Attention-Based Convolutional Neural Network and Bidirectional Gated Recurrent Unit for Human Activity Recognition
- 1 December 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1132-1138
Abstract
Using the data collected by the sensors embedded in smartphones for human activity recognition has become an important research direction. In order to overcome the problem of handcrafted feature extraction in traditional machine learning, we propose an attention-based model which combines convolutional neural network (CNN) and bidirectional gated recurrent unit (BiGRU) for human activity recognition. This model can extract local features of the original data by CNN, and construct the extracted features into a time series as the input of BiGRU, the BiGRU can capture the temporal dependencies and extract the features from the input, by introducing the attention mechanism, the influence of key input can be strengthened. The features are classified by the Softmax function. The recognition accuracy rate on the Wireless Sensor Data Mining (WISDM) dataset reaches 98.5%, which is improved compared with the state-of-the-art methods.Keywords
Funding Information
- National Key R&D Program of China (2018YFC2001700)
This publication has 15 references indexed in Scilit:
- Real-time human activity recognition from accelerometer data using Convolutional Neural NetworksApplied Soft Computing, 2018
- Towards reading trackers in the wild2017
- Robust Human Activity Recognition Using Smartphone Sensors via CT-PCA and Online SVMIEEE Transactions on Industrial Informatics, 2017
- Random forests based recognition of human activities and postural transitions on smartphone2016
- Compressive Sequential Learning for Action Similarity LabelingIEEE Transactions on Image Processing, 2015
- Activity Recognition on Smartphones via Sensor-Fusion and KDA-Based SVMsInternational Journal of Distributed Sensor Networks, 2014
- Deep Learning of Representations: Looking Forward2013
- Activity recognition using cell phone accelerometersACM SIGKDD Explorations Newsletter, 2011
- Activity Recognition Using Hierarchical Hidden Markov Models on a Smartphone with 3D AccelerometerLecture Notes in Computer Science, 2011
- Inferring Activities from Interactions with ObjectsIEEE Pervasive Computing, 2004