TY - GEN
T1 - Cellular User Clustering
T2 - 2nd International Conference on Intelligent Manufacturing and Robotics, ICIMR 2024
AU - Yan, Kong Zi
AU - Max,
AU - Aslam, Saad
AU - PP Abdul Majeed, Anwar
AU - Chen, Wei
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.
PY - 2025
Y1 - 2025
N2 - The rapid evolution of wireless communication systems emphasizes the need for efficient data transfer mechanisms, particularly considering cellular communication. For efficient data transfer, this study considers clustering cellular users and showcases the performance gains across different performance matrices. We create a cellular communication environment on MATLAB and use K-Medoids, Hierarchical Clustering with Ward's Linkage, and DBSCAN algorithms to cluster the users. Subsequently, we evaluate the performance of the system by considering user data rate, throughput, and spectral efficiency. We also propose an algorithm, based on signal strength measurements and optimized using different existing techniques. In this study, we utilize the Calinski-Harabasz criterion, Gap statistic, and Silhouette score to determine the optimal number of clusters, refining network performance through successive adjustments. A comprehensive comparative study of clustering algorithms shows consistent improvements across all performance parameters, underscoring their robustness in ensuring reliable communication. Notably, the proposed algorithm boosted the signal strength by approximately 15% which resulted in improvement of other parameters such as user data rate and throughput.
AB - The rapid evolution of wireless communication systems emphasizes the need for efficient data transfer mechanisms, particularly considering cellular communication. For efficient data transfer, this study considers clustering cellular users and showcases the performance gains across different performance matrices. We create a cellular communication environment on MATLAB and use K-Medoids, Hierarchical Clustering with Ward's Linkage, and DBSCAN algorithms to cluster the users. Subsequently, we evaluate the performance of the system by considering user data rate, throughput, and spectral efficiency. We also propose an algorithm, based on signal strength measurements and optimized using different existing techniques. In this study, we utilize the Calinski-Harabasz criterion, Gap statistic, and Silhouette score to determine the optimal number of clusters, refining network performance through successive adjustments. A comprehensive comparative study of clustering algorithms shows consistent improvements across all performance parameters, underscoring their robustness in ensuring reliable communication. Notably, the proposed algorithm boosted the signal strength by approximately 15% which resulted in improvement of other parameters such as user data rate and throughput.
KW - Clustering Algorithms
KW - Network Performance
KW - Spectral Efficiency
KW - User Data Rates
UR - http://www.scopus.com/inward/record.url?scp=105002725070&partnerID=8YFLogxK
U2 - 10.1007/978-981-96-3949-6_32
DO - 10.1007/978-981-96-3949-6_32
M3 - Conference Proceeding
AN - SCOPUS:105002725070
SN - 9789819639489
T3 - Lecture Notes in Networks and Systems
SP - 401
EP - 409
BT - Selected Proceedings from the 2nd International Conference on Intelligent Manufacturing and Robotics, ICIMR 2024 - Advances in Intelligent Manufacturing and Robotics
A2 - Chen, Wei
A2 - Ping Tan, Andrew Huey
A2 - Luo, Yang
A2 - Huang, Long
A2 - Zhu, Yuyi
A2 - PP Abdul Majeed, Anwar
A2 - Zhang, Fan
A2 - Yan, Yuyao
A2 - Liu, Chenguang
PB - Springer Science and Business Media Deutschland GmbH
Y2 - 22 August 2024 through 23 August 2024
ER -