检索结果-内蒙古大学图书馆

Electricity Demand Prediction through Artificial Intelligence Methods

Electricity Demand Prediction through Artificial Intelligenc...

2024 International Conference on Sustainable Computing and Integrated Communication in Changing Landscape of AI, ICSCAI 2024

作者： Kumar, Neeraj Mittal, Tanusha Al-Jawahry, Hassan M. Bansal, Saloni Deepak, A. Deepika, N.M. Kaushik, Rohit Department of Electrical Engineering Doon Institute of Engineering and Technology Uttarakhand Rishikesh India Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun India Department of Computers Techniques Engineering College of Technical Engineering The Islamic University Najaf Iraq Department of Computer Engineering and Applications GLA University Mathura India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Tamilnadu Chennai India Institute of Aeronautical Engineering Dundigal Hyderabad India Faculty of Management SRM Institute of Science and Technology NCR Campus India

ISBN: (纸本)9798350355338

Recently accurate predictions of electricity demands have emerged from the Liberalization and commercialization of the energy area. The future energy or intelligent grid market. A better request-side management method and a shift of mindset are required for a more credible system scale estimate of up to one year. However, electricity is difficult to forecast as elements, including sociological and environmental activity and climatic influences, are affected. The two methodologies utilized to predict cargo, in general, are artificial intelligence and analytical procedures. All analytical methodologies are frequently used in regression literature: linear regression, Box-Jenkins’ methodology, and nonparametric methods. The analytical approaches function effectively in everyday settings regarding meteorological, sociological, and psychological problems but don’t give satisfying outcomes. Consequently, the period of time does not change on the basis of economic developments. Inference systems tactics are among the artificial intelligence systems. © 2024 IEEE.

关键词： Demand response

来源：评论

学校读者我要写书评

暂无评论

Sleep Stage and Sleep Disorder Detection using Spatial and Temporal Attention based Capsule Network 1

Sleep Stage and Sleep Disorder Detection using Spatial and T...

引用

1st International Conference on Software, Systems and Information Technology, SSITCON 2024

作者： Devi, R. Renuga Elavarasi, S. Anitha Venkateswarlu, Chetti Anitha, R. Ali, Hassan Mohamed Srm Institute of Science and Technology Ramapuram Department of Computer Science and Applications Chennai India Sona College of Technology Department of Computer Science and Engineering Salem India Maisammaguda Department of Electronics and Communication Engineering Hyderabad India New Prince Shri Bhavani College of Engineering and Technology Department of Information Technology Chennai India The Islamic University College of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq

ISBN: (纸本)9798350352931

Sleep is referred as a cyclic process which is the most important part in human life. The sleep disorder and its stages are observed from time waveforms such as Electroencephalogram (EEG), Electrocardiograms (ECG), and Electromyograms (EMG) while diagnosing patients. However, the existing Deep Learning (DL) based neural network used for multi-modal sleep stage and sleep disorder detection has limitations in decision making that results in inaccurate detection of sleep stage. To overcome this limitation, a Spatial and Temporal Attention based Capsule Network (STA-CapsNet) is proposed for sleep stage and sleep disorder detecting for multimodal waveforms. The proposed CapsNet model with spatial and temporal attention mechanism focuses on informative regions that helps in making decision and classifies the sleep stages accurately. Firstly, the time waveforms are acquired and preprocessed to convert the signals into Red Green Blue (RGB) images for precise classification of sleep disorders. These RGB images are fed to proposed STA-CapsNet model for classifying the six stages of sleep correctly. Experimental results of the proposed STA-CapsNet method achieved accuracy of 9 6. 8 9 %which is higher than the existing approaches such as Convolutional Neural Network (CNN) and Visual Geometry Group-16 (VGG-16). © 2024 IEEE.

关键词： Sleep research

来源：评论

学校读者我要写书评

暂无评论

SciMRC: Multi-perspective Scientific Machine Reading Comprehension 30

SciMRC: Multi-perspective Scientific Machine Reading Compreh...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Zhang, Xiao Zheng, Heqi Nie, Yuxiang Huang, Heyan Mao, Xian-Ling School of Computer Science and Technology Beijing Institute of Technology China Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications China Southeast Academy of Information Technology Beijing Institute of Technology China State Grid Smart Grid Research Institute Co. Ltd. China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong

ISBN: (纸本)9782493814104

Scientific Machine Reading Comprehension (SMRC) aims to facilitate the understanding of scientific texts through human-machine interactions. While existing dataset has significantly contributed to this field, it predominantly focus on single-perspective question-answer pairs, thereby overlooking the inherent variation in comprehension levels among different readers. To address this limitation, we introduce a novel multi-perspective scientific machine reading comprehension dataset, SciMRC, which incorporates perspectives from beginners, students, and experts. Our dataset comprises 741 scientific papers and 6,057 question-answer pairs, with 3,306, 1,800, and 951 pairs corresponding to beginners, students, and experts respectively. Extensive experiments conducted on SciMRC using pre-trained models underscore the importance of considering diverse perspectives in SMRC and highlight the challenging nature of our scientific machine comprehension tasks. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Detection and Evaluation of Cybersecurity Threats in MANET Based on AI 4

Detection and Evaluation of Cybersecurity Threats in MANET B...

引用

4th International Conference on Ubiquitous Computing and Intelligent Information Systems, ICUIS 2024

作者： Mohandas, R. Vaigandla, Karthik Kumar Sivapriya, N. Kirubasankar, K. Chennai Institute of Technology Department of Electronics & Communication Engineering Tamil Nadu Chennai India Balaji Institute of Technology and Science Department of Electronics & Communication Engineering Telangana Warangal India Cauvery College for Women Department of Computer Applications Tamil Nadu Trichy India

ISBN: (纸本)9798331529635

This research focuses on the use of AI to enhance the security of Mobile Ad-hoc Networks (MANETs), which aredecentralized and mobile wireless networks characterized by their dynamic nature. The work aims to assess the risks associated with cyber activities and identify various sorts of cyber threats, such as Distributed Denial of Service (DDoS) attacks, malware invasions, data leaks and unauthorized access attempts. This will be achieved by using Artificial Intelligence (AI)-powered algorithms and models. The objective is to enhance the accuracy in identifying and categorizing these threats, hence increasing the security and dependability of MANET networks. Anomaly detection is a supplementary protection mechanism that specifically targets the hardware and network traffic of MANETs. Implementing a monitoring strategy is necessary in order to detect any anomalous activity that might potentially indicate security vulnerabilities or attacks in the MANET setups. The primary objective is to identify and address the unique characteristics of timely detection, which may enhance the security capabilities of MANET against cyber attacks. Machine learning (ML) algorithms often demonstrate impressive performance in efficiently identifying and accurately classifying various cyber threats, including DDoS attacks, malware infiltrations, and attempted unauthorized access. This anomaly detection technology effectively identifies robot abnormalities and malicious actions in network data, while also proactively avoiding system vulnerabilities or threats. In addition, this research discovered very effective AI-based cybersecurity solutions for dynamic decentralized MANET systems. These systems were specifically designed for tasks such as street-view switching, route finding, self healing, and self configuration. © 2024 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Security Challenges in Multi-Cloud Environments: Solutions and Best Practices 7

Security Challenges in Multi-Cloud Environments: Solutions a...

引用

7th International Conference on Contemporary Computing and Informatics, IC3I 2024

作者： Madanan, Mukesh Patel, Pratik Agrawal, Prateek Mudholkar, Pankaj Mudholkar, Megha Jaganraja, V. Dhofar University Department of Computer Science Oman National Forensic Sciences University India India Marwadi University Faculty of Computer Applications Gujarat Rajkot360003 India Marwadi University Department of Computer Engineering Gujarat Rajkot360003 India Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Avadi Chennai600062 India

ISBN: (纸本)9798350350067

The aim of this research paper is to investigate how machine learning can be incorporated to improve security around multi-clouds, with specific reference to the challenges. Based on the datasets obtained from Kaggle, this study uses both unsupervised learning, more specifically the Isolation Forest technique and supervised learning, such as regression-based forecast for identifying possible security threats. The evaluation shows that through the use of ML techniques risk that originates from multi-cloud systems may be well managed while, at the same time, the utilization of cloud resources could be enhanced to produce the best results. The results make it possible to conclude that machine learning still holds a huge potential in the sphere of cloud security and provides a range of recommendations and recommendations for organizations that have to manage their multi-cloud environment. Possible future studies are devoted to the investigation of deep learning models and the incorporation of blockchain technology for more security and effectiveness of the system. © 2024 IEEE.

关键词： Cloud security

来源：评论

学校读者我要写书评

暂无评论

Real-Time Anomaly Detection in IoT Healthcare Devices With LSTM 1

Real-Time Anomaly Detection in IoT Healthcare Devices With L...

引用

1st International Conference on Artificial Intelligence for Innovations in Healthcare Industries, ICAIIHI 2023

作者： Varshney, Neeraj Madan, Parul Shrivastava, Anurag Srivastava, Arun Pratap Kumar, C Praveen Akhilesh Khan, Kumar Gla University Department of Computer Engineering and Applications Mathura India Graphic Era Deemed to Be University Department of Computer Science & Engineering Uttarakhand Dehradun India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamilnadu Chennai India Lloyd Institute of Engineering and Technology Greater Noida India Institute of Aeronautical Engineering Department of Computer Science and Engineering Telangana Hyderabad India Lloyd Law College Greater Noida India

ISBN: (纸本)9798350330915

In this study, LSTM-based models are used to investigate real-time anomaly detection in IoT healthcare equipment. The study demonstrates the way these models are incredibly successful in improving patient outcomes and data security. The results regularly show great memory, and accuracy, alongside precision, underscoring their suitability for critical care situations. While acknowledging the importance of this accomplishment, the research also points out some possible drawbacks, such as the reliance on historical data and the requirement for more model scalability and interpretability research. Recommendations cover practical implementations, cutting-edge data security safeguards, and thorough standards. Model optimization for resource-constrained IoT devices, and edge computing, as well as improved model interpretability through comprehensibility approaches and federated learning should be prioritized in future development. © 2023 IEEE.

关键词： data security interpretability IoT healthcare LSTM-based models patient outcomes real-time anomaly detection scalability

来源：评论

学校读者我要写书评

暂无评论

Scalable Data Clustering For Health Behavior Analysis In Big Data Cloud Environments 1

Scalable Data Clustering For Health Behavior Analysis In Big...

引用

1st International Conference on Artificial Intelligence for Innovations in Healthcare Industries, ICAIIHI 2023

作者： Bhardwaj, Diwakar Bordoloi, Dibyhash Deepak, A. Mayuri, K. Yadav, Dinesh Kumar Kumar, Navneet Institute of Engineering and Technology Gla University Department of Computer Engineering and Applications Mathura India Graphic Era Deemed to Be University Department of Computer Science & Engineering Uttarakhand Dehradun India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Tamilnadu Chennai India Institute of Aeronautical Engineering Department of Computer Science and Engineering Telangana Hyderabad India Lloyd Institute of Engineering and Technology Greater Noida India Lloyd Law College Greater Noida India

ISBN: (纸本)9798350330915

This work addresses the requirement for scalable data organization methods in big data cloud systems for behavioral analysis. Researchers embrace an interpretive attitude and use a deductive strategy and descriptive method to find subtle patterns in the data on health behavior. It makes use of sophisticated clustering algorithms that are tailored for based on the cloud processing and leverages additional data from numerous sources. Four unique behavioral clusters can be identified based on the results: 'Active Lifestyle Choices Enthusiasts,' 'Balanced Wellness Seekers,' 'Sedentary nevertheless Conscious Eaters,' in addition 'Erratic Healthcare Engagers.' These clusters include various levels of physical activity, nutritional preferences, and nights of sleep and offer useful information for customized therapies. The effectiveness of interpretivism in comprehending subjective sensations and the use of cyberspace for effective data processing are highlighted in critical examination. However, suggestions for more research include exploratory methods, longitudinal evaluation of data, and the incorporation of immediate information streams. This study advances the field by showing how scalable clustering algorithms in cloud systems may be used to analyze behavior related to health. A thorough framework for comprehending behavioral patterns is provided by the integration of interpretative concepts, which enhances the depth of investigation. This strategy has the potential to inform tailored healthcare plans and targeted actions, ultimately benefiting public health programs. © 2023 IEEE.

关键词： comprehending enhancing health medical smartphone apps

来源：评论

学校读者我要写书评

暂无评论

Federated Learning for Secure Healthcare Image Analysis in the Cloud 1

Federated Learning for Secure Healthcare Image Analysis in t...

引用

1st International Conference on Artificial Intelligence for Innovations in Healthcare Industries, ICAIIHI 2023

作者： Varshney, Neeraj Madan, Parul Shrivastava, Anurag Kumar, C Praveen Rao, A.L.N. Khan, Akhilesh Kumar Gla University Department of Computer Engineering and Applications Mathura India Graphic Era Deemed to Be University Department of Computer Science & Engineering Uttarakhand Dehradun India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamilnadu Chennai India Institute of Aeronautical Engineering Department of Computer Science and Engineering Telangana Hyderabad India Lloyd Institute of Engineering and Technology Greater Noida India Lloyd Law College Greater Noida India

ISBN: (纸本)9798350330915

This study investigates the use of federated learning in healthcare picture analysis with the goal of improving diagnostic precision while safeguarding patient data privacy. A specialized federated learning framework was created, showing considerable gains in precision, privacy protection, as well as computational effectiveness. Sophisticated security measures, such as access limits and encryption, successfully protected private medical picture data. Blockchain technology in addition to the suggested hybrid cloud architecture offered scalable and secure alternatives for healthcare organizations. Decision-makers can take action based on the practical ramifications. Future research ought to concentrate on customizing federated learning to particular imaging modalities, investigating edge computing applications, and evaluating the long-term advantages and difficulties in the field of healthcare. © 2023 IEEE.

关键词： Blockchain Data Privacy Federated Learning Healthcare Image Analysis Hybrid Cloud Security Measures

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Watermarking Scheme Using DWT and Haar Transform for Image Authentication 3rd

A Hybrid Watermarking Scheme Using DWT and Haar Transform fo...

引用

3rd International Conference on Advanced Computing and applications, ICACA 2024

作者： Jana, Sachchidananda Pal, Pabitra Mahadani, Asim Kumar Giri, Debasis Department of Computer Science & Applications Prabhat Kumar College Contai West Bengal Purba Medinipur721404 India Department of Computer Applications Maulana Abul Kalam Azad University of Technology West Bengal Nadia741249 India Department of Computer Science and Engineering Bankura Unnayani Institute of Engineering West Bengal Bankura India Department of Information Technology Maulana Abul Kalam Azad University of Technology West Bengal Nadia741249 India

ISBN: (纸本)9789819747986

The safe transfer and preservation of medical images is crucial in the age of digital healthcare. Watermarking medical images is an essential method of adding patient data, hospital logos, and other pertinent information to these images without compromising their confidentiality, integrity, or validity. To overcome the aforementioned difficulties, this abstract offers a unique and reliable medical image watermarking system that makes use of Particle Swarm Optimization (PSO), Discrete Wavelet Transform (DWT), and Singular Value Decomposition (SVD) approaches. There are three main phases to the suggested plan. The medical image is first broken down into its frequency components using DWT, which makes watermark embedding more effective. Subsequently, the PSO method is utilized to maximize the choice of image segments for incorporation, guaranteeing that the watermark remains undetectable and robust against diverse attacks. In the last step, the watermark’s strength is increased by using the SVD approach to embed it in the singular values of certain image blocks. Comprehensive tests are conducted to assess the efficacy of the suggested approach, taking into account performance measures like the Structural Similarity Index (SSIM) and Peak Signal-to-Noise Ratio (PSNR), as well as resistance against typical assaults such as noise addition, compression, and cropping. The testing findings show that the method effectively embeds the watermark while maintaining image quality and making sure it is robust to attack. The suggested method is appropriate for clinical and telemedicine applications as it also protects the confidentiality and integrity of patient data. By advancing the development of effective and safe medical image watermarking methods, this research helps to protect the privacy and veracity of critical healthcare data. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Discrete wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Quantum Machine Learning Driven Malicious User Prediction for Cloud Network Communications

IEEE Networking Letters

引用

IEEE Networking Letters 2022年第4期4卷 174-178页

作者： Gupta, Rishabh Saxena, Deepika Gupta, Ishu Makkar, Aaisha Singh, Ashutosh Kumar National Institute of Technology Department of Computer Applications Kurukshetra136119 India National Sun Yat-sen University Department of Computer Science and Engineering Kaohsiung804 Taiwan University of Derby Department of Computer Science and Engineering DerbyDE22 1GB United Kingdom

This letter proposes a novel malicious user prediction model based on quantum machine learning that estimates the vicious entity present in the communication system precedently before allocating the data in the distributed environments. The proposed model scrutinizes the behavior of each user and estimates probable data breaches using a developed malicious user predictor unit. The model computes essential scores associated with each user request for the learning process of the prediction unit by generating training samples. The predictor unit exploits the computational and behavioral properties of Qubits and Quantum gates for the accurate prediction of the malicious user with high precision to grant access to non-malicious data requests only. The experimental evaluation and comparison of the proposed model with state-of-the-art methods reveal that it significantly improves the security of the system up to 33.28%. © 2019 IEEE.

关键词： Forecasting

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：