检索结果-内蒙古大学图书馆

A HYBRID SWARM INTELLIGENCE APPROACH FOR OPTIMIZING MULTIMODAL LARGE LANGUAGE MODELS DEPLOYMENT IN EDGE-CLOUD-BASED FEDERATED LEARNING ENVIRONMENTS

arXiv

引用

arXiv 2025年

作者： Rjoub, Gaith Elmekki, Hanae Islam, Saidul Bentahar, Jamal Dssouli, Rachida Concordia Institute for Information Systems Engineering Concordia University Montreal Canada Department of Computer Science Khalifa University Abu Dhabi United Arab Emirates Faculty of Information Technology Aqaba University of Technology Aqaba Jordan

The combination of Federated Learning (FL), Multimodal Large Language Models (MLLMs), and edge-cloud computing enables distributed and real-time data processing while preserving privacy across edge devices and cloud infrastructure. However, the deployment of MLLMs in FL environments with resource-constrained edge devices presents significant challenges, including resource management, communication overhead, and non-IID data. To address these challenges, we propose a novel hybrid framework wherein MLLMs are deployed on edge devices equipped with sufficient resources and battery life, while the majority of training occurs in the cloud. To identify suitable edge devices for deployment, we employ Particle Swarm Optimization (PSO), and Ant Colony Optimization (ACO) is utilized to optimize the transmission of model updates between edge and cloud nodes. This proposed swarm intelligence-based framework aims to enhance the efficiency of MLLM training by conducting extensive training in the cloud and fine-tuning at the edge, thereby reducing energy consumption and communication costs. Our experimental results show that the proposed method significantly improves system performance, achieving an accuracy of 92%, reducing communication cost by 30%, and enhancing client participation compared to traditional FL methods. These results make the proposed approach highly suitable for large-scale edge-cloud computing systems. Copyright © 2025, The Authors. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

DPS: Design Pattern Summarisation Using Code Features

arXiv

引用

arXiv 2025年

作者： Nazar, Najam Sikka, Sameer Treude, Christoph School of Computer and Mathematical Sciences The University of Adelaide Australia School of IT and Engineering Ada University Azerbaijan Faculty of Engineering and Information Technology The University of Melbourne Australia School of Computing and Information Systems Singapore Management University Singapore

Automatic summarisation has been used efficiently in recent years to condense texts, conversations, audio, code, and various other artefacts. A range of methods, from simple template-based summaries to complex machine learning techniques—and more recently, large language models—have been employed to generate these summaries. Summarising software design patterns is important because it helps developers quickly understand and reuse complex design concepts, thereby improving software maintainability and development efficiency. However, the generation of summaries for software design patterns has not yet been explored. Our approach utilises code features and JavaParser to parse the code and create a JSON representation. Using an NLG library on this JSON representation, we convert it into natural language text that acts as a summary of the code, capturing the contextual information of the design pattern. Our empirical results indicate that the summaries generated by our approach capture the context in which patterns are applied in the codebase. Statistical evaluations demonstrate that our summaries closely align with human-written summaries, as evident from high values in the ROUGE-L, BLEU-4, NIST, and FrugalScore metrics. A follow-up survey further shows that DPS summaries were rated as capturing context better than human-generated summaries. Copyright © 2025, The Authors. All rights reserved.

关键词： Software design

来源：评论

学校读者我要写书评

暂无评论

Leveraging Generalizability of Image-to-Image Translation for Enhanced Adversarial Defense

arXiv

引用

arXiv 2025年

作者： Zhang, Haibo Yao, Zhihua Sakurai, Kouichi Saitoh, Takeshi Department of Artificial Intelligence Faculty of Computer Science and Systems Engineering Kyushu Institute of Technology Japan Faculty of Economics and Business Administration The University of Kitakyushu Japan Department of Informatics Faculty of Information Science and Electrical Engineering Kyushu University Japan

In the rapidly evolving field of artificial intelligence, machine learning emerges as a key technology characterized by its vast potential and inherent risks. The stability and reliability of these models are important, as they are frequent targets of security threats. Adversarial attacks, first rigorously defined by Ian Goodfellow et al. in 2013, highlight a critical vulnerability: they can trick machine learning models into making incorrect predictions by applying nearly invisible perturbations to images. Although many studies have focused on constructing sophisticated defensive mechanisms to mitigate such attacks, they often overlook the substantial time and computational costs of training and maintaining these models. Ideally, a defense method should be able to generalize across various, even unseen, adversarial attacks with minimal overhead. Building on our previous work on image-to-image translation-based defenses, this study introduces an improved model that incorporates residual blocks to enhance generalizability. The proposed method requires training only a single model, effectively defends against diverse attack types, and is well-transferable between different target models. Experiments show that our model can restore the classification accuracy from near zero to an average of 72% while maintaining competitive performance compared to state-of-the-art methods. Significantly, our model operates more efficiently, reducing the time needed to process individual images and speeding up the training process to achieve faster convergence. Robustness tests further confirm stable performance under varying attack strengths, demonstrating the model’s practical value in real-world adversarial settings. Copyright © 2025, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Have Java Production Methods Co-Evolved With Test Methods Properly?: A Fine-Grained Repository-Based Co-Evolution Analysis 48

Have Java Production Methods Co-Evolved With Test Methods Pr...

引用

48th Euromicro Conference on Software engineering and Advanced Applications, SEAA 2022

作者： Kita, Tenma Aman, Hirohisa Amasaki, Sousuke Yokogawa, Tomoyuki Kawahara, Minoru Department of Computer Science Faculty of Engineering Ehime University Matsuyama Ehime790–8577 Japan Center for Information Technology Ehime University Matsuyama Ehime790–8577 Japan Faculty of Computer Science and Systems Engineering Okayama Prefectural University Soja Okayama719–1197 Japan

ISBN: (纸本)9781665461528

Any source code of a software product (production code) is expected to be tested to ensure its correct behavior. Whenever a developer updates production code, the developer should also update or create the corresponding test code to check if the updated parts still work correctly. Such a desirable co-evolution relationship between production and test code forms a logical coupling. Although the logical coupling is detectable through an association analysis on the code repository such as Git, the detection granularity is coarse because the conventional repository is at the file level. For observing those logical couplings as precisely as possible, this paper utilizes the finer-grained, Java method-level repository (FinerGit). Then the paper proposes a metric measuring the extent to which a production method has co-evolved with test methods and conducts a case study using ten open-source projects. The results show that most Java methods (98% on average) have co-evolved with test methods, but some have not;The proposed metric helps detect those methods having the potential risk that the developers might not test adequately. © 2022 IEEE.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

BD-ECG: Identification of Myocardial Infarction in ECG via Behavior Coupling 22

BD-ECG: Identification of Myocardial Infarction in ECG via B...

引用

6th International Conference on information System and Data Mining, ICISDM 2022

作者： Iqbal, Uzair Wah, Teh Ying Ur Rehman, Muhammad Habib Bilal, Muhammad Ahmed, Adeel Department of Computer Science National University of Computer and Emerging Sciences Pakistan Department of Information Systems Faculty of Computer Science and Information Technology University of Malaya Malaysia Division of Imaging Sciences and Biomedical Engineering Kings College London United Kingdom Department of Computer Science Quaid-e-Azam University Pakistan

ISBN: (纸本)9781450396257

In the cardiovascular diseases, early detection and identification of the relationship between different diseases are still open problems for cardiologists. In this paper, we propose a novel scheme for behavioral detection in electrocardiography data named as Behavioral detection-Electrography. The Behavioral detection-Electrography is used for early detection of abnormalities in electrography especially myocardial infarction. The Behavioral detection-Electrography embeds the two-tier architecture in which we integrate the behavioral relationship concepts with myocardial detection algorithm. In future the highlighted integral scheme will help us to identify the nature of cardiovascular diseases either it's normal or abnormal © 2022 ACM.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Automatic Detection of Some Tajweed Rules

Automatic Detection of Some Tajweed Rules

引用

Learning and technology Conference (L&T)

作者： Dahlia Omran Sahar Fawzi Ahmed Kandil Systems and Biomedical Engineering Faculty of Engineering Cairo University Giza Egypt Information Technology & Computer Science Nile University Giza Egypt

correct understanding of the Holy Quran is an essential duty for all Muslims. Tajweed rules guide the reciter to perform Holy Quran reading exactly as it was uttered by Prophet Muhammad peace be upon him. This work focused on the recognition of one Quranic recitation rule. Qalqalah rule is applied to five letters of the Arabic Alphabet (Baa/Daal/Jeem/Qaaf/Taa) having sukun vowelization. The proposed system used the Mel Frequency Cepstral Coefficients (MFCC) as the feature extraction technique, and the Convolutional Neural Networks (CNN) model was used for recognition. The available dataset consists of 3322 audio samples from different surahs of the Quran for four professional readers (Sheihk) AlHussary, AlMinshawy, Abdel Baset, and Ayman Swayed. The best results were gained using Ayman Swayed audio samples with a validation accuracy of 90.8%.

关键词： Training Neural networks Feature extraction Pattern recognition Convolutional neural networks Mel frequency cepstral coefficient

来源：评论

学校读者我要写书评

暂无评论

Contrast enhancement of optical videoscope images

引用

Iran Journal of computer Science 2023年第3期6卷 261-275页

作者： Ammar, Reda Aboshosha, Sahar El-Hag, Noha A. Saifeldeen, Reda El-Shafai, Walid El-Banby, Ghada M. Ashiba, Huda I. Khalaf, Ashraf A. M. Elazm, Atef Abou El-Rabaie, El-Sayed M. Abd El-Samie, Fathi E. El-Safrawey, Amir Department of Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf 32952 Egypt Department of Electronics and Electrical Comm. Faculty of Engineering Minia University Minya Egypt Department of Management of Information Systems Higher Institute of Commercial Science El-Mahala El-Kobra Egypt Department of Industrial Electronics and Control Engineering Faculty of Electronic Engineering Menoufia University Menouf 32952 Egypt Department of Electronics and Electrical Communications Engineering Bilbis Higher Institute of Engineering Sharqia Bilbis Egypt Security Engineering Laboratory Computer Science Department Prince Sultan University Riyadh 11586 Saudi Arabia Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh 11671 Saudi Arabia

The videoscope (VS) images have poor quality and low contrast. Hence, in this paper, three proposed frameworks to improve the quality of VS images are presented. The first framework depends on contrast-limited adaptive histogram equalization (CLAHE) with adaptive gamma correction. The second framework depends on homomorphic processing. The third framework is based on the homomorphic enhancement with histogram equalization. The first one is superior from the entropy perspective, while the third one is superior from the contrast perspective. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2023.

关键词： Fuzzy enhancement Histogram equalization Homomorphic enhancement Spectral entropy

来源：评论

学校读者我要写书评

暂无评论

Detection of Android Malware using Machine Learning

Detection of Android Malware using Machine Learning

引用

2021 International Mobile, Intelligent, and Ubiquitous Computing Conference, MIUCC 2021

作者： Fiky, Ahmed Hashem El Elshenawy, Ayman Madkour, Mohamed Ashraf Al-Azhar University Systems and Computer Engineering Faculty of Engineering Cairo Egypt Software Engineering and Information Technology Department Faculty of Engineering and Technology Egyptian Chinees University Cairo Egypt

ISBN: (纸本)9781665412438

Nowadays, smartphones became an integral part of human life due to the great necessity for their daily activities. Most smartphone users are downloading and installing mobile apps without worrying about security. Therefore, smartphones are a winning goal for malware, mainly with Android devices. So, it was necessary to provide an intelligent model for detecting malware applications before installing them on android smartphones. In this paper, an intelligent model using machine learning algorithms is proposed for detecting the malware applications in smartphones based on the static malware analysis technique. The contents of an android application features are analyzed, such as permissions, intents, system commands, and API-calls that were extracted from the application manifest file and source code. The proposed model is applied on two separate datasets DREBIN and MALGENOME. The experimental results are compared with some other similar researches, and their results were analyzed. The results indicate that the performance of the proposed model outperforms other similar models for some selected classifiers and can reliably detect both malware and benign Android applications with high accuracy. © 2021 IEEE.

关键词： Android malware

来源：评论

学校读者我要写书评

暂无评论

Predictive Multimodal Deep Learning-Based Sustainable Renewable and Non-Renewable Energy Utilization

引用

computer systems Science & engineering 2023年第10期47卷 1267-1281页

作者： Abdelwahed Motwakel MarwaObayya Nadhem Nemri Khaled Tarmissi Heba Mohsen Mohammed Rizwanulla Ishfaq Yaseen Abu Sarwar Zamani Department of Information Systems College of Business Administration in Hawtat bani TamimPrince Sattam bin Abdulaziz UniversityHowtat Bani Tamim16622Saudi Arabia Department of Biomedical Engineering College of EngineeringPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Information Systems College of Computer ScienceKing Khalid UniversityAbhaSaudi Arabia Department of Computer Sciences College of Computing and Information SystemUmm Al-Qura UniversitySaudi Arabia Department of Computer Science Faculty of Computers and Information TechnologyFuture University in EgyptNew Cairo11835Egypt Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam bin Abdulaziz UniversityAlKharjSaudi Arabia

Recently,renewable energy(RE)has become popular due to its benefits,such as being inexpensive,low-carbon,ecologically friendly,steady,and *** RE sources are gradually combined with non-renewable energy(NRE)sources into electric grids to satisfy energy *** energy utilization is highly related to national energy policy,energy prediction using artificial intelligence(AI)and deep learning(DL)based models can be employed for energy prediction on RE and NRE power *** energy consumption of RE and NRE sources using effective models becomes *** this motivation,this study presents a new multimodal fusionbased predictive tool for energy consumption prediction(MDLFM-ECP)of RE and NRE power *** data may influence the prediction performance of the results in prediction *** proposed MDLFMECP technique involves pre-processing,fusion-based prediction,and hyperparameter *** addition,the MDLFM-ECP technique involves the fusion of four deep learning(DL)models,namely long short-termmemory(LSTM),bidirectional LSTM(Bi-LSTM),deep belief network(DBN),and gated recurrent unit(GRU).Moreover,the chaotic cat swarm optimization(CCSO)algorithm is applied to tune the hyperparameters of the DL *** design of the CCSO algorithm for optimal hyperparameter tuning of the DL models,showing the novelty of the work.A series of simulations took place to validate the superior performance of the proposed method,and the simulation outcome emphasized the improved results of the MDLFM-ECP technique over the recent approaches with minimum overall mean absolute percentage error of 3.58%.

关键词： Sustainability renewable energy power source energy prediction deep learning fusion model metaheuristics

来源：评论

学校读者我要写书评

暂无评论

Performance Comparison of the Invasive Weed Optimization K-Means Algorithm with Particle Swarm Optimization K-Means for Banking Data

Performance Comparison of the Invasive Weed Optimization K-M...

引用

International Conference on Cybernetics and Intelligent System (ICORIS)

作者： Ni Luh Gede Pivin Suwirmayanti I Ketut Gede Darma Putra Made Sudarma I Made Sukarsa Emy Setyaningsih Department of Computer Systems Faculty of Informatics and Computer Institut Teknologi dan Bisnis STIKOM Bali Bali Indonesia Department of Information Technology Faculty of Engineering Udayana University Jimbaran Hill Bali Indonesia Department of Electrical Engineering Faculty of Engineering Udayana University Jimbaran Hill Bali Indonesia Department of Computer Systems Engineering Faculty of Applied Science Universitas AKPRIND Indonesia Yogyakarta Indonesia

ISBN: (数字)9798331539603

ISBN: (纸本)9798331539610

Banking produces extensive and diverse data, so a clustering process is needed to understand customer behavior patterns and transactions more effectively. This clustering has been widely utilized with the K-Means algorithm due to its simplicity and efficiency. However, this algorithm is limited in determining the optimal cluster center, affecting the accuracy of the clustering results. This study proposes applying two metaheuristic algorithms, Invasive Weed Optimization (IWO) and Particle Swarm Optimization (PSO), as additional solutions combined with K-Means. These two algorithms were chosen because of their ability to find global solutions and convergence speed to handle large and complex banking data. The results show the superiority of IWOKM compared to PSOKM in terms of SSE and DBI. From the SSE value, IWOKM produces a lower value (3029.77), which indicates that this method is better at minimizing clustering errors and producing more accurate clustering than PSOKM (80007.09). From the DBI value, IWOKM also produces a better value (1.6684) than PSOKM (1.6782), which shows that the clusters produced by IWOKM are more compact and more separated. However, in terms of computation time, PSOKM is more efficient, with a faster average computation time. Although IWOKM produces better clustering quality, PSOKM offers advantages in terms of processing speed. This finding confirms that the selection of the IWO algorithm is more appropriate for use on datasets with characteristics such as the German Credit Dataset.

关键词： Accuracy Consumer behavior Metaheuristics Clustering algorithms Banking Computational efficiency Particle swarm optimization Intelligent systems Cybernetics Convergence

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：