检索结果-内蒙古大学图书馆

5th International Conference on Advanced information Technologies, ICAIT 2024

作者： Thar, Kaung Wai Wai, Thinn Thinn University of Information Technology Faculty of Computer Science Yangon Myanmar

ISBN: (纸本)9798331510046

Financial fraud has become a significant threat to companies and organizations in recent years. The extent of bank fraud is difficult to ascertain because much of it remains undisclosed or undetected. Despite numerous measures to prevent financial fraud, it continues to negatively affect individuals and businesses, with losses from fraud on the rise. Today, most financial transactions are conducted virtually worldwide, and online fraud incurs multi-billion-dollar losses for the global economy annually. Consequently, fraud detection has become one among the most formidable real-life problems. Imbalanced datasets are part of the main difficulties in fraud detection. Additionally, the constantly changing nature of fraudulent behavior complicates the instructional process for state-of-the-art binary classifiers in machine learning. In this work, an extensive predictive analytics framework is introduced for identifying fraud cases and addressing the issue of Imbalanced datasets in training fraud detection models. This framework is constructed through the experimentation with a combination of sampling algorithms with Hidden Markov Model, feature engineering techniques. The proposed framework offers a data-centric method utilized for financial credit card analysis of Imbalanced data with real time transactions and is adaptable to other fields in all financial transaction types of large datasets. © 2024 IEEE.

关键词： Predictive analytics

来源：评论

学校读者我要写书评

暂无评论

Multisource Data Fusion Using MLP for Human Activity Recognition

引用

computers, Materials & Continua 2025年第2期82卷 2109-2136页

作者： Sujittra Sarakon Wansuree Massagram Kreangsak Tamee Department of Computer Science and Information Technology Faculty of ScienceNaresuan UniversityPhitsanulok65000Thailand Center of Excellence for Innovation and Technology for Detection and Advanced Materials(ITDAM) Faculty of ScienceNaresuan UniversityPhitsanulok65000Thailand Center of Excellence in Nonlinear Analysis and Optimizations Faculty of ScienceNaresuan UniversityPhitsanulok65000Thailand

This research investigates the application of multisource data fusion using a Multi-Layer Perceptron (MLP) for Human Activity Recognition (HAR). The study integrates four distinct open-source datasets—WISDM, DaLiAc, MotionSense, and PAMAP2—to develop a generalized MLP model for classifying six human activities. Performance analysis of the fused model for each dataset reveals accuracy rates of 95.83 for WISDM, 97 for DaLiAc, 94.65 for MotionSense, and 98.54 for PAMAP2. A comparative evaluation was conducted between the fused MLP model and the individual dataset models, with the latter tested on separate validation sets. The results indicate that the MLP model, trained on the fused dataset, exhibits superior performance relative to the models trained on individual datasets. This finding suggests that multisource data fusion significantly enhances the generalization and accuracy of HAR systems. The improved performance underscores the potential of integrating diverse data sources to create more robust and comprehensive models for activity recognition.

关键词： Multisource data fusion human activity recognition multi-layer perceptron(MLP) artificial intelligent

来源：评论

学校读者我要写书评

暂无评论

Towards robust and efficient intrusion detection in IoMT: a deep learning approach addressing data leakage and enhancing model generalizability

引用

Multimedia Tools and Applications 2024年 1-20页

作者： Bouke, Mohamed Aly El Atigh, Hayate Abdullah, Azizol Department of Communication Technology and Network Faculty of Computer Science and Information Technology Universiti Putra Malaysia Serdang43400 Malaysia Departement of Computer Engineering Faculty of Computer Engineering Bandirma Onyedi Eylul University Balikesir10200 Turkey

The Internet of Medical Things (IoMT) brings advanced patient monitoring and predictive analytics to healthcare but also raises cybersecurity and data privacy issues. This paper introduces a deep-learning model for IoMT intrusion detection, utilizing the WUSTL EHMS 2020 dataset, which focuses on cyber threats like man-in-the-middle attacks and data injection. Our sequential model, trained with TensorFlow, surpasses traditional predictive accuracy and efficiency methods. It achieves 99% accuracy with reduced loss and excels in precision, recall, F1 Score, and ROC AUC. The model uses 25 key features from 45, preventing overfitting and addressing data leakage in preprocessing. These steps ensure the model's reliability for IoMT cybersecurity, demonstrating its effectiveness in real-world scenarios. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Wireless Sensor Security Issues on Data Link Layer:A Survey

引用

computers, Materials & Continua 2023年第5期75卷 4065-4084页

作者： Muhammad Zulkifl Hasan Zurina Mohd Hanapi Muhammad Zunnurain Hussain Department of Communication Technology and Network Faculty of Computer Science and Information TechnologyUniversiti Putra MalaysiaSerdangSelangor43400Malaysia

A computer network can be defined as many computing devices connected via a communication medium like the *** network development has proposed how humans and devices communicate *** networks have improved,facilitated,and made conventional forms of communication ***,it has also led to uptick in-network threats and *** 2022,the global market for information technology is expected to reach$170.4 ***,in contrast,95%of cyber security threats globally are caused by human *** networks may be utilized in several control systems,such as home-automation,chemical and physical assault detection,intrusion detection,and environmental *** proposed literature review presents a wide range of information on Wireless Social Networks(WSNs)and Internet of Things(IoT)*** aim is first to be aware of the existing issues(issues with traditional methods)and network attacks on WSN and IoT systems and how to defend *** second is to review the novel work in the domain and find its *** goal is to identify the area’s primary gray field or current research divide to enable others to address the ***,we concluded that *** Rapid Spanning Tree Protocol(RSTP)messages have higher efficiency in network performance degradation than alternative Bridge Data Unit Protocol(BPDU)*** research divides our future research into solutions and newly developed techniques that can assist in completing the lacking *** this research,we have selected articles from 2015 to 2021 to provide users with a comprehensive literature overview.

关键词： Wireless sensor networks(WSN) internet of things(IoT) industrial revolution 4.0(IR4.0) computer networks network security

来源：评论

学校读者我要写书评

暂无评论

Shear Let Transform Residual Learning Approach for Single-Image Super-Resolution

引用

computers, Materials & Continua 2024年第5期79卷 3193-3209页

作者： Israa Ismail Ghada Eltaweel Mohamed Meselhy Eltoukhy Department of Computer Science Faculty of Computers and InformaticsSuez Canal UniversityIsmailia51422Egypt Department of Information Technology College of Computing and Information Technology at KhulaisUniversity of JeddahJeddahSaudi Arabia

Super-resolution techniques are employed to enhance image resolution by reconstructing high-resolution images from one or more low-resolution ***-resolution is of paramount importance in the context of remote sensing,satellite,aerial,security and surveillance ***-resolution remote sensing imagery is essential for surveillance and security purposes,enabling authorities to monitor remote or sensitive areas with greater *** study introduces a single-image super-resolution approach for remote sensing images,utilizing deep shearlet residual learning in the shearlet transform domain,and incorporating the Enhanced Deep Super-Resolution network(EDSR).Unlike conventional approaches that estimate residuals between high and low-resolution images,the proposed approach calculates the shearlet coefficients for the desired high-resolution image using the provided low-resolution image instead of estimating a residual image between the high-and low-resolution *** shearlet transform is chosen for its excellent sparse approximation ***,remote sensing images are transformed into the shearlet domain,which divides the input image into low and high *** shearlet coefficients are fed into the EDSR *** high-resolution image is subsequently reconstructed using the inverse shearlet *** incorporation of the EDSR network enhances training stability,leading to improved generated *** experimental results from the Deep Shearlet Residual Learning approach demonstrate its superior performance in remote sensing image recovery,effectively restoring both global topology and local edge detail information,thereby enhancing image *** to other networks,our proposed approach outperforms the state-of-the-art in terms of image quality,achieving an average peak signal-to-noise ratio of 35 and a structural similarity index measure of approximately 0.9.

关键词： Super-resolution shearlet transform shearlet coefficients enhanced deep super-resolution network

来源：评论

学校读者我要写书评

暂无评论

Energy and QoS-aware virtual machine placement approach for IaaS cloud datacenter

引用

Neural Computing and Applications 2025年第4期37卷 2211-2237页

作者： Elsedimy, E.I. Herajy, Mostafa Abohashish, Sara M. M. Department of Information Technology Management Faculty of Management Technology and Information Systems Port Said University Port Said Egypt Department of Mathematics and Computer Science Faculty of Science Port Said University Port Said Egypt Cyber Secuirty Department Faculty of Science Al-Esraa University College Baghdad Iraq

Virtualization technology enables cloud providers to abstract, hide, and manage the underlying physical resources of cloud data centers in a flexible and scalable manner. It allows placing multiple independent virtual machines (VMs) on a single server in order to improve resource utilization and energy efficiency. However, determining the optimal VM placement is crucial as it directly impacts load balancing, energy consumption, and performance degradation within the data center. Furthermore, deciding on VM placement based on a single factor is usually insufficient to improve data center performance because many factors must be considered, and ignoring them may be too expensive. This paper improves a new multi-objective VM placement (MVMP) algorithm using a quantum particle swarm optimization (QPSO) technique. We call it QPSO-MOVMP, and its objective is to find the Pareto optimal solution for the VM placement problem by balancing different goals. This algorithm generates Pareto optimal solutions that save power by minimizing the number of running physical machines, avoid performance degradation by maintaining service level agreement (SLA), and improve load balancing by keeping server loads at optimal utilization. The experimental results show that QPSO-MOVMP had superior performance in terms of power consumption and performance degradation compared to three other multi-objective algorithms and three conventional single-objective algorithms. Simulation results show that the proposed QPSO-MOVMP achieves a consumption of 2.4 × 104 watts in power. Furthermore, it outperformed the others, achieving a minimum of 12% SLA breaches while experiencing a significant surge in requests from VMs. Moreover, the proposed model generated Pareto solutions that had a better distribution than those derived from a comparative method. © The Author(s) 2025.

关键词： Particle swarm optimization (PSO)

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

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

Fusion of Hash-Based Hard and Soft Biometrics for Enhancing Face Image Database Search and Retrieval

引用

computers, Materials & Continua 2023年第12期77卷 3489-3509页

作者： Ameerah Abdullah Alshahrani Emad Sami Jaha Nahed Alowidi Department of Computer Science Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia

The utilization of digital picture search and retrieval has grown substantially in numerous fields for different purposes during the last decade,owing to the continuing advances in image processing and computer vision *** multiple real-life applications,for example,social media,content-based face picture retrieval is a well-invested technique for large-scale databases,where there is a significant necessity for reliable retrieval capabilities enabling quick search in a vast number of *** widely employ faces for recognizing and identifying ***,face recognition through formal or personal pictures is increasingly used in various real-life applications,such as helping crime investigators retrieve matching images from face image databases to identify victims and ***,such face image retrieval becomes more challenging in large-scale databases,where traditional vision-based face analysis requires ample additional storage space than the raw face images already occupied to store extracted lengthy feature vectors and takes much longer to process and match thousands of face *** work mainly contributes to enhancing face image retrieval performance in large-scale databases using hash codes inferred by locality-sensitive hashing(LSH)for facial hard and soft biometrics as(Hard BioHash)and(Soft BioHash),respectively,to be used as a search input for retrieving the top-k matching ***,we propose the multi-biometric score-level fusion of both face hard and soft BioHashes(Hard-Soft BioHash Fusion)for further augmented face image *** experimental outcomes applied on the Labeled Faces in the Wild(LFW)dataset and the related attributes dataset(LFW-attributes),demonstrate that the retrieval performance of the suggested fusion approach(Hard-Soft BioHash Fusion)significantly improved the retrieval performance compared to solely using Hard BioHash or Soft BioHash in isolation,where the suggested method provides an augmented

关键词： Face image retrieval soft biometrics similar pictures hashing database search large databases score-level fusion multimodal fusion

来源：评论

学校读者我要写书评

暂无评论

Advancing Smart Sensor Networks and Carbon-Based Biosensors through Artificial Intelligence: A Deep Learning Approach to Optoelectronic Device Innovation

引用

IEEE Access 2025年 13卷 86083-86109页

作者： Luo, Keliang Putra University of Malaysia Software Engineering Faculty of Computer Science and Information Technology Kuala Lumpur43400 Malaysia

This research proposes a novel artificial decision-marking framework suitable for modern smart sensor networks and carbon-based biosensor systems which deals with uncertainty and the peculiarity of the data. To achieve the goals, the approach relies on the optoelectronic properties of carbon nanomaterials and already combines AI and deep learning. This raises the level of sensing, real-time data fusion, and adaptive decision-making within the environment to unprecedented levels. To enhance sensor evaluation in sensor manufacturing, we take a step further and implement Dombi Interval Valued Intuitionistic Fuzzy Sets (D-IVIFs) and work with Dombi Interval Valued Intuitionistic Fuzzy Dombi Bonferroni Mean (D-IVIFDBM) for hierarchical decision-making. Moreover, two Multi-Attribute Group Decision Making (MAGDM) methods IVIFWDBM and IVIFWDGBM are developed for expert evaluation aggregation in selection tasks of different criteria to enhance selection accuracy. These experiments did demonstrate improvements in decision accuracy as well as better overall performance than conventional models of comparison. The numerical experiments showed that these methods are more effective than traditional MAGDM models. Introducing such an advanced decision framework in deep learning systems enables improved adaptability, security, and resilience in next-generation sensor networks and biosensor devices. The new paradigm enables real-time signal interpretation and adaptive learning and provides effective solutions in harsh environments where severe fluctuations are common. This study assists in addressing the discrepancy between conceptual decision models and actual physical achievements in smart sensing, which will foster the development of more sophisticated and efficient optoelectronic devices. © 2013 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Terrorism Attack Classification Using Machine Learning: The Effectiveness of Using Textual Features Extracted from GTD Dataset

引用

computer Modeling in Engineering & sciences 2024年第2期138卷 1427-1467页

作者： Mohammed Abdalsalam Chunlin Li Abdelghani Dahou Natalia Kryvinska School of Computer Science and Technology Wuhan University of TechnologyWuhan430070China LDDI Laboratory Faculty of Science and TechnologyUniversity of Ahmed DRAIAAdrar01000Algeria Information Systems Department Faculty of ManagementComenius UniversityBratislava82005Slovakia

One of the biggest dangers to society today is terrorism, where attacks have become one of the most significantrisks to international peace and national security. Big data, information analysis, and artificial intelligence (AI) havebecome the basis for making strategic decisions in many sensitive areas, such as fraud detection, risk management,medical diagnosis, and counter-terrorism. However, there is still a need to assess how terrorist attacks are related,initiated, and detected. For this purpose, we propose a novel framework for classifying and predicting terroristattacks. The proposed framework posits that neglected text attributes included in the Global Terrorism Database(GTD) can influence the accuracy of the model’s classification of terrorist attacks, where each part of the datacan provide vital information to enrich the ability of classifier learning. Each data point in a multiclass taxonomyhas one or more tags attached to it, referred as “related tags.” We applied machine learning classifiers to classifyterrorist attack incidents obtained from the GTD. A transformer-based technique called DistilBERT extracts andlearns contextual features from text attributes to acquiremore information from text data. The extracted contextualfeatures are combined with the “key features” of the dataset and used to perform the final classification. Thestudy explored different experimental setups with various classifiers to evaluate the model’s performance. Theexperimental results show that the proposed framework outperforms the latest techniques for classifying terroristattacks with an accuracy of 98.7% using a combined feature set and extreme gradient boosting classifier.

关键词： Artificial intelligence machine learning natural language processing data analytic DistilBERT feature extraction terrorism classification GTD dataset

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：