20 October 2021 in IEEE Transactions on Intelligent Transportation Systems
In order to realize the reliable and safe operation of the smart railways, and provide high quality information transmission service for passengers, the railway system needs to develop innovative communication network and advanced communication technology to meet the gradually increasing service demand of multi-dimensional comprehensive information resources. The Space-Air-Ground Integrated Network ( SAGIN ) can provide seamless information services for land, sea, air and space users, and is an effective solution to the challenge posed by the future smart railways to the all-time, all-domain, all-air, high-reliability and high-throughput communication. This paper aims to comprehensively discuss the technical development and application examples of High-Speed Railways ( HSRs ) based on SAGIN . Firstly, we analysis the development of the SAGIN and the mobile communication network of the HSRs , and comprehensively discuss the single network architecture of the space-based, air-based and ground-based networks, as well as the integrated network, and discuss the application scenario and network structure of the combination of the integrated networks. At the same time, the communication services, existing problems and key technologies of the space-based, air-based and ground-based networks are discussed, and the application trend of the SAGIN in HSRs is presented. Furthermore, the application scenarios of Artificial Intelligence (AI) technologies in solving the efficient resource utilization of smart railways communication and the SAGIN are studied. Based on these technologies, we point out the research direction for the future development of AI technologies in SAGIN in HSRs communications.
12 February 2020 in IEEE Access
For large-scale iris recognition tasks, the determination of classification thresholds remains a challenging task, especially in practical applications where sample space is growing rapidly. Due to the complexity of iris samples, the classification threshold is difficult to determine with the increase of samples. The key issue to solving such threshold determination problems is to obtain iris feature vectors with more obvious discrimination. Therefore, we train deep convolutional neural networks based on a large number of iris samples to extract iris features. More importantly, an optimized center loss function referred to Tight Center (T-Center) Loss is used to solve the problem of insufficient discrimination caused by the traditional Softmax loss function. In order to evaluate the effectiveness of our proposed method, cosine similarity is used to estimate the similarity between the features on the published iris recognition datasets ND-IRIS-0405, CASIA-Thousand and IITD. Our experiment results prove that the T-Center loss can minimize intra-class variance and maximize inter-class variance, which achieve significant performance on the benchmark experiments.
6 October 2020 in IEEE Transactions on Intelligent Transportation Systems
15 January 2018 in EURASIP Journal on Wireless Communications and Networking
The developments in wireless sensor network (WSN) that enriches with the unique capabilities of cognitive radio technique are giving impetus to the evolution of Cognitive Wireless Sensor Network (CWSN). In a CWSN, wireless sensor nodes can opportunistically transmit on vacant licensed frequencies and operate under a strict interference avoidance policy with the other licensed users. However, typical constraints of energy conservation from battery-driven design, local spectrum availability, reachability with other sensor nodes, and large-scale network architecture with complex topology are factors that maintain an acceptable network performance in the design of CWSN. In addition, the distributed nature of sensor networks also forces each sensor node to act cooperatively for a goal of maximizing the performance of overall network. The desirable features of CWSN make Multi-agent Reinforcement Learning (RL) technique an attractive choice. In this paper, we propose a reinforcement learning-based transmission power and spectrum selection scheme that allows individual sensors to adapt and learn from their past choices and those of their neighbors. Our proposed scheme is multi-agent distributed and is adaptive to both the end-to-end source to sink data requirements and the level of residual energy contained within the sensors in the network. Results show significant improvement in network lifetime when compared with greedy-based resource allocation schemes.