检索结果-内蒙古大学图书馆

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

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

ClipArtGAN: An Application of Pix2Pix Generative Adversarial Network for Clip Art Generation

引用

Multimedia Tools and Applications 2025年 1-25页

作者： Elnabawy, Reham H. Abdennadher, Slim Hellwich, Olaf Eldawlatly, Seif Technische Universität Berlin Berlin Germany Computer Science and Engineering Department Faculty of Media Engineering and Technology German University in Cairo Cairo Egypt Computer Science Department Faculty of Informatics and Computer Science German International University New Administrative Capital Egypt Computer and Systems Engineering Department Faculty of Engineering Ain Shams University 1 El-sarayat st. Abbassia Cairo Egypt Computer Science and Engineering Department The American University in Cairo Cairo Egypt School of Information Technology New Giza University Giza Egypt

An image can convey a thousand words. This statement emphasizes the importance of illustrating ideas visually rather than writing them down. Although detailed image representation is typically instructive, there are several contexts where simplification of image representations may be more informative. One way to provide an abstract representation of an object is via clip art, which is a simple graphic illustration of an object that can be included in documents or presentations. Clip art representation can be utilized in graphic design for concepts expression and daily life objects illustration. Furthermore, clip art had shown remarkable advantages when compared to real images in terms of editing and manipulation since clip art geometry can be easily edited in addition to the feasibility of storing it in a resolution-independent manner. However, it can be difficult to automatically create clip arts that resemble any object. Here, we propose a novel deep learning model, named ClipArtGAN, that utilizes Generative Adversarial Networks (GANs) to convert a photo of an object to its corresponding clip art. To our knowledge, this is the first GAN model based on Pix2Pix architecture that is capable of automatically generating clip art for any arbitrary object. Three training datasets were collected to train and compare two GAN models based on Pix2Pix and CycleGAN architectures. Our results demonstrate that the mean accuracy obtained using ClipArtGAN utilizing Pix2Pix outperforms that of CycleGAN by 58% and that of Google Images-based search by 54%. These results indicate the efficacy of ClipArtGAN in generating representative clip art images. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Fog Computing-based Real-Time Emotion Recognition using Physiological Signals 27

Fog Computing-based Real-Time Emotion Recognition using Phys...

引用

27th International Conference on Advanced Communications Technology, ICACT 2025

作者： Erzurumluoglu, Omur Fatmanur Ozlem, Kadir Atalay, Asli Tuncay Atalay, Ozgur Ince, Gokhan Faculty of Computer and Informatics Engineering Istanbul Technical University Istanbul Turkey Faculty of Textile Technologies and Design Istanbul Technical University Istanbul Turkey

ISBN: (纸本)9791188428137

Emotion recognition based on physiological signals has become a crucial area of research in affective computing and human-computer interaction, with applications in smart homes, workplaces, educational institutions, healthcare, and entertainment. In this study, a real-time emotion recognition system utilizing fog computing architecture was developed by considering the challenges of latency, total response time, resource usage, and security in IoT environments. The random forest machine learning model was trained with time-based statistical features by using the DREAMER dataset. Even though the model achieved an accuracy of 84.21% with 104 features, to meet real-time performance requirements, the system was optimized to calculate 24 features, maintaining a commendable accuracy of 79.70%. Extensive experiments demonstrated the superior performance of fog computing compared to edge and cloud computing in terms of latency, queuing delay, jitter, and most importantly total response time. The results highlight the proposed system's ability to support multiple users simultaneously. Copyright 2025 Global IT Research Institute (GIRI). All rights reserved.

关键词： Fog computing

来源：评论

学校读者我要写书评

暂无评论

Modified MobileNetV2 with Convolutional Block Attention Module for Facial Expression Recognition

Modified MobileNetV2 with Convolutional Block Attention Modu...

引用

2023 International Workshop on Artificial Intelligence and Image Processing, IWAIIP 2023

作者： Nafi'an, Muh. Hafidh Ilmi Bachtiar, Fitra Abdurrachman Setiawan, Budi Darma Brawijaya University Computer Science Faculty Informatics Engineering Department Malang Indonesia

ISBN: (纸本)9798350382914

Facial emotion recognition is one of the artificial intelligence implementations used to recognize emotions based on data learned by computers. Unlike humans, who can recognize a person's emotions directly, computers need several trainings procedures conducted by humans to be able to recognize a person's emotions. Previous research has proposed various methods with deep learning and traditional machine learning approaches to classify emotions based on faces. Some studies obtained relatively high accuracy, but on evaluation by cross-validation, the results were much lower than the accuracy obtained. Therefore, this study proposes an approach using a modified MobileNetV2 deep learning architecture in the residual layer by adding a Convolutional Block Attention Module (CBAM) to improve accuracy and data generalization. This experiment uses the Karolinska Directional Emotional Faces (KDEF) public benchmark dataset. Preprocessing is done with image augmentation to enrich the training data by resizing, center cropping, random horizontal flipping, random affine, and random rotation. The proposed method is evaluated by 5-fold cross-validation and compared with MobileNetV2 without modification and state-of-the-art methods. Experimental results show that the proposed model outperform all comparative methods by achieving a 5 -fold cross-validation accuracy of 94.387%. © 2023 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Cross-Layer Distributed Attack Detection Model for the IoT

引用

International Journal of Ambient Computing and Intelligence 2022年第1期13卷 1-17页

作者： Ahmed, Hassan I. Nasr, Abdurrahman A. Abdel-Mageid, Salah M. Aslan, Heba K. Informatics Department Electronics Research Institute Cairo Egypt Computer Engineering Faculty of Engineering Al-Azhar University Cairo Egypt Computer Engineering Department College of Computer Science and Engineering Taibah University Saudi Arabia Center of Informatics Science Faculty of Information Technology and Computer Science Nile University Egypt

The security of IoT that is based on layered approaches has shortcomings such as the redundancy, inflexibility, and inefficiently of security solutions. There are many harmful attacks in IoT networks such as DoS and DDoS attacks, which can compromise the IoT architecture in all layers. Consequently, cross layer approach is proposed as an effective and practical security defending mechanism. Cross-layer distributed attack detection model (CLDAD) is proposed to enhance security solutions for IoT environments. CLDAD presents a general detection method of DDoS in sensing layer, network layer, and application layer. CLDAD is based on big data analytics techniques, which enable the detection process to be performed in a distributed way, so the model can detect DDoS attacks in any layer on-the-fly and the model support the scalability of the IoT environment. CLDAD is tested based on three datasets, namely artificial jamming attack dataset, BoT-IoT dataset, and BoT-IoT-based HTTP. The results showed that the proposed model is efficient in detecting attacks in the three layers of the IoT. Copyright © 2022, IGI Global.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Advanced Design Pattern Selection Methodology through Weighted Semantic Ontologies for Microservices

Advanced Design Pattern Selection Methodology through Weight...

引用

2024 International Conference on computer and Applications, ICCA 2024

作者： Attia, Rabab Atef Ghoniemy, Samy Hamdy, Abeer The British University in Egypt Faculty of Informatics and Computer Science Cairo Egypt Galala University Computer Science and Engineering Program Cairo Egypt

ISBN: (纸本)9798350367560

Seamless communication between authorities, people, and smart devices is crucial in today's globally interconnected world. Unprecedented demands on software design result from the advent of ubiquitous connectivity, which allows connections at any time and from any location. By structuring applications as separate services that can communicate both internally inside a platform and externally across platforms, microservices (MS) architecture satisfies these requirements. One of the most difficult parts, though, is still controlling communication between MS services, which calls for knowledge of the best design patterns. In order to solve this, we suggest a context-aware recommender system that is adapted to MS design patterns. This system not only makes recommendations for appropriate patterns, but it also gives statistical scores that show how relevant each solution is to the particular issue at hand. Other patterns with ratings indicating their possible feasibility are also displayed by our algorithm. On the other hand, sentence transformers handle intricate, human-like problem descriptions, while our method uses MS Domain Ontologies to distinguish pattern applications, constraints, and best practices. Our methodology provides a refined examination of solution suitability and recommendations through the use of weighing and correlation algorithms. Extensively tested with more than 237 developer-style scenarios, our framework offers qualitative and quantitative insights into its performance and efficacy, showing notable gains over current solutions in terms of offering pattern-specific, contextually accurate guidance for MS communication challenges. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Enhancing Software Cost Estimation Using Feature Selection and Machine Learning Techniques

引用

computers, Materials & Continua 2024年第12期81卷 4603-4624页

作者： Fizza Mansoor Muhammad Affan Alim Muhammad Taha Jilani Muhammad Monsoor Alam Mazliham Mohd Su’ud Department of Software Engineering FAST-National University of Computer&Emerging SciencesKarachi75030Pakistan Faculty of Engineering Science and Technology IQRA UniversityKarachi72500Pakistan Department of Computer Science Bahria UnivesityKarachi74800Pakistan Faculty of Computing Riphah International UniversityIslamabad44600Pakistan Faculty of Computing and Informatics Multimedia University(MMU)Cyberjaya63100SelangorMalaysia

Software cost estimation is a crucial aspect of software project management,significantly impacting productivity and *** research investigates the impact of various feature selection techniques on software cost estimation accuracy using the CoCoMo NASA dataset,which comprises data from 93 unique software projects with 24 *** applying multiple machine learning algorithms alongside three feature selection methods,this study aims to reduce data redundancy and enhance model *** findings reveal that the principal component analysis(PCA)-based feature selection technique achieved the highest performance,underscoring the importance of optimal feature selection in improving software cost estimation *** is demonstrated that our proposed method outperforms the existing method while achieving the highest precision,accuracy,and recall rates.

关键词： Machine learning software cost estimation PCA hyper parameter feature selection

来源：评论

学校读者我要写书评

暂无评论

Shared Parking Concept in the Smart City Environment 8th

Shared Parking Concept in the Smart City Environment

引用

8th International Congress on Information and Communication Technology, ICICT 2023

作者： Špitálová, Zuzana Mandová, Lucia Opatovský, Martin Faculty of Informatics and Information Technology Institute of Computer Engineering and Applied Informatics Slovak University of Technology Bratislava Slovakia

ISBN: (纸本)9789819930906

With the modern city infrastructure and increasing number of subjects in the traffic environment, there is a need for increased number of parking places. As the parking place is usually not used for a whole day, it could be shared with the others in the certain community. As it eliminates the useless driving due to the finding of free parking place, the traffic becomes more effective and produces less emissions. We designed the application for smart city environment, which helps to achieve the described situation. It consists of two parts, the frontend and backend. The data processed by the backend part can be further used for the city infrastructure improvements. The front-end part, designed in React Native, represents the graphical interface. The back-end part, designed in PostgreSQL, represents the database. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Smart city

来源：评论

学校读者我要写书评

暂无评论

Implementing domains in Neo4j

引用

International Journal of Intelligent Information and Database Systems 2024年第3期16卷 258-285页

作者： Cerjan, Maja Rabuzin, Kornelije Šestak, Martina Faculty of Organization and Informatics Varaždin University of Zagreb Pavlinska 2 Varaždin42000 Croatia Faculty of Electrical Engineering and Computer Science Universiti of Maribor Koroška cesta 46 Maribor2000 Slovenia

Data growth has led to the need to apply new ways to process data. Graph databases are increasing their use, which can be seen over the years, with the Neo4j system being the most common. The biggest problem is the small number of implemented constraints that can be used. One of the shortcomings to be explored is the need to create domains, which are used when large amounts of data are manipulated and where the value needs to be limited or when multiple attributes have the same restrictions and data types. The creation of domains can be applied multiple times. This paper summarises the implementation of domains using Neo4j and the Java programming language. © 2024 Inderscience Enterprises Ltd.

关键词： Graph Databases

来源：评论

学校读者我要写书评

暂无评论

Developing an Anti -Phishing Large Language Model: A Focus Group Study on Human, Technological, and Legal Factors 15

Developing an Anti -Phishing Large Language Model: A Focus G...

引用

15th International Conference on Information, Intelligence, Systems and Applications, IISA 2024

作者： Thomopoulos, George A. Kiortsi, Panagiota Sigalas, Damianos Dumi Kosmopoulos, Dimitris Igglezakis, Ioannis Fidas, Christos University of Patras Department of Electrical and Computer Engineering Greece University of Thessaloniki Faculty of Law Aristotle Greece University of Patras Department of Computer Engineering and Informatics Greece

ISBN: (纸本)9798350368833

The phishing problem poses a significant threat in modern information systems, putting both individuals and businesses at risk of financial and professional harm. Owing to social media's rapid development and widespread appeal, deception of this sort is hurting millions of people and growing more dangerous. The current work, as part of the AILA (Artificial Intelligence-driven Framework and Legal Advice Tools for Phishing Prevention and Mitigation in Information Systems) project, aims to specify and validate an AI-driven multifactor (human, technology and legal) anti-phishing data model, with the implementation of focus group studies. The findings assist to provide human, technology, and legislative user model endpoints that will be identified and discussed for explicit and implicit user modeling, which will guide the development of the corresponding AI-driven user modeling and profiling mechanisms. To this end a Large Language System is planned to be employed. © 2024 IEEE.

关键词： Phishing

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：