检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Ma, Youpeng Chen, Tao Li, Ke School of Computer Science and Engineering University of Electronic Science and Technology of China China IDEAS Lab School of Computer Science University of Birmingham United Kingdom Department of Computer Science University of Exeter United Kingdom

As software systems become more complex and configurable, more performance problems tend to arise from the configuration designs. This has caused some configuration options to unexpectedly degrade performance which deviates from their original expectations designed by the developers. Such discrepancies, namely configuration performance bugs (CPBugs), are devastating and can be deeply hidden in the source code. Yet, efficiently testing CPBugs is difficult, not only due to the test oracle is hard to set, but also because the configuration measurement is expensive and there are simply too many possible configurations to test. As such, existing testing tools suffer from lengthy runtime or have been ineffective in detecting CPBugs when the budget is limited, compounded by inaccurate test oracle. In this paper, we seek to achieve significantly faster CPBug testing by neurally prioritizing the testing at both the configuration option and value range levels with automated oracle estimation. Our proposed tool, dubbed NDP, is a general framework that works with different heuristic generators. The idea is to leverage two neural language models: one to estimate the CPBug types that serve as the oracle while, more vitally, the other to infer the probabilities of an option being CPBug-related, based on which the options and the value ranges to be searched can be prioritized. Experiments on several widely-used systems of different versions reveal that NDP can, in general, better predict CPBug type in 87% cases and find more CPBugs with up to 88.88× testing efficiency speedup over the state-of-the-art tools. Copyright © 2025, The Authors. All rights reserved.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

An Intelligent and Dynamic Replication Scheme for Reliable Cloud Environment

An Intelligent and Dynamic Replication Scheme for Reliable C...

引用

Integrated Circuits and Communication Systems (ICICACS), IEEE International Conference on

作者： Damodhar M Ch. D V Subba Rao Department of Computer Science and Engineering Sri Venkateswara University College of Engineering Tirupati India

ISBN: (数字)9798331508456

ISBN: (纸本)9798331508463

Recently, cloud computing research, especially Virtual Machine based replication schemes and their applications, were becoming prevalent. A cloud data center (DC) comprises of hosts with an enormous of virtual machines (VMs) where determining replica quantity and replication order is a tedious task to minimize cost and bandwidth. Majority of the existing dynamic replication techniques rely on budget constraints and server failure rate to guarantee customer requirements. But, there is a strong need to determine replication order of servers to retain the performance and system stability. In this paper, we suggest two different algorithms for better selection with proper and intelligent placement of replicas in the cloud region. The proposed algorithms towards dynamic replication are request based replica selection (RRS) and ant colony optimization (ACO). The foremost proposed algorithm was request based replica selection used for obtaining the best selected replicas depends upon the VM performance ranking and failure probability based on the task requirement. Conversely, the subsequent offered algorithm is ACO that is helpful to find the best location to place the designated replica depends on the least-cost distance metric, and the replicas availability in order to encompass and regulate with the entire network load and the link bottlenecks. The performance of proposed techniques using CloudSim was evaluated against various pro-active fault tolerance strategies. The simulation results gives that dynamic replica selection provides efficient task replication when compared with the existing pro-active algorithms. Additionally, ACO realizes high availability, low cost, and less bandwidth utilization.

关键词： Cloud computing Ant colony optimization Costs Heuristic algorithms Simulation Bandwidth Throughput Virtual machines Stability analysis Servers

来源：评论

学校读者我要写书评

暂无评论

Optimized Machine Learning Techniques for Precise Breast Cancer Detection in Mammograms

引用

SN computer science 2025年第4期6卷 1-22页

作者： Kiran, Puttegowda Veeraprathap, V. Rajashekhar, U. Mahantesh, Mathapati Sudheesh, K.V. Bharath, Kumara Prabhavathi, K. Department of Electronics and Communication Engineering Vidyavardhaka College of Engineering Karnataka Mysuru India Department of Electronics and Communication Engineering ATME College of Engineering Mysuru Karnataka Mysuru India Department of ECE Government Engineering College Huvinahadagali Karnataka Vijayanagara India Department of Computer Science & Engineering Amruta Institute of Engineering and Management Sciences Karnataka Bengaluru India Department of ECE M S Ramaiah University of Applied Science (MSRUAS) Karnataka Bangalore India Department of ECE BGS Institute of Technology Adichunchanagiri University B. G. Nagara Karnataka Mandya India

Breast cancer has recently overtaken cervical cancer as the predominant cancer type in Indian urban areas. Despite considerable research and the development of automated diagnostic machines, current methods are far from perfect, necessitating more reliable medical assessments. Moreover, there's been relatively little research on Indian datasets compared to international resources, despite significant differences due to factors like denser breasts, varying textures, lesion sizes, and compositions. To address this gap, our work focuses on using machine learning to automate breast cancer detection, tailoring models to Indian breast types and utilizing metadata for more accurate assessments. Our analyses show promising results, with the best single model achieving a per-image AUC of 0.95, and averaging four models increasing AUC to 0.98 (sensitivity: 86.7%, specificity: 96.1%) on an independent test set from the INbreast database. These findings highlight the potential of deep learning techniques in improving mammography accuracy and reducing false positives and negatives in clinical settings. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Biomedical applications Breast cancer Deep neural networks Faster-RCNN Machine learning models Mammograms Object detection YOLO V3

来源：评论

学校读者我要写书评

暂无评论

Integration of Deep Learning Architectures with GRU for Automated Leukemia Detection in Peripheral Blood Smear Images

引用

IEEE Access 2025年 13卷 84217-84239页

作者： Bairwa, Amit Kumar Shrotriya, Anita Mathur, Priyanka Joshi, Sandeep Shringi, Sakshi Kumari, Ambika Manipal University Jaipur Department of Artificial Intelligence and Machine Learning Jaipur-Ajmer Express Highway Jaipur India Manipal University Jaipur Department of Computer Science and Engineering Jaipur-Ajmer Express Highway Jaipur India Manipal University Jaipur Computer Applications CDOE Jaipur-Ajmer Express Highway Jaipur India PA Sangma International Medical College and Hospital Department of Anesthesiology Meghalaya India

This paper investigates the integration of deep learning (DL) architectures with Recurrent Neural Networks (RNNs) for automated leukemia detection in Peripheral Blood Smear (PBS) images. Models such as DenseNet201, EfficientNetB3, Inception v3, InceptionResNetV2, MobileNetV2, ResNet50, VGG16, and Xception, each enhanced with a Gated Recurrent Unit (GRU) layer, are employed to capture spatial and temporal dependencies in image data. Through extensive experimentation on a standard leukemia dataset, the performance of each model is evaluated based on accuracy and computational efficiency. Among these, the Xception + GRU model achieves the highest classification accuracy, attaining an impressive 99.69%. This exceptional result underscores the efficacy of combining Convolutional Neural Networks (CNNs) with RNNs, particularly GRUs, in the accurate detection of leukemia from PBS images. The findings offer valuable contributions to the field of medical image analysis, demonstrating the potential of DL techniques to enhance automated disease diagnosis. By advancing the precision of leukemia detection, this study provides promising implications for improving patient care and treatment outcomes. © 2013 IEEE.

关键词： Resuscitation

来源：评论

学校读者我要写书评

暂无评论

Integrity Assessment and Intrusion Detection Using ACGAN-Powered Machine Learning

Integrity Assessment and Intrusion Detection Using ACGAN-Pow...

引用

Data science, Agents & Artificial Intelligence (ICDSAAI), International Conference on

作者： B Mukesh Kumar R Nidhis Kumar V Muthulakshmi Department of Computer Science Engineering St Joseph’s College of Engineering Chennai India

ISBN: (数字)9798331537555

ISBN: (纸本)9798331537562

This study investigates the use of Auxiliary Classifier Generative Adversarial Networks (ACGANs) in addressing imbalanced data within the realm of cybersecurity. ACGANs generate synthetic data mimicking network attacks, contributing to dataset balancing for improved model training. The research focuses on enhancing cybersecurity decision making by refining the accuracy of distinguishing between legitimate and malicious traffic. By leveraging ACGAN-powered machine learning, this project work demonstrates the potential for stronger, more accurate threat detection and integrity assessment, ultimately fostering more advanced and resilient intrusion detection systems.

关键词： Training Accuracy Decision making Intrusion detection Machine learning Network security Data models Threat assessment computer security Synthetic data

来源：评论

学校读者我要写书评

暂无评论

A Synthesis of Approaches in Sign Language Communication Research: Trends and Future Directions 1st

A Synthesis of Approaches in Sign Language Communication Res...

引用

1st International Conference on Advanced Network Technologies and Computational Intelligence, ICANTCI 2024

作者： Gundavarapu, Mallikarjuna Rao Reddy, Alluri Shreya Bhavani, Kandula Durga Divya, Bhukya Sreeja, Linga Dyuti, Mengji Department of Computer Science and Engineering Gokaraju Rangaraju Institute of Engineering and Technology Hyderabad India

ISBN: (纸本)9783031860683

This review delves into the dynamic realm of sign language detection, offering a meticulous exploration of techniques, challenges, and promising directions. Essential for empowering communication among individuals with hearing impairments, sign language detection intersects with cutting-edge technologies. The paper meticulously surveys current methodologies, spanning computer vision, deep learning, and sensor-based innovations. By dissecting challenges like gesture variability, real-time processing constraints, and dataset diversity, the review provides profound insights. Solutions and future trajectories, including advanced neural network architectures and multimodal sensor fusion, are scrutinized. The synthesis of existing knowledge aims to inspire further research, bridging gaps, and propelling the evolution of sign language detection technology. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Model Deep Learning Framework for Plant Disease Detection and Classification using YOLOv5, Xception, and DenseNet

Multi-Model Deep Learning Framework for Plant Disease Detect...

引用

2025 International Conference on Visual Analytics and Data Visualization, ICVADV 2025

作者： Meshram, Kunal K. Khandelwal, Sarika Kumre, Jyoti G H Raisoni College of Engineering Department of Computer Science and Engineering Nagpur India

ISBN: (纸本)9798331521394

Plant diseases lead to food loss and yield reduction, which is a serious challenge to food security globally. Researchers have suggested deep learning models, which are trained using plant disease data like PlantVillage and PlantDoc, as a means of solving this issue. The traditional solutions usually do not work under practical agricultural environments. This research combines machine learning (ML) models and image processing methods for agricultural use. This study utilizes the algorithms, such as MobileNet, VGG16, YOLOv8, and Faster R-CNN, to upgrade plant disease identification and classification. Our method utilizes deep learning architectures for both object detection and plant disease classification. We offer real-time crop analysis to help farmers make informed decisions, achieve maximum productivity, and enhance sustainable agriculture. Leveraging previous work, we seek to enhance performance through DenseNet and Xception for classification and YOLOv5 for object detection. We also use a Flask-based, easy-to-use front-end for authentication-based client testing. © 2025 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Explainable AI Model for Automatic Irrigation System using IOT

Explainable AI Model for Automatic Irrigation System using I...

引用

IT Innovation and Knowledge Discovery (ITIKD), International Conference on

作者： R Rajagopal D. Sumathi Akey Sungheetha Rajesh Sharma R Sheila Mahapatra N. Sivakumar Department of Computer Science and Engineering Alliance College of Advanced Computing Alliance University Bangalore India Department of Computer Science and Engineering Alliance University Bengaluru India Department of Electrical and Electronics Engineering Alliance University Bengaluru Karnataka India Department of Computer Engineering Marwadi University Rajkot Gujarat India

ISBN: (数字)9798350355468

ISBN: (纸本)9798350355475

This paper presents an explainable artificial intelli-gence (XAI) model for automatic irrigation systems using Inter-net of Things (IoT) technology. The proposed system integrates soil moisture sensors, temperature sensors, and humidity sensors with a microcontroller to make data-driven irrigation decisions. A Random Forest classifier i s employed top redict irrigation requirements based on environmental parameters, with SHAP (SHapley Additive exPlanations) values providing transparency and interpretability of model decisions. The system demonstrates a 35 % reduction in water usage and a 20 % increase in crop yield compared to traditional irrigation methods. The integration of explainability enhances user trust and system adoption, making advanced agricultural technology accessible to farmers with varying technical expertise. Experimental results show that the Random Forest model outperforms XGBoost and SVM in accuracy (75%), precision (100% for non-irrigation decisions), and robustness for irrigation management.

关键词： Temperature sensors Support vector machines Irrigation Explainable AI Soil moisture Water conservation Sensor systems Sensors Internet of Things Random forests

来源：评论

学校读者我要写书评

暂无评论

LeafGuard: An AI-Driven Approach for Early Detection of Plant Pathogen Infections

LeafGuard: An AI-Driven Approach for Early Detection of Plan...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： Dudla Anil Kumar Ponnuru Sravya Karthika Shaik Saida Basha Maddala Jyothi Prakash Department of Computer Science and Engineering Lakireddy Bali Reddy College of Engineering Myalavaram India

ISBN: (数字)9798331512248

ISBN: (纸本)9798331512255

The development of an advanced machine learning model for plant disease detection using deep learning methods is the research objective. A plant pathogen image dataset from Kaggle will be used for proper classification of plant health based on various diseases, such as bacterial infection, fungi growth, pests, and viral diseases. Three deep learning models, namely CNN, ResNet, and MobileNet, will be trained on the dataset to make accurate plant health condition predictions. These models will classify plants according to health status and whether affected by bacteria, fungus, pests, virus, or are healthy. The proposed system will upload plant images, and the trained model will provide health predictions. This approach will serve as an effective tool for early detection, improving agricultural practices by enabling timely interventions.

关键词： Deep learning Analytical models Plant diseases Pathogens Accuracy Image recognition Plants (biology) Predictive models Bacteria Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Tamil Text Summarization Using Graph Convolutional Networks And Google’s MT5 Transformer

Tamil Text Summarization Using Graph Convolutional Networks ...

引用

Advancements in Electrical, Electronics, Communication, Computing and Automation (ICAECA), International Conference on

作者： Ashwanth Ram Damodaran Rajeswari Jayaraman Akila Rajesh Department of Computer Science and Engineering Sri Sivasubramaniya Nadar College of Engineering Chennai India

ISBN: (数字)9798331525439

ISBN: (纸本)9798331525446

Text summarization in Tamil language is an important problem in natural language processing and understanding and in information retrieval. Automatic text summarization is getting more attention nowadays as it helps in saving time in decision making by conveying the information concisely. The primary objective of this experimental project is to propose a methodology to address the problem of summarization for Tamil language text documents, which can generate concise meaningful summaries using Graph Convolutional Network (GCN) and Google Multilingual Text-to-Text-Transfer-Transformer (Google mT5). GCN is used to extract important sentences for extractive summarization and Google mT5 to summarize the extracted sentences, which will give a concise summary of the input text document without losing the meaning of the documents. Experiments are carried out using Huggingface datasets, and the ROUGE toolkit is used to evaluate the precision, recall, and F1 score of summaries generated by the system and also human evaluation.

关键词： Technological innovation Graph convolutional networks System performance Text summarization Transformers Solids Natural language processing Internet Multilingual Telecommunication computing

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：