel (IEEEI), 2010 IEEE 26th Convention of}, keywords = {Active learning, Cost-sensitive learning}, abstract={One of the challenges that companies face when launching a campaign to promote new services is selecting the 'right' customers for the campaign, i.e., customers with the highest probability of a positive response. Active learning can be used to efficiently identify this set of customers. It can also prevent approach to non-relevant customers and reduce the campaign's cost. The problem is more challenging when parallel campaigns for multiple new services are launched, given a constraint on the number of promotions that can be offered to the same customer during a defined period of time. The goal is to maximize the total net profit. In this paper we present MutiCamp, a new cost sensitive active learning based algorithm that uses the Hungarian Algorithm to find the optimal match between campaigns and customers. MultiCamp was tested on a real world dataset using a decision tree classifier. Results were compared to a random baseline, indicating the superiority of the proposed algorithm.}, doi={10.1109/EEEI.2010.5661927}, ee = {http://dx.doi.org/10.1109/EEEI.2010.5661927} } @misc{feher2012system, author = {Feher, C. and Moskovitch, R. and Rokach, L. and Elovici, Y.}, title = {System for verifying user identity via mouse dynamics}, year = {2012}, note = {EP Patent 2,490,149}, keywords = {Information security, Cyber security, Authentication, Behavioral biometrics} } @inproceedings{figueiras2012exploration, author = {Figueiras-Vidal, AR and Rokach, L.}, title = {An Exploration of Research Directions in Machine Ensemble Theory and Applications}, pages = {221--226}, year = {2012}, booktitle = {European Symposium on Artificial Neural Networks, Computational Intelligence}, keywords = {Ensemble learning} } @inproceedings{fire2012data, author = {Fire, M. and Kagan, D. and Puzis, R. and Rokach, L. and Elovici, Y.}, organization = {IEEE}, title = {Data mining opportunities in geosocial networks for improving road safety}, pages = {1--4}, year = {2012}, booktitle = {Electrical \& Electronics Engineers in Israel (IEEEI), 2012 IEEE 27th Convention of}, abstract={Traffic measurements, road safety studies, and surveys are required for efficient road planning and ensuring the safety of transportation. Unfortunately, these methods can be cumbersome and very expensive. In this paper we point out a source of transportation information that is based on collaborative community-based navigation applications, such as Waze. Partial and anonimized information publicly exposed by Waze through their application provides valuable information that can significantly ease the future of transportation studies. Moreover, we show that Waze user reports may expose locations plagued with accidents but in lacking police coverage. This knowledge may help police departments to improve road safety by relocating the police units to these locations. Lastly, the data discussed in this paper connects transportation and road safety research to location based services and social network platforms.}, doi={10.1109/EEEI.2012.6377049}, ee = {http://dx.doi.org/10.1109/EEEI.2012.6377049}, keywords = {Social networks, Spatial mining, Geospatial} } @Incollection{fire2013links, author = {Fire, M. and Katz, G. and Rokach, L. and Elovici, Y.}, title = {Links Reconstruction Attack}, year = {2013}, publisher = {Springer New York}, keywords = {Link prediction, Social networks, Privacy, Anonymization, Information security} } @misc{friedmann2012method, author = {Friedmann, M. and Ben-shimon, D. and Rokach, L.}, title = {Method and System for Recommending Geo-Tagged Items}, year = {2012}, note = {US Patent 20,120,303,626}, keywords = {Recommender systems, Collaborative filtering, Spatial mining, Geospatial} } @misc{friedmann2012method, title={Method and System for Recommending Geo-Tagged Items}, author={Friedmann, M. and Ben-shimon, D. and Rokach, L.}, year={2012}, note={EP Patent 2,518,679}, keywords = {Recommender systems, Collaborative filtering, Spatial mining, Geospatial} } @inproceedings{gafny2010detecting, author = {Gafny, M. and Shabtai, A. and Rokach, L. and Elovici, Y.}, organization = {ACM}, title = {Detecting data misuse by applying context-based data linkage}, pages = {3--12}, year = {2010}, booktitle = {Proceedings of the 2010 ACM workshop on Insider threats}, keywords = {Information security, Data misuse, Cyber security, Data leakage} } @inproceedings{gershman2008scheduling, author = {Gershman, A. and Grubshtein, A. and Meisels, A. and Rokach, L. and Zivan, R.}, title = {Scheduling meetings by agents}, year = {2008}, booktitle = {Proc. 7th International Conference on Practice and Theory of Automated Timetabling (PATAT 2008). Montreal (August 2008)}, keywords = {Scheduling} } @misc{harari2001method, author = {Harari, Y. and Rokach, L. and Klevansky, Y.E. and Galili, B.Z. and Tsenter, I.}, title = {Method and system for enabling the exchange, management and supervision of leads and requests in a network}, year = {2001}, note = {US Patent App. 09/801,560}, publisher = {Google Patents}, keywords = {Knowledge management} } @inproceedings{harel2010m, author = {Harel, A. and Shabtai, A. and Rokach, L. and Elovici, Y.}, organization = {ACM}, title = {M-score: estimating the potential damage of data leakage incident by assigning misuseability weight}, pages = {13--20}, year = {2010}, booktitle = {Proceedings of the 2010 ACM workshop on Insider threats}, keywords = {Information security, Data misuse, Cyber security, Data leakage} } @InProceedings{itach2009ensemble, journal = {Workshop Co-Chairs}, author = {Itach, E. and Tenenboim, L. and Rokach, L.}, title = {An Ensemble Method for Multi-label Classification using a Transportation Model}, pages = {49}, year = {2009}, keywords = {Multi-label classification, Ensemble learning} } @techreport{katz2012using, journal = {arXiv preprint arXiv:1212.1131}, author = {Katz, G. and Shani, G. and Shapira, B. and Rokach, L.}, title = {Using Wikipedia to Boost SVD Recommender Systems}, year = {2012}, keywords = {Recommender systems, Collaborative filtering} } @inproceedings{keren2011model, author = {Keren, B. and Kalech, M. and Rokach, L.}, title = {Model-Based Diagnosis with Multi-Label Classification}, pages = {241--248}, year = {2011}, url = {http://www.ise.bgu.ac.il/faculty/liorr/CONF2.pdf}, booktitle = {22nd International Workshop on Principles of Diagnosis}, keywords = {Multi-label classification, Diagnosis} } @inproceedings{khalastchi2012multi, author = {Khalastchi, E. and Kalech, M. and Rokach, L.}, title = {Multi-Layered Model Based Diagnosis in Robots}, year = {2012}, url = {http://www.ise.bgu.ac.il/faculty/liorr/Eli2.pdf}, booktitle = {23rd International Workshop on Principles of Diagnosis (DX 2012)}, keywords = {Diagnosis} } @inproceedings{khalastchi2012sensor, author = {Khalastchi, E. and Kalech, M. and Rokach, L. and Shicel, Y. and Bodek, G.}, title = {Sensor fault detection and diagnosis for autonomous systems}, url = {http://www.ise.bgu.ac.il/faculty/liorr/Eli1.pdf}, year = {2012}, booktitle = {23rd International Workshop on Principles of Diagnosis (DX 2012)}, keywords = {Diagnosis} } @misc{kisilevich2010efficient, author = {Kisilevich, S. and Rokach, L. and Elovici, Y. and Shapira, B.}, title = {Efficient multi-dimensional suppression for k-anonymity}, year = {2010}, note = {EP Patent 2,228,735}, keywords = {Privacy, Anonymization, Information security} } @inproceedings{kisilevich2010geo, author = {Kisilevich, S. and Keim, D. and Rokach, L.}, title = {Geo-Spade: A Generic Google-Earth Based Framework For Analysis And Exploration Of Spatiotemporal Data}, pages = {13--20}, year = {2010}, booktitle = {12th International Conference on Enterprise Information Systems (ICEIS 2010)}, keywords = {Prediction, Spatial mining, Geospatial} } @inproceedings{kisilevichusing, author = {Kisilevich, S. and Keim, D. and Palivatkel, Y. and Rokach, L.}, title = {Using multiplicative hybrid hedonic pricing model for improving revenue management in hotel business}, booktitle = {GeoVis 2011}, year = {2011}, url = {http://www.geomatik-hamburg.de/geoviz/abstracts/26_geovis_final_04_11_2010.pdf}, keywords = {Prediction, Spatial mining, Geospatial} } @incollection{Maimon:2001:DMA:566052.566068, author = {Maimon, Oded and Rokach, Lior}, title = {Data mining by attribute decomposition with semiconductor manufacturing case study}, booktitle = {Data mining for design and manufacturing}, editor = {Braha, Dan}, year = {2002}, isbn = {1-4020-0034-0}, pages = {311--336}, numpages = {26}, url = {http://dl.acm.org/citation.cfm?id=566052.566068}, acmid = {566068}, publisher = {Kluwer Academic Publishers}, address = {Norwell, MA, USA}, keywords = {Ensemble learning, Decomposition, Manufacturing} } @inproceedings{maimon2002space, author = {Maimon, O. and Rokach, L. and Lavi, I.}, organization = {IEEE}, title = {Space decomposition in data mining-a clustering approach}, pages = {101--104}, year = {2002}, booktitle = {Electrical and Electronics Engineers in Israel, 2002. The 22nd Convention of}, abstract={ Decomposition may divide the database horizontally (subsets of rows or tuples) or vertically. It may be aimed at minimizing space and time needed for the classification of a dataset (e.g. sampling, windowing) or rather attempt to improve accuracy (e.g. bagging, boosting). This paper presents a horizontal space-decomposition algorithm, exploiting the K-means clustering algorithm. It is aimed at decreasing error rate compared to the simple classifier embedded in it while being rather understandable.}, doi={10.1109/EEEI.2002.1178345}, ee = {http://dx.doi.org/10.1109/EEEI.2002.1178345}, keywords = {Ensemble learning, Decomposition, Clustering} } @misc{maimon2003medical, author = {Maimon, O. and Ezer, E. and Rokach, L. and Averbuch, M.}, title = {Medical data storage system and method}, month = {feb#{~13}}, year = {2003}, note = {US Patent App. 10/365,405}, publisher = {Google Patents}, keywords = {Medical informatics} } @article{maimon2004ensemble, journal = {Machine Engineering}, author = {Maimon, O. and Rokach, L.}, title = {Ensemble of Decision Trees for Mining Manufacturing Data Sets}, volume = {4}, year = {2004}, number = {1-2}, keywords = {Ensemble learning, Decision trees, Manufacturing} } @inproceedings{maimonefficiency, author = {Maimon, O. and Rokach, L. and Okon, A.}, title = {Efficiency Frontier Generation Methods for Classification Problems in Data Mining}, year = {2004}, url = {http://braude.ort.org.il/industrial/13thconf/html/files/110_p.pdf}, booktitle = {the 13th Israeli Conference of Industrial Engineering and Management}, keywords = {Ensemble learning} } @inproceedings{marom2010using, author = {Marom, N.D. and Rokach, L. and Shmilovici, A.}, organization = {IEEE}, title = {Using the confusion matrix for improving ensemble classifiers}, pages = {000555--000559}, year = {2010}, booktitle = {Electrical and Electronics Engineers in Israel (IEEEI), 2010 IEEE 26th Convention of}, abstract={The code matrix enables to convert a multi class problem into an ensemble of binary classifiers. We suggest a new un-weighted framework for iteratively extending the code matrix which based on confusion matrix. The confusion matrix holds important information which is exploited by the suggested framework. Evaluating the confusion matrix at each iteration enables to make a decision regarding the next one against all classifier that should be added to the current code matrix. We demonstrate the benefits of the method by applying it to Error Correcting Code based ensemble and to AdbaBoost. We use Orthogonal arrays as the basic code matrix.}, doi={10.1109/EEEI.2010.5662159}, ee = {http://dx.doi.org/10.1109/EEEI.2010.5662159}, keywords = {Ensemble learning} } @misc{menahem2009improved, author = {Menahem, E. and Rokach, L. and Elovici, Y.}, title = {An improved stacking schema for classification tasks}, month = {jul#{~15}}, year = {2009}, note = {EP Patent 2,079,040}, keywords = {Ensemble learning} } @misc{menahem2012stacking, author = {Menahem, E. and Rokach, L. and Elovici, Y.}, title = {Stacking schema for classification tasks}, month = {aug#{~14}}, year = {2012}, note = {US Patent 8,244,652}, keywords = {Ensemble learning} } @inproceedings{naamani2008logistic, author = {Naamani, L. and Rokach, L. and Shmilovici, A.}, organization = {IEEE}, title = {A logistic regression method for cost sensetive active learning}, pages = {707--710}, year = {2008}, booktitle = {Electrical and Electronics Engineers in Israel, 2008. IEEEI 2008. IEEE 25th Convention of}, abstract={Direct marketing involves offering a product or service to a carefully selected group of customers, the ones expected to render the most profits. Active learning is a data mining policy which actively selects unlabeled instances for labeling. In this research our goal is to construct a model that minimizes the net acquisition cost of selection of instances for labeling and at the same time maximizes the net profit gained from approaching selected customers. We present a new framework which combines a cost-sensitive active learning algorithm with a logistic regression classifier. We evaluated the framework on two benchmark datasets. The results appear encouraging.}, doi={10.1109/EEEI.2008.4736625}, keywords = {Active learning, Cost-sensitive learning} } @phdthesis{rokach2004decomposition, author = {Rokach, L.}, title = {Decomposition Methodology in Data Mining with Emphasis on Feature Set Decomposition Approach}, school = {Tel Aviv University}, keywords = {Ensemble learning, Decomposition}, year = {2004} } @article{rokach2006data, journal = {Journal of Intelligent Manufacturing}, author = {Rokach, L. and Maimon, O.}, title = {Data mining for improving the quality of manufacturing: a feature set decomposition approach}, ee = {http://dx.doi.org/10.1007/s10845-005-0005-x}, doi = {10.1007/s10845-005-0005-x}, url = {http://www.ise.bgu.ac.il/faculty/liorr/im.pdf}, pages = {285--299}, volume = {17}, year = {2006}, number = {3}, keywords = {Ensemble learning, Manufacturing, Decomposition}, publisher = {Springer} } @book{rokach2008data, author = {Rokach, L. and Maimon, O.Z.}, title = {Data mining with decision trees: theory and applications}, volume = {69}, year = {2008}, publisher = {World Scientific Pub Co Inc}, keywords = {Decision trees} } @book{rokach2008decomposition, author = {Maimon, O. and Rokach, L.}, title = {Decomposition Methodology for Knowledge Discovery and Data Mining}, year = {2005}, publisher = {World Scientific Pub Co Inc}, keywords = {Ensemble learning, Decomposition} } @article {ESP:ESP2273, author = {Svoray, Tal and Michailov, Evgenia and Cohen, Avraham and Rokach, Lior and Sturm, Arnon}, title = {Predicting gully initiation: comparing data mining techniques, analytical hierarchy processes and the topographic threshold}, journal = {Earth Surface Processes and Landforms}, volume = {37}, number = {6}, publisher = {John Wiley & Sons, Ltd}, issn = {1096-9837}, ee = {http://dx.doi.org/10.1002/esp.2273}, url = {http://www.geog.bgu.ac.il/gis/images/publications/Michailov.pdf}, doi = {10.1002/esp.2273}, pages = {607--619}, keywords = {Spatial mining, Geospatial, Ensemble learning}, year = {2012}, } @InProceedings{rokach2010ensemble, journal = {Working Notes}, author = {Rokach, L. and Itach, E.}, title = {An Ensemble Method for Multi-label Classification using an Approximation Algorithm for the Set Covering Problem}, pages = {37}, year = {2010}, keywords = {Multi-label classification} } @misc{rokach2010next, author = {Rokach, L. and Antwarg, L. and Shapira, B.}, title = {Next-step prediction system and method}, month = {aug#{~25}}, year = {2010}, note = {EP Patent 2,221,719}, keywords = {Sequence mining, Decision trees} } @book{rokach2010pattern, author = {Rokach, L.}, title = {Pattern classification using ensemble methods}, volume = {75}, year = {2010}, publisher = {World Scientific Publishing Company Incorporated}, keywords = {Ensemble learning} } @article{rokach2012automatic, journal = {Journal of Intelligent Manufacturing}, author = {Rokach, L. and Hutter, D.}, title = {Automatic discovery of the root causes for quality drift in high dimensionality manufacturing processes}, pages = {1915--1930}, volume = {23}, year = {2012}, number = {5}, ee = {http://dx.doi.org/10.1007/s10845-011-0517-5}, doi = {10.1007/s10845-011-0517-5}, url = {http://www.ise.bgu.ac.il/faculty/liorr/MANU2.pdf}, publisher = {Springer Netherlands}, keywords = {Manufacturing, Anomaly detection} } @inproceedings{rokach2012machine, author = {Rokach, L. and Feldman, A. and Kalech, M. and Provan, G.}, organization = {IEEE}, title = {Machine-learning-based circuit synthesis}, pages = {1--5}, year = {2012}, booktitle = {Electrical \& Electronics Engineers in Israel (IEEEI), 2012 IEEE 27th Convention of}, keywords = {Ensemble learning, Active learning} } @InCollection{romano2006data, journal = {Lecture Notes in Computer Science}, author = {Romano, R. and Rokach, L. and Maimon, O.}, title = {Data Mining and Agent-Oriented Computing-Automatic Discovery of Regular Expression Patterns Representing Negated Findings in Medical Narrative Reports}, pages = {300--311}, volume = {4032}, year = {2006}, publisher = {Berlin: Springer-Verlag, 1973-}, keywords = {Sequence mining, Text mining, Medical informatics} } @InProceedings{sapir2008methodology, author = {Sapir, L. and Shmilovici, A. and Rokach, L.}, organization = {IEEE}, title = {A methodology for the design of a fuzzy data warehouse}, pages = {2--14}, volume = {1}, year = {2008}, url = {http://www.ise.bgu.ac.il/faculty/liorr/sapir.pdf}, abstract={A data warehouse is a special database used for storing business oriented information for future analysis and decision-making. In business scenarios, where some of the data or the business attributes are fuzzy, it may be useful to construct a warehouse that can support the analysis of fuzzy data. Here, we outline how Kimballpsilas methodology for the design of a data warehouse can be extended to the construction of a fuzzy data warehouse. A case study demonstrates the viability of the methodology.}, doi={10.1109/IS.2008.4670400}, ee = {http://dx.doi.org/10.1109/IS.2008.4670400}, booktitle = {Intelligent Systems, 2008. IS'08. 4th International IEEE Conference}, keywords = {Databases, Fuzzy logic} } @misc{schclar2011system, author = {Schclar, A. and Rokach, L. and Shapira, B. and Glass, G. and Jepsen, K. and Henke, K.}, title = {System and method for the detection of usability problems in an interactive application}, year = {2011}, note = {EP Patent 2,367,113}, keywords = {Human computer interaction} } @inproceedings{shani2007stereotypes, author = {Shani, G. and Meisles, A. and Gleyzer, Y. and Rokach, L. and Ben-Shimon, D.}, organization = {The AAAI Press}, title = {A stereotypes-based hybrid recommender system for media items}, pages = {76--83}, year = {2007}, booktitle = {AAAI Workshop on Intelligent Techniques for Web Personalization, Vancouver}, keywords = {Recommender systems} } @misc{shani2008interactive, author = {Shani, G. and Rokach, L. and Meisels, A. and Piratla, N.}, title = {An interactive hybrid recommender system}, month = {apr#{~2}}, year = {2008}, note = {EP Patent 1,906,316}, keywords = {Recommender systems} } @misc{shani2011interactive, author = {Shani, G. and Rokach, L. and Meisels, A. and Piratla, N.}, title = {Interactive hybrid recommender system}, month = {sep#{~13}}, year = {2011}, note = {US Patent 8,019,707}, publisher = {Google Patents}, keywords = {Recommender systems} } @misc{shapira2011system, author = {Shapira, B. and Mimran, D. and Meyer, J. and Rokach, L. and Peretz, S. and Glass, G. and Henke, K. and Schneider, L.}, title = {A system for detecting usability problems of users while using their mobile devices}, month = {sep#{~28}}, year = {2011}, note = {EP Patent 2,369,481}, keywords = {Human computer interaction} } @article{shapira2012facebook, journal = {User Modeling and User-Adapted Interaction}, publisher = {Springer Netherlands}, author = {Bracha Shapira and Lior Rokach and Shirley Freilikhman}, title = {Facebook single and cross domain data for recommendation systems}, volume = {23}, number = {2-3}, year = {2013}, pages = {211-247}, ee = {http://dx.doi.org/10.1007/s11257-012-9128-x}, keywords = {Recommender systems, Social networks} } @inproceedings{shimshon2010clustering, author = {Shimshon, T. and Moskovitch, R. and Rokach, L. and Elovici, Y.}, organization = {IEEE}, title = {Clustering di-graphs for continuously verifying users according to their typing patterns}, pages = {000445--000449}, year = {2010}, booktitle = {Electrical and Electronics Engineers in Israel (IEEEI), 2010 IEEE 26th Convention of}, keywords={Information security, Cyber security, Authentication, Clustering, Behavioral biometrics, Keystroke dynamics}, abstract={Traditionally users are authenticated based on a username and password. However, a logged station is still vulnerable to imposters when the user leaves her computer without logging off. Keystroke dynamics methods can be useful to continuously verify a user, after the authentication process has successfully ended. Within the last decade several studies proposed the use of keystroke dynamics as a behavioral biometric tool to verify users. We propose a new method, for compactly representing the keystroke patterns by joining similar pairs of consecutive keystrokes. The proposed method considers clustering di-graphs based on their temporal features. The proposed method was evaluated on 10 legitimate users and 15 imposters. Encouraging results suggest that the proposed method detection performance is better than that of existing methods. Specifically we reach a False Acceptance Rate (FAR) of 0.41% and a False Rejection Rate (FRR) of 0.63%.}, doi={10.1109/EEEI.2010.5662182}, ee = {http://dx.doi.org/10.1109/EEEI.2010.5662182} } @article{tahan2012mal, journal = {The Journal of Machine Learning Research}, author = {Tahan, G. and Rokach, L. and Shahar, Y.}, title = {Mal-ID: Automatic Malware Detection Using Common Segment Analysis and Meta-Features}, ee = {http://www.jmlr.org/papers/volume13/tahan12a/tahan12a.pdf}, url = {http://www.ise.bgu.ac.il/faculty/liorr/Tahan12a.pdf}, pages = {949--979}, volume = {13}, year = {2012}, publisher = {JMLR. org}, keywords = {Feature extraction, Malware detection, Cyber security, Information security} } @inproceedings{tenenboim2009multi, author = {Tenenboim, L. and Rokach, L. and Shapira, B.}, title = {Multi-label classification by analyzing labels dependencies}, pages = {117--131}, year = {2009}, booktitle = {European conference on machine learning (ECML)/principles and practice of knowledge discovery in databases (PKDD)-1st international workshop on learning from multi-label data (MLD'2009)}, keywords = {Multi-label classification} } @inproceedings{tenenboim2010identification, author = {Tenenboim-Chekina, L. and Rokach, L. and Shapira, B.}, title = {Identification of label dependencies for multi-label classification}, pages = {53--60}, year = {2010}, booktitle = {Proceedings of the second International Workshop on Learning from Multi-Label data}, keywords = {Multi-label classification} } @incollection{zeira2004change, title={Change detection in classification models induced from time series data}, author={Zeira, G. and Maimon, O. and Last, M. and Rokach, L.}, booktitle={Data Mining in Time Series Databases, M. Last, A. Kandel, and H. Bunke (Editors)}, volume={57}, pages={101--125}, year={2004}, publisher = {World Scientific Publishing Company Incorporated}, keywords = {Time-series} } @InProceedings{zilberman2010analyzing, journal = {Proc. of the 2010 Workshop on Collaborative Methods for Security and Privacy (CollSec'10), Washington, DC}, author = {Zilberman, P. and Shabtai, A. and Rokach, L.}, title = {Analyzing Group Communication for Preventing Accidental Data Leakage via Email}, year = {2010}, keywords = {Information security, Data leakage, Cyber security} } @article{rokach21, journal = {Journal of Intelligent Manufacturing}, author = {Rokach, Lior and Romano, Roni and Maimon, Oded}, title = {Mining manufacturing databases to discover the effect of operation sequence on the product quality}, ee = {http://dx.doi.org/10.1007/s10845-008-0084-6}, doi = {10.1007/s10845-008-0084-6}, url = {http://www.ise.bgu.ac.il/faculty/liorr/seqman.pdf}, volume = {19}, number = {3}, year = {2008}, keywords = {Manufacturing, Sequence mining} } @article{Averbuch3, journal = {Clinical Pharmacology & Therapeutics}, author = {Averbuch, M. and Maimon, O. and Rokach, L. and Ezer, E.}, title = {Free-text information retrieval system for a rapid enrollment of patients into clinical trials}, volume = {77}, number = {2}, year = {2005}, keywords = {Information retrieval, Medical informatics, Text mining} } @InProceedings{ 5, author = {Kisilevich, Slava and Keim, Daniel and Rokach, Lior}, series = {Lecture Notes in Geoinformation and Cartography}, title = {A Novel Approach to Mining Travel Sequences Using Collections of Geotagged Photos}, editor = {Painho, M. and Santos, M. Y. and Pundt, H.}, organization = {Springer Berlin Heidelberg}, pages = {163--182}, booktitle = {Geospatial Thinking}, keywords = {Spatial mining, Geospatial, Sequence mining}, year = {2010} } @article{antwarg2012highlighting, journal = {Behaviour and Information Technology}, author = {Antwarg, L. and Lavie, T. and Rokach, L. and Shapira, B. and Meyer, J.}, title = {Highlighting items as means of adaptive assistance}, ee = {http://www.tandfonline.com/doi/pdf/10.1080/0144929X.2011.650710}, doi = {10.1080/0144929X.2011.650710}, url = {http://www.ise.bgu.ac.il/faculty/liorr/LIAT1.pdf}, year = {2012}, publisher = {Taylor \& Francis}, keywords = {Human computer interaction} } @inproceedings{averbuch2004context, author = {Averbuch, M. and Karson, T. and Ben-Ami, B. and Maimon, O. and Rokach, L.}, organization = {OCSL Press}, title = {Context-sensitive medical information retrieval}, pages = {282}, volume = {107}, year = {2004}, booktitle = {Medinfo 2004: proceedings of the 11th World Conference on Medical Informatics}, keywords = {Information retrieval, Medical informatics, Ensemble learning, Text mining} } @inproceedings{baltrunas2010best, author = {Baltrunas, L. and Kaminskas, M. and Ricci, F. and Rokach, L. and Shapira, B. and Luke, K.H.}, title = {Best usage context prediction for music tracks}, year = {2010}, booktitle = {Proceedings of the 2nd Workshop on Context Aware Recommender Systems}, keywords = {Recommender systems} } @inproceedings{chekina2012introducing, author = {Chekina, L. and Rokach, L. and Shapira, B.}, title = {Introducing diversity among the models of multi-label classification ensemble}, pages = {239--244}, year = {2012}, booktitle = {European Symposium on Artificial Neural Networks, Computational Intelligence}, keywords = {Multi-label classification} } @inproceedings{dahan2012proactive, author = {Dahan, H. and Maimon, O. and Cohen, S. and Rokach, L.}, organization = {IEEE}, title = {Proactive data mining using decision trees}, pages = {1--5}, year = {2012}, doi = {10.1109/EEEI.2012.6377048}, ee = {http://dx.doi.org/10.1109/EEEI.2012.6377048}, booktitle = {Electrical \& Electronics Engineers in Israel (IEEEI), 2012 IEEE 27th Convention of}, abstract={Most of the existing data mining algorithms are #x2018;passive #x2019;. That is, they produce models which can describe patterns, but leave the decision on how to react to these patterns in the hands of the user. In contrast, in this work we describe a proactive approach to data mining, and describe an implementation of that approach, using decision trees. We show that the proactive role requires the algorithms to consider additional domain knowledge, which is exogenous to the training set. We also suggest a novel splitting criterion, termed maximalutility, which is driven by the proactive agenda.}, keywords = {Active learning, Cost-sensitive learning, Decision trees} } @inproceedings{zakin2007identifying, title={Identifying computers hidden behind a NAT using machine learning techniques}, author={Zakin, O. and Levi, M. and Elovici, Y. and Rockach, L. and Shafrir, N. and Sinter, G. and Pen, O.}, booktitle={The 6th European Conference on Information Warfare and Security}, pages={335--340}, year={2007}, keywords = {Clustering, Information security, Cyber security} } @article{aaa, author = {Lena Chekina and Dan Gutfreund and Aryeh Kontorovich and Lior Rokach and Bracha Shapira}, title = {Exploiting label dependencies for improved sample complexity}, journal = {Machine Learning}, volume = {91}, number = {1}, year = {2013}, pages = {1-42}, ee = {http://dx.doi.org/10.1007/s10994-012-5312-9}, issn={0885-6125}, doi={10.1007/s10994-012-5312-9}, publisher={Springer US}, keywords={Multi-label classification, Ensemble learning}, language={English} } @article{DBLP:journals/isci/EloviciRA13, author = {Yuval Elovici and Lior Rokach and Sahin Albayrak}, title = {Guest editorial: Special issue on data mining for information security}, journal = {Inf. Sci.}, volume = {231}, year = {2013}, pages = {1-3}, ee = {http://dx.doi.org/10.1016/j.ins.2013.01.027}, bibsource = {DBLP, http://dblp.uni-trier.de} }