Ebook: Computer Systems and Communication Technology

We are delighted to present the proceedings of the 2023 5th International Conference on Computer Systems and Communication Technology (ICCSCT 2023), held in Kuala Lumpur, Malaysia, from November 24–25, 2023.

The vision behind ICCSCT 2023 was to establish a premier interdisciplinary platform for researchers, practitioners, and educators to showcase and discuss the latest innovations, trends, challenges, and solutions in the fields of Computer Systems and Engineering, Computer Graphics and Multimedia, and Communication Technology.

The conference comprised three distinct sessions, featuring oral presentations, keynote speeches, and an engaging online Q&A discussion format. With participation from 50 attendees representing 12 countries, including Australia, Canada, China, Germany, India, Kazakhstan, Pakistan, Poland, Nepal, Saudi Arabia, the UK, and the USA, the event showcased a truly global perspective.

A total of 8 keynote speeches and 42 oral presentations enriched the conference agenda. Keynote speakers were allotted 30 minutes each, while oral presenters had 15 minutes, followed by a dynamic 3-minute Question and Answer (Q&A) session.

We extend our heartfelt gratitude to all the authors who submitted papers and the dedicated delegates whose active participation contributed to making ICCSCT a vibrant platform for sharing ideas and innovations.

Special thanks are due to our committee members for their unwavering guidance and support. The commendable efforts of our peer reviewers significantly enhanced the quality of the papers through constructive critical comments, improvements, and corrections. We sincerely appreciate their invaluable contributions, which played a pivotal role in the success of the conference.

Prof. Wenfeng Zheng

Editor of the ICCSCT2023 Proceeding

The University of Electronic Science and Technology of China

Email: winfirms@uestc.edu.cn

https://faculty.uestc.edu.cn/zhengwenfeng/en/index.htm

The reconstruction of public sports service system is the core issue facing the construction of free trade port. Through the investigation of the status quo of public sports service system in the construction of free trade port, the gap between Hainan free trade port and international and domestic public sports service system is concluded through computer statistical analysis and research. And then through the expert demonstration, under the leadership and support of the government, a series of public sports service system and industrial development policies and measures suitable for the construction of free trade ports are formulated.

Crowd management is a significant topic especially for countries that support gathering events frequently. The Kingdom of Saudi Arabia hosts and manages one of the world class annual religious gatherings known as “pilgrimage”. Several challenges are raised for managing and controlling such mass gathering event. In this paper we propose a comprehensive framework for event processes modelling and management. The framework consists of four main stages starts with acquiring temporal data and ends by modelling different processes of the event. The main contribution of this work is to demonstrate how process mining techniques can be used innovatively to model the movement flow of crowd. Synthetic data is used to show a proof-of-concept of the proposed framework and the applicability of using it in modelling and monitoring real crowd movement scenarios.

Maritime vessels utilizing shore power while docked offer significant potential for substantial reduction of exhaust emissions, consequently mitigating atmospheric pollution within port environs. However, the substantial initial investment costs associated with constructing shore power infrastructure and retrofitting vessels with shore power access equipment pose a substantial challenge, as the short-term economic returns are not readily apparent. This unfavorable aspect significantly impedes the widespread adoption of shore power technology. Furthermore, dynamic factors such as government subsidy policies, environmental mandates for maritime vessels, electricity pricing, fuel costs, and port queuing strategies exert direct influence over the economic returns of shore power systems, thereby introducing significant complexities into the comprehensive evaluation of their economic viability.In response to these challenges, this paper presents a simulation model designed to replicate the behaviors of vessels, shore power facilities, and dynamic factors. This model offers a detailed estimation of the economic benefits of shore power systems throughout their entire lifecycle under various operational strategies. The simulation model is implemented using the Anylogic tool. The results indicate that the simulation outcomes over the past three years closely align with actual data, thus affirming the reliability of the model. The simulation model serves as a valuable decision-making tool for vessel operators, shore power stakeholders, and governmental authorities. It is conducive to the promotion of shore power adoption and enables the projection of the economic benefits of shore power systems over a defined time horizon.

Aiming at the target localization problem in monocular vision, this paper proposes a nonlinear target localization method under non-orthoptic conditions. First, an image is captured using a monocular camera and a network framework based on YOLOv7 is constructed to detect the target in the image. Then, based on the principle of aperture imaging, the imaging models of orthophoto and non-orthophoto are established, and the nonlinear relationship between pixel coordinates and world coordinates in the image is deduced, so as to calculate the relative position coordinates of the target. In order to verify the validity of this nonlinear imaging model, we choose different shapes and numbers of ship targets for verification. The experimental results show that the target localization accuracy of monocular vision can reach more than 90% under non-orthoptic conditions.

Focusing on the collaborative control of quadrotor Unmanned Aerial Vehicles (UAVs) and underactuated Unmanned Surface Vessels (USVs), this article presents a cooperative control algorithm based on fixed-time theory. By constructing an adaptive neural network to approximate model uncertainty and unknown disturbances in the system, this algorithm satisfies the coordinated motion constraints between UAVs and USVs, while achieving group control objectives such as trajectory tracking. Additionally, this article employs the fixed-time method in the Lyapunov function to analyze system stability, ensuring that the cooperative control error converges within a fixed time, ultimately enabling fast and stable tracking of targets between UAVs and USVs. Finally, the effectiveness of the proposed algorithm is verified through numerical simulation experiments.

The article describes a technology processing ontological model of words in public political discourse. The research task is developing an information question-answering system of political discourse in Kazakh language. The Python programming language, Sparql data-query language, and Owlready module are used to develop the system.

The purpose of this paper is to investigate the interactions between driver manipulation behaviors. Firstly, representative samples from driving behavior dataset were screened. Secondly, four characteristic indicators were constructed. Thirdly, the Apriori algorithm was established for correlation analysis on these four driving behaviors in order to obtain the influence relationship between different driving behaviors. Therefore, the correlation between different undesirable driving behaviors and reveals the intrinsic law of driver manipulation behavior were illustrated, which provided great significance for improving the warning effect and intervention efficiency of automotive active safety systems.

Safety procedures are the fundamental criteria to ensure the safety of personnel and equipment, and their proficiency and the rigor of the application are crucial. According to the actual existing training technology digital means is relatively backward, intuitive, affect the lack of training depth and effect, this paper to the switch room equipment as the object, based on 3Dmodeling and virtual simulation technology design and developed a can realize safety procedures learning, training of 3D visualization software tools, to solve the difficulty of maintenance training, safety procedures training tools missing problems.

To improve the visibility and clarity of images in underwater environment, this paper proposes an underwater image enhancement method based on multi-scale fusion. Firstly, the white balance method is used to correct the color of the underwater image, and the original color of the underwater elements is restored as much as possible. Secondly, the dark channel prior algorithm is used to solve the underwater image blur problem. Then, the CLAHE algorithm is used to enhance the contrast of the image. Finally, using weight allocation or fusion rules, multi-scale information and multi-stage fusion of the image are used to generate the final enhanced underwater image. Quantitative image quality evaluation indexes PSNR, SSIM and UIQE are used to evaluate underwater image quality. The results show that the proposed method can effectively solve the problem of underwater image color deviation, make the color of the image more accurate and natural, improve the contrast and brightness of the underwater image, and have better visual effect and richer detail information.

Non-halogenated flame retardants are becoming the trend in the development of polymer flame retardant materials due to their high flame retardant efficiency and low generation of toxic smoke gases. Non-halogenated flame retardants achieve flame retardancy by forming a dense char layer and generating non-combustible gases, with the micro-porous structure of the char residue being crucial for studying the flame retardant mechanism. This study focuses on the segmentation of pores in scanning electron microscopy (SEM) images of the combustion char layer of non-halogenated flame retardant materials, which are cropped and labeled to form a unified dataset. We investigate the SEM image pore segmentation using data augmentation and transfer learning, addressing the challenge of limited sample size. We explore the impact of different data augmentation techniques and transfer learning on model performance. Additionally, we compare convolutional neural network (CNN) segmentation algorithms with traditional segmentation methods. Experimental results demonstrate that CNN segmentation algorithms outperform traditional methods in terms of segmentation accuracy. Offline data augmentation enhances model stability compared to online data augmentation, and adopting transfer learning significantly improves model performance metrics. Specifically, when training with VGG backbone weights through transfer learning, the average pixel accuracy and average intersection over union reach 94.49% and 89.88%, respectively.