{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T19:53:24Z","timestamp":1790711604262,"version":"4.1.0"},"reference-count":102,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2021,9,3]],"date-time":"2021-09-03T00:00:00Z","timestamp":1630627200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,9,3]],"date-time":"2021-09-03T00:00:00Z","timestamp":1630627200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"name":"israel science foundation","award":["1119\/19"],"award-info":[{"award-number":["1119\/19"]}]},{"name":"israel science foundation","award":["1119\/19"],"award-info":[{"award-number":["1119\/19"]}]},{"name":"hasso plattner institute research school"},{"DOI":"10.13039\/501100018707","name":"technion hiroshi fujiwara cyber security research center","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100018707","id-type":"DOI","asserted-by":"crossref"}]},{"name":"israel cyber bureau"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2021,10]]},"DOI":"10.1007\/s10994-021-06047-x","type":"journal-article","created":{"date-parts":[[2021,9,3]],"date-time":"2021-09-03T22:53:10Z","timestamp":1630709590000},"page":"2835-2866","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["RADE: resource-efficient supervised anomaly detection using decision tree-based ensemble methods"],"prefix":"10.1007","volume":"110","author":[{"given":"Shay","family":"Vargaftik","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Isaac","family":"Keslassy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ariel","family":"Orda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3844-5940","authenticated-orcid":false,"given":"Yaniv","family":"Ben-Itzhak","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,9,3]]},"reference":[{"key":"6047_CR1","unstructured":"Appel, R., Fuchs, T., Doll\u00e1r, P., & Perona, P. (2013). Quickly boosting decision trees\u2013pruning underachieving features early. In International conference on machine learning (pp. 594\u2013602)."},{"issue":"9","key":"6047_CR2","doi-asserted-by":"publisher","first-page":"2281","DOI":"10.1109\/TKDE.2013.73","volume":"26","author":"N Asadi","year":"2014","unstructured":"Asadi, N., Lin, J., & De Vries, A. P. (2014). Runtime optimizations for tree-based machine learning models. IEEE Transactions on Knowledge and Data Engineering, 26(9), 2281\u20132292.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"6047_CR3","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1016\/j.ins.2016.04.019","volume":"378","author":"RAR Ashfaq","year":"2017","unstructured":"Ashfaq, R. A. R., Wang, X. Z., Huang, J. Z., Abbas, H., & He, Y. L. (2017). Fuzziness based semi-supervised learning approach for intrusion detection system. Information Sciences, 378, 484\u2013497.","journal-title":"Information Sciences"},{"issue":"15","key":"6047_CR4","doi-asserted-by":"publisher","first-page":"1601","DOI":"10.1002\/sim.4492","volume":"31","author":"M Banerjee","year":"2012","unstructured":"Banerjee, M., Ding, Y., & Noone, A. M. (2012). Identifying representative trees from ensembles. Statistics in Medicine, 31(15), 1601\u20131616.","journal-title":"Statistics in Medicine"},{"key":"6047_CR5","volume-title":"Comparison of neural networks and discriminant analysis in predicting forest cover types","author":"JA Blackard","year":"1998","unstructured":"Blackard, J. A. (1998). Comparison of neural networks and discriminant analysis in predicting forest cover types. Colorado State University."},{"key":"6047_CR6","volume-title":"Arcing classifiers (technical report)","author":"L Breiman","year":"1996","unstructured":"Breiman, L. (1996a). Arcing classifiers (technical report). Department of Statistics, University of California."},{"issue":"1","key":"6047_CR7","first-page":"49","volume":"24","author":"L Breiman","year":"1996","unstructured":"Breiman, L. (1996b). Stacked regressions. Machine Learning, 24(1), 49\u201364.","journal-title":"Machine Learning"},{"issue":"1","key":"6047_CR8","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5\u201332.","journal-title":"Machine Learning"},{"key":"6047_CR9","unstructured":"Bridges, S. M., Vaughn, R. B., et al. (2000). Fuzzy data mining and genetic algorithms applied to intrusion detection. In Proceedings of 12th annual Canadian information technology security symposium (pp. 109\u2013122)."},{"key":"6047_CR10","doi-asserted-by":"crossref","unstructured":"Browne, J., Tomita, T., Mhembere, D., Burns, R., & Vogelstein, J. (2018). Forest packing: Fast, parallel decision forests. arXiv preprint arXiv:1806.07300.","DOI":"10.1137\/1.9781611975673.6"},{"key":"6047_CR11","unstructured":"Buitinck, L., Louppe, G., Blondel, M., Pedregosa, F., Mueller, A., Grisel, O., Niculae, V., Prettenhofer, P., Gramfort, A., Grobler, J., & Layton, R. (2013). API design for machine learning software: Experiences from the scikit-learn project. In ECML PKDD workshop: Languages for data mining and machine learning (pp. 108\u2013122)."},{"key":"6047_CR12","doi-asserted-by":"crossref","unstructured":"Bunkhumpornpat, C., Sinapiromsaran, K., & Lursinsap, C. (2009). Safe-level-smote: Safe-level-synthetic minority over-sampling technique for handling the class imbalanced problem. In Pacific-Asia conference on knowledge discovery and data mining (pp. 475\u2013482). Springer.","DOI":"10.1007\/978-3-642-01307-2_43"},{"key":"6047_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2017.09.005","author":"F Carcillo","year":"2017","unstructured":"Carcillo, F., Dal Pozzolo, A., Le Borgne, Y. A., Caelen, O., Mazzer, Y., & Bontempi, G. (2017). Scarff: A scalable framework for streaming credit card fraud detection with spark. Information Fusion. https:\/\/doi.org\/10.1016\/j.inffus.2017.09.005.","journal-title":"Information Fusion"},{"key":"6047_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2019.05.042","author":"F Carcillo","year":"2019","unstructured":"Carcillo, F., Le Borgne, Y. A., Caelen, O., Kessaci, Y., Obl\u00e9, F., & Bontempi, G. (2019). Combining unsupervised and supervised learning in credit card fraud detection. Information Sciences. https:\/\/doi.org\/10.1016\/j.ins.2019.05.042","journal-title":"Information Sciences"},{"key":"6047_CR15","doi-asserted-by":"publisher","first-page":"113269","DOI":"10.1016\/j.eswa.2020.113269","volume":"150","author":"GD Cavalcanti","year":"2020","unstructured":"Cavalcanti, G. D., & Soares, R. J. (2020). Ranking-based instance selection for pattern classification. Expert Systems with Applications, 150, 113269.","journal-title":"Expert Systems with Applications"},{"issue":"3","key":"6047_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1541880.1541882","volume":"41","author":"V Chandola","year":"2009","unstructured":"Chandola, V., Banerjee, A., & Kumar, V. (2009). Anomaly detection: A survey. ACM Computing Surveys (CSUR), 41(3), 1\u201358.","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"6047_CR17","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1613\/jair.953","volume":"16","author":"NV Chawla","year":"2002","unstructured":"Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). Smote: Synthetic minority over-sampling technique. Journal of Artificial Intelligence Research, 16, 321\u2013357.","journal-title":"Journal of Artificial Intelligence Research"},{"key":"6047_CR18","doi-asserted-by":"crossref","unstructured":"Chen, T., & Guestrin, C. (2016) Xgboost: A scalable tree boosting system. In Proceedings of the 22nd ACM sigkdd international conference on knowledge discovery and data mining (pp. 785\u2013794). ACM.","DOI":"10.1145\/2939672.2939785"},{"key":"6047_CR19","doi-asserted-by":"crossref","unstructured":"Chu, F., & Zaniolo, C. (2004). Fast and light boosting for adaptive mining of data streams. In Pacific-Asia conference on knowledge discovery and data mining (pp. 282\u2013292). Springer.","DOI":"10.1007\/978-3-540-24775-3_36"},{"issue":"1","key":"6047_CR20","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1177\/001316446002000104","volume":"20","author":"J Cohen","year":"1960","unstructured":"Cohen, J. (1960). A coefficient of agreement for nominal scales. Educational and Psychological Measurement, 20(1), 37\u201346.","journal-title":"Educational and Psychological Measurement"},{"key":"6047_CR21","volume-title":"Adaptive machine learning for credit card fraud detection","author":"A Dal Pozzolo","year":"2015","unstructured":"Dal\u00a0Pozzolo, A. (2015). Adaptive machine learning for credit card fraud detection. Universit\u00e9 Libre de Bruxelles."},{"key":"6047_CR22","doi-asserted-by":"publisher","unstructured":"Dal Pozzolo, A., Caelen, O., Johnson, R., & Bontempi, G. (2015). Calibrating probability with undersampling for unbalanced classification.https:\/\/doi.org\/10.1109\/SSCI.2015.33","DOI":"10.1109\/SSCI.2015.33"},{"issue":"1\u20134","key":"6047_CR23","doi-asserted-by":"publisher","first-page":"131","DOI":"10.3233\/IDA-1997-1302","volume":"1","author":"M Dash","year":"1997","unstructured":"Dash, M., & Liu, H. (1997). Feature selection for classification. Intelligent Data Analysis, 1(1\u20134), 131\u2013156.","journal-title":"Intelligent Data Analysis"},{"issue":"6","key":"6047_CR24","first-page":"446","volume":"4","author":"L Dhanabal","year":"2015","unstructured":"Dhanabal, L., & Shantharajah, S. (2015). A study on NSL-KDD dataset for intrusion detection system based on classification algorithms. International Journal of Advanced Research in Computer and Communication Engineering, 4(6), 446\u2013452.","journal-title":"International Journal of Advanced Research in Computer and Communication Engineering"},{"issue":"2","key":"6047_CR25","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1023\/A:1007607513941","volume":"40","author":"TG Dietterich","year":"2000","unstructured":"Dietterich, T. G. (2000). An experimental comparison of three methods for constructing ensembles of decision trees: Bagging, boosting, and randomization. Machine Learning, 40(2), 139\u2013157.","journal-title":"Machine Learning"},{"key":"6047_CR26","unstructured":"Dua, D., & Graff, C. (2017). UCI machine learning repository. http:\/\/archive.ics.uci.edu\/ml"},{"key":"6047_CR27","doi-asserted-by":"crossref","unstructured":"Felzenszwalb, P. F., Girshick, R. B., & McAllester, D. (2010) Cascade object detection with deformable part models. In 2010 IEEE computer society conference on computer vision and pattern recognition (pp. 2241\u20132248). IEEE.","DOI":"10.1109\/CVPR.2010.5539906"},{"key":"6047_CR28","doi-asserted-by":"crossref","unstructured":"Ferri, C., Flach, P., & Hern\u00e1ndez-Orallo, J. (2004). Delegating classifiers. In Proceedings of the twenty-first international conference on Machine learning (p.\u00a037).","DOI":"10.1145\/1015330.1015395"},{"key":"6047_CR29","unstructured":"Freund, Y., Schapire, R. E., et al. (1996). Experiments with a new boosting algorithm. In ICML (vol.\u00a096, pp. 148\u2013156). Citeseer."},{"key":"6047_CR30","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1214\/aos\/1013203451","volume":"29","author":"JH Friedman","year":"2001","unstructured":"Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. Annals of Statistics, 29, 1189\u20131232.","journal-title":"Annals of Statistics"},{"key":"6047_CR31","doi-asserted-by":"crossref","unstructured":"Gama, J., Rocha, R., & Medas, P. (2003). Accurate decision trees for mining high-speed data streams. In Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining (pp. 523\u2013528). ACM.","DOI":"10.1145\/956750.956813"},{"key":"6047_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.knosys.2012.09.004","volume":"40","author":"XS Gan","year":"2013","unstructured":"Gan, X. S., Duanmu, J. S., Wang, J. F., & Cong, W. (2013). Anomaly intrusion detection based on PLS feature extraction and core vector machine. Knowledge-Based Systems, 40, 1\u20136.","journal-title":"Knowledge-Based Systems"},{"key":"6047_CR33","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1016\/j.jpdc.2019.07.007","volume":"134","author":"E Garc\u00eda-Mart\u00edn","year":"2019","unstructured":"Garc\u00eda-Mart\u00edn, E., Rodrigues, C. F., Riley, G., & Grahn, H. (2019). Estimation of energy consumption in machine learning. Journal of Parallel and Distributed Computing, 134, 75\u201388.","journal-title":"Journal of Parallel and Distributed Computing"},{"issue":"1","key":"6047_CR34","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s10994-006-6226-1","volume":"63","author":"P Geurts","year":"2006","unstructured":"Geurts, P., Ernst, D., & Wehenkel, L. (2006). Extremely randomized trees. Machine Learning, 63(1), 3\u201342.","journal-title":"Machine Learning"},{"key":"6047_CR35","doi-asserted-by":"crossref","unstructured":"Graczyk, M., Lasota, T., Trawi\u0144ski, B., & Trawi\u0144ski, K. (2010). Comparison of bagging, boosting and stacking ensembles applied to real estate appraisal. In Asian conference on intelligent information and database systems (pp. 340\u2013350). Springer.","DOI":"10.1007\/978-3-642-12101-2_35"},{"key":"6047_CR36","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1016\/j.ijinfomgt.2018.08.006","volume":"45","author":"RAA Habeeb","year":"2019","unstructured":"Habeeb, R. A. A., Nasaruddin, F., Gani, A., Hashem, I. A. T., Ahmed, E., & Imran, M. (2019). Real-time big data processing for anomaly detection: A survey. International Journal of Information Management, 45, 289\u2013307.","journal-title":"International Journal of Information Management"},{"issue":"01","key":"6047_CR37","doi-asserted-by":"publisher","first-page":"45","DOI":"10.4236\/jilsa.2014.61005","volume":"6","author":"MAM Hasan","year":"2014","unstructured":"Hasan, M. A. M., Nasser, M., Pal, B., & Ahmad, S. (2014). Support vector machine and random forest modeling for intrusion detection system (IDS). Journal of Intelligent Learning Systems and Applications, 6(01), 45.","journal-title":"Journal of Intelligent Learning Systems and Applications"},{"key":"6047_CR38","doi-asserted-by":"crossref","unstructured":"Hastie, T., Tibshirani, R., & Friedman, J. (2009). Unsupervised learning. In The elements of statistical learning (pp. 485\u2013585). Springer.","DOI":"10.1007\/978-0-387-84858-7_14"},{"key":"6047_CR39","unstructured":"Jin, Y., & Chuang, J. (2017). Medium corporation. Tree boosting with XGBoost. Why Does XGBoost win every machine learning competition? https:\/\/bit.ly\/2TVWit1. Online; Accessed 7 September 2019"},{"key":"6047_CR40","doi-asserted-by":"crossref","unstructured":"Kabir, A., Ruiz, C., & Alvarez, S. A. (2018). Mixed bagging: A novel ensemble learning framework for supervised classification based on instance hardness. In 2018 IEEE international conference on data mining (ICDM) (pp. 1073\u20131078). IEEE.","DOI":"10.1109\/ICDM.2018.00137"},{"issue":"3","key":"6047_CR41","first-page":"147","volume":"1","author":"AG Karegowda","year":"2012","unstructured":"Karegowda, A. G., Jayaram, M., & Manjunath, A. (2012). Cascading k-means clustering and k-nearest neighbor classifier for categorization of diabetic patients. International Journal of Engineering and Advanced Technology, 1(3), 147\u2013151.","journal-title":"International Journal of Engineering and Advanced Technology"},{"key":"6047_CR42","unstructured":"Kayacik, H. G., Zincir-Heywood, A. N., & Heywood, M. I. (2005). Selecting features for intrusion detection: A feature relevance analysis on KDD 99 intrusion detection datasets. In Proceedings of the third annual conference on privacy, security and trust (vol. 94, pp. 1723\u20131732)."},{"key":"6047_CR43","unstructured":"Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., & Liu, T. Y. (2017). Lightgbm: A highly efficient gradient boosting decision tree. In Advances in neural information processing systems (pp. 3146\u20133154)."},{"key":"6047_CR44","doi-asserted-by":"crossref","unstructured":"Ko, J. H., Na, T., Amir, M. F., Mukhopadhyay, S. (2018). Edge-host partitioning of deep neural networks with feature space encoding for resource-constrained internet-of-things platforms. arXiv preprint arXiv:1802.03835.","DOI":"10.1109\/AVSS.2018.8639121"},{"key":"6047_CR45","doi-asserted-by":"crossref","unstructured":"Kruegel, C., & Vigna, G. (2003). Anomaly detection of web-based attacks. In Proceedings of the 10th ACM conference on computer and communications security (pp. 251\u2013261). ACM.","DOI":"10.1145\/948109.948144"},{"key":"6047_CR46","unstructured":"Kveton, B., Szepesvari, C., Wen, Z., & Ashkan, A. (2015). Cascading bandits: Learning to rank in the cascade model. In International conference on machine learning (pp. 767\u2013776)."},{"issue":"1","key":"6047_CR47","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1109\/72.977291","volume":"13","author":"N Kwak","year":"2002","unstructured":"Kwak, N., & Choi, C. H. (2002). Input feature selection for classification problems. IEEE Transactions on Neural Networks, 13(1), 143\u2013159.","journal-title":"IEEE Transactions on Neural Networks"},{"key":"6047_CR48","doi-asserted-by":"crossref","unstructured":"Lebichot, B., Le\u00a0Borgne, Y.A., He, L., Obl\u00e9, F., & Bontempi, G. (2020). Deep-learning domain adaptation techniques for credit cards fraud detection (pp. 78\u201388). 10.1007\/978-3-030-16841-4\\_8","DOI":"10.1007\/978-3-030-16841-4_8"},{"key":"6047_CR49","doi-asserted-by":"crossref","unstructured":"Leite, R., & Brazdil, P. (2004). Improving progressive sampling via meta-learning on learning curves. In European conference on machine learning (pp. 250\u2013261). Springer.","DOI":"10.1007\/978-3-540-30115-8_25"},{"key":"6047_CR50","first-page":"583","volume":"14","author":"M Li","year":"2014","unstructured":"Li, M., Andersen, D. G., Park, J. W., Smola, A. J., Ahmed, A., Josifovski, V., Long, J., Shekita, E. J., & Su, B. Y. (2014). Scaling distributed machine learning with the parameter server. OSDI, 14, 583\u2013598.","journal-title":"OSDI"},{"key":"6047_CR51","unstructured":"Liaw, A., Wiener, M., et al. (2002). Classification and regression by randomforest. R News, 2(3), 18\u201322."},{"issue":"1","key":"6047_CR52","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1109\/TVCG.2017.2744378","volume":"24","author":"S Liu","year":"2017","unstructured":"Liu, S., Xiao, J., Liu, J., Wang, X., Wu, J., & Zhu, J. (2017). Visual diagnosis of tree boosting methods. IEEE Transactions on Visualization and Computer Graphics, 24(1), 163\u2013173.","journal-title":"IEEE Transactions on Visualization and Computer Graphics"},{"key":"6047_CR53","unstructured":"Machine Learning Group - ULB. (2013). Credit card fraud detection dataset. https:\/\/www.kaggle.com\/isaikumar\/creditcardfraud. Online; Accessed 26 August 2019."},{"key":"6047_CR54","unstructured":"Machine Learning Repository - UCI. (1998). Forest cover type dataset. https:\/\/archive.ics.uci.edu\/ml\/datasets\/Covertype. Online; Accessed 26 August 2019."},{"key":"6047_CR55","unstructured":"Machine Learning Repository - UCI. (1999). KDD cup 1999 dataset. http:\/\/kdd.ics.uci.edu\/databases\/kddcup99\/kddcup99.html. Online; Accessed 26 August 2019."},{"issue":"9","key":"6047_CR56","doi-asserted-by":"publisher","first-page":"1630","DOI":"10.1587\/transinf.2014OPP0004","volume":"98","author":"Y Mishina","year":"2015","unstructured":"Mishina, Y., Murata, R., Yamauchi, Y., Yamashita, T., & Fujiyoshi, H. (2015). Boosted random forest. IEICE Transactions on Information and systems, 98(9), 1630\u20131636.","journal-title":"IEICE Transactions on Information and systems"},{"key":"6047_CR57","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/j.jnca.2018.12.006","volume":"128","author":"N Moustafa","year":"2019","unstructured":"Moustafa, N., Hu, J., & Slay, J. (2019). A holistic review of network anomaly detection systems: A comprehensive survey. Journal of Network and Computer Applications, 128, 33\u201355.","journal-title":"Journal of Network and Computer Applications"},{"key":"6047_CR58","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1016\/j.proeng.2012.01.849","volume":"30","author":"AP Muniyandi","year":"2012","unstructured":"Muniyandi, A. P., Rajeswari, R., & Rajaram, R. (2012). Network anomaly detection by cascading k-means clustering and c4.5 decision tree algorithm. Procedia Engineering, 30, 174\u2013182.","journal-title":"Procedia Engineering"},{"key":"6047_CR59","unstructured":"Obradovic, Z., & Vucetic, S. (2004). Challenges in scientific data mining: Heterogeneous, biased, and large samples. Citeseer: Tech. rep."},{"key":"6047_CR60","unstructured":"Olson, M. (2017). Jousboost: An R package for improving machine learning classifier probability estimates."},{"key":"6047_CR61","doi-asserted-by":"crossref","unstructured":"Oza, N. C., & Russell, S. (2001). Experimental comparisons of online and batch versions of bagging and boosting. In Proceedings of the seventh ACM SIGKDD international conference on Knowledge discovery and data mining (pp. 359\u2013364). ACM.","DOI":"10.1145\/502512.502565"},{"key":"6047_CR62","doi-asserted-by":"crossref","unstructured":"Parthasarathy, S. (2002). Efficient progressive sampling for association rules. In 2002 IEEE international conference on data mining, 2002. Proceedings (pp. 354\u2013361). IEEE.","DOI":"10.1109\/ICDM.2002.1183923"},{"key":"6047_CR63","unstructured":"Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., & Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12, 2825\u20132830."},{"key":"6047_CR64","unstructured":"Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A. V., & Gulin, A. (2018). Catboost: Unbiased boosting with categorical features. In Advances in neural information processing systems (pp. 6638\u20136648)."},{"key":"6047_CR65","doi-asserted-by":"crossref","unstructured":"Provost, F., Jensen, D., & Oates, T. (1999). Efficient progressive sampling. In Proceedings of the fifth ACM SIGKDD international conference on knowledge discovery and data mining (pp. 23\u201332). ACM.","DOI":"10.1145\/312129.312188"},{"key":"6047_CR66","unstructured":"PyPI & XGBoost. (2018). XGBoost. https:\/\/pypi.org\/project\/xgboost\/. Online; Accessed 7 September 2019."},{"key":"6047_CR67","unstructured":"Ravanshad, A. (2018). Medium corporation. Gradient boosting vs random forest. https:\/\/bit.ly\/2lT5IZ4. Online; Accessed 7 September 2019."},{"issue":"8","key":"6047_CR68","doi-asserted-by":"publisher","first-page":"2661","DOI":"10.1016\/j.adhoc.2013.04.014","volume":"11","author":"S Raza","year":"2013","unstructured":"Raza, S., Wallgren, L., & Voigt, T. (2013). Svelte: Real-time intrusion detection in the internet of things. Ad Hoc Networks, 11(8), 2661\u20132674.","journal-title":"Ad Hoc Networks"},{"issue":"3","key":"6047_CR69","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1145\/3178582","volume":"51","author":"PAA Resende","year":"2018","unstructured":"Resende, P. A. A., & Drummond, A. C. (2018). A survey of random forest based methods for intrusion detection systems. ACM Computing Surveys (CSUR), 51(3), 48.","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"6047_CR70","unstructured":"Right to Explanation. (2019). Wikipedia, the free encyclopedia. https:\/\/en.wikipedia.org\/wiki\/Right_to_explanation. Online; Accessed 26 August 2019."},{"key":"6047_CR71","doi-asserted-by":"crossref","unstructured":"Roe, B. P., Yang, H. J., & Zhu, J. (2006). Boosted decision trees, a powerful event classifier. In Statistical problems in particle physics, astrophysics and cosmology (pp. 139\u2013142). World Scientific.","DOI":"10.1142\/9781860948985_0029"},{"issue":"2\u20133","key":"6047_CR72","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1016\/j.nima.2004.12.018","volume":"543","author":"BP Roe","year":"2005","unstructured":"Roe, B. P., Yang, H. J., Zhu, J., Liu, Y., Stancu, I., & McGregor, G. (2005). Boosted decision trees as an alternative to artificial neural networks for particle identification. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 543(2\u20133), 577\u2013584.","journal-title":"Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment"},{"key":"6047_CR73","unstructured":"Sabhnani, M., & Serpen, G. (2003). Application of machine learning algorithms to KDD intrusion detection dataset within misuse detection context. In MLMTA (pp. 209\u2013215)."},{"key":"6047_CR74","doi-asserted-by":"crossref","unstructured":"Schapire, R. E. (2003). The boosting approach to machine learning: An overview. In Nonlinear estimation and classification (pp. 149\u2013171). Springer.","DOI":"10.1007\/978-0-387-21579-2_9"},{"key":"6047_CR75","doi-asserted-by":"crossref","unstructured":"Schneible, J., & Lu, A. (2017). Anomaly detection on the edge. In MILCOM 2017-2017 IEEE military communications conference (MILCOM) (pp. 678\u2013682). IEEE.","DOI":"10.1109\/MILCOM.2017.8170817"},{"key":"6047_CR76","unstructured":"Scikit - RF (2019). sklearn.ensemble.randomforestclassifier. https:\/\/scikit-learn.org\/stable\/modules\/generated\/sklearn.ensemble.RandomForestClassifier.html#sklearn.ensemble.RandomForestClassifier. Online; Accessed 7 September 2019."},{"key":"6047_CR77","doi-asserted-by":"crossref","unstructured":"Seyedhosseini, M., Paiva, A. R., & Tasdizen, T. (2011). Fast adaboost training using weighted novelty selection. In The international joint conference on neural networks (pp. 1245\u20131250). IEEE.","DOI":"10.1109\/IJCNN.2011.6033366"},{"key":"6047_CR79","doi-asserted-by":"crossref","unstructured":"Shen, H., Han, S., Philipose, M., & Krishnamurthy, A. (2017). Fast video classification via adaptive cascading of deep models. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3646\u20133654).","DOI":"10.1109\/CVPR.2017.236"},{"key":"6047_CR80","doi-asserted-by":"publisher","first-page":"488","DOI":"10.1016\/j.ins.2014.03.066","volume":"278","author":"K Singh","year":"2014","unstructured":"Singh, K., Guntuku, S. C., Thakur, A., & Hota, C. (2014). Big data analytics framework for peer-to-peer botnet detection using random forests. Information Sciences, 278, 488\u2013497.","journal-title":"Information Sciences"},{"key":"6047_CR81","doi-asserted-by":"crossref","unstructured":"Sleeman\u00a0IV, W. C., & Krawczyk, B. (2019). Bagging using instance-level difficulty for multi-class imbalanced big data classification on spark. In 2019 IEEE international conference on big data (big data) (pp. 2484\u20132493). IEEE.","DOI":"10.1109\/BigData47090.2019.9006058"},{"issue":"2","key":"6047_CR82","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1111\/coin.12047","volume":"32","author":"MR Smith","year":"2016","unstructured":"Smith, M. R., & Martinez, T. (2016). A comparative evaluation of curriculum learning with filtering and boosting in supervised classification problems. Computational Intelligence, 32(2), 167\u2013195.","journal-title":"Computational Intelligence"},{"issue":"2","key":"6047_CR83","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1007\/s10994-013-5422-z","volume":"95","author":"MR Smith","year":"2014","unstructured":"Smith, M. R., Martinez, T., & Giraud-Carrier, C. (2014). An instance level analysis of data complexity. Machine Learning, 95(2), 225\u2013256.","journal-title":"Machine Learning"},{"key":"6047_CR84","unstructured":"Tan, S. C., Ting, K. M., & Liu, T. F. (2011). Fast anomaly detection for streaming data. In Twenty-second international joint conference on artificial intelligence."},{"key":"6047_CR85","unstructured":"Tang, J., Alelyani, S., & Liu, H. (2014). Feature selection for classification: A review. Data classification: Algorithms and applications (p.\u00a037)."},{"key":"6047_CR86","doi-asserted-by":"crossref","unstructured":"Tavallaee, M., Bagheri, E., Lu, W., & Ghorbani, A. (2009). A detailed analysis of the KDD cup 99 data set. In Symposium on computational intelligence for security and defense applications (CISDA) (pp. 1\u20136). IEEE.","DOI":"10.1109\/CISDA.2009.5356528"},{"key":"6047_CR87","doi-asserted-by":"crossref","unstructured":"Teerapittayanon, S., McDanel, B., & Kung, H. (2016). Branchynet: Fast inference via early exiting from deep neural networks. In 2016 23rd International conference on pattern recognition (ICPR) (pp. 2464\u20132469). IEEE.","DOI":"10.1109\/ICPR.2016.7900006"},{"key":"6047_CR88","doi-asserted-by":"crossref","unstructured":"Teerapittayanon, S., McDanel, B., & Kung, H. (2017). Distributed deep neural networks over the cloud, the edge and end devices. In 2017 IEEE 37th international conference on distributed computing systems (ICDCS) (pp. 328\u2013339). IEEE.","DOI":"10.1109\/ICDCS.2017.226"},{"issue":"1","key":"6047_CR89","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-020-00320-x","volume":"7","author":"S Thudumu","year":"2020","unstructured":"Thudumu, S., Branch, P., Jin, J., & Singh, J. J. (2020). A comprehensive survey of anomaly detection techniques for high dimensional big data. Journal of Big Data, 7(1), 1\u201330.","journal-title":"Journal of Big Data"},{"key":"6047_CR90","unstructured":"Ting, K. M., & Witten, I. H. (1997). Stacking bagged and dagged models."},{"key":"6047_CR91","doi-asserted-by":"crossref","unstructured":"Ukil, A., Bandyoapdhyay, S., Puri, C., & Pal, A. (2016). Iot healthcare analytics: The importance of anomaly detection. In 2016 IEEE 30th international conference on advanced information networking and applications (AINA) (pp. 994\u2013997). IEEE.","DOI":"10.1109\/AINA.2016.158"},{"key":"6047_CR92","doi-asserted-by":"crossref","unstructured":"Van\u00a0Essen, B., Macaraeg, C., Gokhale, M., & Prenger, R. (2012). Accelerating a random forest classifier: Multi-core, GP-GPU, or FPGA? In 20th international symposium on field-programmable custom computing machines (pp. 232\u2013239). IEEE.","DOI":"10.1109\/FCCM.2012.47"},{"key":"6047_CR78","unstructured":"Vargaftik, S., & Ben-Itzhak, Y. (2019). RADE\u2019s code. https:\/\/research.vmware.com\/admin\/projects\/efficient-machine-learning-classification"},{"key":"6047_CR93","doi-asserted-by":"crossref","unstructured":"Viola, P., Jones, M., et al. (2001). Rapid object detection using a boosted cascade of simple features. CVPR (1), 1(511\u2013518), 3.","DOI":"10.1109\/CVPR.2001.990517"},{"key":"6047_CR94","doi-asserted-by":"crossref","unstructured":"Walmsley, F. N., Cavalcanti, G. D., Oliveira, D. V., Cruz, R. M., & Sabourin, R. (2018) An ensemble generation method based on instance hardness. In 2018 international joint conference on neural networks (IJCNN) (pp. 1\u20138). IEEE.","DOI":"10.1109\/IJCNN.2018.8489269"},{"key":"6047_CR95","unstructured":"Wang, Y., & Patrick, J. (2009). Cascading classifiers for named entity recognition in clinical notes. In Proceedings of the workshop on biomedical information extraction (pp. 42\u201349). Association for Computational Linguistics."},{"issue":"2","key":"6047_CR96","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1016\/S0893-6080(05)80023-1","volume":"5","author":"DH Wolpert","year":"1992","unstructured":"Wolpert, D. H. (1992). Stacked generalization. Neural Networks, 5(2), 241\u2013259.","journal-title":"Neural Networks"},{"key":"6047_CR97","doi-asserted-by":"crossref","unstructured":"Xuan, S., Liu, G., Li, Z., Zheng, L., Wang, S., & Jiang, C. (2018). Random forest for credit card fraud detection. In 2018 IEEE 15th international conference on networking, sensing and control (ICNSC) (pp. 1\u20136). IEEE.","DOI":"10.1109\/ICNSC.2018.8361343"},{"issue":"3","key":"6047_CR98","doi-asserted-by":"publisher","first-page":"5718","DOI":"10.1016\/j.eswa.2008.06.108","volume":"36","author":"SJ Yen","year":"2009","unstructured":"Yen, S. J., & Lee, Y. S. (2009). Cluster-based under-sampling approaches for imbalanced data distributions. Expert Systems with Applications, 36(3), 5718\u20135727.","journal-title":"Expert Systems with Applications"},{"key":"6047_CR99","doi-asserted-by":"crossref","unstructured":"Zhang, J., Wang, T., Ng, W. W., Zhang, S., & Nugent, C. D. (2019). Undersampling near decision boundary for imbalance problems. In 2019 International conference on machine learning and cybernetics (ICMLC) (pp. 1\u20138). IEEE.","DOI":"10.1109\/ICMLC48188.2019.8949290"},{"key":"6047_CR100","doi-asserted-by":"crossref","unstructured":"Zhang, J., & Zulkernine, M. (2005) Network intrusion detection using random forests. In PST. Citeseer","DOI":"10.1109\/ARES.2006.7"},{"key":"6047_CR101","doi-asserted-by":"crossref","unstructured":"Zhao, Z., Mehrotra, K. G., & Mohan, C. K. (2018.) Online anomaly detection using random forest. In International conference on industrial, engineering and other applications of applied intelligent systems (pp. 135\u2013147). Springer.","DOI":"10.1007\/978-3-319-92058-0_13"},{"issue":"5","key":"6047_CR102","first-page":"1017","volume":"34","author":"Z Zheng","year":"2016","unstructured":"Zheng, Z., Cai, Y., & Li, Y. (2016). Oversampling method for imbalanced classification. Computing and Informatics, 34(5), 1017\u20131037.","journal-title":"Computing and Informatics"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-021-06047-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-021-06047-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-021-06047-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,3]],"date-time":"2022-09-03T01:41:55Z","timestamp":1662169315000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-021-06047-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,3]]},"references-count":102,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2021,10]]}},"alternative-id":["6047"],"URL":"https:\/\/doi.org\/10.1007\/s10994-021-06047-x","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,3]]},"assertion":[{"value":"3 September 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 July 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 July 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 September 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}