检索结果-内蒙古大学图书馆

Enhancing malware detection performance: leveraging K-Nearest Neighbors with Firefly Optimization Algorithm

Multimedia Tools and applications 2025年第12期84卷 10071-10094页

作者： Al Saaidah, Adeeb Abualhaj, Mosleh M. Shambour, Qusai Y. Abu-Shareha, Ahmad Adel Abualigah, Laith Al-Khatib, Sumaya N. Alraba’nah, Yousef H Department of Networks and Cybersecurity Al-Ahliyya Amman University Amman Jordan Department of Software Engineering Al-Ahliyya Amman University Amman Jordan Department of Data Science and Artificial Intelligence Al-Ahliyya Amman University Amman Jordan Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman19328 Jordan Research Center University of Tabuk Tabuk71491 Saudi Arabia MEU Research Unit Middle East University Amman11831 Jordan Department of Electrical and Computer Engineering Lebanese American University Byblos13-5053 Lebanon College of Engineering Yuan Ze University Taoyuan32003 Taiwan Applied Science Research Center Applied Science Private University Amman11931 Jordan School of Engineering and Technology Sunway University Malaysia Petaling Jaya27500 Malaysia

Malware detection plays a crucial role in ensuring robust cybersecurity amidst the ever-evolving cyber threats. This research paper delves into the realm of machine learning (ML) algorithms for malware detection, with a specific emphasis on the K-Nearest Neighbors (KNN) algorithm, utilizing tailored parameter settings and the Firefly Optimization Algorithm (FOA). The study leverages the MalMem-2022 dataset to assess the efficacy of KNN and KNN with FOA in malware detection. The impact of parameter tuning and feature selection on classification is elucidated by comparing the performance of both approaches. Encouragingly, the results reveal promising advancements in one of the multiclass classification scenarios when employing KNN with FOA, yielding noteworthy enhancements in Accuracy, Recall, Precision, Matthews Correlation Coefficient, TNR, and F1-score by 2.65%, 2.65%, 2.47%, 3.59%, 0.17%, and 2.61%, respectively. These findings accentuate the significance of optimizing KNN’s parameters and implementing FOA for feature selection, culminating in heightened accuracy in malware detection. The symbiotic fusion of KNN and FOA exhibits remarkable effectiveness in augmenting the classification model’s performance, thus offering valuable insights for bolstering cybersecurity measures. Adopting ML algorithms, particularly KNN with specific parameter settings and FOA, presents a promising avenue for enhancing malware detection capabilities. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

Multi-view Transformer-Based Network for Prerequisite Learning in Concept Graphs 23rd

Multi-view Transformer-Based Network for Prerequisite Learn...

引用

23rd International Semantic Web Conference, ISWC 2024

作者： Wang, Zhichun Shao, Yifeng Peng, Boci Li, Bangui Li, Yun Wang, Qianren Li, Nijun School of Artificial Intelligence Beijing Normal University Beijing China Engineering Research Center of Intelligent Technology and Educational Application Ministry of Education Beijing China School of Intelligence Science and Technology Peking University Beijing China School of Computer Science and Engineering Beihang University Beijing China Advanced Cognitive AI Lab Shanghai Huawei Technologies Shanghai China

ISBN: (纸本)9783031778438

Prerequisite learning is the task of identifying prerequisite relations among concepts, which is important for many ai-based educational applications. Previous approaches explore different kinds of learning resources to obtain useful features for predicting prerequisites. Early approaches use handcrafted features while recent approaches use neural networks to encode information of concepts. To further improve the results of prerequisite learning, we build concept graphs to include comprehensive information about concepts from open data and learning resources, and propose a Multi-view Transformer-based Network (MTN) to encode multi-view features of concepts in the graph. Multi-view features are fused to make accurate predictions of concept prerequisites. We evaluate our approach on four public datasets and compare it with recently published approaches. The results show that our approach can achieve state-of-the-art results in the task of prerequisite learning. The source code and data are available at https://***/kg-bnu/MTN. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Breakthrough in breast tumor detection and diagnosis: a noise-resilient, rotation-invariant framework

引用

Multimedia Tools and applications 2025年 1-27页

作者： Nosheen, Fariha Khan, Salabat Sharif, Muhammad Kim, Do Hyeun Alkanhel, Reem AbdelSamee, Nagwan Department of Computer Science COMSATS University Islamabad Attock Campus Attock43600 Pakistan Department of Computer Engineering Jeju National University Jeju Special Self-Governing Province Jeju-Si63243 Korea Republic of Big Data Research Center Jeju National University Jeju63243 Korea Republic of Department of Information Technology College of Computer and Information Sciences Princess Nourahbint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia

The fact that early-stage breast cancer typically presents no signs, poses a global risk to the lives of women. Digital mammography is just one method among many that can detect breast cancer in its early stages. Despite extensive research, most methods for detecting breast cancers still produce a large number of false positives. The difficulty in improving detection accuracy is in reducing false positives by differentiating masses from normal tissues. Using the textural properties of the masses, this study aims to develop a computer-aided diagnosis system that reduces the number of false positive and negative mammography results. The suggested method initially partitions regions of interest (ROI) into small patches to extract an abnormality region and micro-pattern, which permits the extraction of specific information about the image's content in targeted areas. Reducing the computational complexity of an image analysis operation is accomplished by partitioning a ROI into smaller patches rather than processing the complete image at once. Due to the significant impact the noise has on detection accuracy in mammograms, a textural descriptor that is insensitive to noise is introduced to describe image features such as lines, spots, flat areas, and edges. By expanding the rotation-invariant and noise-tolerant descriptor histograms, we generate an improved histogram that preserves the original regional patterns and spatial relationships between masses. To distinguish between "normal" and "mass" and "benign" and "malignant", Support Vector Machines (SVM) is employed with grid search based hyperparameter optimization. Our proposed approach was evaluated using the Digital database for Screening Mammography (DDSM), which contains over 1024 ROI cases. This database is a well-established benchmark for testing new mammography analysis methods. Each case in the DDSM database has been analyzed and interpreted by qualified radiologists, with comprehensive information provided thr

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Enhancing Breast Cancer Diagnosis with Vision Transformers: A Novel Approach using MaskGuided Attention for Ultrasound Image Classification

Enhancing Breast Cancer Diagnosis with Vision Transformers: ...

引用

Pervasive Computational Technologies (ICPCT), International Conference on

作者： Deena Sivakumar Anamika Kumari Divya Dharshini K Samiksha S Hemachandran M Department of Computer Science and Engineering Sri Ramachandra Institute of Higher Education and Research Chennai Department of Computer Science (AI & Data Analytics) Sri Ramachandra Institute of Higher Education and Research Chennai

ISBN: (数字)9798331508685

ISBN: (纸本)9798331519476

Deep learning models, notably convolutional neural networks (CNNs), demonstrate great promise in medical image processing. Nonetheless, CNNs frequently encounter challenges in capture holistic context and long- range dependencies in high-resolution images, which are crucial for accurate medical diagnostics. A new state-of-the-art technique called Vision Transformers (ViTs) uses self-attention mechanisms for gathering global correlations between image patches, thereby addressing some of the inherent limitations of CNNs. This study investigates the application of ViTs for diagnosing breast cancer from ultrasound images of tumor. The findings suggest that ViTs not only achieve competitive accuracy in identifying breast cancer lesions but also offer superior interpretability through attention mechanism, which can aid clinicians in understanding model decisions. This paper highlights the potential of ViTs as a powerful tool in medical imaging, particularly for breast cancer diagnosis, and outlines future research directions for enhancing clinical applicability.

关键词： Deep learning computer vision Accuracy Attention mechanisms Ultrasonic imaging Transformers Breast cancer Convolutional neural networks Medical diagnosis Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

A Vertical Federated Multiview Fuzzy Clustering Method for Incomplete data

引用

IEEE Transactions on Fuzzy Systems 2025年第5期33卷 1510-1524页

作者： Li, Yan Hu, Xingchen Yu, Shengju Ding, Weiping Pedrycz, Witold Kiat, Yeo Chai Liu, Zhong National University of Defense Technology Laboratory for Big Data and Decision Changsha410073 China National University of Defense Technology School of Computer Changsha410073 China Nantong University School of Artificial Intelligence and Computer Science Nantong226019 China Gliwice44-100 Poland University of Alberta Department of Electrical and Computer Engineering EdmontonABT6G 2R3 Canada Istinye University Research Center of Performance and Productivity Analysis Istanbul34010 Turkey Nanyang Technological University College of Computing and Data Science 639798 Singapore

Multiview fuzzy clustering (MVFC) has gained widespread adoption owing to its inherent flexibility in handling ambiguous data. The proliferation of privatization devices has driven the emergence of new challenge in MVFC research works. Federated learning, a technique that can jointly train without directly using raw data, has gain significant attention in decentralized MVFC. However, their applicability depends on the assumptions of data integrity and independence between different views. In fact, while within distributed environments, data typically exhibits two challenging problems: 1) multiple views within a single client;2) incomplete data. Existing methods exhibit limitations in effectively addressing these challenges. Hence, in this study, we aim at achieving the effective clustering for incomplete data by a novel vertical federated MVFC framework. Specifically, a unified clustering framework is designed to capture both local client learning and global server training. For the local client learning, the data reconstruction strategy and prototype alignment strategy are introduced to ensure the preservation of data structure and refinement of clustering relationships, which mitigates the impact of incomplete data. Meanwhile, the global training process implements aggregation based on client-specific information. The whole process is realized based on the unified fuzzy clustering framework, promoting collaborative learning between client-specific and server information. Theoretical analyses and extensive experiments are carefully conducted to validate the effectiveness and efficiency of the proposed method from multiple perspectives. © 1993-2012 IEEE.

关键词： data integrity

来源：评论

学校读者我要写书评

暂无评论

A Trace-Selection Preprocessing Approach of Discovering Structurally Complete ICN-Process Models from Process Logs 3rd

A Trace-Selection Preprocessing Approach of Discovering Str...

引用

3rd International Conference on Advances in Information and Communication Technology, ICTA 2024

作者： Pham, Dinh-Lam Batzaya, Tsagaantsooj Kim, Kyoung-Sook Chang, Jeong-Hyun Kim, Kwanghoon Pio CCSRI Kyonggi University Gyeonggi Suwon16227 Korea Republic of Department of Public Safety Bigdata Graduate School of Kyonggi University Gyeonggi Suwon16227 Korea Republic of Data Process Engineering Research Laboratory Faculty of AI Computer Science and Engineering Kyonggi University Gyeonggi Suwon16227 Korea Republic of

ISBN: (纸本)9783031809422

In business process life-cycle management and reengineering through process mining, it is crucial for the process mining system to discover structurally safe and complete business process models from process logs. However, most process mining systems typically suffer from discovering inaccurate and unstructured business process models due to various types of anomalous traces hidden in process logs. In this paper, we therefore propose a process log preprocessing approach that purifies a corresponding process log dataset by selecting a group of reasonable process log traces and applying to discover an essential business process model satisfying the structural completeness requirement of matched-pairing and proper-nesting properties. The theoretical basis of the proposed approach is the mathematical graph model of information control net model that is the typical representation of business process models. Finally, we practically demonstrate the conceptual excellence and functional correctness of the proposed preprocessing approach through experimental verifications using real business process enactment log datasets available in the 4TU center for research data. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Reengineering

来源：评论

学校读者我要写书评

暂无评论

Optical polarized orthogonal matrix

引用

Photonics research 2025年第2期13卷 373-381页

作者： SHUJUN ZHENG JIAREN TAN XIANMIAO XU HONGJIE LIU YI YANG XIAO LIN XIAODI TAN Information Photonics Research Center College of Photonic and Electronic EngineeringFujian Normal University Department of Electrical and Computer Engineering Duke University College of Photonic and Electronic Engineering Key Laboratory of Opto-Electronic Science and for Medicine of Ministry of EducationFujian Provincial Key Laboratory of Photonics TechnologyFujian Provincial Engineering Technology Research Center of Photoelectric Sensing ApplicationFujian Normal University

Multiplexing technology serves as an effective approach to increase both information storage and transmission capability. However, when exploring multiplexing methods across various dimensions, the polarization dimension encounters limitations stemming from the finite orthogonal combinations. Given that only two mutually orthogonal polarizations are identifiable on the basic Poincaré sphere, this poses a hindrance to polarization modulation. To overcome this challenge, we propose a construction method for the optical polarized orthogonal matrix(OPOM), which is not constrained by the number of orthogonal combinations. Furthermore, we experimentally validate its application in high-dimensional multiplexing of polarization holography. We explore polarization holography technology, capable of recording amplitude, phase, and polarization, for the purpose of recording and selective reconstruction of polarization multi-channels. Our research reveals that, despite identical polarization states, multiple images can be independently manipulated within distinct polarization channels through orthogonal polarization combinations, owing to the orthogonal selectivity among information.

关键词： Multiplex holography Optical data storage Optical encryption Orbital angular momentum multiplexing Signal transmission Three dimensional displays

来源：评论

学校读者我要写书评

暂无评论

Automated Testing for Service-Oriented Architecture: Leveraging Large Language Models for Enhanced Service Composition

引用

IEEE Access 2025年 13卷 89627-89640页

作者： Mahsun Altin Behcet Mutlu Deniz Kilinc Altan Cakir Department of Computer Engineering Istanbul Technical University İstanbul Türkiye Wingie Enuygun Group İstanbul Türkiye Department of Computer Engineering University of Bakirçay İzmir Türkiye Department of Data Science and Analytics Istanbul Technical University İstanbul Türkiye Artificial Intelligence Data Science Research and Application Center Istanbul Technical University İstanbul Türkiye Parton Big Data Analytics and Consulting ITU Ari Teknokent İstanbul Türkiye Adin.Ai Wilmington DE USA

This article explores the application of Large Language Models (LLMs), including proprietary models such as Openai’s ChatGPT 4o and ChatGPT 4o-mini, Anthropic’s Claude 3.5 Sonnet and Claude 3.7 Sonnet, and Google’s Gemini 1.5 Pro, Gemini 2.0 Flash, and Gemini 2.0 Flash-Lite, as well as open-source alternatives including Qwen2.5-14B-Instruct-1M, and commercially accessed models such as DeepSeek R1 and DeepSeek V3, which were tested via APIs despite having open-source variants, to automate validation and verification in application Programming Interface (API) testing within a Service-Oriented Architecture (SOA). Our system compares internal responses from the Enuygun Web Server against third-party API outputs in both JSON and XML formats, validating critical parameters such as flight prices, baggage allowances, and seat availability. We generated 100 diverse test scenarios across varying complexities (1-4 flight results) by randomly altering request and response parameters. Experimental results show that Google Gemini 2.0 Flash achieved high accuracy (up to 99.98%) with the lowest completion time (85.34 seconds), while Qwen2.5-14B-Instruct-1M exhibited limited capability in processing complex formats. Models such as Openai’s ChatGPT and Anthropic’s Claude Sonnet models also demonstrated strong performance in single-flight validation scenarios, making them suitable for low-latency, high-precision tasks. Our findings indicate that some open-source models can offer promising cost-effective alternatives, though performance significantly varies. This integration of LLMs reduced manual workload, improved test scalability, and enabled real-time validation across large-scale datasets. As LLM technologies mature, we anticipate further advances in automation, accuracy, and efficiency in software validation systems.

关键词： Indexing Service-oriented architecture Software testing Software systems Scalability Accuracy Software development management Real-time systems Complexity theory Software reliability

来源：评论

学校读者我要写书评

暂无评论

OHMiner: An Overlap-centric System for Efficient Hypergraph Pattern Mining 25

OHMiner: An Overlap-centric System for Efficient Hypergraph ...

引用

20th European Conference on computer Systems, EuroSys 2025, co-located 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS 2025

作者： Qi, Hao Luo, Kang He, Ligang Zhang, Yu Cai, Minzhi Dai, Jingxin He, Bingsheng Jin, Hai Zhang, Zhan Zhao, Jin Yue, Hengshan Yu, Hui Liao, Xiaofei National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China Department of Computer Science University of Warwick United Kingdom National University of Singapore Singapore Zhejiang Lab China Jilin University China

ISBN: (纸本)9798400711961

Hypergraph Pattern Mining (HPM) aims to identify all the instances of user-interested subhypergraphs (patterns) in hypergraphs, which has been widely used in various applications. However, existing solutions either need significant enumeration overhead because they extend subhypergraphs at the granularity of vertices, or suffer from massive redundant computations because they often need to repeatedly fetch and process the same incident hyperedges for different vertices. This paper presents an overlap-centric system named OHMiner to efficiently support HPM. OHMiner proposes an overlap-centric execution model to determine the subhypergraphs isomorphism through computing and comparing overlaps among hyperedges using set operations. This model aims to efficiently handle the vertices that collectively share the same incident hyperedges. To automatically and precisely retrieve an arbitrary pattern’s overlapping semantics without performing redundant set computations, OHMiner further proposes a redundancy-free compiler, which constructs an Overlap Intersection Graph (OIG) for the pattern, optimizes the OIG, and generates an overlap-centric execution plan to guide the procedure of HPM. Moreover, OHMiner designs an overlap-centric parallel execution engine, which adopts an incremental overlap-pruned approach to fast validate candidates for HPM. Additionally, it proposes a degree-aware data store to support efficient generation of candidates. Through evaluating OHMiner on a broad range of real-world hypergraphs with various patterns, our experimental results show that OHMiner outperforms the state-of-the-art HPM system by 5.4×-22.2×. © 2025 Copyright held by the owner/author(s).

关键词： Compiler

来源：评论

学校读者我要写书评

暂无评论

dataJudge: Cross-Chain data Consistency Verification Based on Extended Merkle Hash Tree 24th

DataJudge: Cross-Chain Data Consistency Verification Based o...

引用

24th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2024

作者： Xu, Yuwei Zeng, Junyu Cao, Jie Dai, Shengjiang Xiang, Qiao Cheng, Guang School of Cyber Science and Engineering Southeast University Nanjing China Purple Mountain Laboratories for Network and Communication Security Nanjing China Engineering Research Center of Blockchain Application Supervision and Management Nanjing China Department of Electrical and Computer Engineering Queen’s University Kingston Canada School of Informatics Xiamen University Xiamen China

ISBN: (纸本)9789819615414

Consortium blockchains, with their decentralized characteristics, have found widespread applications across various industries. However, this also forms isolated data islands. These data islands have become obstacles to data sharing between industries, and the issue of cross-chain data consistency verification remains unresolved. Current mainstream cross-chain technologies solve asset transfer issues through complex transaction steps, thus failing to meet the need for efficient data transmission. Existing research has proposed solutions for cross-chain data consistency verification, but two major issues remain. Firstly, these schemes do not consider data changes or support data dynamic operations. Secondly, these schemes involve a significant amount of complex computations, leading to slow efficiency. To address the above issues, we propose dataJudge, a cross-chain data consistency verification scheme based on an extended Merkle hash tree. This scheme not only verifies cross-chain data consistency but also effectively fills the gap in existing schemes regarding dynamic operations. Additionally, we modify the paillier homomorphic encryption. To improve efficiency, we do not introduce many complex computations. Furthermore, the extended Merkle hash tree structure enhances efficiency. Finally, we implement a prototype system and evaluate it. The results demonstrate that dataJudge can effectively verify cross-chain data consistency and outperform existing schemes such as DCIV and BeDCV. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： data consistency

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：