论文信息 - Recognition of multiple overlapping activities using compositional CNN-LSTM model

Recognition of multiple overlapping activities using compositional CNN-LSTM model

This paper introduces a new task, a recognition of multiple overlapping activities in the context of activity recognition. We propose a compositional CNN+LSTM algorithm. The experimental results show on the artificial dataset that it improved the accuracy from 27% to 43%.

Sozo Inoue | Tsuyoshi Okita | Tsuyoshi Okita | Sozo Inoue

[1] Paul Lukowicz,et al. Collecting complex activity datasets in highly rich networked sensor environments , 2010, 2010 Seventh International Conference on Networked Sensing Systems (INSS).

[2] Joshua B. Tenenbaum,et al. Automatic Construction and Natural-Language Description of Nonparametric Regression Models , 2014, AAAI.

[3] Daniel Roggen,et al. Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition , 2016, Sensors.

[4] Shaohan Hu,et al. DeepSense: A Unified Deep Learning Framework for Time-Series Mobile Sensing Data Processing , 2016, WWW.

[5] Naonori Ueda,et al. Mobile activity recognition for a whole day: recognizing real nursing activities with big dataset , 2015, UbiComp.

[6] Young-Koo Lee,et al. Semi-Markov conditional random fields for accelerometer-based activity recognition , 2010, Applied Intelligence.