{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T15:55:14Z","timestamp":1781020514006,"version":"3.54.1"},"reference-count":48,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2019,5,29]],"date-time":"2019-05-29T00:00:00Z","timestamp":1559088000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>The need for robust unsupervised anomaly detection in streaming data is increasing rapidly in the current era of smart devices, where enormous data are gathered from numerous sensors. These sensors record the internal state of a machine, the external environment, and the interaction of machines with other machines and humans. It is of prime importance to leverage this information in order to minimize downtime of machines, or even avoid downtime completely by constant monitoring. Since each device generates a different type of streaming data, it is normally the case that a specific kind of anomaly detection technique performs better than the others depending on the data type. For some types of data and use-cases, statistical anomaly detection techniques work better, whereas for others, deep learning-based techniques are preferred. In this paper, we present a novel anomaly detection technique, FuseAD, which takes advantage of both statistical and deep-learning-based approaches by fusing them together in a residual fashion. The obtained results show an increase in area under the curve (AUC) as compared to state-of-the-art anomaly detection methods when FuseAD is tested on a publicly available dataset (Yahoo Webscope benchmark). The obtained results advocate that this fusion-based technique can obtain the best of both worlds by combining their strengths and complementing their weaknesses. We also perform an ablation study to quantify the contribution of the individual components in FuseAD, i.e., the statistical ARIMA model as well as the deep-learning-based convolutional neural network (CNN) model.<\/jats:p>","DOI":"10.3390\/s19112451","type":"journal-article","created":{"date-parts":[[2019,5,29]],"date-time":"2019-05-29T11:31:28Z","timestamp":1559129488000},"page":"2451","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":86,"title":["FuseAD: Unsupervised Anomaly Detection in Streaming Sensors Data by Fusing Statistical and Deep Learning Models"],"prefix":"10.3390","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7818-0361","authenticated-orcid":false,"given":"Mohsin","family":"Munir","sequence":"first","affiliation":[{"name":"German Research Center for Artificial Intelligence (DFKI) GmbH, 67663 Kaiserslautern, Germany"},{"name":"Fachbereich Informatik, Technische Universit\u00e4t Kaiserslautern, 67663 Kaiserslautern, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4600-7331","authenticated-orcid":false,"given":"Shoaib Ahmed","family":"Siddiqui","sequence":"additional","affiliation":[{"name":"German Research Center for Artificial Intelligence (DFKI) GmbH, 67663 Kaiserslautern, Germany"},{"name":"Fachbereich Informatik, Technische Universit\u00e4t Kaiserslautern, 67663 Kaiserslautern, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3336-5677","authenticated-orcid":false,"given":"Muhammad Ali","family":"Chattha","sequence":"additional","affiliation":[{"name":"German Research Center for Artificial Intelligence (DFKI) GmbH, 67663 Kaiserslautern, Germany"},{"name":"Fachbereich Informatik, Technische Universit\u00e4t Kaiserslautern, 67663 Kaiserslautern, Germany"},{"name":"School of Electrical Engineering and Computer Science (SEECS), National University of Sciences and Technology (NUST), 44000 Islamabad, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas","family":"Dengel","sequence":"additional","affiliation":[{"name":"German Research Center for Artificial Intelligence (DFKI) GmbH, 67663 Kaiserslautern, Germany"},{"name":"Fachbereich Informatik, Technische Universit\u00e4t Kaiserslautern, 67663 Kaiserslautern, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4239-6520","authenticated-orcid":false,"given":"Sheraz","family":"Ahmed","sequence":"additional","affiliation":[{"name":"German Research Center for Artificial Intelligence (DFKI) GmbH, 67663 Kaiserslautern, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2019,5,29]]},"reference":[{"key":"ref_1","unstructured":"Vertatique (2019, February 20). How Many Billion IoT Devices by 2020?. Available online: http:\/\/www.vertatique.com\/50-billion-connected-devices-2020."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"15667","DOI":"10.1109\/ACCESS.2017.2686092","article-title":"Green IoT: An Investigation on Energy Saving Practices for 2020 and Beyond","volume":"5","author":"Arshad","year":"2017","journal-title":"IEEE Access"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Beghi, A., Brignoli, R., Cecchinato, L., Menegazzo, G., and Rampazzo, M. (2015, January 21\u201323). A data-driven approach for fault diagnosis in HVAC chiller systems. Proceedings of the 2015 IEEE Conference on Control Applications (CCA), Sydney, Australia.","DOI":"10.1109\/CCA.2015.7320737"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Laptev, N., Amizadeh, S., and Flint, I. (2015, January 10\u201313). Generic and scalable framework for automated time-series anomaly detection. Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Sydney, Australia.","DOI":"10.1145\/2783258.2788611"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1016\/j.scs.2017.07.016","article-title":"Data analytics for occupancy pattern learning to reduce the energy consumption of HVAC systems in office buildings","volume":"35","author":"Capozzoli","year":"2017","journal-title":"Sustain. Cities Soc."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Last, M., Kandel, A., and Bunke, H. (2018). Data Analytics: Industrial Perspective & Solutions for Streaming Data. Data Mining in Time Series and Streaming Databases, World Scientific. Chapter 7.","DOI":"10.1142\/10655"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Hawkins, D.M. (1980). Identification of Outliers, Springer.","DOI":"10.1007\/978-94-015-3994-4"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Breunig, M.M., Kriegel, H.P., Ng, R.T., and Sander, J. (2000, January 15\u201318). LOF: Identifying density-based local outliers. Proceedings of the 2000 ACM SIGMOD international conference on Management of data, Dallas, TX, USA.","DOI":"10.1145\/342009.335388"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Liu, F.T., Ting, K.M., and Zhou, Z.H. (2008, January 15\u201319). Isolation forest. Proceedings of the 2008 Eighth IEEE International Conference on Data Mining, Pisa, Italy.","DOI":"10.1109\/ICDM.2008.17"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1016\/j.cviu.2018.02.006","article-title":"Deep-anomaly: Fully convolutional neural network for fast anomaly detection in crowded scenes","volume":"172","author":"Sabokrou","year":"2018","journal-title":"Comput. Vis. Image Underst."},{"key":"ref_11","unstructured":"Goldstein, M., and Dengel, A. (2012, January 24\u201327). Histogram-based outlier score (hbos): A fast unsupervised anomaly detection algorithm. Proceedings of the Poster and Demo Track of the 35th German Conference on Artificial Intelligence (KI-2012), Saarbr\u00fccken, Germany."},{"key":"ref_12","unstructured":"Kejariwal, A. (2019, February 12). Introducing Practical and Robust Anomaly Detection in a Time Series. Available online: https:\/\/blog.twitter.com\/engineering\/en_us\/a\/2015\/introducing-practical-and-robust-anomaly-detection-in-a-time-series.html."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1991","DOI":"10.1109\/ACCESS.2018.2886457","article-title":"DeepAnT: A Deep Learning Approach for Unsupervised Anomaly Detection in Time Series","volume":"7","author":"Munir","year":"2019","journal-title":"IEEE Access"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Lavin, A., and Ahmad, S. (2015, January 9\u201311). Evaluating Real-Time Anomaly Detection Algorithms\u2014The Numenta Anomaly Benchmark. Proceedings of the Machine 2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA), Miami, FL, USA.","DOI":"10.1109\/ICMLA.2015.141"},{"key":"ref_15","unstructured":"Chalapathy, R., and Chawla, S. (2019). Deep Learning for Anomaly Detection: A Survey. arXiv."},{"key":"ref_16","unstructured":"Ma, J., and Perkins, S. (2003, January 15\u201318). Time-series novelty detection using one-class support vector machines. Neural Networks, 2003. Proceedings of the 2003 Joint Conference of the Fourth International Conference on Information, Singapore."},{"key":"ref_17","unstructured":"Shyu, M.L., Chen, S.C., Sarinnapakorn, K., and Chang, L. (2003). A Novel Anomaly Detection Scheme based on Principal Component Classifier, Miami Univ Coral Gables FL Department of Electrical and Computer Engineering. Technical Report."},{"key":"ref_18","unstructured":"Adams, R.P., and MacKay, D.J. (2007). Bayesian online changepoint detection. arXiv."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"134","DOI":"10.1016\/j.neucom.2017.04.070","article-title":"Unsupervised real-time anomaly detection for streaming data","volume":"262","author":"Ahmad","year":"2017","journal-title":"Neurocomputing"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1007\/s10994-016-5567-7","article-title":"Expected similarity estimation for large-scale batch and streaming anomaly detection","volume":"105","author":"Schneider","year":"2016","journal-title":"Mach. Learn."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Wang, C., Viswanathan, K., Lakshminarayan, C., Talwar, V., Satterfield, W., and Schwan, K. (2011, January 23\u201327). Statistical techniques for online anomaly detection in data centers. Proceedings of the 12th IFIP\/IEEE International Symposium on Integrated Network Management (IM 2011) and Workshops, Dublin, Ireland.","DOI":"10.1109\/INM.2011.5990537"},{"key":"ref_22","unstructured":"Aggarwal, C.C. (2016). An Introduction to Outlier Analysis. Outlier Analysis, Springer."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1145\/1541880.1541882","article-title":"Anomaly detection: A survey","volume":"41","author":"Chandola","year":"2009","journal-title":"ACM Comput. Surv."},{"key":"ref_24","unstructured":"Goldstein, M. (2014). Anomaly Detection in Large Datasets. [Ph.D. Thesis, University of Kaiserslautern]."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Ramaswamy, S., Rastogi, R., and Shim, K. (2000, January 15\u201318). Efficient algorithms for mining outliers from large data sets. Proceedings of the 2000 ACM SIGMOD International Conference on Management of Data, Dallas, TX, USA.","DOI":"10.1145\/342009.335437"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Tang, J., Chen, Z., Fu, A.W.C., and Cheung, D.W. (2002). Enhancing effectiveness of outlier detections for low density patterns. Advances in Knowledge Discovery and Data Mining, Springer.","DOI":"10.1007\/3-540-47887-6_53"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Jin, W., Tung, A.K., Han, J., and Wang, W. (2006). Ranking outliers using symmetric neighborhood relationship. Advances in Knowledge Discovery and Data Mining, Springer.","DOI":"10.1007\/11731139_68"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Vasiliadis, G., Polychronakis, M., and Ioannidis, S. (2011, January 17\u201321). MIDeA: A multi-parallel intrusion detection architecture. Proceedings of the 18th ACM conference on Computer and communications security, Chicago, IL, USA.","DOI":"10.1145\/2046707.2046741"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Buda, T.S., Caglayan, B., and Assem, H. (2018). DeepAD: A Generic Framework Based on Deep Learning for Time Series Anomaly Detection. Pacific-Asia Conference on Knowledge Discovery and Data Mining, Springer.","DOI":"10.1007\/978-3-319-93034-3_46"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"9653230","DOI":"10.1155\/2016\/9653230","article-title":"An improved ARIMA-based traffic anomaly detection algorithm for wireless sensor networks","volume":"2016","author":"Yu","year":"2016","journal-title":"Int. J. Distrib. Sens. Netw."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Yaacob, A.H., Tan, I.K., Chien, S.F., and Tan, H.K. (July, January 29). ARIMA based network anomaly detection. Proceedings of the 2010 Second International Conference on Communication Software and Networks, HongKong, China.","DOI":"10.1109\/ICCSN.2010.55"},{"key":"ref_32","unstructured":"Whittle, P. (1951). Hypothesis Testing in Time Series Analysis, Almqvist and Wiksell International."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Kang, M.J., and Kang, J.W. (2016). Intrusion detection system using deep neural network for in-vehicle network security. PLoS ONE, 11.","DOI":"10.1371\/journal.pone.0155781"},{"key":"ref_34","unstructured":"Trippi, R.R., and Turban, E. (1992). Neural Networks in Finance And Investing: Using Artificial Intelligence to Improve Real World Performance, McGraw-Hill, Inc."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1016\/0895-4356(90)90005-A","article-title":"The individual over time: Time series applications in health care research","volume":"43","author":"Crabtree","year":"1990","journal-title":"J. Clin. Epidemiol."},{"key":"ref_36","first-page":"165","article-title":"Deep Learning Trends for Video Based Activity Recognition: A Survey","volume":"8","author":"Kushwaha","year":"2018","journal-title":"Int. J. Sens. Wirel. Commun. Control"},{"key":"ref_37","unstructured":"Malhotra, P., Vig, L., Shroff, G., and Agarwal, P. (2015). Long short term memory networks for anomaly detection in time series. Proceedings, Presses Universitaires de Louvain."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Chauhan, S., and Vig, L. (2015, January 19\u201321). Anomaly detection in ECG time signals via deep long short-term memory networks. Proceedings of the 2015 IEEE International Conference on Data Science and Advanced Analytics (IEEE DSAA\u20192015), Paris, French.","DOI":"10.1109\/DSAA.2015.7344872"},{"key":"ref_39","unstructured":"Lipton, Z.C., Kale, D.C., Elkan, C., and Wetzell, R. (2016). Learning to Diagnose with LSTM Recurrent Neural Networks. arXiv."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Liu, Q., Chen, E., Ge, Y., and Zhao, J.L. (2014). Time series classification using multi-channels deep convolutional neural networks. International Conference on Web-Age Information Management, Springer.","DOI":"10.1007\/978-3-319-08010-9_33"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"18042","DOI":"10.1109\/ACCESS.2017.2747560","article-title":"Network traffic classifier with convolutional and recurrent neural networks for Internet of Things","volume":"5","author":"Carro","year":"2017","journal-title":"IEEE Access"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Du, X., El-Khamy, M., Lee, J., and Davis, L. (2017, January 27\u201329). Fused DNN: A deep neural network fusion approach to fast and robust pedestrian detection. Proceedings of the WACV 2017, Santa Rosa, CA, USA.","DOI":"10.1109\/WACV.2017.111"},{"key":"ref_43","first-page":"1","article-title":"Automatic Time Series Forecasting: The forecast Package for R","volume":"27","author":"Hyndman","year":"2008","journal-title":"J. Stat. Softw. Art."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"1035","DOI":"10.1109\/TPWRS.2005.846054","article-title":"Day-ahead electricity price forecasting using the wavelet transform and ARIMA models","volume":"20","author":"Conejo","year":"2005","journal-title":"IEEE Trans. Power Syst."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"1014","DOI":"10.1109\/TPWRS.2002.804943","article-title":"ARIMA models to predict next-day electricity prices","volume":"18","author":"Contreras","year":"2003","journal-title":"IEEE Trans. Power Syst."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"21","DOI":"10.5430\/jms.v7n1p21","article-title":"The tea industry and a review of its price modelling in major tea producing countries","volume":"7","author":"Gunathilaka","year":"2016","journal-title":"J. Manag. Strategy"},{"key":"ref_47","unstructured":"Koch, G., Zemel, R., and Salakhutdinov, R. (2015, January 6\u201311). Siamese neural networks for one-shot image recognition. Proceedings of the 32 nd International Conference on Machine Learning, Lille, France."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Singh, N., and Olinsky, C. (2017, January 14\u201319). Demystifying Numenta anomaly benchmark. Proceedings of the IJCNN 2017: International Joint Conference on Neural Networks, Anchorage, Alaska.","DOI":"10.1109\/IJCNN.2017.7966038"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/19\/11\/2451\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T12:54:21Z","timestamp":1760187261000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/19\/11\/2451"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5,29]]},"references-count":48,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2019,6]]}},"alternative-id":["s19112451"],"URL":"https:\/\/doi.org\/10.3390\/s19112451","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,5,29]]}}}