TY - GEN
T1 - Accuracy evaluations of human moving pattern using communication quality based on machine learning
AU - Kawakami, Wataru
AU - Kanai, Kenji
AU - Wei, Bo
AU - Katto, Jiro
N1 - Funding Information:
This work was supported by JSPS KAKENHI Grant Numbers 15H01684 and 17K12681.
PY - 2017/12/19
Y1 - 2017/12/19
N2 - In this paper, we performed human moving pattern recognition using communication quality: cellular download throughputs, Received Signal Strength Indicators (RSSIs) and cellular base station IDs. We apply three machine learning algorithms, such as Support Vector Machine (SVM), K-Nearest Neighbor (KNN) and Random Forest (RF) and evaluate recognition accuracy of human moving patterns. Results conclude that the communication quality can recognize moving patterns with high accuracy.
AB - In this paper, we performed human moving pattern recognition using communication quality: cellular download throughputs, Received Signal Strength Indicators (RSSIs) and cellular base station IDs. We apply three machine learning algorithms, such as Support Vector Machine (SVM), K-Nearest Neighbor (KNN) and Random Forest (RF) and evaluate recognition accuracy of human moving patterns. Results conclude that the communication quality can recognize moving patterns with high accuracy.
KW - Communication quality
KW - Human activity recognition
KW - Machine learning
KW - Mobile sensing
UR - http://www.scopus.com/inward/record.url?scp=85045764320&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85045764320&partnerID=8YFLogxK
U2 - 10.1109/GCCE.2017.8229351
DO - 10.1109/GCCE.2017.8229351
M3 - Conference contribution
AN - SCOPUS:85045764320
T3 - 2017 IEEE 6th Global Conference on Consumer Electronics, GCCE 2017
SP - 1
EP - 2
BT - 2017 IEEE 6th Global Conference on Consumer Electronics, GCCE 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 6th IEEE Global Conference on Consumer Electronics, GCCE 2017
Y2 - 24 October 2017 through 27 October 2017
ER -