TY - GEN
T1 - A learning based human interaction modeling using mobile sensing
AU - Kulshrestha, Tarun
AU - Saxena, Divya
AU - Niyogi, Rajdeep
N1 - Funding Information:
ACKNOWLEDGMENT The third author was in part supported by a research grant from Google.
Publisher Copyright:
© 2019 IEEE.
PY - 2019/12
Y1 - 2019/12
N2 - Online social networks are emerging as a convenient platform where users build social relations with other individuals having similar interests, family/work background, etc. However, existing human interaction modeling is based on social graphs which are not more precise for friend suggestions in real-life. In this paper, we leverage the basic feats of deep learning for developing human interaction system, named MyCompanion, based on the user's lifestyle/activity information collected using the mobile crowd sensing. We collect a user's local knowledge, such as local information, ambient, and activity type, activity location and activity time. Then, the collected information is further aggregated and transferred to the deep learning enabled cloud server for user's daily schedule/activities analysis. We propose a schedule matching algorithm which finds the similarity among individuals' activities w.r.t. their activity type, activity time and activity location to recommend the most suitable friend(s) to the users. We develop a real-time testbed to perform a spatio-temporal analysis of the collected data from the users' smartphones. We also perform several experiments for evaluating the system performance. Our proof-of-concept prototype shows the usability of the proposed system.
AB - Online social networks are emerging as a convenient platform where users build social relations with other individuals having similar interests, family/work background, etc. However, existing human interaction modeling is based on social graphs which are not more precise for friend suggestions in real-life. In this paper, we leverage the basic feats of deep learning for developing human interaction system, named MyCompanion, based on the user's lifestyle/activity information collected using the mobile crowd sensing. We collect a user's local knowledge, such as local information, ambient, and activity type, activity location and activity time. Then, the collected information is further aggregated and transferred to the deep learning enabled cloud server for user's daily schedule/activities analysis. We propose a schedule matching algorithm which finds the similarity among individuals' activities w.r.t. their activity type, activity time and activity location to recommend the most suitable friend(s) to the users. We develop a real-time testbed to perform a spatio-temporal analysis of the collected data from the users' smartphones. We also perform several experiments for evaluating the system performance. Our proof-of-concept prototype shows the usability of the proposed system.
KW - Crowdsourcing
KW - Friend's suggestion
KW - Human interactions
KW - Lstm
KW - Mobile crowd sensing
KW - Recurrent neural networks
KW - Similarity index
KW - Social networks
UR - http://www.scopus.com/inward/record.url?scp=85085520072&partnerID=8YFLogxK
U2 - 10.1109/ISPA-BDCloud-SustainCom-SocialCom48970.2019.00150
DO - 10.1109/ISPA-BDCloud-SustainCom-SocialCom48970.2019.00150
M3 - Conference article published in proceeding or book
AN - SCOPUS:85085520072
T3 - Proceedings - 2019 IEEE Intl Conf on Parallel and Distributed Processing with Applications, Big Data and Cloud Computing, Sustainable Computing and Communications, Social Computing and Networking, ISPA/BDCloud/SustainCom/SocialCom 2019
SP - 1049
EP - 1058
BT - Proceedings - 2019 IEEE Intl Conf on Parallel and Distributed Processing with Applications, Big Data and Cloud Computing, Sustainable Computing and Communications, Social Computing and Networking, ISPA/BDCloud/SustainCom/SocialCom 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 17th IEEE International Conference on Parallel and Distributed Processing with Applications, 9th IEEE International Conference on Big Data and Cloud Computing, 9th IEEE International Conference on Sustainable Computing and Communications, 12th IEEE International Conference on Social Computing and Networking, ISPA/BDCloud/SustainCom/SocialCom 2019
Y2 - 16 December 2019 through 18 December 2019
ER -
