检索结果-内蒙古大学图书馆

A novel attention based deep learning model for software defect prediction with bidirectional word embedding system

soft Computing 2025年第4期29卷 2171-2188页

作者： Devi, M. Chitra Rajkumar, T. Dhiliphan Department of Computer Science and Engineering Kalasalingam Academy of Research and Education Krishnankoil626126 India

software defect prediction (sDP) is considered a dynamic research problem and is beneficial during the testing stage of the software development life cycle. several artificial intelligence-based methods were available to predict these software defects. However, the detection accuracy is still low due to imbalanced datasets, poor feature learning, and tuning of the model's parameters. This paper proposes a novel attention-included Deep learning (DL) model for sDP with effective feature learning and dimensionality reduction mechanisms. The system mainly comprises ‘6’ phases: dataset balancing, source code parsing, word embedding, feature extraction, dimensionality reduction, and classification. First, dataset balancing was performed using the density peak based k-means clustering (DPKMC) algorithm, which prevents the model from having biased outcomes. Then, the system parses the source code into abstract syntax trees (AsTs) that capture the structure and relationship between different elements of the code to enable type checking and the representative nodes on AsTs are selected to form token vectors. Then, we use bidirectional encoder representations from transformers (BERT), which converts the token vectors into numerical vectors and extracts semantic features from the data. We then input the embedded vectors to multi-head attention incorporated bidirectional gated recurrent unit (MHBGRU) for contextual feature learning. After that, the dimensionality reduction is performed using kernel principal component analysis (KPCA), which transforms the higher dimensional data into lower dimensions and removes irrelevant features. Finally, the system used a deep, fully connected network-based softMax layer for defect prediction, in which the cross-entropy loss is utilized to minimize the prediction loss. The experiments on the National Aeronautics and space Administration (NAsA) and AEEEM show that the system achieves better outcomes than the existing state-of-the-art models f

关键词： Dimensionality reduction

来源：评论

学校读者我要写书评

暂无评论

A power optimization approach for mixed polarity Reed–Muller logic circuits based on multi-strategy fusion memetic algorithm

引用

Frontiers of Information Technology & Electronic Engineering 2025年第3期26卷 415-426页

作者： Mengyu ZHANG Zhenxue HE Yijin WANG Xiaojun ZHAO Xiaodan ZHANG Limin XIAO Xiang WANG Intelligent Agricultural Equipment Research Institute Hebei Agricultural UniversityBaoding 071001China Key Laboratory of Agricultural Big Data of Hebei Province Hebei Agricultural UniversityBaoding 071001China School of Computer Science and Engineering Beihang UniversityBeijing 100191China School of Electronic Information Engineering Beihang UniversityBeijing 100191China

The power optimization of mixed polarity Reed–Muller(MPRM)logic circuits is a classic combinatorial optimization *** optimization approaches often suffer from slow convergence and a propensity to converge to local optima,limiting their effectiveness in achieving optimal power ***,we propose a novel multi-strategy fusion memetic algorithm(MFMA).MFMA integrates global exploration via the chimp optimization algorithm with local exploration using the coati optimization algorithm based on the optimal position learning and adaptive weight factor(COA-OLA),complemented by population management through truncation ***,leveraging MFMA,we propose a power optimization approach for MPRM logic circuits that searches for the best polarity configuration to minimize circuit *** results based on Microelectronics Center of North Carolina(MCNC)benchmark circuits demonstrate significant improvements over existing power optimization *** achieves a maximum power saving rate of 72.30%and an average optimization rate of 43.37%;it searches for solutions faster and with higher quality,validating its effectiveness and superiority in power optimization.

关键词： Power optimization Multi-strategy fusion memetic algorithm(MFMA) Mixed polarity Reed-Muller(MPRM) Combinatorial optimization problem

来源：评论

学校读者我要写书评

暂无评论

Dimensional-noise-aware battery lifetime prediction via an EM-TLs framework

引用

Progress in Natural science:Materials International 2025年第1期35卷 146-155页

作者： Chenlong Yu Ting Lu Guohua Liu Xiaoang Zhai Wuyan Deng Jiayu Wan Yang Liu Xin Li School of Computer Science and Technology Donghua University Future Battery Research Center Global Institute of Future Technology Shanghai Jiaotong University Data Science Research Center Duke Kunshan University

Machine learning has been massively utilized to construct data-driven solutions for predicting the lifetime of rechargeable batteries in recent years, which project the physical measurements obtained during the early charging/discharging cycles to the remaining useful lifetime. While most existing techniques train the prediction model through minimizing the prediction error only, the errors associated with the physical measurements can also induce negative impact to the prediction accuracy. Although total-least-squares(TLs) regression has been applied to address this issue, it relies on the unrealistic assumption that the distributions of measurement errors on all input variables are equivalent, and cannot appropriately capture the practical characteristics of battery degradation. In order to tackle this challenge, this work intends to model the variations along different input dimensions, thereby improving the accuracy and robustness of battery lifetime prediction. In specific, we propose an innovative EM-TLs framework that enhances the TLs-based prediction to accommodate dimension-variate errors, while simultaneously investigating the distributions of them using expectation-maximization(EM). Experiments have been conducted to validate the proposed method based on the data of commercial Lithium-Ion batteries, where it reduces the prediction error by up to 29.9 % compared with conventional TLs. This demonstrates the immense potential of the proposed method for advancing the R&D of rechargeable batteries.

关键词： Battery lifetime prediction Dimension-variate measurement error Energy storage Expectation-maximization Total-least-squares regression

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Cloud Computing Through Reinforcement learning-based Workload scheduling

引用

International Journal of Advanced computer science and Applications 2025年第4期16卷 645-656页

作者： Malipatil, Ashwini R Paramasivam, M.E. Gulyamova, Dilfuza saravanan, Aanandha Ramesh, Janjhyam Venkata Naga Muniyandy, Elangovan Ghodhbani, Refka Department of Computer Science and Engineering BNM Institute of Technology Bangalore India Department of ECE Sona College of Technology Salem India Computer Engineering Department University of Information Technologies in Tashkent Tashkent Uzbekistan Department of ECE Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai India Department of CSE Graphic Era Hill University Dehradun248002 India Department of CSE Graphic Era Deemed to be University Uttarakhand Dehradun248002 India Department of Biosciences-Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India Applied Science Research Center Applied Science Private University Amman Jordan Center for Scientific Research and Entrepreneurship Northern Border University Arar73213 Saudi Arabia

The basis for current digital infrastructure is cloud computing, which allows for scalable, on-demand computational resource access. Data center power consumption, however, has skyrocketed because of demand increases, raising operating costs and their footprint. Traditional workload scheduling algorithms often assign performance and cost priority over energy efficiency. This paper proposes a workload scheduling method utilizing deep reinforcement learning (DRL) that adjusts dynamically according to present cloud situations to ensure optimal energy efficiency without compromising performance. The proposed method utilizes Deep Q-Networks (DQN) to perform feature engineering to identify key workload parameters such as execution time, CPU and memory consumption, and subsequently schedules tasks smartly based on these results. based on evaluation output, the model brings down the latency to 15 ms and throughput up to 500 tasks/sec with 92% efficiency in load balancing, 95% resource usage, and 97% Qos. The proposed approach yields improved performance in terms of key parameters compared to conventional approaches such as Round Robin, FCFs, and heuristic methods. These findings show how reinforcement learning can significantly enhance the scalability, reliability, and sustainability of cloud environments. Future work will focus on enhancing fault tolerance, incorporating federated learning for decentralized optimization, and testing the model on real-world multi-cloud infrastructures. © (2025), (science and Information Organization). All Rights Reserved.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

XGBoost-Liver:An Intelligent Integrated Features Approach for Classifying Liver Diseases Using Ensemble XGBoost Training Model

引用

computers, Materials & Continua 2025年第4期83卷 1459-1474页

作者： sumaiya Noor salman A.AlQahtani salman Khan Business and Management Sciences Department Purdue UniversityWest LafayetteIN 47907USA New Emerging Technologies and 5G Network and Beyond Research Chair Department of Computer EngineeringCollege of Computer and Information SciencesKing Saud UniversityRiyadh11564Saudi Arabia Department of Computer Science Abdul Wali Khan University MardanMardan23200KPKPakistan

The liver is a crucial gland and the second-largest organ in the human body and also essential in digestion,metabolism,detoxification,and *** diseases result from factors such as viral infections,obesity,alcohol consumption,injuries,or genetic *** significant health risks and demand timely diagnosis and treatment to enhance survival ***,diagnosing liver diseases relied heavily on clinical expertise,often leading to subjective,challenging,and time-intensive ***,early detection is essential for effective intervention,and advancements in machine learning(ML)have demonstrated remarkable success in predicting various conditions,including Chronic Obstructive Pulmonary Disease(COPD),hypertension,and *** study proposed a novel XGBoost-liver predictor by integrating distinct feature methodologies,including Ranking and statistical projection-based strategies to detect early signs of liver *** Fisher score method is applied to perform global interpretation analysis,helping to select optimal features by assessing their contributions to the overall *** performance of the proposed model has been extensively evaluated through k-fold cross-validation ***,the performance of the proposed model is evaluated using individual and hybrid ***,the XGBoost-Liver model performance is compared to that of commonly used classifier ***,its performance is compared with the existing state-of-the-art computational *** experimental results show that the proposed model performed better than the existing predictors,reaching an average accuracy rate of 92.07%.This paper demonstrates the potential of machine learning to improve liver disease prediction,enhance diagnostic accuracy,and enable timely medical interventions for better patient outcomes.

关键词： Machine learning deep neural network sHAP(sHapley Additive exPlanation) liver disease classifica-tion sMOTE(synthetic minority over-sampling technique)

来源：评论

学校读者我要写书评

暂无评论

Multi-agent deep reinforcement learning based resource management in heterogeneous V2X networks

引用

Digital Communications and Networks 2025年第1期11卷 182-190页

作者： Junhui Zhao Fajin Hu Jiahang Li Yiwen Nie School of Electronic and Information Engineering Beijing Jiaotong UniversityBeijing 100044China School of Information Engineering East China Jiaotong UniversityNanchang 330013China Research Institute of China United Network Communications Group Co. Ltd.Beijing100048China

In Heterogeneous Vehicle-to-Everything Networks(HVNs),multiple users such as vehicles and handheld devices and infrastructure can communicate with each other to obtain more advanced ***,the increasing number of entities accessing HVNs presents a huge technical challenge to allocate the limited wireless *** model-driven resource allocation approaches are no longer applicable because of rich data and the interference problem of multiple communication modes reusing resources in *** this paper,we investigate a wireless resource allocation scheme including power control and spectrum allocation based on the resource block reuse *** meet the high capacity of cellular users and the high reliability of Vehicle-to-Vehicle(V2V)user pairs,we propose a data-driven Multi-Agent Deep Reinforcement learning(MADRL)resource allocation scheme for the *** results demonstrate that compared to existing algorithms,the proposed MADRL-based scheme achieves a high sum capacity and probability of successful V2V transmission,while providing close-to-limit performance.

关键词： Data-driven Deep reinforcement learning Resource allocation V2X communications

来源：评论

学校读者我要写书评

暂无评论

Optimization of laser annealing parameters based on bayesian reinforcement learning

引用

Journal of Intelligent Manufacturing 2025年第4期36卷 2479-2492页

作者： Chang, Chung-Yuan Feng, Yen-Wei Rawat, Tejender singh Chen, shih-Wei Lin, Albert shihchun Institute of Electronics Engineering National Yang-Ming Chiao-Tung University Hsinchu30010 Taiwan Taiwan Semiconductor Research Institute No. 26 Prosperity Road I Hsinchu Science Park Hsinchu City300091 Taiwan

Developing new semiconductor processes consumes tremendous time and cost. Therefore, we applied Bayesian reinforcement learning (BRL) with the assistance of technology computer-aided design (TCAD). The fixed or variable prior BRL is tested where the TCAD prior is fixed or is changed by the experimental sampling and decays during the entire RL procedure. The sheet resistance (Rs) of the samples treated by laser annealing is the optimization target. In both cases, the experimentally sampled data points are added to the training dataset to enhance the RL agent. The model-based experimental agent and a model-free TCAD Q-Table are used in this study. The results of BRL proved that it can achieve lower Rs minimum values and variances at different hyperparameter settings. Besides, two action types, i.e., point to state and increment of levels, are proven to have similar results, which implies the method used in this study is insensitive to the different action types. © The Author(s) 2024.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Parallelism in GNN: Possibilities and Limits of Current Approaches 15th

Parallelism in GNN: Possibilities and Limits of Current A...

引用

15th International Conference on Parallel Processing and Applied Mathematics, PPAM 2024

作者： Mele, Valeria Carracciuolo, Luisa Romano, Diego University of Naples "Federico II" Naples Italy Italian National Research Council - CNR Rome Italy

ISBN: (纸本)9783031856990

Graph Neural Networks (GNNs) have emerged as powerful tools for learning on graph-structured data, demonstrating state-of-the-art performance in various applications such as social network analysis, biological network modeling, and recommendation systems. However, the computational complexity of GNNs poses significant challenges for scalability, particularly with large-scale graphs. Parallelism in GNNs addresses this issue by distributing computation across multiple processors, using techniques such as data parallelism and model parallelism. Data parallelism involves partitioning the graph data across different processors, while model parallelism splits the neural network’s layers or operations. These parallelization strategies, along with optimizations such as asynchronous updates and efficient communication protocols, enable GNNs to handle larger graphs and improve training efficiency. This work explores the key computational kernels and looks for those where parallelism could significantly enhance the scalability and performance of GNNs, highlighting the algebraic aspects of each one. This is the first step to better compare recent advances and their implications for future research. © The Author(s), under exclusive license to springer Nature switzerland AG 2025.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

CNN Issues in skin Lesion Classification: Data Distribution and Quantity

引用

IEEE ACCEss 2025年 13卷 58848-58862页

作者： Ramella, Giuliana serino, Luca Natl Res Council CNR Inst Applicat Calculus M Picone I-80131 Naples Italy Natl Res Council CNR Inst High Performance Comp & Networking I-80131 Naples Italy

Convolutional Neural Networks (CNNs) have become indispensable tools in skin cancer classification, aiding clinical experts to achieve earlier and more accurate diagnoses, improving treatment outcomes, and driving advancements in medical research. Despite their pivotal role, the most popular CNN architecture families exhibit a critical issue related to the distribution and quantity of available data, potentially compromising their performance and generalization abilities. This challenge is commonly overlooked in most skin lesion classification papers, which mainly rely on weighted classification techniques. Directly using appropriately dataset balancing or Transfer learning (TL) methods, as suggested in recent studies, has the potential to deliver more satisfactory results, providing a more effective approach to addressing this issue. In the effort to tackle this problem, we provide a comprehensive quantitative evaluation aimed at identifying the most critical new emerging computational aspects and the related effective techniques. specifically, we propose twelve Computational Models (CMs) based on four prominent CNN models with increasing structural complexity. We assess their effectiveness in both pretrained and unpretrained versions, incorporating TL strategies as well. Our experiments focus on the IsIC 2018 image dataset, a benchmark widely recognized for its extensive application in skin cancer research yet challenged by significant class imbalance issues. To mitigate this, we also randomly extracted a balanced image subset from IsIC 2018 for evaluation purposes. The experimental results, regarding four different scenarios, provide valuable insights into the design and utilization of CNNs for skin lesion classification, laying the groundwork for further investigations.

关键词： Lesions skin Training Convolutional neural networks computer architecture Computational modeling Image resolution Transfer learning Melanoma Image segmentation Balanced image dataset convolutional neural network dermoscopic image skin lesion classification transfer learning unbalanced image dataset

来源：评论

学校读者我要写书评

暂无评论

Machine learning-based Prediction of Corrosion Inhibition Efficiency of Expired Pharmaceuticals: Model Development and Application

引用

Journal of Bio- and Tribo-Corrosion 2025年第1期11卷 1-12页

作者： Putra, Dzaki Asari surya Ardyansyah, Nibras Bahy Putranto, Nicholaus Verdhy Trisnapradika, Gustina Alfa Akrom, Muhamad Rustad, supriadi Dipojono, Hermawan Kresno Maezono, Ryo Faculty of Computer Science Study Program in Informatics Engineering Universitas Dian Nuswantoro Semarang50131 Indonesia Research Center for Materials Informatics Faculty of Computer Science Universitas Dian Nuswantoro Semarang50131 Indonesia Quantum and Nano Technologies Research Group Faculty of Industrial Technology Institut Teknologi Bandung Bandung40132 Indonesia School of Information Science Japan Advanced Institute of Science and Technology Ishikawa923-1292 Japan

Corrosion poses a significant challenge in industries due to material degradation and high maintenance costs, making effective inhibitors essential. Recent studies suggest expired pharmaceuticals as alternative corrosion inhibitors, but identifying the most efficient compounds can be time-consuming. This study applies machine learning models, particularly Gradient Boosting Regressor (GBR), to predict corrosion inhibition efficiency (CIE). The developed model is integrated into a web-based application, enabling real-time, accurate CIE predictions. Results show GBR as the more precise model for predicting CIE, with low error rates. The streamlit-based web application offers a user-friendly platform, facilitating quick identification of suitable inhibitors. It is flexible, supporting analysis beyond corrosion inhibitors, and significantly enhances the efficiency of the evaluation process. © The Author(s), under exclusive licence to springer Nature switzerland AG 2025.

关键词： Adversarial machine learning

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：