9072

Transforming Sensor Data to the Image Domain for Deep Learning - an Application to Footstep Detection

Monit Shah Singh, Vinaychandran Pondenkandath, Bo Zhou, Paul Lukowicz, Marcus Liwicki

The International Joint Conference on Neural Networks International Joint Conference on Neural Networks (IJCNN-2017), May 14-19, Anchorage,, Alaska, USA , IEEE , 2017
Convolutional Neural Networks (CNNs) have be- come the state-of-the-art in various computer vision tasks, but they are still premature for most sensor data, especially in pervasive and wearable computing. A major reason for this is the limited amount of annotated training data. In this paper, we propose the idea of leveraging the discriminative power of pre-trained deep CNNs on 2-dimensional sensor data by transforming the sensor modality to the visual domain. By three proposed strategies, 2D sensor output is converted into pressure distribution imageries. Then we utilize a pre-trained CNN for transfer learning on the converted imagery data. We evaluate our method on a gait dataset of floor surface pressure mapping. We obtain a classification accuracy of 87.66%, which outperforms the conventional machine learning methods by over 10%.

Show BibTex:

@inproceedings {
       abstract = {Convolutional Neural Networks (CNNs) have be- come the state-of-the-art in various computer vision tasks, but they are still premature for most sensor data, especially in pervasive and wearable computing. A major reason for this is the limited amount of annotated training data. In this paper, we propose the idea of leveraging the discriminative power of pre-trained deep CNNs on 2-dimensional sensor data by transforming the sensor modality to the visual domain. By three proposed strategies, 2D sensor output is converted into pressure distribution imageries. Then we utilize a pre-trained CNN for transfer learning on the converted imagery data. We evaluate our method on a gait dataset of floor surface pressure mapping. We obtain a classification accuracy of 87.66%, which outperforms the conventional machine learning methods by over 10%.},
       number = {}, 
       month = {}, 
       year = {2017}, 
       title = {Transforming Sensor Data to the Image Domain for Deep Learning - an Application to Footstep Detection}, 
       journal = {}, 
       volume = {}, 
       pages = {}, 
       publisher = {IEEE}, 
       author = {Monit Shah Singh, Vinaychandran Pondenkandath, Bo Zhou, Paul Lukowicz, Marcus Liwicki}, 
       keywords = {},
       url = {http://www.dfki.de/web/forschung/publikationen/renameFileForDownload?filename=sensor2image_deepnet.pdf&file_id=uploads_3120}
}