Alexander Verner
ABSTRACT
Most existing machine learning (ML) based solutions for anomaly detection in sensory data rely on carefully hand-crafted features. This approach has a fundamental limitation since it is often application-specific and requires considerable human effort from domain experts. Deep learning models have been demonstrated to have the ability to abstract relevant high-level features from raw data. Long short-term memory (LSTM) recurrent neural networks have proven effective in complex time-series prediction problems. In this paper, we propose an LSTM-based method for anomaly detection in sensory data. We systematically investigate its effectiveness on raw time-series of real medical sensors measurements and show that it achieves the same level of performance as traditional ML models operating on carefully designed feature vectors. The proposed method achieved micro, macro, and weighted precision, recall, and F1-score of over 0.99.
- Mosenia, A., Sur-Kolay, S., Raghunathan, A., & Jha, N. K. (2017). Wearable medical sensor-based system design: A survey. IEEE Transactions on Multi-Scale Computing Systems, 3(2), 124--138. J. Clerk Maxwell, A Treatise on Electricity and Magnetism, 3rd ed., vol. 2. Oxford: Clarendon, 1892, pp. 68--73.Google Scholar
Cross Ref
- Luo, R., Misra, M., & Himmelblau, D. M. (1999). Sensor fault detection via multiscale analysis and dynamic PCA. Industrial & Engineering Chemistry Research, 38(4), 1489--1495.Google ScholarCross Ref
- Geng, Z., Tang, F., Ding, Y., Li, S., & Wang, X. (2017). Noninvasive continuous glucose monitoring using a multisensor-based glucometer and time series analysis. Scientific reports, 7(1), 12650.Google Scholar
- Van Der Meulen, M. (2004). On the use of smart sensors, common cause failure and the need for diversity. 6th International Symposium Programmable Electronic Systems in Safety Related Applications.Google Scholar
- Salehinejad, H., Baarbe, J., Sankar, S., Barfett, J., Colak, E., & Valaee, S. (2017). Recent Advances in Recurrent Neural Networks. arXiv preprint arXiv:1801.01078.Google Scholar
- Karim, F., Majumdar, S., Darabi, H., & Chen, S. (2018). LSTM fully convolutional networks for time series classification. IEEE Access, 6, 1662--1669.Google ScholarCross Ref
- Chandola, V., Banerjee, A., & Kumar, V. (2009). Anomaly detection: A survey. ACM computing surveys (CSUR), 41(3), 15.Google ScholarDigital Library
- Patcha, A., & Park, J. M. (2007). An overview of anomaly detection techniques: Existing solutions and latest technological trends. Computer networks, 51(12), 3448--3470. Elsevier.Google Scholar
- Yao, Z. G., Cheng, L., & Wang, Q. L. (2012). Sensor fault detection, diagnosis and validation-a survey. Applied Mechanics and Materials, 229, 1265--1271. Trans Tech Publications.Google ScholarCross Ref
- Pires, I. M., Garcia, N. M., Pombo, N., Florez-Revuelta, F., & Rodriguez, N. D. (2016). Validation Techniques for Sensor Data in Mobile Health Applications. Journal of Sensors, 2016.Google ScholarCross Ref
- Salahat, E., & Qasaimeh, M. (2017). Recent advances in features extraction and description algorithms: A comprehensive survey. 2017 IEEE International Conference on Industrial Technology (ICIT), 1059--1063.Google ScholarCross Ref
- Fehst, V., La, H. C., Nghiem, T. D., Mayer, B. E., Englert, P., & Fiebig, K. H. (2018). Automatic vs. manual feature engineering for anomaly detection of drinking-water quality. Proceedings of the Genetic and Evolutionary Computation Conference Companion, 5--6. ACM.Google ScholarDigital Library
- Juvenile Diabetes Research Foundation Continuous Glucose Monitoring Study Group (2008). JDRF randomized clinical trial to assess the efficacy of real-time continuous glucose monitoring in the management of type 1 diabetes: research design and methods. Diabetes Technol Ther. 10(4), 310--321.Google ScholarCross Ref
- Reitermanova, Z. (2010). Data splitting. WDS, 10, (31--36).Google Scholar
- Goutte, C., & Gaussier, E. (2005). A probabilistic interpretation of precision, recall and F-score, with implication for evaluation. European Conference on Information Retrieval, 345--359. Springer, Berlin, Heidelberg.Google ScholarDigital Library
- Probst, P., & Boulesteix, A. L. (2017). To tune or not to tune the number of trees in random forest?. arXiv preprint arXiv:1705.05654.Google Scholar
- Genuer, R. (2012). Variance reduction in purely random forests. Journal of Nonparametric Statistics, 24(3), 543--562.Google ScholarCross Ref
- Raileanu, L. E., & Stoffel, K. (2004). Theoretical comparison between the gini index and information gain criteria. Annals of Mathematics and Artificial Intelligence, 41(1), 77--93.Google ScholarDigital Library
- Rennie, J. D., Shih, L., Teevan, J., & Karger, D. R. (2003). Tackling the poor assumptions of naive Bayes text classifiers. Proceedings of the 20th international conference on machine learning (ICML-03).Google Scholar
- Ba, J., & Caruana, R. (2014). Do deep nets really need to be deep?. Advances in neural information processing systems, 2654--2662.Google Scholar
- Reimers, N., & Gurevych, I. (2017). Optimal hyperparameters for deep lstm-networks for sequence labeling tasks. arXiv preprint arXiv:1707.06799.Google Scholar
- Lipton, Z. C., Kale, D. C., Elkan, C., & Wetzel, R. (2015). Learning to diagnose with LSTM recurrent neural networks. arXiv preprint arXiv:1511.03677.Google Scholar
- You, Y., Demmel, J., Keutzer, K., Hsieh, C., Ying, C., & Hseu, J. (2018). Large-Batch Training for LSTM and Beyond. arXiv preprint arXiv: 1901.08256.Google Scholar
- Graves, A., Mohamed, A. R., & Hinton, G. (2013). Speech recognition with deep recurrent neural networks. IEEE international conference on acoustics, speech and signal processing (ICASSP), 6645--6649.Google ScholarCross Ref
- Hermans, M., & Schrauwen, B. (2013). Training and analysing deep recurrent neural networks. Advances in neural information processing systems, 190--198.Google Scholar
- Neishi, M., Sakuma, J., Tohda, S., Ishiwatari, S., Yoshinaga, N., & Toyoda, M. (2017). A bag of useful tricks for practical neural machine translation: Embedding layer initialization and large batch size. Proceedings of the 4th Workshop on Asian Translation (WAT2017), 99--109.Google Scholar
- Graves, A. (2012). Supervised sequence labelling. In Supervised sequence labelling with recurrent neural networks (pp. 5-13). Springer, Berlin, Heidelberg.Google ScholarCross Ref
- Moniz, J. R. A., & Krueger, D. (2018). Nested LSTMs. arXiv preprint arXiv:1801.10308.Google Scholar
Index Terms
- An LSTM-Based Method for Detection and Classification of Sensor Anomalies
Recommendations
Analysis of Deep Learning Models for Anomaly Detection in Time Series IoT Sensor Data
IC3-2022: Proceedings of the 2022 Fourteenth International Conference on Contemporary ComputingThe anomaly detection in Internet of Things (IoT) sensor data has become an important research area because of the possibility of noise and unavailability of labels in the sensors readings. The conventional machine learning algorithms cannot detect the ...
Performance evaluation of Emergency Department patient arrivals forecasting models by including meteorological and calendar information: A comparative study
AbstractThe volume of daily patient arrivals at Emergency Departments (EDs) is unpredictable and is a significant reason of ED crowding in hospitals worldwide. Timely forecast of patients arriving at ED can help the hospital management in early planning ...
Graphical abstractDisplay Omitted
Highlights- Emergency Department (ED) patient arrivals forecasting models are proposed.
- Random Forest (RF) regressor, Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) methods are used.
- Models are implemented by ...
CNN features with bi-directional LSTM for real-time anomaly detection in surveillance networks
AbstractIn current technological era, surveillance systems generate an enormous volume of video data on a daily basis, making its analysis a difficult task for computer vision experts. Manually searching for unusual events in these massive video streams ...
Comments