Human Activity Recognition from Accelerometer with Convolutional and Recurrent Neural Networks
Tóm tắt
Smartphones are present in most people’s daily lives. Sensors embedded in these devices open the possibility of monitoring users’ activities. The classification of the intricate data patterns collected through these sensors is a challenging task when considering hand-crafted features and pattern recognition algorithms. In this work, to face this challenge, we propose a convolutional neural network architecture along with two methods for transforming sensor data stream into images, and two recurrent neural networks, a long short time memory network and a gated recurrent unit network. The proposed model was evaluated using the UniMiB SHAR dataset. This dataset was acquired with accelerometers of mobile devices. The best macro average accuracy for classification of 17 types of activities, with 5-fold-cross-validation method, 95.49% was obtained with a gated recurrent unit network. The best macro average accuracy for classification with leave-one-subject-out method, 71.36%, was obtained with a convolutional neural network. These results are better than others previously published in the literature with the same dataset.
Tài liệu tham khảo
Falco ID, Pietro GD, Sannino G (2020) Evaluation of artificial intelligence techniques for the classification of different activities of daily living and falls. Neural Comput & Applic 32:747–758. https://doi.org/10.1007/s00521-018-03973-1
Li F, Shirahama K, Nisar MA, Köping L, Grzegorzek M (2018) Comparison of feature learning methods for human activity recognition using wearable sensors. Sensors 18:1–22. https://doi.org/10.3390/s18020679
Lisowska A, O’Neil A, Poole I (2018) Cross-cohort evaluation of machine learning approaches to fall detection from accelerometer data, 11th international joint conference on biomedical engineering systems and technologies
Lv T, Wang X, Jin L, Xiao Y, Song M (2020) A hybrid network based on dense connection and weighted feature aggregation for human activity recognition. IEEE Access 8:68320–68332. https://doi.org/10.1109/ACCESS.2020.2986246
Micucci D, Mobilio M, Napoletano P (2017) UniMiB SHAR: a dataset for human activity recognition using acceleration data from smartphones. Appl Sci 7:1–19. https://doi.org/10.3390/app7101101
Park SY, Ju H, Park CG (2016) Stance phase detection of multiple actions for military drill using foot-mounted IMU, International Conference on Indoor Positioning and Indoor Navigation
Sharma A, Vans E, Shigemizu D, Boroevich KA, Tsunoda T (2019) Deepinsight: a methodology to transform a non-image data to an image for convolution neural network architecture. Sci Rep 9:1–7. https://doi.org/10.1038/s41598-019-47765-6
Subasi A, Radhwan M, Kurdi R, Khateeb K (2018) IoT based mobile healthcare system for human activity recognition, 15th learning and technology conference
Yang J, Lee J, Choi J (2011) Activity recognition based on RFID object usage for smart Mobile devices. J Comput Sci Technol 26:239–246. https://doi.org/10.1007/s11390-011-9430-9
Yin J, Yang Q, Pan JJ (2008) Sensor-based abnormal human-activity detection. IEEE Trans Knowl Data Eng 20:1082–1090. https://doi.org/10.1109/TKDE.2007.1042