{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T16:21:16Z","timestamp":1772727676211,"version":"3.50.1"},"reference-count":29,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2021,10,27]],"date-time":"2021-10-27T00:00:00Z","timestamp":1635292800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001381","name":"National Research Foundation, Singapore","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100008629","name":"Infocomm Media Development Authority","doi-asserted-by":"crossref","award":["T2EP20120-0006"],"award-info":[{"award-number":["T2EP20120-0006"]}],"id":[{"id":"10.13039\/501100008629","id-type":"DOI","asserted-by":"crossref"}]},{"name":"National Science Foundation","award":["CNS-2008878"],"award-info":[{"award-number":["CNS-2008878"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Internet Things"],"published-print":{"date-parts":[[2022,2,28]]},"abstract":"<jats:p>\n            The advances in deep neural networks (DNN) have significantly enhanced real-time detection of anomalous data in IoT applications. However, the complexity-accuracy-delay dilemma persists: Complex DNN models offer higher accuracy, but typical IoT devices can barely afford the computation load, and the remedy of offloading the load to the cloud incurs long delay. In this article, we address this challenge by proposing an adaptive anomaly detection scheme with hierarchical edge computing (HEC). Specifically, we first construct multiple anomaly detection DNN models with increasing complexity and associate each of them to a corresponding HEC layer. Then, we design an adaptive model selection scheme that is formulated as a\n            <jats:italic>contextual-bandit problem<\/jats:italic>\n            and solved by using a\n            <jats:italic>reinforcement learning policy network<\/jats:italic>\n            . We also incorporate a parallelism policy training method to accelerate the training process by taking advantage of distributed models. We build an HEC testbed using real IoT devices and implement and evaluate our contextual-bandit approach with both univariate and multivariate IoT datasets. In comparison with both baseline and state-of-the-art schemes, our adaptive approach strikes the best accuracy-delay tradeoff on the univariate dataset and achieves the best accuracy and F1-score on the multivariate dataset with only negligibly longer delay than the best (but inflexible) scheme.\n          <\/jats:p>","DOI":"10.1145\/3480172","type":"journal-article","created":{"date-parts":[[2021,10,27]],"date-time":"2021-10-27T17:26:03Z","timestamp":1635355563000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":19,"title":["Adaptive Anomaly Detection for Internet of Things in Hierarchical Edge Computing: A Contextual-Bandit Approach"],"prefix":"10.1145","volume":"3","author":[{"given":"Mao V.","family":"Ngo","sequence":"first","affiliation":[{"name":"Singapore University of Technology and Design, Singapore"}]},{"given":"Tie","family":"Luo","sequence":"additional","affiliation":[{"name":"Missouri University of Science and Technology, Rolla, MO, USA"}]},{"given":"Tony Q. S.","family":"Quek","sequence":"additional","affiliation":[{"name":"Singapore University of Technology and Design, Singapore"}]}],"member":"320","published-online":{"date-parts":[[2021,10,27]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.5555\/2969239.2969370"},{"key":"e_1_3_2_3_2","unstructured":"Raghavendra Chalapathy and Sanjay Chawla. 2019. Deep learning for anomaly detection: A survey. arxiv:1901.03407 [cs.LG]. Retrieved from https:\/\/arxiv.org\/abs\/1901.03407."},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3132211.3134458"},{"key":"e_1_3_2_5_2","unstructured":"Lasse Espeholt Raphael Marinier Piotr Stanczyk Ke Wang and Marcin Michalski. 2020. SEED RL: Scalable and efficient deep-RL with accelerated central inference. arxiv:1910.06591 [cs.LG]. Retrieved from https:\/\/arxiv.org\/abs\/1910.06591."},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.5555\/2621979"},{"key":"e_1_3_2_7_2","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","author":"Han Song","year":"2016","unstructured":"Song Han, Huizi Mao, and William J. Dally. 2016. Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. In Proc. ICLR.","journal-title":"Proc. ICLR"},{"key":"e_1_3_2_8_2","article-title":"Distilling the knowledge in a neural network","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. In Proce NIPS 2014 Deep Learning Workshop.","journal-title":"Proce NIPS 2014 Deep Learning Workshop"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3093337.3037698"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2005.79"},{"issue":"1","key":"e_1_3_2_11_2","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.dcan.2018.10.008","article-title":"Enabling intelligence in fog computing to achieve energy and latency reduction","volume":"5","author":"La Quang Duy","year":"2019","unstructured":"Quang Duy La, Mao V. Ngo, Thinh Quang Dinh, Tony Q. S. Quek, and Hyundong Shin. 2019. Enabling intelligence in fog computing to achieve energy and latency reduction. Dig. Commun. Netw. 5, 1 (2019), 3\u20139.","journal-title":"Dig. Commun. Netw."},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2018.1700202"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.5555\/3294771.3294979"},{"key":"e_1_3_2_14_2","volume-title":"Proc. IEEE ICC","author":"Luo T.","year":"2018","unstructured":"T. Luo and S. G. Nagarajan. 2018. Distributed anomaly detection using autoencoder neural networks in WSN for IoT. In Proc. IEEE ICC."},{"key":"e_1_3_2_15_2","article-title":"LSTM-based encoder-decoder for multi-sensor anomaly detection","author":"Malhotra Pankaj","year":"2016","unstructured":"Pankaj Malhotra, Anusha Ramakrishnan, Gaurangi Anand, Lovekesh Vig, Puneet Agarwal, and Gautam Shroff. 2016. LSTM-based encoder-decoder for multi-sensor anomaly detection. In Proc. ICML Workshop.","journal-title":"Proc. ICML Workshop"},{"key":"e_1_3_2_16_2","first-page":"89","volume-title":"Proc. ESANN","author":"Malhotra Pankaj","year":"2015","unstructured":"Pankaj Malhotra, Lovekesh Vig, Gautam Shroff, and Puneet Agarwal. 2015. Long short term memory networks for anomaly detection in time series. In Proc. ESANN. 89."},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2018.2844341"},{"key":"e_1_3_2_18_2","unstructured":"Mao V. Ngo Hakima Chaouchi Tie Luo and Tony Q. S. Quek. 2020. Adaptive anomaly detection for IoT data in hierarchical edge computing. In AAAI\u201920 workshops . Retrieved from https:\/\/arxiv.org\/abs\/2001.03314."},{"key":"e_1_3_2_19_2","article-title":"Contextual-bandit anomaly detection for IoT data in distributed hierarchical edge computing","author":"Ngo Mao V.","year":"2020","unstructured":"Mao V. Ngo, Tie Luo, Hakima Chaouchi, and Tony Q. S. Quek. 2020. Contextual-bandit anomaly detection for IoT data in distributed hierarchical edge computing. In Proc. IEEE ICDCS Demo Track.","journal-title":"Proc. IEEE ICDCS Demo Track"},{"key":"e_1_3_2_20_2","first-page":"1","volume-title":"GLOBECOM","author":"Ngo M. V.","year":"2020","unstructured":"M. V. Ngo, T. Luo, H. T. Hoang, and T. Q. S. Quek. 2020. Coordinated container migration and base station handover in mobile edge computing. In GLOBECOM. 1\u20136."},{"key":"e_1_3_2_21_2","volume-title":"Anomaly Detection for Temporal Data Using Long Short-term Memory (LSTM)","author":"Singh Akash","year":"2017","unstructured":"Akash Singh. 2017. Anomaly Detection for Temporal Data Using Long Short-term Memory (LSTM). Master\u2019s thesis."},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330672"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969173"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.5555\/3009657.3009806"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3299710.3211336"},{"key":"e_1_3_2_26_2","first-page":"2464","volume-title":"Proc. ICPR","author":"Teerapittayanon S.","year":"2016","unstructured":"S. Teerapittayanon, B. McDanel, and H. T. Kung. 2016. BranchyNet: Fast inference via early exiting from deep neural networks. In Proc. ICPR. 2464\u20132469."},{"key":"e_1_3_2_27_2","first-page":"328","volume-title":"Proc. IEEE ICDCS","author":"Teerapittayanon Surat","year":"2017","unstructured":"Surat Teerapittayanon, Bradley McDanel, and Hsiang-Tsung Kung. 2017. Distributed deep neural networks over the cloud, the edge and end devices. In Proc. IEEE ICDCS. 328\u2013339."},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"e_1_3_2_29_2","first-page":"8817","volume-title":"Proc. CVPR","author":"Wu Zuxuan","year":"2018","unstructured":"Zuxuan Wu, Tushar Nagarajan, Abhishek Kumar, Steven Rennie, Larry S. Davis, Kristen Grauman, and Rogerio Feris. 2018. Blockdrop: Dynamic inference paths in residual networks. In Proc. CVPR. 8817\u20138826."},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2019.2894703"}],"container-title":["ACM Transactions on Internet of Things"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3480172","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3480172","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:31:16Z","timestamp":1750188676000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3480172"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,27]]},"references-count":29,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,2,28]]}},"alternative-id":["10.1145\/3480172"],"URL":"https:\/\/doi.org\/10.1145\/3480172","relation":{},"ISSN":["2691-1914","2577-6207"],"issn-type":[{"value":"2691-1914","type":"print"},{"value":"2577-6207","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10,27]]},"assertion":[{"value":"2020-06-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-08-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-10-27","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}