检索结果-内蒙古大学图书馆

12th IEEE Conference on Systems, Process and Control, ICSPC 2024

作者： Amit, Mohamad Azan Samah, Khyrina Airin Fariza Abu Ghazali, Nurulhuda Suffian, Maswati Mansor, Mastura Zahidi, Nurul Emyza Universiti Teknologi MARA Melaka Branch College of Computing Informatics and Mathematics Jasin Campus Melaka Malaysia

ISBN: (纸本)9798350391398

The growing competition between more than 20 licensed electronic hailing (e-hailing) services in Malaysia requires the analysis of consumer satisfaction since understanding consumers' perceptions is crucial for service improvement. This data can be obtained from consumer reviews of e-hailing services. The paper details how the reviews can be analysed at the aspect level and represents the results using various data visualisation techniques to comprehensively understand consumer satisfaction. This study employs a modified waterfall model to develop a visualisation dashboard for the aspect-based sentiment analysis of Malaysia's e-hailing services. It comprises five phases: requirement, design, implementation, testing, and deployment. We evaluate the result by conducting a usability test using the Post-Study System Usability Questionnaire (PSSUQ). The questionnaire was distributed using a survey method involving 35 respondents. Based on the survey analysis, we received 92.83% for system usefulness, 91.33% for information quality and 94.17% for interface quality. As a result, the usability test of this study achieved an overall satisfaction of 92.67%. We conclude that the system is the best imaginable and accepted. © 2024 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Learning Human Anatomy Using Augmented Reality Mobile Application

Learning Human Anatomy Using Augmented Reality Mobile Applic...

引用

2023 International Conference on Digital Applications, Transformation and Economy, ICDATE 2023

作者： Abdullah, Nur Atiqah Sia Rokmain, Nur Shakila Sahira Universiti Teknologi Mara School of Computing Sciences College of Computing Informatics and Media Selangor Shah Alam Malaysia

ISBN: (纸本)9798350310689

In this current era of technological advancement, the development of Augmented Reality (AR) technology already has a major influence on the education domain. Therefore, more efforts to create educational applications for learners to understand diverse topics using AR. This paper aims to share the experience of developing a mobile application for learning human anatomy using AR. We selected the marker-based technique as the AR technique and Android platform for mobile application development. We follow the Mobile Application Development Life Cycle (MADLC) for the development process. During the design phase, we define the system architecture, use case diagram, algorithm design, and user interface design. Then, we utilize Unity3D, Vuforia, Visual Studio Code, Blender, and AR Core during the development. The Unity's features in this AR application include importing the Vuforia database, image targets, camera conversion, 3D modeling of human anatomy and organs, canvas, and panel, and the lean touch tool kit for scaling and rotating 3D models. As a result, we successfully developed a mobile application for learning human anatomy using AR. This application helps the learner understand as well as enhances the learning experience in human anatomy. © 2023 IEEE.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Intelligent and Secure Evolved Framework for Vaccine Supply Chain Management Using Machine Learning and Blockchain

引用

SN Computer Science 2025年第2期6卷 1-28页

作者： Abdel-salam, Mahmoud Elhoseny, Mohamed El-hasnony, Ibrahim M. Faculty of Computers and Information Science Mansoura University Mansoura Egypt College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates

Supply chain management (SCM) ensures that fragile goods are delivered from their origin to their destination without suffering any damage. The COVID-19 pandemic’s widespread has exposed systemic weaknesses in SCM across a variety of sectors, particularly healthcare. This paper aims to tackle issues related to vaccine expiration and fraudulent vaccine records by facilitating vaccine traceability and innovative contract features. The proposed model suggests utilizing an intelligent and secure framework that merges machine learning intelligent techniques with blockchain technology. The proposed model utilizes the Ethereum blockchain’s characteristics to establish novel smart contracts between diverse participants in the supply chain. In addition, the proposed model presents two modules to assist in predicting the demand for vaccines and analyzing the sentiment of vaccine reviews to improve the quality of vaccines. Therefore, an Improved Honey Badger Algorithm (IHBA) is presented to enhance the performance of the Long Short-Term Memory (LSTM) algorithm in predicting vaccine demand besides the credibility evaluation of reviews. For the vaccine demand prediction module, a real dataset obtained from the centers for Disease Control and Prevention (CDC) is collected and the proposed model is applied obtaining the minimum RMSE of 1.3828 for the prediction results compared with other approaches. For the review analysis module, a publicly available dataset from the University of California, Irvine (UCI) is used, and the proposed model achieved a high accuracy of user reviews of 90.6% compared with other related approaches. The proposed model is compared with other related metaheuristic algorithms and the standard deep learning optimizers. The proposed new algorithm outperforms other competitors for tuning the hyperparameters of deep learning models. Finally, the proposed system presents implications for sustainable supply chain management, enterprise operations, and public pol

关键词： Blockchain HBA Intelligent LSTM Intelligent machine learning Intelligent model Machine learning Supply chain management Sustainability Traceability

来源：评论

学校读者我要写书评

暂无评论

Sales Promotion Mobile Application using Augmented Reality 8

Sales Promotion Mobile Application using Augmented Reality

引用

8th IEEE International Conference on Recent Advances and Innovations in Engineering, ICRAIE 2023

作者： Sia Abdullah, Nur Atiqah Anak Ulan, Amelia Natasha Dora Rosli, Marshima Mohd Universiti Teknologi MARA School of Computing Sciences College of Computing Informatics and Mathematics Selangor Shah Alam Malaysia

ISBN: (纸本)9798350315516

Nowadays, most people utilize innovative technologies to fulfill their needs, which drives the retail industry's global evolution. To stay relevant and survive in an industry, retailers acquire a competitive advantage over their competitors. Thus, this paper aims to share an enhanced shopping experience in retail stores with augmented reality. It covers the process of identifying a suitable augmented reality (AR) approach in retail stores, constructing a mobile application, and evaluating the functionality of the application. After extensive research, marker-based AR techniques on Android were best suited to create the mobile application. By using the Mobile Development Life Cycle, we cover requirement gathering, then planning out the system architecture, use case diagram, algorithm design, and user interface design. Unity, Figma, and Vuforia are utilized to develop the application. After testing, the mobile application is ready for its final launch. We believe that this mobile application provides the competitive advantage that retailers need. © 2023 IEEE.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Evaluating Chinese Large Language Models on Discipline Knowledge Acquisition via Assessing Memorization and Robustness 1

Evaluating Chinese Large Language Models on Discipline Knowl...

引用

1st Data Contamination Workshop, CONDA 2024

作者： Liu, Chuang Jin, Renren Steedman, Mark Xiong, Deyi College of Intelligence and Computing Tianjin University Tianjin China School of Informatics University of Edinburgh United Kingdom

ISBN: (纸本)9798891761353

Chinese large language models (LLMs) demonstrate impressive performance on NLP tasks, particularly on discipline knowledge benchmarks, where certain Chinese LLMs are very competitive to GPT-4. Previous research has viewed these advancements as potential outcomes of data contamination or leakage, prompting efforts to create new detection methods and address evaluation issues in LLM benchmarks. However, there has been a lack of comprehensive assessment of the evolution of Chinese LLMs. To bridge this gap, this paper offers a thorough investigation of Chinese LLMs on discipline knowledge evaluation, delving into the advancements of various LLMs, including a group of related models and others. Specifically, we have conducted six assessments ranging from knowledge memorization to comprehension for robustness, encompassing tasks like predicting incomplete questions and options, identifying behaviors by the contaminational fine-tuning, and answering rephrased questions. Experimental findings indicate a positive correlation between the release time of LLMs and their memorization capabilities, but they struggle with variations in original question-options pairs. Additionally, our findings suggest that question descriptions have a more significant impact on the performance of LLMs. ©2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Sociotechnical AI Education Course Design for CS Majors and Non-Majors 56

Sociotechnical AI Education Course Design for CS Majors and ...

引用

56th Annual SIGCSE Technical Symposium on Computer Science Education, SIGCSE TS 2025

作者： Tadimalla, Sri Yash Maher, Mary Lou UNC Charlotte College of Computing and Informatics Charlotte NC United States

ISBN: (纸本)9798400705328

As generative AI increasingly integrates into society and education, the number of institutions implementing AI usage policies and offering introductory AI courses is rising. These introductory AI courses mustn't replicate the "gateway/weed-out" phenomenon observed in introductory computer science courses like CS1 and CS2. Literature in computer science education suggests that interventions such as summer camps, bridge courses, and socio-technical courses have improved the sense of belonging and retention among students from underrepresented groups, thereby broadening participation in computer science. Building on previous work to create a socio-technical curriculum for all ages and education levels, this paper presents a course for teaching introductory AI concepts that adopts a socio-technical approach, complete with weekly activities and content designed for broad access. The course has been taught as a 1-credit general education course, primarily for freshmen and first-year students from various majors, and a 3-credit course for CS majors at all levels. This paper provides a curriculum and resources to teach a socio-technical introductory AI course. This approach is important because it not only democratizes AI education across diverse student backgrounds but also equips all students with the critical socio-technical multidisciplinary perspective necessary to navigate and shape the future ethical landscape of AI technology. © 2025 Copyright held by the owner/author(s).

关键词： AI curriculum AI education intro to AI socio-technical AI literacy

来源：评论

学校读者我要写书评

暂无评论

Web Service Prediction and Composition Based on Harris Hawks Optimization and Deep Learning

引用

SN Computer Science 2025年第5期6卷 1-25页

作者： Elhoseny, Mohamed Abdel-salam, Mahmoud El-hasnony, Ibrahim M. College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates Faculty of Computers and Information Science Mansoura University Mansoura Egypt

QoS-aware service composition suffers from many problems due to the uncertainties of its working environment. Besides, the many candidate services for service composition consume more processing and execution time. This paper presents a four-phases framework for reliable dynamic Web service composition. The preprocessing phase helps to reduce the percentage of missing values of the dataset. Then, clustering phase applies self-organizing maps (SOM) algorithm to cluster the QoS data to reduce data sparsity and cold-start problems of web services. Then, the prediction phase predicts uncertain QoS values of services using an optimized LSTM deep learning model. In the composition module, an improved hybrid optimization algorithm IHHO-SWO is the proposed integrating the Spider Wasp Optimizer (SWO) and is applied to generate a composite service that fits the end user requirements. An exhaustive experimental and statistical study validates the superior performance of the suggested framework. The study reveals that the framework is able to successfully deal with service prediction and composition challenges such as outlier handling, cold start, and data sparsity, lowering these problems considerably. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Classification Data analysis Harris Hawk Optimization Prediction model Service composition Spider Wasp Optimization

来源：评论

学校读者我要写书评

暂无评论

Enhancing Engagement: Assessing Usability and Scoring Model in the Road Safety Spot Hazard Game

Enhancing Engagement: Assessing Usability and Scoring Model ...

引用

2024 International Conference on Computer Engineering, Network and Intelligent Multimedia, CENIM 2024

作者： Salleh, Siti Salwa Ishak, Siti Zaharah Fariza Abu Samah, Khyrina Airin College of Computing Informatics and Mathematics University Technology MARA Negeri Sembilan Malaysia Malaysia Institute of Road Safety Research Selangor Malaysia College of Engineering University Technology MARA Shah Alam Malaysia College of Computing Informatics and Mathematics University Technology MARA Melaka Malaysia

ISBN: (纸本)9798350368802

Incorporating gaming components teaches children how to spot potential road risks in a safe and controlled environment, removing the need to expose them to real-world dangers. To make this work, learning game applications must be engaging while still ensuring that children learn critical skills like hazard awareness and safe behavior. To achieve this, a study was done with the goal of developing a spot-hazard game with a competitive scoring mechanism. There are five phases to the study. The study began with the collection of user requirements, followed by the design, implementation, and testing of usability. It was created for children aged 7 to 12 and features hazard spot modules that demonstrate road safety and encourage cautious behavior. The results indicate that players initially scored the game with the 'life-time + score' scoring mechanism approach at 83.7%, whereas the game's linear scoring method obtained 73.3%. The game prototype's overall usability score was 77%, with scoring features at 84.3%, implying a 7.8% improvement from pre- to post-test results. This demonstrates that participants prefer appealing scoring approaches. Similarly, three main themes emerged from the interview: ease of understanding, perceived fairness, and suggestions for improvement, as highlighted by the participants. In future work, this scoring mechanism will be integrated into an interactive quiz for a children's spot-hazard road safety program with the local community. © 2024 IEEE.

关键词： game life-time road safety score spot hazard

来源：评论

学校读者我要写书评

暂无评论

Conceptualizing Hybrid Descriptive-Semantic Techniques to Enhance Sentiment Analysis of YouTube Reviews: Malaysian Island Contexts 12

Conceptualizing Hybrid Descriptive-Semantic Techniques to En...

引用

12th IEEE Conference on Systems, Process and Control, ICSPC 2024

作者： Bidin, Nurain Batrisyia Binti Samah, Khyrina Airin Fariza Abu Aminuddin, Raihah Binti Universiti Teknologi MARA Melaka Branch College of Computing Informatics and Mathematics Jasin Campus Melaka Malaysia

ISBN: (纸本)9798350391398

Island tourism is a prominent sector in Malaysia that attracts tourists from various countries. The popularity of Malaysia's islands as vacation destinations necessitates thorough research and analysis to identify the ideal vacation spots. With the rise of YouTube as a communication and expression platform, it has become a valuable source of information where users share their perspectives and ideas through video reviews. Following that, Sentiment Analysis (SA) comprehends the context of any word and the emotions expressed in a sentence in order to determine relevant topics by analysing user preferences and trends. Thus, this research aims to enhance SA on YouTube reviews to gain extensive perspectives and insights from users, focusing on Malaysia's islands. This research proposes two techniques combining descriptive and semantic analysis to enhance performance in SA: Aspect-Based Sentiment Analysis (ABSA) for sentiment labelling and Support Vector Machine (SVM) for sentiment classification. Furthermore, this research also involved two phases in developing the comparative technique: 1) problem assessment and research study and 2) techniques for descriptive and semantics. As a result, this research outcome will support decision-making processes, improve the island tourism experience, and contribute to the overall growth of the Malaysian tourism industry. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Topsis with Ratings Based on Sub-Criteria for Selection of Supplier 5

Fuzzy Topsis with Ratings Based on Sub-Criteria for Selectio...

引用

5th International Conference on Artificial Intelligence and Data Sciences, AiDAS 2024

作者： Razak, Samsiah Abdul Ramli, Nazirah Azmi, Muhammad Ikmal Hakim Nor Nor, Muhammad Ikmal Mohd Noreddie, Hadizul Alif Hakimi College of Computing Informatics and Mathematics Universiti Teknologi Mara Cawangan Perak Kampus Tapah Tapah Road Perak35400 Malaysia College of Computing Informatics and Mathematics Universiti Teknologi Mara Cawangan Pahang Kampus Jengka Pahang Bandar Jengka26400 Malaysia College of Computing Informatics and Mathematics Universiti Teknologi Mara Cawangan Negeri Sembilan Kampus Seremban Negeri Sembilan Seremban70300 Malaysia

ISBN: (纸本)9798331528553

The success of a company greatly depends on the supplier's selection. Similar to traditional approaches, the process of supplier selection relies on human assessment, which is inherently subjective and vague. The fuzzy TOPSIS has been successfully applied in many multi-criteria decision-making processes in uncertain environments, including the selection of suppliers. The majority of fuzzy TOPSIS methods take into account the ratings of alternatives for each primary criterion. However, there is still a shortage of studies that utilise ratings based on sub-criteria. This paper aims to determine the optimal criteria for selecting a supplier in the Information Technology (IT) business, with the ratings assigned according to sub-criteria related to benefits and costs. Furthermore, the study aims to determine the finest supplier meeting the established criteria within the IT industry. There are two phases involved, where the first phase consists of converting the benefit and cost sub-criteria into the main criteria using the normalisation and averaging method, and the second phase involves the Closeness Coefficient (CC), Fuzzy Positive Ideal Solution (FPIS), Fuzzy Negative Ideal Solution (FNIS) and the ranking using the centroid method. The outcomes indicated that among the four accessible suppliers, Supplier 1 (S1) is the best option, followed by Supplier 2 (S2), Supplier 4 (S4) and Supplier 3 (S3). The study also determines the criteria that need to be prioritised, which are product performance and service performance. Fuzzy TOPSIS, which has ratings based on benefit and cost sub-criteria, has the potential to automate the procedure and address vagueness or uncertainty during the selection process. © 2024 IEEE.

关键词： Costs

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：