检索结果-内蒙古大学图书馆

Conference on Information and Knowledge Technology

作者： Hossein Hosseini Mohammad Sobhan Zare Amir Hossein Mohammadi Arefeh Kazemi Zahra Zojaji Mohammad Ali Nematbakhsh Department of software engineering University of Isfahan Isfahan Iran ADAPT Research Centre Dublin City University Dublin Ireland Department of software engineering Faculty of Computer Engineering University of Isfahan Isfahan Iran

ISBN: (数字)9798331522254

ISBN: (纸本)9798331522261

Retrieval augmented generation (RAG) models, which integrate large-scale pre-trained generative models with external retrieval mechanisms, have shown significant success in various natural language processing (NLP) tasks. However, applying RAG models in Persian language as a low-resource language, poses distinct challenges. These challenges primarily involve the preprocessing, embedding, retrieval, prompt construction, language modeling, and response evaluation of the system. In this paper, we address the challenges towards implementing a real-world RAG system for Persian language called PersianRAG. We propose novel solutions to overcome these obstacles and evaluate our approach using several Persian benchmark datasets. Our experimental results demonstrate the capability of the PersianRAG framework to enhance question answering task in Persian.

关键词： Analytical models Computational modeling Retrieval augmented generation Benchmark testing Hyperparameter optimization Question answering (information retrieval) Data models Prompt engineering Optimization

来源：评论

学校读者我要写书评

暂无评论

Alzheimer's Disease Classification Approach Using MRI Imaging

Alzheimer's Disease Classification Approach Using MRI Imagin...

引用

Mobile, Intelligent, and Ubiquitous Computing Conference (MIUCC), International

作者： Eman Khaled Farah Amr Farah Essam Maryam Nouh Youssef Sherif Zyad Yakan Ziad El Gayar Ashraf AbdelRaouf Department of Computer Engineering and Software Systems Faculty of Engineering Ain Shams University Cairo Egypt Faculty of Computer Scinece Misr International University Cairo Egypt

Alzheimer's disease (AD) is a slowly progressing, irreversible brain condition that weakens memory and negatively affects the patient's quality of life. Alzheimer's disease (AD) can be identified using Magnetic Resonance Imaging (MRI) data. For an early diagnosis of the disease, various medical and diagnostic approaches are being investigated. Even while MRI is a useful tool for locating AD-related brain symptoms, the acquisition process is time-consuming, largely because workflow bottlenecks must be manually evaluated. In order to find the best effective method for detecting the disease, this research examines the basic technique for analyzing MRI images. To carry out our study to slow progression of the disease by the use of Alzheimer's disease (AD) prognosis, a dataset from The Alzheimer's Disease Neuroimaging Initiative (ADNI) will be imported and fitted. The outcomes highlight the tremendous potential of integrating imaging data for automated categorization of Alzheimer's disease (AD) using multidisciplinary AI techniques. With a deep three-dimensional convolutional network (3D CNN) being used to handle the three-dimensional MRI input and a Transformer encoder being applied to manage the genetic sequence input, the suggested solution merges machine learning, bioinformatics, and other image processing techniques. After various experiments by checking the results accuracy, it is stated that the CNN model is never enough to provide us with the desired accuracy either by training on both skull stripped data or the GM tissue segmented data. Although, it is relatively better at the skull stripped dataset training, but the results accuracy and predicted classes show that inferring some classifiers after extracting the features from the CNN would increase the accuracy and results. After applying Support Vector Machine SVM-RBF, SVM-POLY, and XGBoost, it is concluded that the training of the Skull Stripped Dataset with features extracted from the CNN model we provided an

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Solar Energy Production Forecasting with Ensemble-based Learning Techniques

Enhancing Solar Energy Production Forecasting with Ensemble-...

引用

International Conference on Cybernetics and Intelligent System (ICORIS)

作者： Hany Abdelsalam Alireza Souri Nihat Inanç Department of Software Engineering Faculty of Engineering Haliç University Istanbul Türkiye Department of Computer Engineering Faculty of Engineering Haliç University Istanbul Turkiye Department of Electrical and Electronics Engineering Faculty of Engineering Haliç University Istanbul Türkiye

ISBN: (数字)9798331539603

ISBN: (纸本)9798331539610

The global trend in renewable energy solutions has emphasized the urgent need for accurate forecasting of solar energy production. This study examines the potential of ensemble-based learning techniques in predicting solar energy production by leveraging historical data collected from 11 solar photovoltaic installations in Calgary, Canada, spanning from September 2015 to March 2023. The dataset was carefully preprocessed to handle missing values, duplicates, and to extract meaningful features that align with the nature of time series data. A range of ML models were implemented and assessed by several forecasting evaluation metrics, including Mean Absolute Error (MAE), Mean Squared Error (MSE), and R-squared $(\mathrm{R}^{2})$ . The experimental results demonstrate the superior performance of ensemble methods, particularly XGBoost and Light GBM, in solar energy forecasting. XGBoost achieved the best performance, with an MAE of 25.36, an MSE of 3599.66, and $\mathrm{R}^{2}$ of 0.957, outperforming models such as Random Forest and Neural Networks. The practical implications of these findings suggest that accurate solar energy forecasting can significantly enhance operational planning and optimize energy management in solar power plants, contributing to more reliable and efficient renewable energy systems.

关键词： Analytical models Renewable energy sources Accuracy Neural networks Solar energy Production Predictive models Reliability Forecasting Random forests

来源：评论

学校读者我要写书评

暂无评论

HistoDX: Revolutionizing Breast Cancer Diagnosis Through Advanced Imaging Techniques

引用

IEEE Access 2025年 13卷 94416-94436页

作者： Wishal Arshad Tehreem Masood H. M. Shahzad Hassan A. Ahmed Syed Hamza Ahmed Hafiz Muhammad Tayyab Khushi Faculty of Software Engineering and Information Technology University of Central Punjab Lahore Pakistan Faculty of Computer Science and Information Technology Superior University Lahore Pakistan Department of Software Engineering Superior University Lahore Pakistan Department of Information Systems Monte Ahuja College of Business Cleveland State University Cleveland OH USA

Breast cancer is the second leading cause of mortality among women worldwide, highlighting the need for efficient histopathology-based screening methods for early diagnosis. This study introduces HistoDX, a deep learning framework to classify Invasive Ductal Carcinoma (IDC) using 277,524 histopathology image patches ( $50\times 50$ pixels) from Paul Mooney’s IDC dataset on Kaggle, comprising No Cancer and IDC(+) classes. HistoDX employs a preprocessing pipeline with normalization, data augmentation, and class balancing via oversampling and weighted loss to address the class imbalance. A customized convolutional neural network, built on EfficientNetV2-B3 with additional layers, achieves 97% accuracy and a 0.91 ROC-AUC score on the test set. Validation on BreakHis (97% accuracy) and BACH (90% accuracy) datasets confirm generalizability, though detecting under sampled IDC(+) cases remains challenging. Low training and test losses underscore reliability. HistoDX empowers pathologists by enhancing diagnostic efficiency and minimizing subjectivity through effective class imbalance mitigation. Its robust performance across diverse datasets like BreakHis and BACH suggests readiness for clinical integration. Future research into advanced augmentation techniques, ensemble models, and whole-slide image analysis could further optimize accuracy, sensitivity, and scalability, paving the way for broader adoption in precision oncology.

关键词： Breast cancer Cancer Accuracy Tumors Feature extraction Computational modeling Imaging Histopathology Deep learning Breast

来源：评论

学校读者我要写书评

暂无评论

PersianRAG: A Retrieval-Augmented Generation System for Persian Language

arXiv

引用

arXiv 2024年

作者： Hosseini, Hossein Kazemi, Arefeh Zare, Mohammad Sobhan Zojaji, Zahra Mohammadi, Amir Hossein Nematbakhsh, Mohammad Ali Department of software engineering University of Isfahan Isfahan Iran ADAPT Research Centre Dublin City University Dublin Ireland Department of software engineering Faculty of Computer Engineering University of Isfahan Isfahan Iran

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Fused Machine Learning Approach for Intrusion Detection System

引用

computers, Materials & Continua 2023年第2期74卷 2607-2623页

作者： Muhammad Sajid Farooq Sagheer Abbas Atta-ur-Rahman Kiran Sultan Muhammad Adnan Khan Amir Mosavi School of Computer Science National College of Business Administration and EconomicsLahore54000Pakistan Department of Computer Science College of Computer Science and Information TechnologyImam Abdulrahman Bin Faisal UniversityP.O.Box 1982Dammam 31441Saudi Arabia Department of CIT The Applied CollegeKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Software Gachon UniversitySeongnam13120Korea John von Neumann Faculty of Informatics Obuda UniversityBudapest1034Hungary Institute of Information Engineering Automation and MathematicsSlovak University of Technology in BratislavaBratislava81107Slovakia Faculty of Civil Engineering TU-DresdenDresden01062Germany

The rapid growth in data generation and increased use of computer network devices has amplified the infrastructures of *** interconnectivity of networks has brought various complexities in maintaining network availability,consistency,and *** learning based intrusion detection systems have become essential to monitor network traffic for malicious and illicit *** intrusion detection system controls the flow of network traffic with the help of computer *** deep learning algorithms in intrusion detection systems have played a prominent role in identifying and analyzing intrusions in network *** this purpose,when the network traffic encounters known or unknown intrusions in the network,a machine-learning framework is needed to identify and/or verify network *** Intrusion detection scheme empowered with a fused machine learning technique(IDS-FMLT)is proposed to detect intrusion in a heterogeneous network that consists of different source networks and to protect the network from malicious *** proposed IDS-FMLT system model obtained 95.18%validation accuracy and a 4.82%miss rate in intrusion detection.

关键词： Fused machine learning heterogeneous network intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Self-Optimizing Memory Controllers: Proposing Request-level Scheduling 2

Self-Optimizing Memory Controllers: Proposing Request-level ...

引用

2nd International Conference on computer Science, engineering and Applications, ICCSEA 2022

作者： Shawky, Alaa Watheq El-Kharashi, M. Safar, Mona Dessouky, Mohamed Ain Shams University Faculty of Engineering Electronics and Communications Dept. Cairo Egypt Siemens Digital Industries Software Cairo Egypt Ain Shams University Faculty of Engineering Computer and Systems Engineering Dept. Cairo Egypt

ISBN: (数字)9781665458344

ISBN: (纸本)9781665458344

Self-Optimizing Memory Controllers present a great potential in the future of memory controllers. As they alleviate the burden of designing an optimal memory scheduling policy, while providing adaptability to different workloads and systems. Previous state-of-art controllers scheduled memory accesses on the command level. This causes the agent to lose sight of the relation between commands and can lead to the issuing of unuseful sequences of precharge/activate of rows or closing banks that should have been left open, and vice versa. In this work we propose a bank-aware self-optimizing memory controller that schedules memory references on the request-level, presenting to the agent the actual problem it needs to tackle. This simplifies the evaluation of system attributes and eliminates the need for correction mechanisms that was needed in previous controllers. With the proposed algorithm a maximum of 18% increase in the data bus utilization is achieved compared to the commonly used FR-FCFS algorithm. © 2022 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Task Offloading and Resource Allocation in IoT Based Mobile Edge Computing Using Deep Learning

引用

computers, Materials & Continua 2023年第8期76卷 1463-1477页

作者： Ily s Abdullaev Natalia Prodanova KAruna Bhaskar ELaxmi Lydia Seifedine Kadry Jungeun Kim Dean of the Faculty of Economics Department of Management and MarketingFaculty of EconomicsUrgench State UniversityUrganch220100Uzbekistan Basic Department Financial Control Analysis and Audit of Moscow Main Control DepartmentPlekhanov Russian University of EconomicsMoscow117997Russia Department of Computer Science and Engineering KL Deemed to UniversityVaddeswaramGunturAndhra PradeshIndia Department of Computer Science and Engineering GMR Institute of TechnologyAndhra PradeshRajamIndia Department of Applied Data Science Noroff University CollegeKristiansandNorway Artificial Intelligence Research Center(AIRC) Ajman UniversityAjman346United Arab Emirates Department of Electrical and Computer Engineering Lebanese American UniversityByblosLebanon Department of Software Kongju National UniversityCheonan31080Korea

Recently,computation offloading has become an effective method for overcoming the constraint of a mobile device(MD)using computationintensivemobile and offloading delay-sensitive application tasks to the remote cloud-based data *** city benefitted from offloading to edge *** a mobile edge computing(MEC)network in multiple *** comprise N MDs and many access points,in which everyMDhasM independent real-time *** study designs a new Task Offloading and Resource Allocation in IoT-based MEC using Deep Learning with Seagull Optimization(TORA-DLSGO)*** proposed TORA-DLSGO technique addresses the resource management issue in the MEC server,which enables an optimum offloading decision to minimize the system *** addition,an objective function is derived based on minimizing energy consumption subject to the latency requirements and restricted *** TORA-DLSGO technique uses the deep belief network(DBN)model for optimum offloading ***,the SGO algorithm is used for the parameter tuning of the DBN *** simulation results exemplify that the TORA-DLSGO technique outperformed the existing model in reducing client overhead in the MEC systems with a maximum reward of 0.8967.

关键词： Mobile edge computing seagull optimization deep belief network resource management parameter tuning

来源：评论

学校读者我要写书评

暂无评论

Comparison of YOLO Algorithms for Vehicle Accident Detection and Classification

Comparison of YOLO Algorithms for Vehicle Accident Detection...

引用

Emerging Smart Technologies and Applications (eSmarTA), International Conference on

作者： Ahmed N. Nusari Abdulfattah E. Ba Alawi Ferhat Bozkurt İbrahim Yücel Özbek Electrical and Electronics Engineering Department Faculty of Engineering Ataturk University Erzurum Turkey Computer and Control Engineering Department Faculty of Engineering Sana’a University Sana’a Yemen Computer Engineering Department Faculty of Engineering Ataturk University Erzurum Turkey Software Engineering Department Faculty of Engineering & IT Taiz University Taiz Yemen Electrical and Electronics Department Faculty of Engineering Ataturk University Erzurum Turkey

ISBN: (数字)9798350354133

ISBN: (纸本)9798350354140

Early detection of vehicle accidents is essential for immediate response and to decrease the severity of injuries while vehicle accidents occur. Among the advanced algorithms YOLOv6, YOLOv7, YOLOv8, and YOLOv9 are compared in this article to determine their performance in detecting vehicle accidents that are categorized as "severity" or "moderate." The study emphasizes how important deep learning is to enhancing accident detection systems. Out of all the models evaluated, YOLOv8m has the highest precision (0.979), and the highest recall (0.927) for YOLOv8n. Furthermore, YOLOv9c performs admirably in mAP50, receiving a score of 0.977, indicating its resilience in identifying accidents under a variety of circumstances. YOLOv9e is noteworthy for its better mAP50-95, which reaches a high of 0.941, demonstrating its ability to localize accident incidents accurately. These results provide valuable insight into how well particular algorithms perform in real-world situations. Through a close examination of their performance measures, this research aids in the advancement of more effective accident detection systems, which in turn improves emergency response operations and lessens the effects of accidents on people and communities. This comparison research emphasizes how crucial it is to use state-of-the-art technology to increase accident detection accuracy and enable timely and efficient response.

关键词： YOLO Deep learning Technological innovation Accuracy Computational modeling Scalability Emergency services

来源：评论

学校读者我要写书评

暂无评论

Streamlining Attendance with Voice Recognition via Gaussian Mixture Model

Streamlining Attendance with Voice Recognition via Gaussian ...

引用

2024 International Conference on IT and Industrial Technologies, ICIT 2024

作者： Ali, Noor Ali, Khadija Ali, Fatimah Ali, Aaminah Ali, Nisar Ali, Raja Hashim A-levels Lahore Grammer School 55 Main Gulberg Lahore54660 Pakistan Department of Software Engineering NUST College of Electrical and Mechanical Engineering Islamabad43701 Pakistan Department of Artificial Intelligence Faculty of Computer Science & Engineering GIK Institute of Engineering Sciences & Technology Topi23460 Pakistan Department of Business University of Europe for Applied Sciences Potsdam14469 Germany Faculty of Engineering and Applied Science University of Regina ReginaS4S0A2 Canada

ISBN: (纸本)9798331504465

Voice recognition systems are crucial because they allow seamless human-computer interaction and improve accessibility for users of all abilities. The use of these technologies in hands-free control, language translation, virtual assistants, transcription services, and hands-free control is revolutionising how we engage with technology and enhancing convenience and productivity in general. Several attendance systems based on voice recognition exist, but we wanted to deploy an attendance system with a good graphical user interface specifically for students of GIK Institute. For this purpose, we wanted to make a user-friendly and accurate voice recognition system based and trained on self-provided data of ten students. This study introduces an AI-driven attendance system, which demonstrates high efficiency and accuracy in identifying students’ daily class attendance. To achieve this, the Gaussian Mixture Model approach was employed. The paper also delves into the utilization of libraries and methods, encompassing the training and validation of well-known machine learning models. Additionally, the system’s performance, its strengths, weaknesses and potential areas for improvement are also discussed in the study. © 2024 IEEE.

关键词： Students

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：