ABSTRACT
At the SHL recognition challenge 2018, Team Tesaguri developed a human activity recognition method. First, we obtained the FFT spectrogram from 60-second acceleration and gyro sensor data for each of six axes. A five-second sliding window was used for FFT processing. About 70% of the spectrogram figures from the Sussex-Huawei Locomotion-Transportation dataset were used for training data. Our model was based on CNN using FFT spectrogram images. After training for 50 epochs, F-measure was about 90% for acceleration data and 85% for gyro data. Next, considering the results of each sensor axis, to improve the recognition rate, we combined the information of multiple sensors. Specifically, we synthesized new images by combining the FFT spectrogram figures of two axes and the best combination condition was examined by correlation analysis. The highest score, 93% recognition, came from the vertically arranged images derived from the norm of acceleration and the y-axis gyro.
- H. Gjoreski, M. Ciliberto, F. J. Ordoñez Morales, D. Roggen, S. Mekki, and S. Valentin. "A versatile annotated dataset for multimodal locomotion analytics with mobile devices." In Proc. ACM Conference on Embedded Networked Sensor Systems. 2017. Google ScholarDigital Library
- H. Gjoreski, M. Ciliberto, L. Wang, F. J. Ordonez Morales, S. Mekki, S. Valentin, and D. Roggen. "The University of Sussex-Huawei locomotion and transportation dataset for multimodal analytics with mobile devices." IEEE Access, 2018, {In Print}.Google Scholar
- J. Wang, Y. Chen, S. Hao, X. Peng, and L. Hu. "A survey: Deep learning for sensor-based activity recognition." Pattern Recognition Letters. 2017.Google Scholar
- A. Krizhevsky, I. Sutskever, and G. E. Hinton. "ImageNet classification with deep convolutional neural networks." In Proc. 25th International Conference on Neural Information Processing Systems. Vol. 1, pp. 1097--1105. 2012. Google ScholarDigital Library
- Y. Mohammad, K. Matsumoto, and K. Hoashi. "Primitive activity recognition from short sequences of sensory data." Applied Intelligence. 2018. Google ScholarDigital Library
- M. A. Alsheikh, A. Selim, D. Niyato, L. Doyle, S. Lin, and H-P. Tan. "Deep activity recognition models with triaxial accelerometers." In Proc. 2016 AAAI Workshop. 2016.Google Scholar
- M. Ciliberto, F. J. Ordoñez Morales, H. Gjoreski, D. Roggen, S. Mekki, and S. Valentin. "High reliability Android application for multidevice multimodal mobile data acquisition and annotation." In Proc. ACM Conference on Embedded Networked Sensor Systems. 2017. Google ScholarDigital Library
- L. Wang, H. Gjoreski, K. Murao, T. Okita, and D. Roggen. "Summary of the Sussex-Huawei Locomotion-Transportation recognition challenge." Proc. 6th International Workshop on Human Activity Sensing Corpus and Applications (HASCA2018). Singapore, Oct. 2018.Google Scholar
Index Terms
- Application of CNN for Human Activity Recognition with FFT Spectrogram of Acceleration and Gyro Sensors
Recommendations
CNN for human activity recognition on small datasets of acceleration and gyro sensors using transfer learning
UbiComp/ISWC '19 Adjunct: Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable ComputersThis paper describes an activity recognition method for the Sussex-Huawei Locomotion-Transportation (SHL) recognition challenge by Team TDU-DSML. The CNN model reported in our 2018 SHL Challenge was adopted. 5-second FFT spectrogram images from all axes ...
Human activity recognition using multi-input CNN model with FFT spectrograms
UbiComp/ISWC '20 Adjunct: Adjunct Proceedings of the 2020 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2020 ACM International Symposium on Wearable ComputersAn activity recognition method developed by Team DSML-TDU for the Sussex-Huawei Locomotion-Transportation (SHL) recognition challenge was descrived. Since the 2018 challenge, our team has been developing human activity recognition models based on a ...
Implementation of Rehabilitation Exercise Posture Determination System Based on CNN Using EMG and Acceleration Sensors
Intelligent Human Computer InteractionAbstractA number of musculoskeletal disorders occur worldwide in occupations that perform physically demanding tasks. In order to treat musculoskeletal disorders, rehabilitation must be performed, but it is not easy to correctly perform rehabilitation ...
Comments