检索结果-内蒙古大学图书馆

An Efficient Security Solution for Industrial Internet of Things Applications

Computers, Materials & Continua 2022年第8期72卷 3961-3983页

作者： Alaa Omran Almagrabi Department of Information Systems Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddahKingdom of Saudi Arabia

The Industrial Internet of Things(IIoT)has been growing for presentations in industry in recent *** for the IIoT has unavoidably become a problem in terms of creating safe *** to continual needs for new functionality,such as foresight,the number of linked devices in the industrial environment *** of fewer signatories gives strong authentication solutions and prevents trustworthy third parties from being publicly certified among available encryption *** this blockchain-based endpoint protection platform(BCEPP)has been proposed to validate the network policies and reduce overall latency in isolation or hold endpoints.A resolver supports the encoded model as an input;network functions can be optimized as an output in an infrastructure *** configuration of the virtual network functions(VNFs)involved fulfills network *** output ensures that the final service is supplied at the least cost,including processing time and network *** to the findings of this comparison,our design is better suited to simplified trust management in IIoT ***,the experimental results show the adaptability and resilience of our suggested confidence model against behavioral changes in hostile settings in IIoT *** experimental results show that our proposed method,BCEPP,has the following,when compared to other methods:high computational cost of 95.3%,low latency ratio of 28.5%,increased data transmitting rate up to 94.1%,enhanced security rate of 98.6%,packet reception ratio of 96.1%,user satisfaction index of 94.5%,and probability ratio of 33.8%.

关键词： Industrial internet of things(IIoT) blockchain trusted third parties endpoint verification

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Analysis of Scientific Paper Abstracts: Exploring Clustering Algorithms 3

Unsupervised Analysis of Scientific Paper Abstracts: Explori...

引用

3rd International Conference on Digital Transformation and Applications, ICDXA 2024

作者： Ong, Ming Zheng Tan, Natalie Jie Yin Lim, Siew Mooi Ee, Jia Hui Tunku Abdul Rahman University of Management and Technology Faculty of Computing and Information Technology Kuala Lumpur Malaysia

ISBN: (纸本)9798350373424

The number of scientific publications published online has increased significantly in tandem with the rise of the Internet. The quantity of online articles has significantly expanded in recent years. As the quantity of scientific papers continues to grow exponentially, researchers are having challenges organising and generating relevant insights from the vast amount of information accessible. Unsupervised clustering techniques are applied in this research to categorise scientific papers based on the abstract. Centroid Based Clustering, Spectral Clustering, Distribution Based Clustering (DBSCAN), Grid Based Clustering, and hybrid LDA-BERT KMeans Clustering are the clustering algorithms explored in this study. Results showed that Centroid-Based Clustering resulted in 15 clusters with a silhouette score of 0.0038, Spectral Clustering produced 10 clusters with a silhouette score of 0.0046, DBSCAN formed a single cluster only, Grid-Based Clustering achieved 82 clusters with a silhouette score of 0.3061, and Hybrid LDA-BERT KMeans Clustering yielded 6 clusters with a silhouette score of 0.3951. Possible reasons that the algorithms are less effective compared to one another in this specific task are also investigated. © 2024 IEEE.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Job Resumes Recommendation using Integration of Fuzzy Discernibility Matrix Feature Selection and Convolutional Neural Network Multi-label Text Classification

Informatica (Slovenia)

引用

Informatica (Slovenia) 2025年第13期49卷 49-58页

作者： Hayami, Regiolina Yusoff, Nooraini Daud, Kauthar Mohd Fatma, Yulia Department of Informatics Engineering Faculty Computer Science Universitas Muhammadiyah Riau Indonesia Faculty of Data Science and Computing Universiti Malaysia Kelantan 16100 Malaysia Center for Artificial Intelligence Technology Faculty of Information Science and Technology Universiti Kebangsaan Malaysia 43600 Malaysia

The manual analysis of job resumes poses specific challenges, including the time-intensive process and the high likelihood of human error, emphasizing the need for automation in content-based recommendations. Recent advancements in deep learning, particularly Convolutional Neural Networks (CNN) for Multi-label Text Classification (MLTC), offer a promising solution for addressing these challenges through artificial intelligence. While CNN is renowned for its robust feature extraction capabilities, it faces specific challenges such as managing high-dimensional data and poor data interpretability. To address these limitations, this study employs the Fuzzy Discernibility Matrix (FDM) feature selection technique to determine the relevance of skills for each job vacancy. FDM assigns weights to the features of each job category and ranks their relevance based on the highest scores, which are then utilized in the MLTC CNN model. The integration of FDM and MLTC CNN serves as the foundation for generating content-based recommendations derived from key features in job resumes. This study produces a content-based job recommendation system that displays the top three job categories, accompanied by explanations of the skills supporting each selected category. These recommendations also consider cosine similarity values between analyzed items and the integrated results of FDM and MLTC CNN. The application of FDM for feature weighting has been proven to enhance multi-label text classification outcomes by providing better insights during the feature selection process. With a recall of 97.26%, precision of 94.81%, and accuracy of 98.58%, the MLTC model integrating FDM feature selection and CNN demonstrates robust performance characteristics in content-based job recommendation tasks. © 2025 Slovene Society Informatika. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Two-Factor Authentication Scheme Based on the Usage of Schnorr Signcryption Algorithm

Informatica (Slovenia)

引用

Informatica (Slovenia) 2023年第5期47卷 159-172页

作者： Bazar, Hussein Al Abdel-Wahab, Ahmed Alshar’e, Marwan Abualkishik, Abdallah Riyadh Saudi Arabia Faculty of Engineering Al-Azhar University Cairo Egypt Faculty of Computing and Information Technology Sohar University Sohar Oman

With the current continuous increase in the usage of communication technologies and data transmission amount, the available web services and mobile applications are used to access and complete several online activities such as online education, e-commerce, and online financial transactions. The needs for a strong and secure access control authentication solution for users’ data and the available online resources are crucial. Authentication can play a major role in protection by implementing a solution, which allows users to prove their identities and provide access permission to all legitimate users only. This paper proposes two-factor authentication scheme based on the usage of a modified copy of the Schnorr Signcryption algorithm. The proposed scheme achieves the target goal of this paper, which provides the users with an efficient solution that can be implemented in any authentication solution as the second factor, with no special requirement and can be used to authenticate the users and control recourses access permission. Moreover, a Java-based application is developed to examine the proposed scheme in a client-server architecture where it is found that the solution can successfully authenticate authorized users and reject any unauthorized access request with an adequate security protection level and acceptable performance. © 2023 Slovene Society Informatika. All rights reserved.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Identification of Skin Conditions with Convolutional Neural Networks: A Deep Learning Approach 3

Identification of Skin Conditions with Convolutional Neural ...

引用

3rd International Conference on Digital Transformation and Applications, ICDXA 2024

作者： Leong, Jing En Goh, Ching Pang Tunku Abdul Rahman University of Management and Technology Faculty of Computing and Information Technology Kuala Lumpur Malaysia

ISBN: (纸本)9798350373424

This paper presents a robust approach for detecting skin diseases using advanced image detection methods supported by Convolutional Neural Network (CNN) models. Traditionally, skin diseases are diagnosed by experienced dermatologists. However, due to a scarcity of these specialists, there is a pressing need for alternative, reliable solutions. Our methodology capitalizes on image detection techniques to accurately and efficiently identify potential skin diseases from photographs. The cornerstone of our approach is the CNN model, which is renowned for its efficacy in processing visual data. The system we developed demonstrates a high level of accuracy, achieving a validation accuracy of at least 80 % in the identification of specific skin diseases. This level of precision is particularly noteworthy, considering the inherent challenges in diagnosing skin conditions through images. Despite this success, our research also acknowledges the difficulties in gathering a vast, diverse dataset of skin disease images from the internet. Such datasets are crucial for training and refining our model to ensure its effectiveness across various skin types and conditions. Furthermore, this paper investigates the factors that might lead to inaccuracies in predictions. It addresses common issues such as variations in image quality, lighting conditions, and the presence of similar-looking skin conditions, which can all potentially confound the model's decision-making process. By understanding and mitigating these factors, we aim to enhance the model's reliability and accuracy, moving closer to bridging the gap between automated detection and expert human diagnosis. This research not only contributes to the field of medical image analysis but also offers a promising tool for assisting dermatologists and improving patient outcomes in skin disease diagnosis. © 2024 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Sign Language to Text Translation with Computer Vision: Bridging the Communication Gap 3

Sign Language to Text Translation with Computer Vision: Brid...

引用

3rd International Conference on Digital Transformation and Applications, ICDXA 2024

作者： Thong, So Xue Tan, Eng Lip Goh, Ching Pang Turku Abdul Rahman University of Management and Technology Faculty of Computing and Information Technology Kuala Lumpur Malaysia

ISBN: (纸本)9798350373424

This research paper addresses the communication barriers faced by individuals using sign language and those without hearing difficulties. With limited adoption of sign language and a scarcity of proficient human translators, there is a need for innovative solutions. This research presents a real-time sign language translation system using computer vision technology. The system utilizes Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks for static and dynamic sign recognition, respectively. Word segmentation which utilized 'word-ninja' and a Large Language Model (LLM) contributed to accurate sentence generation. The proposed system integrates machine translation and text-to-speech functionalities to improve the system's accessibility. The methodology involves data collection, landmark recognition, and the implementation of recognition and translation models. The results show impressive accuracy which are 99.20% and 90.08% for static and dynamic sign recognition respectively. However, issues such as environmental conditions have affected the detection accuracy and made errors in recognising similar signs. Sentence generation also provided a pretty decent result which is 90% of the accuracy from the output provided by the LLM model. Despite these challenges, the system still contributes to reducing communication barriers and promoting inclusivity in society. © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

From Complexity to Clarity: Tatabahasa-Centric Lemmatization in Malay Texts 3

From Complexity to Clarity: Tatabahasa-Centric Lemmatization...

引用

3rd International Conference on Digital Transformation and Applications, ICDXA 2024

作者： Tan, Xin Yi Tan, Chi Wee Tunku Abdul Rahman University of Management and Technology Faculty of Computing and Information Technology Kuala Lumpur Malaysia

ISBN: (纸本)9798350373424

This paper explores the pivotal role of lemmatization tools in Natural Language Processing (NLP) and their significance in enhancing language understanding and text analysis. Through a comprehensive evaluation of various lemmatization techniques, both established and emerging, we aim to improve the precision of NLP applications. Our assessment encompasses diverse linguistic datasets, revealing insights into the strengths and limitations of each approach and guiding the selection of appropriate tools. What differentiates this study is its focus on the substantial advancement accomplished by the rule-based model, which exhibits an impressive 88% precision and outperforms the Sastrawi model by around 3%. Moreover, we introduce innovative strategies to enhance lemmatization outcomes, specifically addressing challenges in multilingual and low-resource language contexts. © 2024 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Usability Study of Augmented Reality Training Application for Can Manufacturing Company 3

Usability Study of Augmented Reality Training Application fo...

引用

3rd International Conference on Digital Transformation and Applications, ICDXA 2024

作者： Tan, Bee Sian Chong, Tik Joe Chew, Ying Ying Tunku Abdul Rahman University of Management and Technology Faculty of Computing and Information Technology Kuala Lumpur Malaysia

ISBN: (纸本)9798350373424

This paper presents a usability study that focuses on the usability of an Augmented Reality (AR) factory manufacturing training application. This study recruited two distinct participants groups - AR developers and factory's stakeholders. This approach aimed to gather the comprehensive insights into the application's alignment with the technical and business strategies. The usability study is conducted using system usability scale (SUS) questionnaire with 12 participants. The results showed AR developers with score 50.4 and factory's stakeholders with score 57.1. The findings reveal the strengths and potential of this AR applications. From the visual aspects, AR developers complemented the 3D models that was clear and well designed and suggested improvement on the model's size in the process of viewing the machine in AR environment. The stakeholders suggested improvement on the 3D model's realism to increase the immersiveness of learning experience. In the interaction aspects, stakeholders preferred direct interaction rather than reliance of button and slider in the process AR training. Meanwhile from the business aspects, this application increases the learner's retention in the process of training. This application offers a safe and remote environment for training. In conclusion, this study evaluates the application's alignment with both technical and business strategies and the results have provided valuable insights. © 2024 IEEE.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

Industrial revolution 4.0 in water supply, wastewater and stormwater management: opportunities, challenges, and impacts

引用

Environmental technology Reviews 2024年第1期13卷 144-168页

作者： Kuok, Kuok King Chiu, Po Chan Bakri, Muhammad Khusairy Bin Rahman, Md. Rezaur Yun, Chin Mei Faculty of Engineering Computing and Science Swinburne University of Technology Sarawak Campus Kuching Malaysia Faculty of Computer Science and Information Technology Universiti Malaysia Sarawak Kota Samarahan Malaysia Faculty of Engineering Universiti Malaysia Sarawak Kota Samarahan Malaysia

Industrial Revolution 4.0 (IR 4.0) is the revolution that promotes customized and flexible mass production technologies in automation and manufacturing processes. The application of industrial revolution 4.0, such as the Internet of Things (IoT), Cyber-Physical System (CPS), and big data, are used in the water industry to provide better water quality, accurate real-time data, etc. This paper compiles IR 4.0 technology applications, advantages, disadvantages, impacts, and challenges in the water sector, including water supply, wastewater treatment, and stormwater management. It is found that the current water industry is facing a few challenges, such as managing water services, balancing water costs with energy prices, maintaining aging water and wastewater infrastructure, and environmental issues. However, with the application of numerous IR 4.0 innovations, all the challenges can be solved or minimized. Meanwhile, the advantages and impacts of adopting IR 4.0 in water industries are thoroughly discussed. Despite the numerous advantages of IR 4.0, significant drawbacks have restricted the adoption of IR 4.0 in the water industry. The high start-up cost, reluctance, uncertainty, and problems of adopting IR 4.0 are some key challenges that need to be addressed. Generally, IR 4.0 provides more benefits to the community as it helps improve the water system’s performance and efficiencies and creates a more sustainable environment. © 2023 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Water supply

来源：评论

学校读者我要写书评

暂无评论

Research on an Intelligent Evaluation System for Used Car Prices Based on Improved Machine Learning Algorithms

Journal of Network Intelligence

引用

Journal of Network Intelligence 2023年第2期8卷 461-477页

作者： Lin, Xianning Hashim, Salwa School of Information Technology Guangdong Technology College Zhaoqing526100 China Faculty of Engineering Computing and Science Swinburne University of Technology Kuching93350 Malaysia

The advent of the big data era offers great opportunities for the development of online trading platforms for used cars. However, problems such as lack of appraisal data, asymmetric appraisal information and high cost of the appraisal process can limit the use of the three traditional used car price appraisal methods. Therefore, it is important to design an accurate and reasonable used car valuation method in the current immature market. As an advanced machine learning model, the Random Forest algorithm has strong advantages in terms of prediction accuracy, missing value handling and noise tolerance. Therefore, this paper introduces the Random Forest model into the study of used car value evaluation and improves the Random Forest model. Firstly, based on the characteristic price theory, 16 indicators were selected as characteristic variables among the factors influencing the value of used cars, and divided into 7 physical variables, 6 functional variables and 3 market variables. Secondly, aiming at the problems of poor training accuracy and relatively poor voting ability, an Inertia Bacterial Foraging Optimization Random Forest algorithm (IBFO-RF) is proposed. A multiplicative weight is set for all decision trees to match their training accuracy, and then the basic parameters of the Random Forest algorithm are optimally selected iteratively using inertia weighted bacterial foraging optimization to improve the output correctness. Finally, the data is imported into the random forest model, and according to the average decreasing degree of mean square error, an intelligent evaluation system for evaluating the value of used cars is established. It was validated against other algorithms on four datasets in the UCI dataset. The experimental results show that the validation of the proposed IBFO-RF algorithm can effectively improve the accuracy of the final classification and has significant advantages in handling the classification problem. The proposed intelligent used ca

关键词： Mean square error

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：