Yin Sheng

Dr. Yin Sheng

orcid

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
22 September 2022 in IEEE Transactions on Computational Social Systems
Verified
Journal Article
Closed access
Libo ZhangLibo Zhang
Libo Zhang
ZYZhihang Yu
Zhihang Yu
SWShiyu Wu
Shiyu Wu
HZHaibin Zhu
Haibin Zhu
YSYin Sheng
Yin Sheng
Based on role-based collaboration (RBC), group role assignment (GRA) optimizes a team’s overall performance by assigning the most appropriate individual agents from the team’s viewpoint based on agents’ role-playing abilities. As an extension of GRA, GRA with a training plan (GRATP) deals with the impact of training on team management. Considering the correlation between roles, the training of one agent on one role also affects the performance of the agent in other roles. Moreover, in the adaptive collaboration (AC) problem, the training time also affects significantly the agent’s ability, as an agent’s ability changes over time. However, the existing GRATP models fail to consider these factors in the collaboration process. Therefore, we aim to address the role-correlation-based adaptive GRATP (RCA-GRATP) in this article. This article contributes two aspects to the literature on AC. 1) RCA-GRATP problem is abstracted based on RBC and GRA. To the best of the authors’ knowledge, this is the first article that explicitly considers role correlation in the RBC problems. 2) A comprehensive formalization of RCA-GRATP and two solving algorithms for diverse situations are proposed to solve the formalized problems. Experiments are carried out to verify the effectiveness of the proposed algorithms in diverse scenarios.

10 July 2024 in IEEE Systems, Man, and Cybernetics Magazine
Verified
Journal Article
Closed access
HZHaibin Zhu
Haibin Zhu
DLDongning Liu
Dongning Liu
HMHua Ma
Hua Ma
YSYin Sheng
Yin Sheng
Libo ZhangLibo Zhang
Libo Zhang
QJQian Jiang
Qian Jiang
In addition to outlining the key components of the Environments – Classes, Agents, Roles, Groups, and Objects (E-CARGO) model and Role-Based Collaboration (RBC) methodology, this article aims to serve as a comprehensive research guide for scholars and researchers embarking on investigations within their research fields. By offering persuasive and illustrative arguments, the authors furnish valuable and pragmatic guidelines, equipping potential researchers with insights on selecting pertinent topics, crafting compelling scenarios, engaging in effective modeling practices, and designing rigorous experiments. The elucidation of these fundamental steps not only facilitates a clearer understanding of the intricate aspects of E-CARGO and RBC but also provides a road map for researchers to navigate the intricacies of conducting solid and insightful research within these frameworks.

1 January 2022 in Wireless Communications and Mobile Computing
Verified
Journal Article
Open access
PDF file
WHWenting Hu
Wenting Hu
YSYin Sheng
Yin Sheng
XZXianjun Zhu
Xianjun Zhu
There is a semantic gap between people’s understanding of images and the underlying visual features of images, which makes it difficult for image retrieval results to meet the needs of individual interests. To overcome the semantic gap in image retrieval, this paper proposes a semantic image retrieval method based on interest selection. This method analyses the interest points of individual selections and gives the weight of the interest selection in different regions of an image. By extracting the underlying visual features of different regions, this paper constructs two feature vector methods after users’ interest point weighting. The two methods are called interest weighted summation and interest weighting. Finally, this paper compares the accuracy of different image classification methods using a support vector machine classification algorithm. The experimental results show that the target classification accuracy of the classification algorithm based on interest weighted summation is higher than that of the traditional and interest weighted methods. The classification algorithm based on interest weighted summation has the highest overall effect on target object classification in the four experimental scenarios. Therefore, the interest point selection method can effectively improve the overall satisfaction of image recommendation and can be used as a novel solution to overcome the semantic gap.

14 November 2019
Verified
Book Chapter
Closed access
PDF file
YSYin Sheng
Yin Sheng
Wenting HuWenting Hu
Wenting Hu
XZXianjun Zhu
Xianjun Zhu

20 March 2024 in Research Square
Verified
Preprint
Open access
PDF file
YAYves Fidèle Aikoun
Yves Fidèle Aikoun
YSYin Sheng
Yin Sheng
New challenges have arisen in the field of wireless communication systems since the advent of Fifth Generation (5G) networks and the main objectives of delivering higher data rates, ultra-low latency, more reliability, and massive network capacity. While massive multiple-input multiple-output (MIMO) systems have emerged as a key technology for delivering a more uniform user experience to multiple users simultaneously, the deployment of multiple radiated elements in a confined area can lead to interference between the transmitted and received signals, resulting in the degradation of system efficiency. Therefore, interference management techniques are essential to mitigate this impact and enhance system performance. This review aims to explore interference management techniques in massive MIMO systems, including beamforming methods, non-orthogonal multiple access (NOMA), and joint transmission coordinated multi-point (JT-CoMP). The objective is to analyze the performance of these techniques in terms of the network capacity, coverage, and reliability and to compare their effectiveness in reducing interference. The valuable insights gained from this investigation will serve to inform the design and optimization of these systems.

17 October 2026 in Applied Sciences
Verified
Journal Article
Open access
PDF file
YSYin Sheng
Yin Sheng
HZHaibin Zhu
Haibin Zhu
XHXiaopeng Huang
Xiaopeng Huang
ZYZhang Yuhang
Zhang Yuhang
Project makespan in role-based work depends not only on task precedence and workload but also on how different members are assigned and reassigned to executable roles. This paper models project tasks using the Environments—Classes, Agents, Roles, Groups, and Objects (E-CARGO) model, in which tasks are represented as roles with workloads, assignment bounds, and precedence relations. The duration of each role depends not only on its workload but also on the number and qualifications of the members assigned to it. Aggregate role duration, defined as the sum of all role durations, provides a role-level duration measure for concurrent roles under parallel execution. To reduce this metric, a Greedy Group Role Assignment (GGRA) algorithm is proposed for executable parallel roles under lower and upper role bounds; an Adaptive Group Role Assignment (AGRA) method then embeds GGRA in a role relation graph by repeatedly identifying executable roles, assigning project members, updating remaining workloads, and recording the resulting project makespan. In the experiments, GGRA reduces aggregate role duration by 6.04% on average relative to Linear Programming-based Group Role Assignment (LPGRA) and wins against LPGRA in 97.56% of repeated instances. On complete project graphs with non-chain precedence structures, the main project-level benefit of AGRA comes from its adaptive scheduling mechanism, which exploits executable parallel roles and updates unfinished workloads as roles are completed. In structured qualification gap instances, AGRA with GGRA reduces makespan by 10.02% on average relative to Static GRA and by 16.82% on average relative to AGRA with LPGRA under the same total member budget. These results indicate that adaptive role assignment based on E-CARGO can complement the Critical Path Method (CPM) and the Program Evaluation and Review Technique (PERT) by making role duration, aggregate role duration, and project makespan dependent on the assignment of members to roles.