Abstract | ||
---|---|---|
With the development of GPS technology, a new Mobile Internet of Things (M-IoT) is emerging, which perceives the city's rhythm and pulse day and night to collect a large scale of city data. It is urgent to innovate M-IoT service system for these large-scale and heterogeneous data. To cope with the problem, this article proposes a Mobile-IoT based multi-modal reinforcement learning service framework from data perspective, which has three highlights, i) Developing Action-aware High-order Transition Tensor (AHTT) to fuse the heterogeneous data from M-IoTs in a unified form. ii) Developing Multi-modal Markov Decision Process (MMDP) to model the multi-modal reinforcement learning for M-IoT service framework. iii) Developing Tensor Policy Iteration algorithm (TPIA) to solve the optimal tensor policy. Due to using tensor keeps the multi-modal relations of the context information in the process of solving the optimal policy. The proposed M-IoT service system provides more personalized service for taxi drivers. The experiment results shows that most taxi drivers earn more revenue according to the tensor policy. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/TSC.2020.2964663 | IEEE Transactions on Services Computing |
Keywords | DocType | Volume |
Multi-modal reinforcement learning,mobile Internet of Things,service framework,social sensors,multi-modal Markov decision process,action-aware high-order transition tensor,tensor policy iteration algorithm,optimal tensor policy | Journal | 13 |
Issue | ISSN | Citations |
4 | 1939-1374 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Puming Wang | 1 | 16 | 3.00 |
Laurence T. Yang | 2 | 6870 | 682.61 |
Jintao Li | 3 | 21 | 3.33 |
Xue Li | 4 | 0 | 0.68 |
Xiaokang Zhou | 5 | 225 | 25.50 |