检索结果-内蒙古大学图书馆

2025 International Conference on Computing for Sustainability and Intelligent Future, COMP-SIF 2025

作者： Iqbal, J. L. Mazher Gurrapu, Omprakash Saritha, P.S. Rajesh Kanna, R. Jayanthi, R. Tejaskumar, M.B. Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Electronics and Communication Engineering Avadi India Volvo Trucks NC United States Dhanalakshmi Srinivasan College of Engineering Department of Artificial intelligence and data science Coimbatore India Christ University Department of Computer Science Bangalore India Dayananda Sagar College of Engineering Department of Master of Computer Applications Bengaluru India Don Bosco Institute of Technology Bangalore India

ISBN: (纸本)9798331538538

The employ of deep learning methods for the diagnosis and prognosis model of chronic diseases is an important discovery to change the healthcare service. Some of the chronic diseases which prevalence and incidence rates remain high globally include diabetes, cardiovascular diseases, chronic kidney diseases, and cancers. There is nothing more critical than early diagnosis and accurate prediction of the patients' condition and the best course of action that has to be taken. This paper aims at examining the possibility of utilizing ANN, Random Forest, XGBoost, and CNN to forecast the occurrence of the. Due to integration of big and varied data which involve clinical characteristics, biochemical parameters and medical images among others, ML models have the ability recognize complex relations not easily recognizable by conventional diagnostic procedures. These illustrations prove that deep learning models or more specifically the convolutional neural networks for image diagnosis outperform other traditional methods in performance and prognosis. Nevertheless, some issues, such as data quality, model's interpretability, and its implementation into clinical practice, are still present. The challenges appeared in this paper are key to understanding the future of ML in healthcare as they can pave the way to the integration of such models into practice, therefore leading to early detection, better prognosis, and effective management of chronic diseases. This paper aims at exploring on how ML can be of significance in transformation of the health care sector and orderly improve patients care. © 2025 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

A Review of Machine Learning Algorithms in Diabetes Management 4

A Review of Machine Learning Algorithms in Diabetes Manageme...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Gayaki, Unnati Daronde, Subodh Tale, Abhay Barhate, Aditya Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Computer Science and Engineering Maharashtra Wardha India Faculty of Engineering and Technology Department of Biomedical Engineering Maharashtra Wardha India Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Artificial Intelligence and Data Science Maharashtra Wardha India Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Artificial Intelligence and Machine Learning Maharashtra Wardha India

ISBN: (纸本)9798331523923

Diabetes is a prevalent and chronic disease affecting millions worldwide, posing significant challenges in its management and treatment. This review article aims to explore the current and potential future roles of machine learning (ML) in diabetes management, focusing on progress, applications, and challenges. It discusses various ML techniques, including support vector machines (SVM), logistic regression, decision trees, ensemble methods, and advanced deep learning approaches such as long short-term memory (LSTM) networks and convolutional neural networks (CNN). These methods have demonstrated benefits in analytics, patient monitoring, decision support systems, personalised treatment, and patient engagement. However, significant challenges persist, such as computational complexity, data quality, limited interoperability of systems, and ethical concerns regarding AI use in healthcare. The article addresses these challenges by fostering collaboration between AI implementers and health care professionals. This collaboration is essential to develop long-term, legally compliant, and solution-oriented frameworks that enhance patient care and diabetes management and pave the way for more efficient and ethical AI applications in healthcare. © 2025 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Parameter-Efficient Image Classification with Convolutional Spiking Neural Network via Fast Sigmoid Surrogate Gradient Descent

Parameter-Efficient Image Classification with Convolutional ...

引用

International Conference on Electrical, computer and Communication engineering (ECCE)

作者： Joy Datta Fabliha Afaf Sarwar Rawhatur Rabbi Puja Saha Md. Golam Rabiul Alam Jia Uddin Aniqua Nusrat Zereen Department of Computer Science & Engineering School of Data & Sciences Brac University Dhaka Bangladesh Department of Computer Science & Engineering Rajshahi University of Engineering & Technology Rajshahi Bangladesh AI and Big Data Department Endicott College Woosong University Daejeon South Korea

ISBN: (数字)9798350357509

ISBN: (纸本)9798350357516

Spiking Neural Networks (SNNs) offer several advantages over traditional Artificial Neural Networks (ANNs), especially in terms of biologically inspired event-driven mechanisms and energy efficiency. This paper aims to demonstrate parameter efficiency of Convolutional Spiking Neural Networks (CSNNs) by training extremely small CSNNs and comparing those with conventional Convolutional Neural Networks (CNNs) of same parameter count and depth, as well as against state-of-the-art SNN implementations. Through experiments conducted on multiple small-scale CSNN models, we observed that CSNNs are able to achieve exceptional parameter efficiency and performance with the help of a fast sigmoid surrogate gradient descent, proving an astonishing balance between accuracy and compactness. The findings fulfill the promise that CSNNs hold as a feasible solution for resource-constrained and low-power applications at the same time, as it demonstrates the biological plausibility of learning in such complex machine learning tasks.

关键词： Training Image recognition Biological system modeling Neurons Spiking neural networks Machine learning computer architecture Energy efficiency Convolutional neural networks Image classification

来源：评论

学校读者我要写书评

暂无评论

Decentralized Intrusion Detection in Peer-to-Peer Networks using Stacking Ensemble Model 1

Decentralized Intrusion Detection in Peer-to-Peer Networks u...

引用

1st International Conference on Intelligent Systems and Computational Networks, ICISCN 2025

作者： Devi, R. Renuga Riadhusin, Rame Anu, D. Swarnateja, R. Revathi, R. Srm Institute of Science and Technology Department of Computer Science and Applications Ramapuram India The Islamic University of Al Diwaniyah College of Technical Engineering Department of Computers Techniques Engineering Al Diwaniyah Iraq Nitte Meenakshi Institute of Technology Department of Artificial Intelligence and Data Science Bengaluru India Dhanalakshmi Srinivasan College of Engineering and Technology Department of Information Technology Mamallapuram India New Prince Shri Bhavani College of Engineering and Technology Department of Electrical and Electronics Engineering Chennai India

ISBN: (纸本)9798331529246

In recent years, due to the rise in Peer to Peer (P2P) networks has brought a significant way in which the data is shared and services are offered over the internet. These P2P networks make use of decentralized architecture in which nodes directly interact and exchange resources. However, due to the use of decentralized architecture, the P2P networks are exposed to various security threats such as data breaches, and other malicious attacks. In this research, Stacking Ensemble Model (SEM) is proposed for network intrusion detection in P2P networks. Initially, the data is considered from network intrusion detection dataset and then preprocessed with data imputation and min-max normalization effectively handles the missing values and rescales the data into significant range. After that, Recursive Feature Elimination (RFE) is incorporated to select optimal features from preprocessed data based on feature importance. Finally, the proposed SEM effectively detects the intrusion in P2P networks which enhances the security. From the results, the proposed SEM model obtained a better outcome in terms of accuracy, precision, recall, and F1-score compared to the existing K-Nearest Neighbor (KNN) by accomplishing 97.20%, 94.71%, 96.62%, and 95.65%, respectively. © 2025 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Mobile Healthcare: Societal Impact, Workforce Adaptation, and Enhanced Predictive Modeling for Diabetes Risk Assessment

AI-Driven Mobile Healthcare: Societal Impact, Workforce Adap...

引用

2025 International Conference on Pervasive Computational Technologies, ICPCT 2025

作者： Hole, Shreyas Rajendra Kolluru, Vinothkumar Gangul, Ranita Kolekar, Sagar Chintakunta, Advaitha Naidu Mungara, Sudeep Bangalore India Institute of Technology Department of Data Science Stevens HobokenNJ07030 United States Delaware State University Computer Science & Engineering Bangalore India Department of Civil Engineering Pune India University of North Carolina at Charlotte Department of Computer Science CharlotteNC28223 United States Masters in Information Systems Stevens Institute of Technology HobokenNJ07030 United States

ISBN: (纸本)9798331508685

With advancements in artificial intelligence, it is natural for the health industry to focus on IOT devices. AI could promote a paradigm shift in how doctors and patients interact through immediate updates, predictive features, and remote access. The focus of this study is the outreach and employment aspects revolving around AI-enabled health care, with special attention to mHealth solutions. We searched through published data and came across 112 relevant studies identifying keywords such as accessibility, empowerment, and workforce. One of the most interesting findings was the fact that AI targeting mobile applications has the possibility of increasing access to health services by approximately 60 percent for rural areas, as well as increasing the patient cooperative rate by approximately 45%, where a predictive health tracking device has been utilized. We proposed two new measures: the Physical Activity and Nutrition Index (PANI) and Health Status Index (HSI), allowing for better diabetes risk predictions with a 0.82 AUC-ROC and better generalizability than traditional baselines, with an improvement of 12%. When identifying the best available ML models, including Logistic Regression, Random Forest, XGBoost, LightGBM, and Bayesian Neural Networks, we found that the hybrid Random Forest + Linear SVC model had the best performance with recall and accuracy of 0.77 and 0.72, respectively. The ability of the model to demonstrate both interpretability and specificity was evident. It was also observed that synthetic data augmentation (SMOTE) increased the recall for minority class predictions by 18% but did not reduce specificity. © 2025 IEEE.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Machine Learning Techniques for Arabic Text Classification Using the SANAD dataset 11

Comparative Analysis of Machine Learning Techniques for Arab...

引用

11th International Conference on Mechatronics and Robotics engineering, ICMRE 2025

作者： Attar, Hani Sharrab, Yousef Smadi, Saja Jbaily, Safa Zarqa University Faculty of Engineering Zarqa Jordan University of Business and Technology College of Engineering Jeddah21448 Saudi Arabia Isra University Department of Data Science and Artificial Intelligence Amman Jordan Yarmouk University Dept. Computer Science Irbid Jordan

ISBN: (纸本)9798331509293

Applying Machine Learning (ML) models for Arabic text classification is a growing research field that has recently raised a large number of research. Generally, classifying text involves selecting a category based on its content from a list of pre-established categories. data classification is among the most popular Natural Language Processing (NLP) activities. Moreover, automatic article classifications, such as the Single-label Arabic News Articles dataset (SANAD), are desperately needed to improve the retrieval of the requested data, which this paper investigates. The ML leverages large datasets to improve efficiency;indeed, by locating focal spots within the text, the learning mechanisms facilitate attention tools better suited for handling lengthy texts. The proposed work employs a dataset of 7,000 articles of separately classified Arab news items and then breaks them into seven categories of 1,000 news stories each: politics, education, sports, religion, culture, finance, and medicine. The investigated SANAD consists of three primary datasets from three news portals: Akhbarana, AlArabiva, and AlCtrl. Finally, to obtain trustable information, this study implements a variety of Conventional ML techniques, K-Nearest Neighbor (KNN), Artificial Neural Network (ANN), Support Vector Machine (SVM), and Logistic Regression model to classify the investigated dataset. Our results show that the suggested solution outperformed the analytical search in the Arabic language in terms of accuracy, whereas the Logistic Regression model shows the best results among the seven utilized publicly available dataset classifications. © 2025 IEEE.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Smart Web Application for Recommending the Selection of Equipment for Organizing Activities in Educational Institutions 10

Smart Web Application for Recommending the Selection of Equi...

引用

10th International Conference on Digital Arts, Media and Technology and 8th ECTI Northern Section Conference on Electrical, Electronics, computer and Telecommunications engineering, ECTI DAMT and NCON 2025

作者： Khongtuan, Tanarin Mekruksavanich, Sakorn University of Phayao Technology and Digital Data Managementc School of Information and Communication Technology Phayao Thailand University of Phayao School of Information and Communication Technology Department of Computer Engineering Phayao Thailand

ISBN: (纸本)9798331543273

Higher education institutions strive to improve the quality of instruction and research to prepare students with essential 21st-century competencies. They promote academic and professional growth through teaching, research initiatives, community engagement, and the preservation of cultural values. One key tool in this effort is an educational resource recommendation system, critical in boosting students' academic outcomes, stimulating engagement in learning activities, and elevating educational standards. This study presents the design and evaluation of a personalized recommendation system for online educational resources, leveraging web technologies and mining techniques integrated within a digital learning infrastructure. The proposed system enhances the intelligence and adaptability of the network-based educational platform, caters to students' personalized learning requirements, and streamlines the process of accessing relevant information by minimizing the time required for resource discovery. © 2025 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

CNN-DBO: Dung Beetle Optimization Based Urban Area Change Detection Using Satellite Images

CNN-DBO: Dung Beetle Optimization Based Urban Area Change De...

引用

Computational, Communication and Information Technology (ICCCIT), International Conference on

作者： Jambukeshwar Pujari Javed Wasim Aprna Tripathi Department of Computer Engineering and Applications Mangalayatan University Aligarh India Department of Data Science Engineering Manipal University Jaipur India

ISBN: (数字)9798331512965

ISBN: (纸本)9798331512972

In recent years, Geographic Information Systems (GIS) have garnered a significant deal of interest for their ability to detect changes in metropolitan areas. One of the uses of change detection in satellite photographs is in the field of urban planning. Other applications include environmental monitoring and remote surveillance. A number of different approaches have been suggested in recent times for the purpose of automatically identifying alterations in the land cover based on GIS photographs. However, due to poor texture, cluttered context, and considerable object scale disparities, the convolutional neural network (CNN) method is only partially successful in capturing the context from geographic information systems (GISs). This is despite the fact that it remains an effective method for detecting change in urban environments. The article presents the construction of a CNN-based change detection model using the utilization of Dung Beetle Optimization (DBO). The DBO algorithm is used to adjust the loss parameter in order to increase the overall performance. The approach that was proposed makes use of the Onera satellite data set and displays an overall accuracy of 97.50% percent. In light of this, it appears that the strategy that is proposed is both very efficient and effective.

关键词： Accuracy Surveillance Urban planning Land surface Satellite images Scattering parameters Convolutional neural networks Environmental monitoring Optimization Geographic information systems

来源：评论

学校读者我要写书评

暂无评论

Opticurve: an optimized informer-curvelet framework for enhanced hyperspectral image segmentation and classification

引用

International Journal of Information Technology (Singapore) 2025年 1-16页

作者： Shaw, Kailash Wou Onn, Choo Li, Baihua Department of Computer Science and Engineering (AIML) Vishwakarma Institute of Technology Maharashtra Pune 411037 India Faculty of Data Science and Information Technology INTI International University Persiaran Perdana BBN Putra Nilai Negeri Sembilan Nilai 71800 Malaysia Department of Computer Science Loughborough University Loughborough LE11 3TU United Kingdom

Hyperspectral image (HSI) classification is crucial for applications in climate action, land use analysis, disaster risk reduction, and informed decision-making, given the complex spatial and spectral variations inherent in HSI data. Traditional methods struggle with accurately capturing these variations, necessitating more advanced techniques. This work introduces an Optimized Linformer-Curvelet (OptiCurve) Framework that integrates CNN-based feature extraction, Curvelet Transform for spatial detail capture, and Linformer for efficient feature representation. By combining these techniques, the model enhances HSI segmentation and classification, supporting improved outcomes in critical areas like environmental monitoring and disaster response. The framework is validated on four standard HSI datasets-Indian Pines, Pavia University, Kennedy Space Center, and Houston University-showing significant performance improvements over existing methods. © Bharati Vidyapeeth's Institute of computer Applications and Management 2025.

关键词： Climate action Disaster risk reduction Feature extraction Hyperspectral image classification Land use Linformer-Curvelet transform

来源：评论

学校读者我要写书评

暂无评论

Improving Medical Imaging Diagnostics with Deep Convolutional Networks for Early Detection and Treatment

Improving Medical Imaging Diagnostics with Deep Convolutiona...

引用

2025 International Conference on Computing for Sustainability and Intelligent Future, COMP-SIF 2025

作者： Krishnakumar, K. Gurrapu, Omprakash Reshma, P. Krishnammal, P. Muthu Khan, Huma Qamar Amane, Ninad Saveetha School of Engineering Chennai India Volvo Trucks North America NC United States Dhanalakshmi Srinivasan College of Engineering Department of Artificial Intelligence and Data Science Coimbatore India VIT-AP University Amaravati India Joginpally B R Engineering College Department of Computer Science and Engineering Hyderabad India Bms Institute of Technology and Management Department of Ai&ml Bangalore India

ISBN: (纸本)9798331538538

Diagnostic imaging is an important technique which helps in diagnosing several diseases at the initial stage in order to take necessary treatments. Nevertheless, conventional techniques tend to have issues with regard to precision, speed, and quantitatively assessing multidimensional medical information. In this paper, we reveal the potential of deep convolutional networks (DCNs) in the field of medical image diagnostic. It means that, with the help of deep learning algorithms DCNs can learn meaningful features of medical images and improve diagnostic accuracy and speed. The near proposed technique involves the use of deep convolutional network model to analyse medical images for diagnosis of diseases such as cancer, heart diseases and neurological disorders. The obtained experimental results demonstrate that the presented model has the highest accuracy of 96.5% with very high sensitivity and specificity coefficients compared to other methods. Further, the interpretability of the proposed DCN model and different aspects of it are discussed to support clinical validation. Through this research, the effectiveness of deep learning in revolutionizing the diagnosis for medical imaging diagnostics while early disease detection and treatment is established. © 2025 IEEE.

关键词： Neuroimaging

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：