ABSTRACT
Time-series classification is gaining significance in pattern recognition as time-series data becomes more abundant along with the increasing digitization of daily life and the rise of the Internet of Things (IoT). One of the biggest challenges lies in the ordered nature of time-series attributes, making traditional machine learning (ML) algorithms designed for static data unsuitable for processing temporal data. The Transformer architecture was introduced as a novel approach in natural language processing for machine translation tasks, relying solely on attention mechanisms without the need for convolution or recurrence. Since machine translation is similar to time-series data, where order is an important factor, it is also worth considering the Transformer for time-series classification. Pre-processing the data is a crucial step in the ML process and can influence the data and impact the effectiveness of the ML models. In this paper, we aim to address the effects of time-series pre-processing and data representation in combination with the Transformer model for Human Activity Recognition (HAR) using IMU data from smart glasses as input. We analyze the results based on established evaluation metrics such as the F1-score and the area under the curve (AUC).
- Aishwarya Asesh. 2022. Normalization and Bias in Time Series Data. In Digital Interaction and Machine Intelligence, Cezary Biele, Janusz Kacprzyk, Wiesław Kopeć, Jan W. Owsiński, Andrzej Romanowski, and Marcin Sikorski (Eds.). Springer International Publishing, Cham, 88–97.Google Scholar
- Gabriela Augustinov, Muhammad Adeel Nisar, Frédéric Li, Amir Tabatabaei, Marcin Grzegorzek, Keywan Sohrabi, and Sebastian Fudickar. 2023. Transformer-Based Recognition of Activities of Daily Living from Wearable Sensor Data. In Proceedings of the 7th International Workshop on Sensor-Based Activity Recognition and Artificial Intelligence(iWOAR ’22). Association for Computing Machinery, Association for Computing Machinery, Rostock, Germany, 1–8. https://doi.org/10.1145/3558884.3558895Google ScholarDigital Library
- Anthony Bagnall, Jason Lines, Aaron Bostrom, James Large, and Eamonn Keogh. 2017. The great time series classification bake off: a review and experimental evaluation of recent algorithmic advances. Data Mining and Knowledge Discovery 31, 3 (01 May 2017), 606–660. https://doi.org/10.1007/s10618-016-0483-9Google ScholarDigital Library
- Hercules Dalianis. 2018. Evaluation Metrics and Evaluation. Springer International Publishing, Cham, 45–53. https://doi.org/10.1007/978-3-319-78503-5_6Google ScholarCross Ref
- Hassan Ismail Fawaz, Germain Forestier, Jonathan Weber, Lhassane Idoumghar, and Pierre-Alain Muller. 2019. Deep learning for time series classification: a review. Data Mining and Knowledge Discovery 33, 4 (mar 2019), 917–963. https://doi.org/10.1007/s10618-019-00619-1Google ScholarDigital Library
- Sandra Hellmers, Sebastian Fudickar, Clemens Büse, Lena Dasenbrock, Andrea Heinks, Jürgen M. Bauer, and Andreas Hein. 2017. Technology Supported Geriatric Assessment. Springer International Publishing, Cham, 85–100. https://doi.org/10.1007/978-3-319-52322-4_6Google ScholarCross Ref
- Sandra Hellmers., Tobias Kromke., Lena Dasenbrock., Andrea Heinks., Jürgen M. Bauer., Andreas Hein., and Sebastian Fudickar.2018. Stair Climb Power Measurements via Inertial Measurement Units - Towards an Unsupervised Assessment of Strength in Domestic Environments. In Proceedings of the 11th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2018) - HEALTHINF. INSTICC, SciTePress, Funchal, 39–47. https://doi.org/10.5220/0006543900390047Google ScholarCross Ref
- Mohammad Hossin and Sulaiman M.N. 2015. A Review on Evaluation Metrics for Data Classification Evaluations. International Journal of Data Mining and Knowledge Management Process 5 (03 2015), 01–11. https://doi.org/10.5121/ijdkp.2015.5201Google ScholarCross Ref
- Muhammad Tausif Irshad, Muhammad Adeel Nisar, Xinyu Huang, Jana Hartz, Olaf Flak, Frédéric Li, Philip Gouverneur, Artur Piet, Kerstin M. Oltmanns, and Marcin Grzegorzek. 2022. SenseHunger: Machine Learning Approach to Hunger Detection Using Wearable Sensors. Sensors 22, 20 (2022), 7711. https://doi.org/10.3390/s22207711Google ScholarCross Ref
- Abdul Kader, Samiha Sharif, Pranta Bhowmick, Fahmida Mim, and Azmain Srizon. 2020. Effective Workflow for High-Performance Recognition of Fruits using Machine Learning Approaches. 7 (02 2020), 1516–1521.Google Scholar
- Frédéric Li, Kimiaki Shirahama, Muhammad Adeel Nisar, Xinyu Huang, and Marcin Grzegorzek. 2020. Deep Transfer Learning for Time Series Data Based on Sensor Modality Classification. Sensors 20, 15 (July 2020), 4271. https://doi.org/10.3390/s20154271Google ScholarCross Ref
- Frédéric Li, Kimiaki Shirahama, Muhammad Adeel Nisar, Lukas Köping, and Marcin Grzegorzek. 2018. Comparison of Feature Learning Methods for Human Activity Recognition Using Wearable Sensors. Sensors 18, 2 (2018), 679. https://doi.org/10.3390/s18020679Google ScholarCross Ref
- Iveta Dirgová Luptáková, Martin Kubovčík, and Jiří Pospíchal. 2022. Wearable Sensor-Based Human Activity Recognition with Transformer Model. Sensors 22, 5 (March 2022), 1911. https://doi.org/10.3390/s22051911Google ScholarCross Ref
- Keras API Reference. 2021. MultiHeadAttention Layer. keras. Retrieved July 30, 2023 from https://keras.io/api/layers/attention_layers/multi_head_attention/Google Scholar
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is All You Need. In Attention is All You Need (Long Beach, California, USA) (NIPS’17). Curran Associates Inc., Red Hook, NY, USA, 6000–6010.Google Scholar
- Qingsong Wen, Tian Zhou, Chaoli Zhang, Weiqi Chen, Ziqing Ma, Junchi Yan, and Liang Sun. 2023. Transformers in Time Series: A Survey. arxiv:2202.07125 [cs.LG]Google Scholar
Index Terms
- Effects of Time-Series Data Pre-processing on the Transformer-based Classification of Activities from Smart Glasses
Recommendations
Exploring the Benefits of Time Series Data Augmentation for Wearable Human Activity Recognition.
iWOAR '23: Proceedings of the 8th international Workshop on Sensor-Based Activity Recognition and Artificial IntelligenceWearable Human Activity Recognition (HAR) is an important field of research in smart assistive technologies. Collecting the data needed to train reliable HAR classifiers is complex and expensive. As a way to mitigate data scarcity, Time Series Data ...
Transformer-Based Recognition of Activities of Daily Living from Wearable Sensor Data
iWOAR '22: Proceedings of the 7th International Workshop on Sensor-based Activity Recognition and Artificial IntelligenceSmart support systems for the recognition of Activities of Daily Living (ADLs) can help elderly people live independently for longer improving their standard of living. Many machine learning approaches have been proposed lately for Human Activity ...
Identifying label noise in time-series datasets
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 ComputersReliably labeled datasets are crucial to the performance of supervised learning methods. Time-series data pose additional challenges. Data points lying on borders between classes can be mislabeled due to perception limitations of human labelers. Sensor ...
Comments