检索结果-内蒙古大学图书馆

Parameter-efficient fine-tuning of pre-trained code models for just-in-time defect prediction

Neural computing and Applications 2024年第27期36卷 16911-16940页

作者： Abu Talib, Manar Bou Nassif, Ali Azzeh, Mohammad Alesh, Yaser Afadar, Yaman Department of Computer Science College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates Department of Computer Engineering College of Computing and Informatics Sharjah United Arab Emirates King Hussein School for Computing Sciences Princess Sumaya University for Technology Amman Jordan

Software engineering workflows use version control systems to track changes and handle merge cases from multiple contributors. This has introduced challenges to testing because it is impractical to test whole codebases to ensure each change is defect-free, and it is not enough to test changed files alone. Just-in-time software defect prediction (JIT-SDP) systems have been proposed to solve this by predicting the likelihood that a code change is defective. Numerous techniques have been studied to build such JIT software defect prediction models, but the power of pre-trained code transformer language models in this task has been underexplored. These models have achieved human-level performance in code understanding and software engineering tasks. Inspired by that, we modeled the problem of change defect prediction as a text classification task utilizing these pre-trained models. We have investigated this idea on a recently published dataset, ApacheJIT, consisting of 44k commits. We concatenated the changed lines in each commit as one string and augmented it with the commit message and static code metrics. Parameter-efficient fine-tuning was performed for 4 chosen pre-trained models, JavaBERT, CodeBERT, CodeT5, and CodeReviewer, with either partially frozen layers or low-rank adaptation (LoRA). Additionally, experiments with the Local, Sparse, and Global (LSG) attention variants were conducted to handle long commits efficiently, which reduces memory consumption. As far as the authors are aware, this is the first investigation into the abilities of pre-trained code models to detect defective changes in the ApacheJIT dataset. Our results show that proper fine-tuning improves the defect prediction performance of the chosen models in the F1 scores. CodeBERT and CodeReviewer achieved a 10% and 12% increase in the F1 score over the best baseline models, JITGNN and JITLine, when commit messages and code metrics are included. Our approach sheds more light on the abilities of l

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Privacy-Aware Federated Learning Framework for IoT Security Using Chameleon Swarm Optimization and Self-Attentive Variational Autoencoder

引用

computer Modeling in engineering & Sciences 2025年第4期143卷 849-873页

作者： Saad Alahmari Abdulwhab Alkharashi Department of Computer Science Applied CollegeNorthern Border UniversityArar91431Saudi Arabia Department of Computer Science College of Computing and InformaticsSaudi Electronic UniversityRiyadh11673Saudi Arabia

The Internet of Things(IoT)is emerging as an innovative phenomenon concerned with the development of numerous vital *** the development of IoT devices,huge amounts of information,including users’private data,are *** systems face major security and data privacy challenges owing to their integral features such as scalability,resource constraints,and *** challenges are intensified by the fact that IoT technology frequently gathers and conveys complex data,creating an attractive opportunity for *** address these challenges,artificial intelligence(AI)techniques,such as machine learning(ML)and deep learning(DL),are utilized to build an intrusion detection system(IDS)that helps to secure IoT *** learning(FL)is a decentralized technique that can help to improve information privacy and performance by training the IDS on discrete linked *** delivers an effectual tool to defend user confidentiality,mainly in the field of IoT,where IoT devices often obtain privacy-sensitive personal *** study develops a Privacy-Enhanced Federated Learning for Intrusion Detection using the Chameleon Swarm Algorithm and Artificial Intelligence(PEFLID-CSAAI)*** main aim of the PEFLID-CSAAI method is to recognize the existence of attack behavior in IoT ***,the PEFLIDCSAAI technique involves data preprocessing using Z-score normalization to transformthe input data into a beneficial ***,the PEFLID-CSAAI method uses the Osprey Optimization Algorithm(OOA)for the feature selection(FS)*** the classification of intrusion detection attacks,the Self-Attentive Variational Autoencoder(SA-VAE)technique can be ***,the Chameleon Swarm Algorithm(CSA)is applied for the hyperparameter finetuning process that is involved in the SA-VAE model.A wide range of experiments were conducted to validate the execution of the PEFLID-CSAAI *** simulated outcomes demonstrated that the PEFLID-CSAAI

关键词： Federated learning internet of things artificial intelligence chameleon swarm algorithm intrusion detection system healthcare IoT devices

来源：评论

学校读者我要写书评

暂无评论

Addressing Imbalance in Health Datasets: A New Method NR-Clustering SMOTE and Distance Metric Modification

引用

computers, Materials & Continua 2025年第2期82卷 2931-2949页

作者： Hairani Hairani Triyanna Widiyaningtyas Didik Dwi Prasetya Afrig Aminuddin Department of Electrical Engineering and Informatics Faculty of EngineeringUniversitas Negeri MalangMalang65145Indonesia Department of Computer Science Universitas BumigoraMataram83127Indonesia Department of Computer Graphic and Multimedia Faculty of ComputingCollege of Computing and Applied SciencesUniversiti Malaysia Pahang Al-Sultan AbdullahPekan26600Malaysia

An imbalanced dataset often challenges machine learning, particularly classification methods. Underrepresented minority classes can result in biased and inaccurate models. The Synthetic Minority Over-Sampling Technique (SMOTE) was developed to address the problem of imbalanced data. Over time, several weaknesses of the SMOTE method have been identified in generating synthetic minority class data, such as overlapping, noise, and small disjuncts. However, these studies generally focus on only one of SMOTE’s weaknesses: noise or overlapping. Therefore, this study addresses both issues simultaneously by tackling noise and overlapping in SMOTE-generated data. This study proposes a combined approach of filtering, clustering, and distance modification to reduce noise and overlapping produced by SMOTE. Filtering removes minority class data (noise) located in majority class regions, with the k-nn method applied for filtering. The use of Noise Reduction (NR), which removes data that is considered noise before applying SMOTE, has a positive impact in overcoming data imbalance. Clustering establishes decision boundaries by partitioning data into clusters, allowing SMOTE with modified distance metrics to generate minority class data within each cluster. This SMOTE clustering and distance modification approach aims to minimize overlap in synthetic minority data that could introduce noise. The proposed method is called “NR-Clustering SMOTE,” which has several stages in balancing data: (1) filtering by removing minority classes close to majority classes (data noise) using the k-nn method;(2) clustering data using K-means aims to establish decision boundaries by partitioning data into several clusters;(3) applying SMOTE oversampling with Manhattan distance within each cluster. Test results indicate that the proposed NR-Clustering SMOTE method achieves the best performance across all evaluation metrics for classification methods such as Random Forest, SVM, and Naїve Bayes, compared t

关键词： SMOTE modification Clustering-SMOTE manhattan distance

来源：评论

学校读者我要写书评

暂无评论

Tri-M2MT:Multi-modalities based effective acute bilirubin encephalopathy diagnosis through multi-transformer using neonatal Magnetic Resonance Imaging

引用

CAAI Transactions on Intelligence Technology 2025年第2期10卷 434-449页

作者： Kumar Perumal Rakesh Kumar Mahendran Arfat Ahmad Khan Seifedine Kadry Department of Computer Science and Engineering Rajalakshmi Engineering CollegeChennaiIndia Department of Computer Science College of ComputingKhon Kaen UniversityKhon KaenThailand Noroff University College and Department of Computer Science and Mathematics Lebanese American UniversityBeirutLebanon

Acute Bilirubin Encephalopathy(ABE)is a significant threat to neonates and it leads to disability and high mortality *** and treating ABE promptly is important to prevent further complications and long-term *** studies have explored ABE ***,they often face limitations in classification due to reliance on a single modality of Magnetic Resonance Imaging(MRI).To tackle this problem,the authors propose a Tri-M2MT model for precise ABE detection by using tri-modality MRI *** scans include T1-weighted imaging(T1WI),T2-weighted imaging(T2WI),and apparent diffusion coefficient maps to get indepth ***,the tri-modality MRI scans are collected and preprocessesed by using an Advanced Gaussian Filter for noise reduction and Z-score normalisation for data *** Advanced Capsule Network was utilised to extract relevant features by using Snake Optimization Algorithm to select optimal features based on feature correlation with the aim of minimising complexity and enhancing detection ***,a multi-transformer approach was used for feature fusion and identify feature correlations ***,accurate ABE diagnosis is achieved through the utilisation of a SoftMax *** performance of the proposed Tri-M2MT model is evaluated across various metrics,including accuracy,specificity,sensitivity,F1-score,and ROC curve analysis,and the proposed methodology provides better performance compared to existing methodologies.

关键词： Acute Bilirubin Encephalopathy(ABE)Diagnosis feature extraction MRI multi-modality multi-transformer neonatal

来源：评论

学校读者我要写书评

暂无评论

Genetic Algorithm Augmented Inception-Net based Image Classifier Accelerated on FPGA

引用

Multimedia Tools and Applications 2023年第29期82卷 45097-45125页

作者： Kaziha, Omar Bonny, Talal Jarndal, Anwar Department of Electrical Engineering College of Engineering University of Sharjah Sharjah United Arab Emirates Department of Computer Engineering College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates

Deep learning models for computer vision applications specifically and for machine learning generally are now the state of the art. The growth of size and complexity of neural networks has made them more and more reliable, yet in greater need of computational power and memory as is evident from the heavy reliance on graphical processing units and cloud computing for training them. As the complexity of deep neural networks increases, the need for fast processing neural networks in real-time embedded applications at the edge also increases and accelerating them using reconfigurable hardware suggests a solution. In this work, a convolutional neural network based on the inception net architecture is first optimized in software and then accelerated by taking advantage of field programmable gate array (FPGA) parallelism. Genetic algorithm augmented training is proposed and used on the neural network to produce an optimum model from the first training run without re-training iterations. Quantization of the network parameters is performed according to the weights of the network. The resulting neural network is then transformed into hardware by writing the register transfer level (RTL) code for FPGAs with exploitation of layer parallelism and a simple trial-and-error allocation of resources with the help of the roofline model. The approach is simple and easy to use as compared to many complex existing methods in literature and relies on trial and error to customize the FPGA design to the model needed to work on any computer vision or multimedia application deep learning model. Simulation and synthesis are performed. The results prove that the genetic algorithm reduces the number of back-propagation epochs in software and brings the network closer to the global optimum in terms of performance. Quantization to 16 bits also shows a reduction in network size by almost half with no performance drop. The synthesis of our design also shows that the Inception-based classifier is cap

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Classification of Privacy Preserved Medical Data with Fractional Tuna Sailfish Optimization Based Deep Residual Network in Cloud

引用

Annals of Data Science 2025年第3期12卷 829-854页

作者： Shikalgar, Shabanam K. Kumar, N. V. S. Pavan Singh, Gavendra Rashid, Faizur Sharad Institute of Technology College of Engineering Yadrav India Koneru Lakshmiah Education Foundation Vijayawada India Department of Software Engineering College of Computing and Informatics Haramaya University Dire Dawa138 Ethiopia College of Computing and Informatics Haramaya University Dire Dawa138 Ethiopia

Nowadays, with the growth of emerging technologies, increased attention has been paid to the classification of privacy-preserved medical data and development of various privacy-preserving models for the promotion of online medical pre-diagnosis systems. Medical data is highly sensitive and it is essential to ensure privacy of medical records from third-party users to increase service quality, satisfy patients and earn trust. The classification of medical preserved data is helpful to build a clinical decision system by classifying patients based on their disease and symptoms. In this article, a hybrid optimization-based deep learning model named Fractional Tuna Sailfish Optimization–Deep Residual Network (FractionalTSFO-DRN) is designed to precisely classify the privacy preserved medical data. A privacy utility coefficient matrix is used to ensure the privacy of medical data by generating a key matrix using Tuna Sailfish Optimization (TSFO) algorithmic technique. The privacy-preserved medical data is allowed for the classification process using DRN and the introduced Fractional TSFO is used to optimize and enhance the classification in DRN. The assessment followed by using heart disease prediction databases proved that the employed classification technique recorded an accuracy of 94.67%, a True Positive Rate of 93.56%, and a True Negative Rate of 89.68% respectively. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Automatic lung cancer detection using hybrid particle snake swarm optimization with optimized mask RCNN

引用

Multimedia Tools and Applications 2024年第31期83卷 76807-76831页

作者： Sudha, R. Maheswari, K. M. Uma Department of Computer Science and Engineering School of computing College of engineering and technology SRM Institute of Science and Technology Kattankulathur India Department of Computing Technologies School of Computing College of engineering and technology SRM Institute of Science and Technology Kattankulathur India

As a result of its aggressive nature and late identification at advanced stages, lung cancer is one of the leading causes of cancer-related deaths. Lung cancer early diagnosis is a serious and difficult challenge that is crucial to a person's survival. The first diagnosis of the malignant nodules is typically made using chest radiography (X-rays) and computed tomography (CT) scans;however, the potential presence of benign nodules results in incorrect conclusions. The early phases of both benign and malignant nodules exhibit striking similarities. In this paper, a novel deep learning-based model is proposed for the precise diagnosis of malignant nodules. The proposed approach consists of two stages namely, pre-processing and lung nodule detection. Initially, the Lung CT scan images are collected from the dataset. Then, to remove the noise present in the input image, we apply an adaptive median filter. Then, to enhance the image, Contrast Limited Adaptive Histogram Equalization (CLAHE) is applied. After pre-processing, the image is given to the optimized mask RCNN classifier to detect the malignant and benign nodules. To enhance the performance of the Mask RCNN classifier, the hyper-parameters are optimally selected using hybrid particle snake swarm optimization (PS2OA). The proposed PS2OA is a hybridization of particle swarm optimization (PSO) and snake swarm optimization (SSO). The performance of the proposed approach is analyzed based on different metrics and effectiveness compared with state-of-the-art works. The proposed approach attained the maximum accuracy of 97.67%. This work aimed at assisting radiologists to detect and diagnose small-size pulmonary nodules more accurately. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Enhancing intrusion detection in IIoT: optimized CNN model with multi-class SMOTE balancing

引用

Neural computing and Applications 2024年第24期36卷 14643-14659页

作者： Eid, Abdulrahman Mahmoud Soudan, Bassel Nassif, Ali Bou Injadat, MohammadNoor Department of Computer Engineering College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates Department of Data Science and AI Faculty of Information Technology Zarqa University Zarqa Jordan

This work introduces an intrusion detection system (IDS) tailored for industrial internet of things (IIoT) environments based on an optimized convolutional neural network (CNN) model. The model is trained on a dataset that was balanced using a novel multi-class implementation of synthetic minority over-sampling technique (SMOTE) that ensures equal representation of all classes. Additionally, systematic optimization will be used to fine tune the hyperparameters of the CNN model and mitigate the effects of the increased size of the training dataset. Evaluation results will demonstrate substantial improvement in performance when the optimized CNN model is trained on the balanced dataset. The proposed IDS will be evaluated using the IIoT-specific WUSTL-IIOT-2021 dataset, and then its generalization capability will be verified using the non-domain specific UNSW_NB15 dataset. The model’s performance will be evaluated using accuracy, precision, recall, and F1-score metrics. The results will demonstrate that the proposed IDS is highly effective with performance exceeding 99.9% on all performance metrics. The IDS is also highly effective in detecting intrusion for generic IT networks achieving improvements in excess of 30% compared to the default baseline model. The results emphasize the versatility and effectiveness of the proposed IDS model, making it a reliable and adaptable solution for enhancing network security across diverse network environments. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Force Sensitive Resistors-Based Real-Time Posture Detection System Using Machine Learning Algorithms

引用

computers, Materials & Continua 2023年第11期77卷 1795-1814页

作者： Arsal Javaid Areeb Abbas Jehangir Arshad Mohammad Khalid Imam Rahmani Sohaib Tahir Chauhdary Mujtaba Hussain Jaffery Abdulbasid S.Banga Department of Electrical and Computer Engineering COMSATS University IslamabadLahore CampusLahore54000Pakistan College of Computing and Informatics Saudi Electronic UniversityRiyadh11673Saudi Arabia Department of Electrical and Computer Engineering College of EngineeringDhofar UniversitySalalah211Oman

To detect the improper sitting posture of a person sitting on a chair,a posture detection system using machine learning classification has been proposed in this *** addressed problem correlates to the third Sustainable Development Goal(SDG),ensuring healthy lives and promoting well-being for all ages,as specified by the World Health Organization(WHO).An improper sitting position can be fatal if one sits for a long time in the wrong position,and it can be dangerous for ulcers and lower spine *** novel study includes a practical implementation of a cushion consisting of a grid of 3×3 force-sensitive resistors(FSR)embedded to read the pressure of the person sitting on ***,the Body Mass Index(BMI)has been included to increase the resilience of the system across individual physical variances and to identify the incorrect postures(backward,front,left,and right-leaning)based on the five machine learning algorithms:ensemble boosted trees,ensemble bagged trees,ensemble subspace K-Nearest Neighbors(KNN),ensemble subspace discriminant,and ensemble RUSBoosted *** proposed arrangement is novel as existing works have only provided simulations without practical implementation,whereas we have implemented the proposed design in *** results validate the proposed sensor placements,and the machine learning(ML)model reaches a maximum accuracy of 99.99%,which considerably outperforms the existing *** proposed concept is valuable as it makes it easier for people in workplaces or even at individual household levels to work for long periods without suffering from severe harmful effects from poor posture.

关键词： Posture detection FSR sensor machine learning real-time KNN

来源：评论

学校读者我要写书评

暂无评论

Sustainable energy management in the AI era: a comprehensive analysis of ML and DL approaches

引用

computing 2025年第6期107卷 1-64页

作者： Javed, Haseeb Eid, Fatma El-Sappagh, Shaker Abuhmed, Tamer Department of Computer Science and Engineering College of Computing and Informatics Sungkyunkwan University Suwon Korea Republic of Technology Management Stony Brook University NY11794 United States Applied Artificial Intelligence College of Computing and Informatics Sungkyunkwan University Suwon Korea Republic of Faculty of Computer Science and Engineering Galala University Suez435611 Egypt Information Systems Department Faculty of Computers and Artificial Intelligence Benha University Banha13518 Egypt

This study comprehensively analyzes the application of innovative deep learning (DL) and machine learning (ML) techniques in smart energy management systems (EMSs), with an emphasis on load forecasting, demand response, and the development of smart energy sectors. The application of various ML and DL models were examined in over 200 studies from 2014 to 2024 in an electrical network's EMS to highlight the key benefits and advances made by each technology for the sustainable management systems in energy sector. The findings emphasize DL and ML models’ enhanced precision and predictive capabilities in load forecasting, their efficacy in enabling efficient demand response mechanisms, and their significance in supporting the development of smart energy sectors. Furthermore, recommendations are made based on the survey results to assist in incorporating these techniques into EMS frameworks, such as investment in data infrastructure, model training and validation, and collaboration between researchers, industry experts, and policymakers. The study also discusses the limitations identified in the literature, such as limited real-world implementations, challenges regarding quality and data availability, and the need for enhanced ML and DL model interpretability. Addressing these limitations can assist in increasing the application and efficacy of ML and DL techniques in EMSs, enabling a more efficient and sustainable energy landscape. Finally, this study facilitates researchers' exploration of ML and DL in energy management, highlighting relevant limitations, strengths, and alternative approaches associated with sustainable energy management. It also indicates potential future research directions for further investigation. © The Author(s) 2025.

关键词： Power management (telecommunication)

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

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

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：