Designing a model to detect and separate data anomalies caused by sensors and medical wearables using LSTM neural network algorithm

Document Type : Research Paper


Department of Information Technology, Central Tehran Branch, Islamic Azad University, Tehran, Iran



Predicting abnormalities of wearable medical devices plays a very important role in saving the lives and health of patients. This importance has opened new horizons for researchers with the development of newer algorithms. The long-term memory algorithm (LSTM) is one of the most important methods that are a special type of recurrent neural network (RNN) that has a high ability in this field and greatly increases the accuracy of correct and incorrect prediction of these abnormalities. In the current research, by using this algorithm and taking into account different parameters, the anomalies related to the sensors of the research field were determined. The results showed that there are influential parameters in the construction of this architecture, which include 3 very important factors: the number of neurons in the LSTM layer, the batch size, and the activation function. Also, the LSTM architecture together with the Dropout layer, with parameters Batch size = N = 128 and Tanh activation function shows a better performance and the lowest amount of error (MAPE) as well as the amount of the calculated mean square error (RMSE) in determining the anomaly. have sensors in the medical field. Investigations related to the results of 16 repetitions of optimization also showed that the process of reducing errors in the correct and incorrect identification of anomalies in the training phase has reached its lowest level with the increase in the number of tests, which shows the optimality and appropriateness of the work process. Therefore, this algorithm has a very good ability to identify errors in sensors and medical wearables, and it will be of great help in identifying the possible failure of sensors, and critical conditions of the patient, informing and finally helping patients in time.


[1] C.C. Aggarwal, Data Mining: The Textbook, Yorktown Heights, Springer, New York, 2015.
[2] R. Alharbi and H. Almagwashi, The privacy requirements for wearable IoT devices in healthcare domain, Proc. Int. Conf. Future. Internet Things Cloud Work, 2019.
[3] G. Appelboom, E. Camacho, M.E. Abraham, S.S. Bruce, E.L. Dumont, B.E. Zacharia, R. D’Amico, J., Slomian, J.Y. Reginster, O.Bruyere, and E.S. Connolly, Smart wearable body sensors for patient self-assessment and monitoring, Arch Public Health 72 (2022), no. 1, 28.
[4] M. Chan, D. Esteve, J.Y. Fourniols, C. Escriba, and E. Campo, Smart wearable systems: Current status and future challenges, Artific. Intell. Med. 56 (2012), no. 3, 137–156.
[5] V. Chandola, A. Banerjee, and V. Kumar, Anomaly detection: A survey, ACM Comput. Surv. 41 (2019), no. 3, 15.
[6] Z. Geng, F. Tang, Y. Ding, S. Li, and X. Wang, Noninvasive continuous glucose monitoring using a multisensor-based glucometer and time series analysis, Sci. Rep. 7 (2017), no. 1, 12650.
[7] M.A. Hayes and M.A. Capretz, Contextual anomaly detection in big sensor data, IEEE Int. Cong. Big Data, 2014, pp. 64–71.
[8] S.M.A. Iqbal, I. Mahgoub, E. Du, M.A. Leavitt, and W. Asghar, Advances in healthcare wearable devices, NPJ Flex. Electron. 5 (2021), no. 9.
[9] S. Jithin, P. Pawan, K. Khushi, P. Sandeep, L. Feng, A. Misa, J. Lawrence, and K. Santosh, Anomaly detection framework for wearables data: A perspective review on data concepts, data analysis algorithms and prospects, Sensors 22 (2022), no. 3, 756.
[10] W. Liu, Z. Wang, X. Liu, N. Zeng, Y. Liu, and F.E. Alsaadi, A survey of deep neural network architectures and their applications, Neurocomputing 234 (2017), 11–26.
[12] B. Mohanta, P. Das, and S. Patnaik, Healthcare 5.0: A paradigm shift in digital healthcare system using artificial intelligence, IoT and 5G communication, Proc. Int. Conf. Appl. Mach. Learn, 2019.
[13] A. Mosenia, S. Sur-Kolay, A. Raghunathan, and N.K. Jha, Wearable medical sensors-based system design: A survey, IEEE Trans. Multi-Scale Comput. Syst. 3 (2017), no. 2, 124–138.
[14] C.C. Noble and D.J. Cook, Graph-based anomaly detection, Proc. 9th ACM SIGKDD Int. Conf. Knowledge Discov. Data Mining, ACM Press, 2017, pp. 631–636.
[15] S. Osman, G. Alexey, and M. Ahmed, Anomaly detection in medical wireless sensor networks using SVM and linear regression models, IEEE. Med. 8 (2015), 34–48.
[16] J.D. Parmar and J.T. Patel, Anomaly Detection in Data Mining: A Review, Int. J. 7 (2017), no. 4.
[17] S. Pourzaker Arabani and H. Ebrahimpour Komleh, The optimization of forecasting ATMs cash demand of Iran banking network using LSTM deep recursive neural network, J. Oper. Res. Appl. 16 (2019), no. 3, 69–88.
[18] S. Rezaei and A.A. Safai, A systematic review of wearable technologies and their applications in health, Inf. Biomed. J. Med. Inf. Res. Center 3 (2015), no. 3, 242–233.
[19] E. Sazonov and M.R. Neuman, Wearable Sensors: Fundamentals, Implementation and Applications, Elsevier, 2014.
[20] J. Schmidhuber, Deep learning in neural networks: An overview, Neural Network 61 (2015), 85–117.
[21] Science Soft, IT consulting and software development services, Wearable Medical Devices, 2021,
[22] M.V. Shcherbakov, A. Brebels, N.L. Shcherbakova, V.A. Kamaev, O.M. Gerget, and D. Devyatykh, Outlier detection and classification in sensor data streams for proactive decision support systems, J. Phys.: Conf. Ser. 803 (2017), no. 1, 012143.
[23] S. Shekhar, C.T. Lu, and P. Zhang, Detecting graph-based spatial outliers: algorithms and applications (a summary of results), Proc. 7th ACM SIGKDD Int. Conf. Knowledge Discov. Data Min., ACM Press, New York, NY, USA, 2001, pp. 371–376.
[24] E.H. Shortliffe and J.J. Cimino, Biomedical Informatics: Computer Applications in Health Care and Biomedicine (Health Informatics), 4th ed., New York, USA, Springer, 2018.
[25] A.K. Sikder, G. Petracca, H. Aksu, T. Jaeger, and A.S. Uluagac, A survey on sensor-based threats to Internet-of Things (IoT) devices and applications, arXiv 2018, arXiv:1802.02041.
[26] B.G. Silverman and J.A. Ichalkaranje, Intelligent Paradigms for Healthcare Enterprises: Systems Thinking (Studies in Fuzziness and Soft Computing), Springer, 2005.
[27] M. Stoecklin, Anomaly detection by finding feature distribution outliers, Proc. ACM CoNEXT Conf., 2006, pp. 32–33.
[28] P. Sun, S. Chawla, and B. Arunasalam, Mining for outliers in sequential databases, SIAM Int. Conf. Data Mining, 2016.
[29] A. Tarar, U. Mohammad, and S.K. Srivastava, Wearable skin sensors and their challenges: A review of transdermal, optical, and mechanical sensors, Biosensors 10 (2020), 56.
[30] M. Van Der Meulen, On the use of smart sensors, common cause failure and the need for diversity, 6th Int. Symp. Program. Electron. Syst. Safety Related Appl., 2004.
[31] X. Zhu and A. Cahan, Wearable technologies and telehealth in care management for chronic illness, C. Weaver, M. Ball, G. Kim, J. Kiel, (eds) Healthcare Information Management Systems, Health Informatics. Springer, Cham, 2016, pp. 375–98.

Articles in Press, Corrected Proof
Available Online from 04 January 2024
  • Receive Date: 19 February 2023
  • Revise Date: 08 April 2023
  • Accept Date: 21 May 2023