{"type":"ScholarlyArticle","title":"Learning What to Monitor: Using Machine Learning to Improve past STL Monitoring","authors":[{"name":"Andrea Brunello","slug":"andrea-brunello","given":"Andrea","family":"Brunello","affiliation":"University of Udine , Udine , Italy"},{"name":"Luca Geatti","slug":"luca-geatti","given":"Luca","family":"Geatti","affiliation":"University of Udine , Udine , Italy"},{"name":"Angelo Montanari","slug":"angelo-montanari","given":"Angelo","family":"Montanari","affiliation":"University of Udine , Udine , Italy"},{"name":"Nicola Saccomanno","slug":"nicola-saccomanno","given":"Nicola","family":"Saccomanno","affiliation":"University of Udine , Udine , Italy"}],"abstract":"Monitoring is a runtime verification technique that can be used to check whether an execution of a system (trace) satisfies or not a given set of properties. Compared to other formal verification techniques, e.g., model checking, one needs to specify the properties to be monitored, but a complete model of the system is no longer necessary. First, we introduce the pure past fragment of Signal Temporal Logic (ppSTL), and we use it to define the monitorable safety (G(ppSTL)) and cosafety (F(ppSTL)) fragments of STL, which properly extend the commonly-used bounded-future fragment. Then, we devise a multi-objective genetic programming algorithm to automatically extend the set of properties to monitor on the basis of the history of failure traces collected over time. The framework resulting from the integration of the monitor and the learning algorithm is then experimentally validated on various public datasets. The outcomes of the experimentation confirm the effectiveness of the proposed solution.","doi":"10.24963/ijcai.2024/362","url":"https://ijcai.org/proceedings/2024/362","pdf":"https://ijcai.org/proceedings/2024/0362.pdf","markdown":"https://ijcai.org/proceedings/2024/362.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/362","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Knowledge Representation and Reasoning","track":"Main Track","number":362,"pages":{"first":3270,"last":3280},"keywords":["Knowledge Representation and Reasoning: KRR: Learning and reasoning","Knowledge Representation and Reasoning: KRR: Qualitative, geometric, spatial, and temporal reasoning","Machine Learning: ML: Explainable/Interpretable machine learning","Machine Learning: ML: Symbolic methods"],"videos":[],"references":[{"position":1,"raw":"[Aggarwal et al., 2018] Karan Aggarwal, Onur Atan, Ahmed K Farahat, Chi Zhang, Kosta Ristovski, and Chetan Gupta. Two birds with one network: Unifying failure event prediction and time-to-failure modeling. In Proceedings of IEEE International Conference on Big Data (Big Data), pages 1308-1317. IEEE, 2018.","title":"Two birds with one network: Unifying failure event prediction and time-to-failure modeling","authors":"Karan Aggarwal, Onur Atan, Ahmed K Farahat, Chi Zhang, Kosta Ristovski, Chetan Gupta","year":"2018","venue":"Proceedings of IEEE International Conference on Big Data (Big Data)","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bauer et al., 2011] Andreas Bauer, Martin Leucker, and Christian Schallhart. Runtime verification for LTL and TLTL. ACM Transactions on Software Engineering and Methodology (TOSEM), 20(4):1-64, 2011.","title":"Runtime verification for LTL and TLTL","authors":"Andreas Bauer, Martin Leucker, Christian Schallhart","year":"2011","venue":"ACM Transactions on Software Engineering and Methodology (TOSEM)","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bilodeau et al., 2024] Blair Bilodeau, Natasha Jaques, Pang Wei Koh, and Been Kim. Impossibility theorems for feature attribution. Proceedings of the National Academy of Sciences, 121(2):e2304406120, 2024.","title":"Impossibility theorems for feature attribution","authors":"Blair Bilodeau, Natasha Jaques, Pang Wei Koh, Been Kim","year":"2024","venue":"Proceedings of the National Academy of Sciences","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Brunello et al., 2023] Andrea Brunello, Dario Della Mon- ica, Angelo Montanari, Nicola Saccomanno, and Andrea Urgolo. Monitors that learn from failures: Pairing STL and genetic programming. IEEE Access, 11:57349-57364, 2023.","title":"Monitors that learn from failures: Pairing STL and genetic programming","authors":"Andrea Brunello, Dario Della Monica, Angelo Montanari, Nicola Saccomanno, Andrea Urgolo","year":"2023","venue":"IEEE Access","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chen et al., 2018] Yukang Chen, Gaofeng Meng, Qian Zhang, Shiming Xiang, Chang Huang, Lisen Mu, and Xinggang Wang. Reinforced evolutionary neural architec- ture search. arXiv preprint arXiv:1808.00193, 2018.","title":"Reinforced evolutionary neural architecture search","authors":"Yukang Chen, Gaofeng Meng, Qian Zhang, Shiming Xiang, Chang Huang, Lisen Mu, Xinggang Wang","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Chen et al., 2020] Diqi Chen, Yizhou Wang, and Wen Gao. Combining a gradient-based method and an evolution strategy for multi-objective reinforcement learning. Ap- plied Intelligence, 50:3301-3317, 2020.","title":"Combining a gradient-based method and an evolution strategy for multi-objective reinforcement learning","authors":"Chen","year":"2020","venue":"Applied Intelligence","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Chicco and Jurman, 2020] Davide Chicco and Giuseppe Ju- rman. The advantages of the matthews correlation coeffi- cient (MCC) over F1 score and accuracy in binary classi- fication evaluation. BMC Genomics, 21(1):1-13, 2020.","title":"The advantages of the matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation","authors":"Davide Chicco, Giuseppe Jurman","year":"2020","venue":"BMC Genomics","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Cranmer et al., 2020] M. Cranmer, Alvaro Sanchez- Gonzalez, P. Battaglia, Rui Xu, K. Cranmer, D. Spergel, and S. Ho. Discovering symbolic models from deep learning with inductive biases. ArXiv, abs/2006.11287, 2020.","title":"Discovering symbolic models from deep learning with inductive biases","authors":"M Cranmer, Alvaro Sanchez-Gonzalez, P Battaglia, Rui Xu, K Cranmer, D Spergel, S Ho","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Deb et al., 2002] K. Deb, A. Pratap, S. Agarwal, and T. Me- yarivan. A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Transactions on Evolutionary Computa- tion, 6(2):182-197, 2002.","title":"A fast and elitist multiobjective genetic algorithm: NSGA-II","authors":"K Deb, A Pratap, S Agarwal, T Meyarivan","year":"2002","venue":"IEEE Transactions on Evolutionary Computation","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Donzé and Maler, 2010] Alexandre Donzé and Oded Maler. Robust satisfaction of temporal logic over real-valued sig- nals. In Krishnendu Chatterjee and Thomas A. Henzinger, editors, Proceedings of the 8th International Conference on Formal Modeling and Analysis of Timed Systems (FOR- MATS 2010), pages 92-106. Springer, 2010.","title":"Robust satisfaction of temporal logic over real-valued signals","authors":"Maler Donzé, Alexandre Donzé, Oded Maler","year":"2010","venue":"Proceedings of the 8th International Conference on Formal Modeling and Analysis of Timed Systems (FOR-MATS 2010)","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Fortin et al., 2012] F. A. Fortin, F. M. De Rainville, M. A. Gardner, M. Parizeau, and C. Gagné. DEAP: Evolution- ary algorithms made easy. Journal of Machine Learning Research, 13:2171-2175, 2012.","title":"DEAP: Evolutionary algorithms made easy","authors":"F A Fortin, F M De Rainville, M A Gardner, M Parizeau, C Gagné","year":"2012","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Gao et al., 2022] Jiechao Gao, Haoyu Wang, and Haiying Shen. Task failure prediction in cloud data centers using deep learning. IEEE Transactions on Services Computing, 15:1411-1422, 2022.","title":"Task failure prediction in cloud data centers using deep learning","authors":"Gao","year":"2022","venue":"IEEE Transactions on Services Computing","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Ghallab et al., 2004] Malik Ghallab, Dana S. Nau, and Paolo Traverso. Automated planning -theory and prac- tice. Elsevier, 2004.","title":"Automated planning -theory and practice","authors":"Malik Ghallab, Dana S Nau, Paolo Traverso","year":"2004","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Gonc ¸alves and Silva, 2013] Ivo Gonc ¸alves and Sara Silva. Balancing learning and overfitting in genetic programming with interleaved sampling of training data. In Proceed- ings of the European Conference on Genetic Programming (EuroGP), pages 73-84. Springer, 2013.","title":"Balancing learning and overfitting in genetic programming with interleaved sampling of training data","authors":"Gonc ¸alves, ; ] Silva, Gonc Ivo, Sara ¸alves, Silva","year":"2013","venue":"Proceedings of the European Conference on Genetic Programming (EuroGP)","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Hajihosseini et al., 2018] Payman Hajihosseini, Moham- mad Mousavi Anzehaee, and Behzad Behnam. Fault de- tection and isolation in the challenging Tennessee Eastman Process by using image processing techniques. ISA Trans- actions, 79:137-146, 2018.","title":"Fault detection and isolation in the challenging Tennessee Eastman Process by using image processing techniques","authors":"Payman Hajihosseini, Mohammad Mousavi Anzehaee, Behzad Behnam","year":"2018","venue":"ISA Transactions","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Hastie et al., 2009] Trevor Hastie, Robert Tibshirani, Jerome H Friedman, and Jerome H Friedman. The elements of statistical learning: data mining, inference, and prediction, volume 2. Springer, 2009.","title":"The elements of statistical learning: data mining, inference, and prediction","authors":"Trevor Hastie, Robert Tibshirani, Jerome H Friedman, Jerome H Friedman","year":"2009","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Havelund and Peled, 2023] Klaus Havelund and Doron Peled. Monitorability for runtime verification. In Pana- giotis Katsaros and Laura Nenzi, editors, Proceedings of the 23rd International Conference on Runtime Verification (RV 2023), volume 14245 of Lecture Notes in Computer Science, pages 447-460. Springer, 2023.","title":"Monitorability for runtime verification","authors":"Peled Havelund, Klaus Havelund, Doron Peled","year":"2023","venue":"Proceedings of the 23rd International Conference on Runtime Verification (RV 2023)","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Holt et al., 2023] Samuel Holt, Zhaozhi Qian, and Mihaela van der Schaar. Deep generative symbolic regression. arXiv preprint arXiv:2401.00282, 2023.","title":"Deep generative symbolic regression","authors":"Holt","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Huang, 2017] X. Huang. Hard drive failure prediction for large scale storage system. 2017. M.Sc Thesis.","title":"Hard drive failure prediction for large scale storage system","authors":"X Huang","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Kim and Sohn, 2020] Tae San Kim and So Young Sohn. Multitask learning for health condition identification and remaining useful life prediction: Deep convolutional neu- ral network approach. Journal of Intelligent Manufactur- ing, 32(8):2169-2179, 2020.","title":"Multitask learning for health condition identification and remaining useful life prediction: Deep convolutional neural network approach","authors":"Sohn ; ] Kim, San Tae, So Kim, Young Sohn","year":"2020","venue":"Journal of Intelligent Manufacturing","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Koza, 1994] John R Koza. Genetic programming as a means for programming computers by natural selection. Statistics and Computing, 4(2):87-112, 1994.","title":"Genetic programming as a means for programming computers by natural selection","authors":"John R Koza","year":"1994","venue":"Statistics and Computing","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Kupferman and Vardi, 2001] Orna Kupferman and Moshe Y Vardi. Model checking of safety proper- ties. Formal Methods in System Design, 19(3):291-314, 2001.","title":"Model checking of safety properties","authors":"Vardi ; ] Orna Kupferman, Moshe Y Kupferman, Vardi","year":"2001","venue":"Formal Methods in System Design","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Leucker and Schallhart, 2009] Martin Leucker and Chris- tian Schallhart. A brief account of runtime verifica- tion. The Journal of Logic and Algebraic Programming, 78(5):293-303, 2009.","title":"A brief account of runtime verification","authors":"Martin Leucker, Christian Schallhart","year":"2009","venue":"The Journal of Logic and Algebraic Programming","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Lu et al., 2020] Sidi Lu, Bing Luo, Tirthak Patel, Yongtao Yao, Devesh Tiwari, and Weisong Shi. Making disk fail- ure predictions SMARTer! In Proceedings of the 21st USENIX Conference on File and Storage Technologies (FAST'23), pages 151-167. USENIX Association, 2020.","title":"Making disk failure predictions SMARTer!","authors":"Sidi Lu, Bing Luo, Tirthak Patel, Yongtao Yao, Devesh Tiwari, Weisong Shi","year":"2020","venue":"Proceedings of the 21st USENIX Conference on File and Storage Technologies (FAST'23)","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Maler and Nickovic, 2004] Oded Maler and Dejan Nick- ovic. Monitoring temporal properties of continuous sig- nals. In Yassine Lakhnech and Sergio Yovine, editors, Proceedings of the Joint International Conferences on Formal Modelling and Analysis of Timed Systems (FOR- MATS 2004) and Formal Techniques in Real-Time and Fault-Tolerant Systems (FTRTFT 2004), pages 152-166. Springer, 2004.","title":"Monitoring temporal properties of continuous signals","authors":"Nickovic Maler, Oded Maler, Dejan Nickovic","year":"2004","venue":"Proceedings of the Joint International Conferences on Formal Modelling and Analysis of Timed Systems (FOR-MATS 2004) and Formal Techniques in Real-Time and Fault-Tolerant Systems (FTRTFT 2004)","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Mundhenk et al., 2021] Terrell Mundhenk, Mikel Landa- juela, Ruben Glatt, Claudio P Santiago, Brenden K Petersen, et al. Symbolic regression via deep rein- forcement learning enhanced genetic programming seed- ing. Advances in Neural Information Processing Systems, 34:24912-24923, 2021.","title":"Symbolic regression via deep reinforcement learning enhanced genetic programming seeding","authors":"Terrell Mundhenk, Mikel Landajuela, Ruben Glatt, Claudio P Santiago, Brenden K Petersen","year":"2021","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Ničković and Yamaguchi, 2020] D. Ničković and T. Ya- maguchi. RTAMT: Online robustness monitors from STL. In Proceedings of the 18th International Sympo- sium on Automated Technology for Verification and Analy- sis (ATVA 2020), volume 12302, pages 564-571. Springer, 2020.","title":"RTAMT: Online robustness monitors from STL","authors":"D Ničković, T Yamaguchi","year":"2020","venue":"Proceedings of the 18th International Symposium on Automated Technology for Verification and Analysis (ATVA 2020)","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Onel et al., 2019] Melis Onel, Chris A. Kieslich, and Efstra- tios N. Pistikopoulos. A nonlinear support vector machine- based feature selection approach for fault detection and diagnosis: Application to the Tennessee Eastman Pro- cess. American Institute of Chemical Engineers Journal, 65(3):992-1005, 2019.","title":"A nonlinear support vector machinebased feature selection approach for fault detection and diagnosis: Application to the Tennessee Eastman Process","authors":"Melis Onel, Chris A Kieslich, Efstratios N Pistikopoulos","year":"2019","venue":"American Institute of Chemical Engineers Journal","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Petmezas et al., 2021] Georgios Petmezas, Kostas Haris, Leandros Stefanopoulos, Vassilis Kilintzis, Andreas Tza- velis, John A Rogers, Aggelos K Katsaggelos, and Nicos Maglaveras. Automated atrial fibrillation detection using a hybrid CNN-LSTM network on imbalanced ECG datasets. Biomedical Signal Processing and Control, 63:102194, 2021.","title":"Automated atrial fibrillation detection using a hybrid CNN-LSTM network on imbalanced ECG datasets","authors":"Georgios Petmezas, Kostas Haris, Leandros Stefanopoulos, Vassilis Kilintzis, Andreas Tzavelis, John A Rogers, Aggelos K Katsaggelos, Nicos Maglaveras","year":"2021","venue":"Biomedical Signal Processing and Control","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Poli et al., 2008] R. Poli, W. Langdon, and N. Mcphee. A Field Guide to Genetic Programming. http://www.gp- field-guide.org.uk, 2008.","title":"A Field Guide to Genetic Programming","authors":"R Poli, W Langdon, N Mcphee","year":"2008","venue":null,"doi":null,"url":"http://www.gp-field-guide.org.uk","internal_url":null},{"position":31,"raw":"[Qian et al., 2021] Kai Qian, Jie Jiang, Yulong Ding, and Shuang-Hua Yang. DLGEA: A deep learning guided evo- lutionary algorithm for water contamination source identi- fication. Neural Computing and Applications, 33:11889- 11903, 2021.","title":"DLGEA: A deep learning guided evolutionary algorithm for water contamination source identification","authors":"Kai Qian, Jie Jiang, Yulong Ding, Shuang-Hua Yang","year":"2021","venue":"Neural Computing and Applications","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Williams and Zipser, 1989] Ronald J. Williams and David Zipser. A learning algorithm for continually running fully recurrent neural networks. Neural Computation, 1(2):270- 280, 1989.","title":"A learning algorithm for continually running fully recurrent neural networks","authors":"Ronald J Williams, David Zipser","year":"1989","venue":"Neural Computation","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}