检索结果-内蒙古大学图书馆

2024 International Conference on Distributed Systems, computer Networks and Cybersecurity, ICDSCNC 2024

作者： Naidu, D J Samatha Jain, Upma Shruthi, S. Rao, K. B. V. Brahma Iqbal, Syed Mohammad Uzair Natrayan, L. Annamacharya Pg College of Computer Studies Department of Master of Computer Applications India Graphic Era Deemed to Be University Department of Computer Science & Engineering Dehradun India Bms Institute of Technology and Management Department of Artificial Intelligence and Machine Learning Bengaluru India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering India Symbiosis Law School Department of Law Pune India Simats Saveetha School of Engineering Department of Mechanical Engineering India

ISBN: (纸本)9798350375442

The Internet of Things (IoT) enables intelligent data exchange across many kinds of interconnected devices in a diverse and unpredictable physical setting. The Internet of Things (IoT) network used in this study is a cluster-based sensor network that includes a base station and an application server that offers various services in a cloud setting. In this setting, assaults may occur in both device-to-device and user-to-device communication. For pervasive devices with limited resources, the use of conventional encryption techniques to address this problem is not practical. In addition, the majority of current trust-based security solutions either address the user level or the devices level. Therefore, this study aims to tackle environment-specific security concerns at the device and user levels in light of the environment's inherent dynamic and dispersed nature. This research explored the usage of a Trust Based Security Framework (TBSF) and Reputation Based Systems in the Internet of Things (IoT) to accurately describe the actions of devices and users. Fuzzy logic was used to calculate both the device trust and the user trust. A trust-based access control system, secure cluster head selection, and safe routing were all built using these trust values. At first, the security of device-to-device communication was addressed by the design and effective implementation of the Trust Aware Device Access Control System (TADACS). © 2024 IEEE.

关键词： Access control

来源：评论

学校读者我要写书评

暂无评论

Gaussian Differential Privacy Integrated Machine Learning Model for Industrial Internet of Things

引用

SN computer science 2023年第5期4卷 454页

作者： Lazar, Arokia Jesu Prabhu Soundararaj, Sivaprakash Sonthi, Vijaya Krishna Palanisamy, Vishnu Raja Subramaniyan, Vanithamani Sengan, Sudhakar Department of Computer Science and Engineering AI & ML CMR Institute of Technology Telangana Hyderabad 501401 India Department of Software Systems School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore 632014 India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram 522502 India Department of Computer Science and Engineering Kongu Engineering College Tamil Nadu Perundurai 638060 India Master of Computer Applications M. Kumarasamy College of Engineering Tamil Nadu Karur 638060 India Department of Computer Science and Engineering PSN College of Engineering and Technology Tamil Nadu Tirunelveli 627152 India

Agriculture, energy, mining, healthcare, and transportation are a few of the top industries transformed by the industrial internet of things (IIoT). Industry 4.0 mainly relies on machine learning (ML) to use the vast interconnectedness and large amounts of IIoT data that IIoT primarily drives. ML approaches are trained on confidential data generated by the IIoT environment often exposes privacy to adversarial assaults. Blockchain-based ML is established in the proposed secured IIoT research work to safeguard and enhance privacy. This research proposes a Gaussian differential privacy-integrated machine learning model (GDPIMLM), created for a scalable and controlled IIoT system, fully connected (FC) layer, implemented blockchain benefits to create a privacy-preserving mechanism while considering other limitations and reasonable time. A probability test using two altered Gaussian distributions (GD) forms the basis for defining Gaussian differential privacy (GDP). Due to a central restriction theorem for differential privacy, GDP is the primary privacy term within the family of Federal differential privacy (f-DP) policies. Ethereum is used to implement experimental evaluations. Data collections show that the recommended method enhances digital data privacy with industry-leading security without reducing performance. The performance analysis of the proposed model of secured industrial internet of things (IIoT) is studied using the accuracy of comparison with existing methods and for diverse distributed entities (DE). The proposed secured IIoT attains a minimal time consumption (TC) of 790 Sec—the highest accuracy of 92%, outperforming the existing method. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Blockchain Industry Industry 4.0 Learning Privacy Security Smart objects

来源：评论

学校读者我要写书评

暂无评论

Transformative Trends in Reinforcement Learning: From Deep Q-Learning to Real-World applications 2

Transformative Trends in Reinforcement Learning: From Deep Q...

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Mani, Chandra Sharma, Tarun Kumar Yadav, Kanchan Gupta, Divya Raj Kumar Goel Institute of Technology Computer Science & Engineering UP Ghaziabad India Abes Engineering College Department of Computer Applications UP Ghaziabad India Gla University Department of Electrical Engineering UP Mathura India Miet Department of Bca UP Meerut India

ISBN: (纸本)9798350371055

Reinforcement studying (RL) is a type of machine studying that maximizes an agent's cumulative praise in an environment. As such, it has been more and more used to address a ramification of sequential selection-making issues successfully. Currently, there were most important breakthroughs within the RL space that have led to expanded research activity and the development of several novel techniques and packages. Those transformative traits include deep learning, model-free exploration, off-policy gaining knowledge of hierarchical techniques, meta-gaining knowledge of multi-agent training, deep reinforcement learning (DRL), and transfer learning. These new strategies to RL allow for the development of more efficient and powerful algorithms, which in flip allow more a hit education and alertness of reinforcement mastering marketers in lots of one of a kind domain names. Similarly, those additives of RL permit faster, more flexible, and stronger schooling for RL marketers. As a result, RL is rapidly turning into a part of many one of a kind areas of studies that require powerful choice-making systems, inclusive of robotics, herbal language processing, and healthcare. © 2024 IEEE.

关键词： Environment Healthcare Hierarchical Reinforcement Strategies

来源：评论

学校读者我要写书评

暂无评论

Exploring the Power of Deep Learning in Anomaly Detection: A Comprehensive Review and Analysis 12th

Exploring the Power of Deep Learning in Anomaly Detection: A...

引用

12th International Conference on Soft Computing for Problem Solving, SocProS 2023

作者： Kumar, Gaurav Kumar, Ankit Pandy, Saroj Kumar Singh, Kamred Udham Singh, Teekam Kumar, Lalan Choudhury, Tanupriya Department of Computer Engineering and Applications GLA University UP Mathura India School of Computing Graphic Era Hill University Dehradun India Department of Computer Science and Engineering Graphic Era Deemed to be University Dehradun India Department of Master of Computer Application GL Bajaj Institute of Technology and Management Greater Noida India Department of Computer Science and Engineering University of Petroleum and Energy Studies Dehradun India

ISBN: (纸本)9789819732913

This paper aims to provide a comprehensive overview of existing and state-of-the-art fraud and intrusion detection strategies, specifically focusing on incorporating neural networks. We begin by discussing the fundamental concept of data mining and its significance in detecting anomalies. By leveraging advanced machine learning and neural network techniques, we can effectively uncover subtle patterns and irregularities within complex datasets. We explore how the development of anomalies has enhanced our ability to identify and mitigate various threats, such as malware attacks and unlawful practices. Traditional detection strategies have proven effective, but as deep learning progresses, we uncover new opportunities and insights that can significantly enhance the accuracy and efficiency of anomaly detection systems. Throughout this study, we delve into the most cutting-edge approaches, ranging from broad neural networks to shallower architectures, and their applicability to fraud and intrusion detection. We analyze the strengths and limitations of these strategies, shedding light on their performance characteristics, scalability, and interpretability. By addressing these key issues, we aim to provide a comprehensive summary of the latest fraud and intrusion detection advancements driven by deep learning methodologies. This research contributes to the broader understanding of data mining's potential in uncovering anomalies and bolstering security measures across diverse domains. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

引用

1st International Conference on Computational Intelligence for engineering and Management applications, CIEMA 2022

作者： Anand Kumar, M. Purohit, Kamlesh Chandra Singh, Anuj Department of Computer Applications Graphic Era Deemed to be University Dehradun India Department of Computer Science Graphic Era Deemed to be University Dehradun India Department of Computer Science and Engineering Graphic Era Deemed to be University Dehradun India

ISBN: (纸本)9789811984921

The concept of bringing fundamental theories and analytical procedures to medicine and biology is known as biomedical engineering. Bio-artificial intelligence medical engineering is one of the newest and fastest-growing branches of research. From the adoption of medical devices to diagnostic expert systems, it can be profitable in the field of healthcare. These gadgets and expert systems generate data that are multidimensional and erratic. The use of deep learning (DL) algorithms in those devices will be useful for signal analysis and disease detection. Multiple levels of neural networks are used in DL, which are a subset of machine learning. It can learn features on its own. Strokes are one of the deadly diseases worldwide, impacting a huge percentage of the population. Stroke-related diseases require immediate medical attention, which requires emergency treatments. If it was treated in the initial stages, then brain injury and other consequences can be avoided. The main objective of this work was to evaluate different machine learning algorithms to find a suitable approach for stroke-related diseases prediction applications. This research work evaluates different machine learning algorithms, namely logistic regression, random forest, support vector machine (SVM), KNN, and the decision tree for predicting and identifying stroke and its related diseases. Finally, deep belief networks are applied for the symptom dataset to get results that are more accurate. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

An Improved Reversible Data Hiding Scheme Based on Referred Frequencies for a VQ Compressed Index 2

An Improved Reversible Data Hiding Scheme Based on Referred ...

引用

2nd International Conference on Machine Vision, Image Processing and Imaging Technology, MVIPIT 2024

作者： Hwang, Min-Shiang Fatima, Kanza Wang, Yu-Lun Chan, Chi-Shiang Wu, Chia-Chun Department of Computer Science & Information Engineering Fintech and Blockchain Research Center Asia University Taichung Taiwan Department of Computer Science & Information Engineering Asia University Taichung Taiwan Department of Management Information Systems National Chung Hsing University Taichung Taiwan Department of M-Commerce and Multimedia Applications Asia University Taichung Taiwan Department of Computer Science and Information Engineering National Quemoy University Kinmen Taiwan

ISBN: (纸本)9798331543037

Nowadays, we usually compress images before uploading them to social media. However, images on social media can easily be copied, so embedding secret messages in compressed images has become increasingly popular. There are many compression methods, such as Huffman, VQ, ZIP, AMBTC, RAR, JPEG, etc. In this article, we propose an improved data hiding in VQ compression method to achieve better capacity and high quality. Experimental results show that our data-hiding approach is practical. ©2024 IEEE.

关键词： compressed image data hiding LSB matching reversible data hiding steganography vector quantization

来源：评论

学校读者我要写书评

暂无评论

Enhanced Camouflage Detection Using Advanced Image Processing Techniques for Real-Time Object Recognition and Pattern Differentiation 5

Enhanced Camouflage Detection Using Advanced Image Processin...

引用

5th International Conference on Sustainable Communication Networks and Application, ICSCNA 2024

作者： Manikandan, G. Deepa, R. Jayalakshmi, V. Thilakavathy, P. Surendran, R. St. Joseph's College of Engineering Anna University Department of Artificial Intelligence and Machine Learning Chennai India School of Computing SRM Institute of Science and Technology Department of Computing Technologies Chennai India SRM Institute of Science and Technology Department of Computer Science and Applications Chennai India Vels Institute of Science and Engineering Vels Institute of Science Technology and Advanced Studies Computer Science and Engineering Chennai India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Chennai India

ISBN: (数字)9798331530013

ISBN: (纸本)9798331530013

The identification of objects that blend in with their surroundings has long been a concern in fields including defence, wildlife monitoring, and surveillance due to the difficulty of detecting such objects. This finding is significant because it could greatly enhance our capacity to detect camouflaged objects, transforming the field of real-time object detection. Existing image processing methods often fail miserably when adequately capturing this aspect. This dissertation's primary focus is identifying devices with complicated patterns, legacy interference, and inadequate contrast;nonetheless, in disguised scenarios, all of these features cause identification to be unsuccessful. This research often suggests a new approach called the Linear Edge Detecting Scheme for Camouflaged Object Detection (LEDS-COD) in these difficult cases. The LEDS-COD system can enhance item visibility in low-comparison settings by highlighting critical edges and descriptions. Pattern differentiation methodologies and modern facility-side recognition techniques are combined to accomplish this goal. The approach successfully differentiated items because it zeroed in on texture and comparative details that would otherwise go unnoticed by humans or advanced algorithms. LEDS-COD is useful in many areas, including the Navy, autonomous surveillance systems, and animal protection, where the real-time identification of hidden devices is essential. Results from a simulation study using various datasets, including concealed objects, show that LEDS-COD surpasses conventional detection methods in recognition accuracy, processing speed, and perseverance. The recommended technique exceeded the requirements for obtaining improved object detection estimates for challenging conditions like those with complex backdrops and changing illumination. According to this study, LEDS-COD can be devastating in improving real-time camouflage detection. © 2024 IEEE.

关键词： Accuracy Image processing Surveillance Image edge detection Wildlife Lighting Object detection Real-time systems Object recognition Protection

来源：评论

学校读者我要写书评

暂无评论

A Patient Response Prediction System using Multi-Scale Feature Fusion Semantic Segmentation Network and Med-YOLO 1

A Patient Response Prediction System using Multi-Scale Featu...

引用

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

作者： Shankari, S. Uma Ali, Hassan Mohamed Durga, Boya Vijaya Vadivu, M. Senthil Mangaiyarkarasi, V. Srm Institute of Science and Technology Ramapuram Department of Computer Science and Applications Chennai India College of Technical Engineering the Islamic University Department of Computers Techniques Engineering Najaf Iraq Maisammaguda School of Computer Science and Engineering Hyderabad India Sona College of Technology Department of Electronics and Communication Engineering Salem India New Prince Shri Bhavani College of Engineering and Technology Department of Electronics and Communication Engineering Chennai India

ISBN: (纸本)9798350352931

Nowadays, most of the people are getting affected with various health issues such as typhoid, diabetes and cancer. A human immune system plays a crucial role in maintaining and balancing human health and reduces the risk of getting ill. Immunotherapy is a treatment which utilizes human body immunity power to fight cancer. There are many challenges in the existing models such as imbalance data, heterogenic data, uncertainties, and lack of temporal data. These challenges are resolved by imposing deep learning techniques and generating a valid information with the clinical details of patient health conditions. Therefore, a hybrid model name called Multi-Scale Feature Fusion Semantic Segmentation Network (MSSNet) and You Look Only Once (MedYOLO) for feature extraction and detection. Initially, Synthetic Minority Over-sampling Technique (SMOTE) is employed to overcome the issue of imbalanced data;further MSSNet is imposed for extracting the optimal features and detected using MedYOLO. Also, to get detailed information and generate cohort, the data collected from GSC hospital with overall details that are essential to predict the patient response to immunotherapy in cancer treatment. In the end, MSSNet-MedYOLO obtained higher accuracy of 98.16% for an effective prediction of patient response which is better than existing Convolutional Neural Network (CNN). © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Sentiment Analysis with Adaptive Neural Networks for Emotion Classification 5

Deep Learning for Sentiment Analysis with Adaptive Neural Ne...

引用

5th International Conference on Sustainable Communication Networks and Application, ICSCNA 2024

作者： Jayalakshmi, V. Thilakavathy, P. Manikandan, G. Deepa, R. Surendran, R. SRM Institute of Science and Technology Department of Computer Science and Applications Tamilnadu Chennai India Computer Science and Engineering Vels Institute of Science and Engineering Vels Institute of Science Technology and Advanced Studies Chennai India St. Joseph's College of Engineering Department of Artificial Intelligence and Machine Learning Chennai India School of Computing SRM institute of Science and Technology Department of Computing Technologies Chennai India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Chennai India

ISBN: (数字)9798331530013

ISBN: (纸本)9798331530013

In understanding human emotions, sentiment analysis has been invaluable in social media monitoring, consumer comment analysis, and psychological evaluations. Customer service, human-computer interface, and public mood comprehension depend on appropriate emotion categorisation. Despite its potential, sentiment analysis struggles with sarcasm, multimodal data integration, and emotion processing. Implementing real-time applications requires improving deep learning model computational complexity. Multimodal Optimised Emotion Analysis using Deep Learning (MOEA-DL) uses CNNs for image processing, RNNs for text., and LSTM networks for sequential audio data. This improves emotion recognition by combining modality strengths. Marketing sentiment, mental health monitoring, social media sentiment, and consumer feedback use MOEA-DL. Multimodal solutions are better than text-based ones for communicating emotion. Customer contacts, film reviews, and social media platforms are used to evaluate the proposed strategy. According to simulations, MOEA-DL categorises emotions more accurately and robustly than previous sentiment analysis methods. Its adaptive neural network lets the system learn and perform well in many cultural and language environments. © 2024 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Improved Contextual Understanding and Emotion Detection in Large-Scale Text Data with Hybrid Deep Learning Models 5

Improved Contextual Understanding and Emotion Detection in L...

引用

5th International Conference on Sustainable Communication Networks and Application, ICSCNA 2024

作者： Thilakavathy, P. Manikandan, G. Deepa, R. Jayalakshmi, V. Surendran, R. Computer Science and Engineering Vels Institute of Science and Engineering Vels Institute of Science Technology and Advanced Studies Chennai India St. Joseph's College of Engineering Anna University Department of Artificial Intelligence and Machine Learning Chennai India School of Computing SRM institute of science and technology Department of Computing Technologies Chennai India SRM Institute of Science and Technology Department of Computer Science and Applications Ramapuram Chennai India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Chennai India

ISBN: (数字)9798331530013

ISBN: (纸本)9798331530013

With the growth of large-scale text datasets from reviews, social media, and other online sources, sentiment analysis is essential for understanding public opinion. Traditional models struggle to understand complicated linguistic sentiments and interdependencies. This research could improve sentiment classification in customer feedback analysis, market sentiment predictions, and social media monitoring. Addressed issues include ambiguous language, sentence context flipping, and the need for robust models that can manage massive datasets. Contextual Detection Text Analysis Using Deep Learning (CDTA-DL) improves contextual knowledge and emotion identification in this research. RNNs and CNNs are used in the CDTA-DL approach to extract spatial and sequential information from text. CDTA-DL helps large-scale sentiment analysis detect sarcasm, implicit emotions, and many expressions. In a comprehensive simulation investigation employing open-access sentiment analysis datasets, CDTA-DL surpassed standard deep learning models in accuracy, recall, and F1 scores. The recommended strategy may increase emotion recognition and contextual understanding, making it ideal for large-scale sentiment analysis in various domains. © 2024 IEEE.

关键词： Contrastive Learning

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：