Machine Learning-based Positioning using Multivariate Time Series Classification for Factory Environments
Keywords:
Indoor Positioning, Machine Learning, Sensor Fusion, Multivariate Time Series ClassificationSynopsis
This is a Chapter in:
Book:
Smart and Sustainable Applications
Print ISBN 978-1-6692-0006-2
Online ISBN 978-1-6692-0005-5
Series:
Chronicle of Computing
Chapter Abstract:
Indoor Positioning Systems have gained significance in numerous industrial applications. While state-of-the-art solutions are accurate, their reliance on external infrastructures can lead to considerable costs, deployment complexities, and privacy concerns, making them suboptimal for specific contexts. Recent advancements in machine learning have surfaced as a potential solution, leveraging data solely from onboard IoT sensors. Nonetheless, the optimal machine learning models for IoT's resource constraints remain uncertain. This research introduces an indoor positioning system using motion and ambient sensors tailored for factories and similar settings with predetermined paths. The problem is framed as multivariate time series classification, comparing various ML models. A novel dataset simulating factory assembly lines is utilized for evaluation. Results demonstrate models achieving over 80% accuracy, with 1 Dimensional-Convolutional Neural Networks showing the most balanced performance followed by Multilayer Perceptrons, considering accuracy, memory footprint and latency. Decision Trees exhibit the lowest memory footprint and latency, rendering its potential for practical implementation.
Keywords:
Indoor Positioning, Machine Learning, Sensor Fusion, Multivariate Time Series Classification
Cite this paper as:
Hemadasa N., Venzke M., Turau V., Huang Y. (2024) Machine Learning-based Positioning using Multivariate Time Series Classification for Factory Environments. In: Tiako P.F. (ed) Smart and Sustainable Applications. Chronicle of Computing. OkIP. https://doi.org/10.55432/978-1-6692-0005-5_9
Presented at:
The 2023 OkIP International Conference on Automated and Intelligent Systems (CAIS) in Oklahoma City, Oklahoma, USA, and Online, on October 2-5, 2023
Contact:
Nisal Hemadasa
nisal.hemadasa@tuhh.de
References
Farahsari, P. S., Farahzadi, A., Rezazadeh, J., & Bagheri, A. (2022), A survey on indoor positioning systems for iot-based applications, IEEE Internet of Things Journal, vol. 9, no. 10.
Frank´o, A., Holl´osi, G., Ficzere, D., & Varga, P. (2022), Applied machine learning for IIoT and smart production—methods to improve production quality, safety and sustainability, Sensors, vol. 22, no. 23, p. 9148.
Kumar, S. Goyal, & Varma, M. (2017), Resource-efficient machine learning in 2 kb ram for the internet of things, in Proceedings of the 34th International Conference on Machine Learning.
Fawaz, H. I., Forestier, G., Weber, J., Idoumghar, L., & Muller, P.-A. (2019), Deep learning for time series classification: a review, Data Mining and Knowledge Discovery, vol. 33, no. 4.
Hemadasa, N., Venzke, M., Turau, V., & Huang, Y. (2023) Machine Learning-based Positioning using Multivariate Time Series Classification for Factory Environments, arXiv 2023, arXiv: http://arxiv.org/abs/2308.11670
Yu, W., Kim, I. Y., & Mechefske C. (2021), Analysis of different RNN autoencoder variants for time series classification and machine prognostics, Mechanical Systems and Signal Processing.
Wang, Z., Yan, W., & Oates T. (2016), Time series classification from scratch with deep neural networks: A strong baseline.
Hayward, S., van Lopik, K., Hinde, C., & West A. (2022), A survey of indoor location technologies, techniques and applications in industry, Internet of Things, vol. 20, p. 100608, Nov.
Yang, T., Cabani, A., & Chafouk, H. (2021), A survey of recent indoor localization scenarios and methodologies, Sensors.
Wu, Y., Zhu, H.-B., Du, Q.-X., & Tang, S.-M. (2018), A survey of the research status of pedestrian dead reckoning systems based on inertial sensors, International Journal of Automation and Computing.
Ouyang, G., & Abed-Meraim, K. (2022), A survey of magnetic-field-based indoor localization, Electronics, vol. 11, no. 6, p. 864.
Sesyuk, A., Ioannou, S., & Raspopoulos, M. (2022), A survey of 3d indoor localization systems and technologies, Sensors.
Poulose, A., Kim, J., & Han, D. S. (2019), A sensor fusion framework for indoor localization using smartphone sensors and wi-fi RSSI measurements, Applied Sciences, vol. 9, no. 20, p. 4379.
Pascacio, P., Casteleyn, S., Torres-Sospedra, J., Lohan, E. S., & Nurmi, J. (2021), Collaborative indoor positioning systems: A systematic review, Sensors, vol. 21, no. 3, p. 1002.
Holcer, S., Torres-Sospedra, J., Gould, M., & Remolar, I. (2020), Privacy in indoor positioning systems: A systematic review, International Conference on Localization and GNSS.
Chiang, T.-H., Sun, Z.-H., Shiu, H.-R., Lin, K. C.-J., & Tseng, Y.-C. (2020), Magnetic field-based localization in factories using neural network with robotic sampling, IEEE Sensors Journal.
Guo, X., Ansari, N., Hu, F., Shao, Y., Elikplim, N. R., & Li, L. (2020), A survey on fusion-based indoor positioning, IEEE Communications Surveys & Tutorials, vol. 22, no. 1, pp. 566–594.
Nessa, A., Adhikari, B., Hussain, F., & Fernando, X. N. (2020), A survey of machine learning for indoor positioning, IEEE Access.
Grewe, T. (2021), Smartphone sensor-based location awareness using decision trees, Master’s thesis, Institute of Telematics, Hamburg University of Technology.
Miao, H., & Lin, F. X. (2021), Enabling large neural networks on tiny microcontrollers with swapping.
Banbury, C., Zhou, C., Fedorov, I., Matas, R., Thakker, U., Gope, D., Reddi, V. J., Mattina, M., & Whatmough P. (2021a), Micronets: Neural network architectures for deploying tinyml applications on commodity microcontrollers, Proceedings of Machine Learning and Systems.
Banbury, C., Reddi, V. J., Torelli, P., Holleman, J., Jeffries, N., Kiraly, C., Montino, P., Kanter, D., Ahmed, S., & Pau et al. D. (2021b), Mlperf tiny benchmark.
Fedorov, I., Stamenovic, M., Jensen, C., Yang, L.-C., Mandell, A., Gan, Y., Mattina, M., & Whatmough P. N. (2020), Tinylstms: Efficient neural speech enhancement for hearing aids, Interspeech.
