Next Article in Journal
UHF Partial Discharge Location in Power Transformers via Solution of the Maxwell Equations in a Computational Environment
Next Article in Special Issue
Evaluating a Spoken Dialogue System for Recording Systems of Nursing Care
Previous Article in Journal
Congestion Control in CoAP Observe Group Communication
Previous Article in Special Issue
Using Greedy Random Adaptive Procedure to Solve the User Selection Problem in Mobile Crowdsourcing
Open AccessArticle

On-Device Deep Learning Inference for Efficient Activity Data Collection

Graduate School of Engineering, Kyushu Institute of Technology, 1-1 Sensui-cho, Tobata-ku, Kitakyushu-shi, Fukuoka 804-8550, Japan
Author to whom correspondence should be addressed.
Sensors 2019, 19(15), 3434;
Received: 9 July 2019 / Revised: 25 July 2019 / Accepted: 1 August 2019 / Published: 5 August 2019
(This article belongs to the Special Issue Mobile Sensing: Platforms, Technologies and Challenges)
Labeling activity data is a central part of the design and evaluation of human activity recognition systems. The performance of the systems greatly depends on the quantity and “quality” of annotations; therefore, it is inevitable to rely on users and to keep them motivated to provide activity labels. While mobile and embedded devices are increasingly using deep learning models to infer user context, we propose to exploit on-device deep learning inference using a long short-term memory (LSTM)-based method to alleviate the labeling effort and ground truth data collection in activity recognition systems using smartphone sensors. The novel idea behind this is that estimated activities are used as feedback for motivating users to collect accurate activity labels. To enable us to perform evaluations, we conduct the experiments with two conditional methods. We compare the proposed method showing estimated activities using on-device deep learning inference with the traditional method showing sentences without estimated activities through smartphone notifications. By evaluating with the dataset gathered, the results show our proposed method has improvements in both data quality (i.e., the performance of a classification model) and data quantity (i.e., the number of data collected) that reflect our method could improve activity data collection, which can enhance human activity recognition systems. We discuss the results, limitations, challenges, and implications for on-device deep learning inference that support activity data collection. Also, we publish the preliminary dataset collected to the research community for activity recognition. View Full-Text
Keywords: activity recognition; data collection; on-device deep learning inference; smartphone sensors; user feedback activity recognition; data collection; on-device deep learning inference; smartphone sensors; user feedback
Show Figures

Figure 1

MDPI and ACS Style

Mairittha, N.; Mairittha, T.; Inoue, S. On-Device Deep Learning Inference for Efficient Activity Data Collection. Sensors 2019, 19, 3434.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map

Back to TopTop