Zhiping Wan

Zhiping Wan

Auto-generated profile, based on publicly available information

Zhiping Wan

Guangzhou Xinhua University, Dongguan, Guangdong, China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 March 2024 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
ZWZhiping Wan
Zhiping Wan
SLShaojiang Liu
Shaojiang Liu
ZXZhiming Xu
Zhiming Xu
WNWeichuan Ni
Weichuan Ni
SYShitong Ye
Shitong Ye
FWFeng Wang
Feng Wang
As intelligent vehicle networks become integral to modern transportation systems, the need for accurate and efficient multi-scene target detection in complex urban environments is increasingly critical. Addressing the challenge of processing and transmitting extensive image data rapidly and accurately under dynamic road conditions, this paper proposes the Multi-scene Target Detection Semantic Communication (MTDSC) method. MTDSC employs convolutional neural networks and region proposal networks for effective target detection in images, and further utilizes spatial pyramid pooling and Long Short-Term Memory (LSTM) networks to assign relevant semantic labels in varied scenarios. These labels are transformed into a transmissible encoding format using a convolutional semantic encoder and a reinforcement learning strategy. The transmission phase leverages variational self-encoders techniques for channel encoding and decoding, ensuring reliable semantic information transfer in complex wireless environments. A crucial aspect of this research is semantic decoding and image reconstruction. To recover original semantic information accurately, a structured Support Vector Machine (SVM) loss function is utilized, designed to capture the structural relationships among labels and enhance the consistency between decoded and original semantic labels. Experimental results show that MTDSC effectively reconstructs semantic images across different road scenes, ensuring key information retention and high-quality image reconstruction, even in low bit rate and complex scenarios.

1 November 2023 in IEEE Transactions on Consumer Electronics
Verified
Journal Article
Closed access
ZWZhiping Wan
Zhiping Wan
SLShaojiang Liu
Shaojiang Liu
ZXZhiming Xu
Zhiming Xu
WNWeichuan Ni
Weichuan Ni
ZCZhaoqi Chen
Zhaoqi Chen
FWFeng Wang
Feng Wang
With the increasing amount of image data required for vision tasks, traditional data transmission methods face the problems of high latency and low reliability, which greatly limit the performance and application potential of the Artificial Intelligence of Things (AIoT). In order to solve this problem, this paper proposes a semantic communication method based on compression ratio optimization, which aims to reduce the communication delay and improve the reliability of data transmission by optimizing the compression and transmission process of image data. First, in the feature extraction phase the method extracts key visual features from the original image data. Subsequently, in the semantic relation extraction phase, we further analyze the association relations between these features to understand the semantic content of the image data. Finally, during the semantic compression stage, we implemented an adaptive optimization method that automatically selects the optimal compression ratio. Compared to traditional methods of wireless data transmission, this approach can significantly minimize transmission delay while ensuring that no critical data is lost. The experimental results show that this semantic communication method not only significantly reduces the completion time of the intelligent task, but also improves the antijamming ability of the image semantic communication.

16 July 2019 in IEEE Access
Verified
Journal Article
Open access
ZWZhiping Wan
Zhiping Wan
ZPZhihong Pan
Zhihong Pan
WNWeichuan Ni
Weichuan Ni
FWFeng Wang
Feng Wang
ZQZemin Qiu
Zemin Qiu
ZXZhiming Xu
Zhiming Xu
Vehicle mobile Internet of Things uses sensor technology, mobile Internet technology, and intelligent computing technology to effectively monitor and provide comprehensive services for vehicle operation status. It is an important part of building a smart city, making urban transportation more efficient, environmentally friendly, intelligent, and safety. In the vehicle mobile Internet of Things, when in-vehicle sensors are in communication with each other, they are often affected by factors, such as network mobility, transmission range, and signal interference. Therefore, in order to ensure the continuity of communication between nodes and improve the quality of network communication, this paper proposes a vehicle mobile Internet of Things coverage enhancement algorithm (PANM). First, we derive the probabilistic analysis model of communication duration by analyzing the functional relationship of vehicle initial velocity, acceleration, spacing distance, and communication duration. Then, under the premise of ensuring the communication duration, in order to improve the coverage of the vehicle mobile Internet of Things, the network overlap ratio is introduced in the probability analysis model. Finally, we improve the network coverage performance of omnidirectional radiation and fan-shaped radiation communication models of vehicle mobile Internet of Things by limiting the overlap ratio threshold. The experimental simulation results indicate that the PANM algorithm can reduce the packet loss rate of the vehicle network and have a shorter communication delay.

15 July 2019 in Wireless Communications and Mobile Computing
Verified
Journal Article
Open access
PDF file
SLShaojiang Liu
Shaojiang Liu
KHKejing Hu
Kejing Hu
WNWeichuan Ni
Weichuan Ni
ZXZhiming Xu
Zhiming Xu
FWFeng Wang
Feng Wang
ZWZhiping Wan
Zhiping Wan
In cognitive relay networks, the cognitive user opportunistically accesses the authorized spectrum segment of the primary user and simultaneously serves as the data relay node of the primary user while sharing the spectrum resource of the primary user. This not only improves the utilization efficiency of the network spectrum resources but also improves the throughput of the primary users. However, if the primary user randomly selects the relay node, there is no guarantee for an optimal throughput. Moreover, the system power consumption may increase. In order to improve the throughput of cognitive relay network and optimize system utility, this paper proposes a cognitive relay network throughput optimization algorithm based on deep reinforcement learning. For the system model of cognitive relay networks, the Markov decision process is used to describe the channel transition probability of the system model in the paper. The algorithm proposes a cooperative wireless network cooperative relay strategy, analyzes the system outage probability under different transmission modes, and optimizes the system throughput by minimizing the outage probability. Then, the maximum utility optimization strategy based on deep reinforcement learning is proposed to maximize the system utility revenue by selecting the optimal behavior. The experimental results show that the proposed algorithm has a good effect in improving system throughput and optimizing system energy efficiency.

1 December 2023 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
FWFeng Wang
Feng Wang
WNWeichuan Ni
Weichuan Ni
SLShaojiang Liu
Shaojiang Liu
ZXZhiming Xu
Zhiming Xu
ZWZhiping Wan
Zhiping Wan
The existing pedestrian target recognition algorithms often suffer from insufficient classification decision, which affects the accuracy of tracking. This paper proposes an algorithm that enhances tracking accuracy by incorporating target information from preceding and subsequent frames in the video. To tackle the issue of drift during target occlusion, the algorithm establishes a feature dictionary by extracting relevant information such as pedestrian contours, key points, and geometric features. Moreover, to address the issue of target drift, this algorithm employs a twin Network and a model update mechanism to process the filtered target information. Experimental results with measured data demonstrate that this algorithm outperforms traditional detection methods in characterizing local features of the target. Moreover, it successfully solves the challenges of classification decision and target drift in pedestrian recognition, offering improved stability and accuracy. This algorithm shows promising prospects for application in smart cities and other relevant domains. Future work will focus on conducting more optimizations to enhance adaptability to various environments and scenarios.