检索结果-内蒙古大学图书馆

Conference of Recent Trends and Applications of Soft Computing in engineering, RTASCE 2024

作者： Selimovic, Mirza Almisreb, Ali Abd Ismail, Nurlaila Amanzholova, Saule Faculty of Computer Science and Engineering International University of Sarajevo Sarajevo Bosnia and Herzegovina College of Engineering Universiti Teknologi MARA Selangor Shah Alam Malaysia Department of Cybersecurity International Information Technology University Almaty Kazakhstan

ISBN: (纸本)9783031828805

The era of cancer diagnosis and treatment can change dramatically through Artificial Intelligence (AI). The present paper looks into AI's transformative attributes alongside the barriers and constraints that need to be solved for clinical integration to be successful. We discuss how AI-assisted solutions can help target therapeutic regime investigation and speed up medical decision-making in different medical fields related to oncology. Next, we highlight the challenges that harnessing AI faces like data standardization, ethical matters, and the level of accuracy of the data and adaptability of AI models. In summary, we underline the necessity of international cooperation, the importance of XAI (explainable AI) for establishing trust, and the conduct of the research in a manner that involves clinical trials and real-time demonstration in patients to guarantee database safety and usefulness in cancer care. AI can change the treatment world of cancers by combatting these obstacles and moving onto new ways. Such possibilities entail more accurate diagnosis, effective therapy, and hopefully, improved outcomes for the patients in the end. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Theranostics

来源：评论

学校读者我要写书评

暂无评论

Exploring the Dark Side: A Systematic Review of Generative AI’s Role in Network Attacks and Breaches

Exploring the Dark Side: A Systematic Review of Generative A...

引用

Conference of Recent Trends and Applications of Soft Computing in engineering, RTASCE 2024

作者： Kurtović, Hamza Šabanović, Esma Almisreb, Ali Abd Saleh, Mohammed A. Ismail, Nurlaila Faculty of Computer Science and Engineering International University of Sarajevo Sarajevo Bosnia and Herzegovina Department of Cybersecurity International Information Technology University Almaty Kazakhstan College of Engineering Universiti Teknologi MARA Selangor Shah Alam Malaysia

ISBN: (纸本)9783031828805

Generative artificial intelligence has a paradoxical nature, which on the one hand brings innovative breakthroughs, and on the other hand brings with it a series of growing challenges. Processing of natural language, computer vision and generating creative content has been significantly changed and redefined, and therefore its darker background emerges through exploitation in cybercrime, which increases the complexity of protecting network systems and infrastructure. The paper explores the conflicting characteristics of generative artificial intelligence in the field of cybersecurity, focusing on the troubling issues it creates. With the advancement of generative artificial intelligence, powerful tools have been discovered to orchestrate new types of cyberattacks, and such attacks threaten not only the confidentiality and integrity of data, but also pose significant threats to business viability and national security. The research conducts a thorough analysis of the literature to explore the role of generative artificial intelligence in these attacks, highlighting its dual function as an enabler of technological progress and a facilitator of cyber risk. An in-depth examination of the vulnerabilities present in network systems and applications that are particularly vulnerable to generative attacks driven by artificial intelligence are sought to be addressed in the paper. Additionally, it assesses future defense methods and technological breakthroughs with the potential to reduce the dangers associated with generative artificial intelligence in the digital world, and aims to provide a special perspective on the dynamic interaction between generative artificial intelligence and cybersecurity issues by analyzing and studying previous research and emphasizing the need to create strong and effective solutions. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Optimizing Deep Learning Models through Spatial Attentive Architectural Enhancements and Binarization Techniques 5

Optimizing Deep Learning Models through Spatial Attentive Ar...

引用

5th International Conference on Emerging Systems and Intelligent Computing, ESIC 2025

作者： Saha, Bishnu Pada Dash, Satya Ranjan Bandyopadhyay, Mainak Barra, Paola Hoang, Vinh Truong Kiit D.U. School of Computer Engineering Bhubaneswar India Kiit D.U. School of Computer Applications Bhubaneswar India University of Naples 'Parthenope' Department of Science and Technology Italy Hcmc Open University Faculty of Information Technology Viet Nam

ISBN: (纸本)9798331522100

Attention mechanisms in vision applications of the computer world dynamically adjust feature weights to amplify the model's capability to perceive information. This adaptive recalibration improves the overall effectiveness of the model. Spatial attention has seen widespread use to boost the efficiency of convolutional neural networks by enhancing their ability to model spatial information. This approach significantly improves CNNs' spatial representation capabilities. Along this line of research, a novel binarized-attention module is drafted by taking spatial attention into consideration. Binary neural networks, which significantly reduce storage and computational requirements, are a promising approach for deploying deep models on resource-constrained devices. This technique offers efficiency in scenarios with limited resources. In this paper, we hereby implemented our algorithm of binarizing the spatial attention module and obtained diverse findings, demonstrating significant improvements in accuracies with fewer classes and degradation of accuracies with higher classes. Various experimental findings reveal that our technique delivers better accuracy with dataset having 10 classes but low accuracy with the one having 100 classes. Additionally, architectural optimizations, including the adoption of deeper networks like ResNet50, contribute to better handling of complex data patterns. While binarization offers computational efficiency, it often results in a trade-off with accuracy. However, selective binarization of specific network layers can mitigate this issue, maintaining a balance between performance and resource utilization. This study provides insights into the synergistic effects of these techniques, offering a pathway for developing efficient and accurate deep learning models suitable for deployment in resource-constrained environments. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of State-of-the-Art Deep Neural Network on High-Resolution Medical Images

A Comparative Study of State-of-the-Art Deep Neural Network ...

引用

Computing and information technology (ICCIT-1441), 2020 International Conference on

作者： Mohammed M Alenazi Ahmad J. Alkhodair Department of Computer Engineering Faculty of Computers and Information Technology University Of Tabuk Tabuk Saudi Arabia

ISBN: (数字)9798350353839

ISBN: (纸本)9798350353846

The growing accessibility and storage of high-resolution chest X-ray images in contemporary hospitals have generated unparalleled prospects for data-driven decision-making in healthcare. Nonetheless, the efficient application of deep learning models for precise diagnosis is hindered by the complex features and fine details inherent in these images. This study aims to tackle these problems by deploying and evaluating three sophisticated deep neural networks-Inception-ResNetV2, ResNet152, and DenseNet201-utilizing a meticulously selected dataset of chest X-ray pictures. The efficacy of neural networks is evaluated by many metrics, including accuracy, precision, recall, Fl-score, and AUC-ROC, which illustrate their proficiency in picture classification tasks with high precision and accuracy. This study's findings yield significant insights into the strengths and shortcomings of each network, presenting possible opportunities for improving high-resolution image classification. Ultimately, these enhancements may provide more efficient and prompt diagnosis in healthcare environments.

关键词： Measurement Training Accuracy Transfer learning Artificial neural networks Radiology X-ray imaging Medical diagnostic imaging Biomedical imaging Image classification

来源：评论

学校读者我要写书评

暂无评论

A dynamic model using k-NN algorithm for predicting diabetes and breast cancer

引用

computers in Biology and Medicine 2025年第Pt B期192卷 110276-110276页

作者： Al-Khamees, Hussein A.A. Sani, Nor Samsiah Gifal, Ahmed Sileh Liu, Luan Xiang Wei Esa, Mohd Isrul Computer Techniques Engineering Department College of Engineering and Technology Al-Mustaqbal University Babil51001 Iraq Center for Artificial Intelligence Technology Faculty of Information Science and Technology Universiti Kebangsaan Malaysia Selangor43600 Malaysia Department of Information Technology College of Computer Science and Information Technology University of Kerbala Karbala56001 Iraq

Healthcare remains a critical focus due to its direct impact on human well-being. Diabetes, currently the fastest-growing chronic disease globally, poses severe health risks, including cardiovascular complications and kidney failure. Simultaneously, breast cancer has become the most prevalent cancer among women, particularly those in their 40s, surpassing other types. Early detection and diagnosis of these two diseases remain a substantial challenge, yet they are crucial for reducing mortality rates. Machine learning algorithms emerged as powerful tools in healthcare for disease classification and prediction, with the k-nearest neighbors (k-NN) being one of the most widely used supervised learning algorithm. Different traditional machine learning methods have been proposed, which are heavily specialized for specific datasets. More deeply, traditional k-NN relies on a static k-value, which may not provide optimal results across diverse datasets. This paper proposes a dynamic k-NN model that adjusts ‘k’ value based on local data characteristics, enhancing prediction accuracy. The proposed model is testing on two publicly available datasets;PIMA Diabetes and Breast Cancer Wisconsin (BCW) datasets. Our results are evaluated using different metrics that are;accuracy, precision, recall, F1_score, and execution time. The results of these metrics are as follows;(81.17%, 97.37%), (83.33% 100%), (54.55%, 86.05%), and (65.93%, 92.5%) for PIMA and BCW datasets respectively. These results demonstrate that the proposed model outperformed several state-of-the-art models. Thus, further highlighting its effectiveness and efficiency in medical data classification. © 2025

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Machine Learning and Deep Learning for Disaster Prediction

A Comparative Study of Machine Learning and Deep Learning fo...

引用

Computational Intelligence Approaches and Applications (ICCIAA), International Conference on

作者： Waleed Amer Ola Nasir Ala Hamarsheh Ali Mahmoud Ali Amani Abu Zaid Walaa Shtayah Department of Cyber Secyrity Faculty of Information Technology Zarqa University Zarqa Jordan Department of Computer Science Faculty of Information Technology Zarqa University Zarqa Jordan Department of computer science Faculty of Information Technology Arab American University Department of Computer Network Faculty of Engineering Technology Al-Balqa Applied University Amman Jordan Department of Artificial Intelligence Faculty of Information Technology Zarqa University Zarqa Jordan

ISBN: (数字)9798331523657

ISBN: (纸本)9798331523664

The analytical procedure known as Disaster Prediction (DP) makes estimates regarding future incident and disaster events before they actually occur. The present research seeks to determine which method produces the best results for DP. The research finds that Deep Learning surpasses Machine Learning and Artificial Intelligence methods when predicting disaster occurrence including or excluding events. The results indicate Deep Learning stands as the top DP method. CNN turned out to be the DL model with the best performance results which produced Accuracy at 0.993 and Precision at 0.986 along with Recall at 0.978. Among the models tested the LSTM model performed as the runner-up with accuracy reaching (0.975), precision at (0.959), while recall obtained (0.992). The research shows how DL technologies prove advantageous for disaster risk assessment plus their capability for developing proactive disaster response strategies.

关键词： Deep learning Accuracy Disasters Risk management Long short term memory Computational intelligence

来源：评论

学校读者我要写书评

暂无评论

Lithium Battery SOH Estimation: A Novel Octave and LSTM Hybrid Neural Network Approach

Lithium Battery SOH Estimation: A Novel Octave and LSTM Hybr...

引用

Iranian Conference on Renewable Energy and Distributed Generation (ICREDG)

作者： Seyed Mohammadreza Mousavi Amirhossein Rahimian Zarif Javad Hamidzadeh Faculty of computer engineering and information technology Sadjad University Mashhad Iran Faculty of Electrical and Biomedical Engineering Sadjad University Mashhad Iran

ISBN: (数字)9798331525132

ISBN: (纸本)9798331525149

The lithium battery (LIB) has emerged as a prominent area of research in energy and industrial applications, due to its superior energy density and efficient energy delivery capabilities. This study addresses the critical requirement for accurate State of Health (SOH) estimation as a significant challenge. The primary objective of this study is to utilize key battery health characteristic parameters to improve the accuracy and computational speed of SOH. Significant gaps have been identified in recent methodologies, particularly in terms of SOH estimation accuracy, computational speed, and simulation parameters. To address these limitations, a novel hybrid neural network (NN) approach is proposed, integrating octave convolution (OCT) and long short-term memory (LSTM). To demonstrate the effectiveness of the proposed method in the optimization process, a comparative analysis is conducted against Convolutional Neural Networks (CNN), OCT, LSTM, and CNN-LSTM architectures. The results indicate a significant reduction in the mean squared error (MSE), decreasing from 80.21 percent in CNN to 0.0758 percent in the proposed OCT-LSTM model. Furthermore, the root mean square error (RMSE) exhibits a substantial reduction of 64.91 percent and 58.14 percent compared to the LSTM and CNN-LSTM models, respectively. The simulation parameters used in this study were reduced from 41,228 for the CNN-LSTM model to 38,668 for the OCT-LSTM model. Empirical results show that the proposed method outperforms state-of-the-art methods in the number of parameters, MSE, RMSE, and estimation accuracy. These findings highlight the method's enhanced efficiency, computational speed, and precision, emphasizing its potential as a significant advancement in this domain.

关键词： Renewable energy sources Accuracy Convolution Computational modeling Estimation computer architecture Lithium batteries Convolutional neural networks Root mean square Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Comparison between Single-Input and Multi-Input Classification with the Application of Canny Feature Extraction and Classification Algorithms on the Toraja Buffalo Dataset 19

Comparison between Single-Input and Multi-Input Classificati...

引用

19th International Conference on Ubiquitous information Management and Communication, IMCOM 2025

作者： Manga, Abdul Rachman Nanda, Assyahrin Handayani, Anik Nur Herwanto, Heru Wahyu Asmara, Rosa Andrie Lantara, Dirgahayu Department of Computer Science Universitas Muslim Indonesia Makassar Indonesia Department of Electrical Engineering Universitas Negeri Malang Malang Indonesia Information Technology Department State Polytechnic of Malang Malang Indonesia Faculty of Industrial Engineering Universitas Muslim Indonesia Makassar Indonesia

ISBN: (纸本)9798331507817

Data classification plays a crucial role in artificial intelligence, particularly in enhancing model accuracy. This study focuses on classifying Toraja buffalo, a livestock breed with significant cultural importance in South Sulawesi, Indonesia. While the Single Input Approach is commonly used for classification, it often fails to capture all the necessary attributes to effectively distinguish between racial traits. Therefore, this research aims to evaluate the effectiveness of a multi-input approach, which integrates multiple data inputs to improve classification performance compared to the Single Input method. We employed four classification techniques: K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Naïve Bayes, and Decision Tree, using both Single Input and Multi Input configurations. Model performance was assessed through Precision, Recall, F1 Score, and Accuracy metrics. The findings indicate that the Multi Input approach consistently outperformed the Single Input method. Notably, KNN achieved its best performance with Multi Input, recording an F1 Score of 0.7263 and an Accuracy of 0.7333, significantly surpassing the results obtained from Single Input. Similarly, SVM also demonstrated substantial performance enhancements with Multi Input. Overall, the study highlights the importance of incorporating a wider array of informative data to enhance the model's capability in accurately classifying specific categories, with KNN showing the most pronounced improvements. © 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

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

Enhancing Healthcare Data Security: Computational Efficiency of Blockchain-Based Digital Signatures 5th

Enhancing Healthcare Data Security: Computational Efficiency...

引用

5th Doctoral Symposium on Computational Intelligence, DoSCI 2024

作者： Xu, Li Goyal, S.B. Rajawat, Anand Singh Niranjala, T. H. A. Shyama Heshini City Graduate School City University Petaling Jaya46100 Malaysia Nanchang Institute of Science and Technology Nanchang China Faculty of Information Technology City University Petaling Jaya46100 Malaysia School of Computer Science and Engineering Sandip University Nashik India

ISBN: (纸本)9789819771776

This study aims to examine the computational efficiency of blockchain-based digital signature technologies with respect to healthcare data security. When thinking about the revolutionary opportunities and risks posed by healthcare data digitization, concerns regarding data privacy and security have come to the forefront. Blockchain technology, which is both decentralised and immutable, offers a promising alternative. Two of its primary uses, data integrity and identity authentication, are made possible by digital signature systems. We conducted a comprehensive analysis to find out how efficient different protocols are in healthcare computing. Among these protocols were EdDSA, ECDSA, and Schnorr signatures. Our research indicates that efficiency is significantly affected by protocol selection. Despite the strong security it provides, data validation delays may occur due to the increased processing expense generated by ECDSA. Schnorr signatures and EdDSA are viable solutions that offer a reasonable compromise between security and efficiency. By delving into optimization methodologies and associated difficulties, this research paved the road for the ethical application of blockchain technology in healthcare. The healthcare industry, policymakers, and IT developers all benefit from our study when it comes to selecting and improving methods for secure and efficient data storage. This study uniquely examines the computational efficiency of blockchain-based digital signature protocols in healthcare data security, addressing optimization methodologies and highlighting the suitability of Schnorr signatures and EdDSA. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Electronic health record

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：