检索结果-内蒙古大学图书馆

3rd International Conference on Intelligent Systems and Sustainable Computing, ICISSC 2023

作者： Sengan, Sudhakar Katbar, Nek Muhammad Kothalanka, Amarendra Shelke, Mayura Chinnathambi, Kalimuthan Sharma, Dilip Kumar Ammasai, Viswanathan Department of Computer Science and Engineering PSN College of Engineering and Technology Tamil Nadu Tirunelveli627451 India School of Mathematics and Statistics Central South University Hunan Changsha410083 China Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram522502 India Department of AI & DS AISSMS IOIT Pune411001 India Deprtment of Information Technology V.S.B. College of Engineering Technical Campus Tamil Nadu Coimbatore642109 India Department of Mathematics Jaypee University of Engineering and Technology Madhya Pradesh Guna473226 India School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore632014 India

ISBN: (纸本)9789819783540

Clinical Decision Support Systems (CDSS) have emerged as crucial tools in healthcare, leveraging vast amounts of data to aid clinicians in their decision-making processes. However, the challenge of efficiently utilizing limited labelled medical data remains. This paper introduces a novel approach using Semi-supervised DC-GAN to address this challenge. Building upon the foundational principles of Generative Adversarial Networks (GANs), this proposed model augments the capabilities of traditional semi-supervised methods, optimizing their performance in the CDSS landscape. Through extensive evaluations, they compared this approach with three widely accepted semi-supervised algorithms: MixMatch, Mean Teacher, and Π-Model. The results indicate that Semi-supervised DC-GAN enhances the data utilization process and significantly improves model training, especially when working with limited labelled datasets. This research underscores the potential of GANs in revolutionizing semi-supervised learning within CDSS, paving the way for more efficient and informed clinical decisions. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Advanced Neural Network Approach for Fetal Heart Rate Classification with Multi-Attribute Analysis 4

Advanced Neural Network Approach for Fetal Heart Rate Classi...

引用

4th IEEE International Conference on ICT in Business Industry and Government, ICTBIG 2024

作者： Rajeswari, D. Chourasiya, Prashant Sivakumar, K.K. Sahu, Neelesh Kumar Jerith, G. Gifta Singh, Pranav Mlr Institute of Technology Department of Cse Hyderabad India Ies University Ies Institute of Technology and Management Department of Computer Science & Engineering M.P. Bhopal India Mohan Babu University School of Liberal Arts and Sciences AP Tirupati India Gyan Ganga Institute of Technology & Sciences Dept of CSE-AIR MP Jabalpur India Malla Redy University Hyderabad School of Engineering Department of Ai & Ml Telangana Hyderabad India Ggits MP India

ISBN: (纸本)9798331518981

Electronic fetal monitoring is an essential diagnostic aid in pregnant women for the evaluation of fetal status and possible pathology. In this research, a sophisticated neural network model is suggested as a means for the arrangement of fetal heart rate indicators with multi attribute analysis to assist in maximizing the classification. We thus use an ANFIS that incorporates the capability of learning from the neural network on the one hand and the reasoning of fuzzy logic on the other. The system employs ECG data and the signals are processed by Independent Component Analysis method to extract the fetal signals. Further, PSD transforming of a signal and RR-interval measurements are incorporated to obtain significant signal characteristics making the discrimination more sensitive and specific. The investigational outcomes also show that the proposed model achieves a much higher overall accuracy than the traditional methods, providing an effective means for the fetal heart monitoring in practice. © 2024 IEEE.

关键词： Fetal monitoring

来源：评论

学校读者我要写书评

暂无评论

Next-Gen Human-computer Interaction: A Hybrid LSTM-CNN Model for Superior Adaptive User Experience

Next-Gen Human-Computer Interaction: A Hybrid LSTM-CNN Model...

引用

Electrical, Electronics, Information and Communication Technologies (ICEEICT), International Conference on

作者： Ravindra Changala J. Manoranjini M. Misba Shital Kakad S Sai Deepthi Ponni Valavan M Department of Computer Science and Engineering Guru Nanak Institutions Hyderabad India Department Of AI&ML Rajalakshmi Engineering College Chennai India Department CSE (AI&ML) Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of AI & DS Vishwakarma Institute of Technology Pune Maharashtra Department IT B V Raju Institute of Technology (Autonomous) Narsapur Hyderabad India Department of AI & DS K. Ramakrishnan College of Engineering Trichy Tamil Nadu India

ISBN: (数字)9798350369083

ISBN: (纸本)9798350369090

In the rapidly evolving landscape of human-computer interaction (HCI), the demand for personalized and adaptive user experiences has grown exponentially. To meet this demand, Research propose a groundbreaking approach leveraging the fusion of Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN) architectures. This hybrid LSTM-CNN model is designed to enhance adaptability, responsiveness, and user engagement across various interactive platforms. Traditional HCI models often struggle to effectively capture the dynamic nature of user behavior and preferences. By integrating LSTM and CNN, This model achieves a synergistic blend of temporal and spatial feature extraction capabilities. The LSTM component excels in capturing sequential dependencies and long-term patterns, enabling the system to learn from past interactions and anticipate future user actions. Meanwhile, the CNN component efficiently processes spatial information, extracting meaningful features from multimedia inputs such as images, videos, and text. One of the key strengths of proposed model is its adaptability to diverse user contexts and preferences. Through continuous learning and adaptation, it dynamically adjusts its interface, content, and interaction patterns to match the evolving needs and preferences of individual users. Moreover, the hybrid architecture enables real-time processing of multimodal inputs, facilitating seamless interaction across a wide range of devices and platforms. In experimental evaluations, Hybrid LSTM-CNN model demonstrated superior performance compared to baseline methods in terms of user satisfaction, engagement, and task completion rates. Furthermore, it exhibited robustness and scalability, making it suitable for deployment in real-world applications across domains such as e-commerce, entertainment, education, and healthcare. In summary, The proposed approach represents a significant advancement in HCI research, paving the way for next-generation interactiv

关键词： Human computer interaction Adaptation models Scalability Streaming media Feature extraction User experience Robustness Convolutional neural networks Long short term memory Videos

来源：评论

学校读者我要写书评

暂无评论

Advanced Hybrid Methodology for Robust Heart Disease Prediction and Feature Optimization

Advanced Hybrid Methodology for Robust Heart Disease Predict...

引用

Machine Learning and Autonomous Systems (ICmlAS), International Conference on

作者： Alekhya G Sudheer Kumar C Ouku Bhulakshmi Harikrishna T V T Ram Pavan Kumar M Boddu L V Siva Rama Krishna Department of CSE (AI&ML) G Pulla Reddy Engineering College Kurnool India Department of CSE Srinivasa Ramanujan Institute of Technology Ananthapuramu India Department of CSE Santhiram Engineering College Nandyal India Department of AI&ML Annamacharya Institute of Technology and Sciences Rajampet India Department of Computer Science Kakaraparti Bhavanarayana College Vijayawada India Department of CSE SRM University Mangalagiri AP India

ISBN: (数字)9798331505745

ISBN: (纸本)9798331505752

This research presents a novel hybrid framework for heart disease prediction, integrating advanced data preprocessing with ensemble learning to enhance diagnostic accuracy. The methodology begins with rigorous data cleansing to ensure reliability, followed by Synthetic Minority Over-sampling Technique (SMOTE) to balance class distribution. Outliers are identified and mitigated using the Z-score method, preserving data integrity. A unique Recursive Hybrid Feature Extraction (RHFE) strategy, combining filter and wrapper techniques, optimizes feature selection by reducing multicollinearity and enhancing model efficiency. Key predictive markers include age, chest pain type, maximum heart rate, ST depression induced by exercise, and major vessel count via fluoroscopy. The refined dataset is used to train an CatBoost -based ensemble model, achieving remarkable performance with 94.2% accuracy, 93.5% precision, 94% recall, and an outstanding ROC AUC score of 0.98. These results highlight the model's robustness and its potential for real-world clinical implementation in early heart disease detection and risk assessment.

关键词： Heart Accuracy Pain Data preprocessing Predictive models Feature extraction Robustness Risk management Ensemble learning Diseases

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Authentication Protocol Suitable for Constrained RFID Systems

引用

IEEE Access 2024年 12卷 61610-61628页

作者： Hosseinzadeh, Mehdi Servati, Mohammad Reza Rahmani, Amir Masoud Safkhani, Masoumeh Lansky, Jan Janoscova, Renata Ahmed, Omed Hassan Tanveer, Jawad Lee, Sang-Woong Duy Tan University Institute of Research and Development Da Nang550000 Viet Nam Duy Tan University School of Medicine and Pharmacy Da Nang550000 Viet Nam Shahid Rajaee Teacher Training University Department of Computer Engineering Tehran16788-15811 Iran National Yunlin University of Science and Technology Future Technology Research Center Douliou Yunlin64002 Taiwan School of Computer Science Tehran19395-5746 Iran University of Finance and Administration Faculty of Economic Studies Department of Computer Science and Mathematics Prague101 00 Czech Republic University of Human Development Department of Information Technology Sulaymaniyah0778-6 Iraq Sejong University Department of Computer Science and Engineering Seoul05006 Korea Republic of Gachon University Pattern Recognition and Machine Learning Laboratory Department of Ai Software Seongnam-si13557 Korea Republic of

RFID technology offers an affordable and user-friendly solution for contactless identification of objects and individuals. However, the widespread adoption of RFID systems raises concerns regarding security and privacy. Vulnerabilities such as message tampering, interception, and eavesdropping pose significant risks to the integrity of the system. This study examines the effectiveness of two recently proposed ultra-lightweight RFID authentication protocols, URASP and KUAJB, in addressing these security challenges. Surprisingly, our findings reveal that both URASP and KUAJB protocols are susceptible to secret disclosure attacks, despite their claims of providing robust security. Consequently, the development of a truly ultra-lightweight protocol that ensures adequate security becomes a formidable task. As a potential solution, the enhancement of the URASP protocol through the integration of a simple cryptographic primitive is suggested to bolster its security measures. © 2013 IEEE.

关键词： Hash functions

来源：评论

学校读者我要写书评

暂无评论

Prompting and Adapter Tuning For Self-Supervised Encoder-Decoder Speech Model

Prompting and Adapter Tuning For Self-Supervised Encoder-Dec...

引用

2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023

作者： Chang, Kai-Wei Chen, Ming-Hsin Lin, Yun-Ping Hsu, Jing Neng Huang, Paul Kuo-Ming Huang, Chien-Yu Li, Shang-Wen Lee, Hung-Yi Graduate Institute of Communication Engineering National Taiwan University Taiwan National Taiwan University Department of Computer Science and Information Engineering Taiwan Meta Ai United States

ISBN: (纸本)9798350306897

Prompting and adapter tuning have emerged as efficient alternatives to fine-tuning (FT) methods. However, existing studies on speech prompting focused on classification tasks and failed on more complex sequence generation tasks. Besides, adapter tuning is primarily applied with a focus on encoder-only self-supervised models. Our experiments show that prompting on Wav2Seq, a self-supervised encoder-decoder model, surpasses previous works in sequence generation tasks. It achieves a remarkable 53% relative improvement in word error rate for ASR and a 27% in F1 score for slot filling. Additionally, prompting competes with the FT method in the low-resource scenario. Moreover, we show the transferability of prompting and adapter tuning on Wav2Seq in cross-lingual ASR. When limited trainable parameters are involved, prompting and adapter tuning consistently outperform conventional FT across 7 languages. Notably, in the low-resource scenario, prompting consistently outperforms adapter tuning. © 2023 IEEE.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Dimensionality Reduction with DLMNN Technique for Handling Secure Medical Data in Healthcare-IoT Model 3

Dimensionality Reduction with DLMNN Technique for Handling S...

引用

3rd International Conference on Artificial Intelligence and Smart Energy, ICaiS 2023

作者： Lalithambigai, M. Kalpana, V. Sasi Kumar, A. Uthayakumar, J. Santhosh, J. Mahaveerakannan, R. Sri Krishna Adithya College of Arts and Science Department of Computer Applications Coimbatore641042 India Vel Tech University India Institute of Engineering and Technology Srinivas University Department of Cloud Technology and Data Science Surathkal Karnataka State Mukka574146 India Dhanalakshmi Srinivasan College of Engineering Department of Ai and Ds Coimbatore India Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9781665462167

Security and maintaining the integrity of sensitive patient information have emerged as major obstacles for healthcare service applications in the wake of IoT's meteoric rise in the healthcare industry. The diagnostic information included in medical photographs is of particular importance, and this research presents a hybrid security strategy to protect against such breaches. Chronic diseases such as Heart Disease (HD), cancer, and chronic respiratory sickness are the main causes of death worldwide. Those who have a heart attack suddenly have a very poor chance of surviving. As a result, this paper proposes a heart disease monitoring scheme, wherein a Deep Learning Modified Neural Network (DLMNN) centred on the Internet of Things is used to aid in the diagnosis and treatment of HD. There are three stages to implementing this strategy: First, there is encryption;second, a combination of information gain (IG) and principle component analysis (PCA) to reduce dimensionality;and third, a classification system. To begin, the patient is fitted with a wearable Internet of Things (IoT) sensor device, which simultaneously uploads its sensor data to a remote server. The sensor data is encrypted using a hybrid encryption scheme that combines the Advanced Encryption Standard (AES) and the Rivest, Shamir, and Adleman (RSA) algorithms. A DLMNN classifier is then used to classify the data after it has been decrypted. There are two types of classification outcomes. It provides information on the patient's heart and notifies the doctor in case of abnormalities. Estimated study results demonstrate that DLMNN is an improvement over previously used algorithms for HD diagnosis. The proposed AES-RSA used to support safe data transfer also yields the highest level of security, i.e. 94.32%, and does so in the quickest time for encryption and decryption. © 2023 IEEE.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

A spatial structural similarity triplet loss for auxiliary vehicle re-identification

引用

science China(Information sciences) 2021年第7期64卷 239-240页

作者： Jianqing ZHU Liu LIU Xiaobin ZHU Huanqiang ZENG College of Engineering Huaqiao University UBTECH Sydney AI Centre School of Computer Science FEIT University of Sydney Department of Computer Science and Technology University of Science and Technology Beijing College of Information Science and Engineering Huaqiao University

Dear editor,Vehicle re-identification aiming to match vehicle images captured by different cameras plays an essential role in video surveillance systems for public security. However, vehicle re-identification is a challenging computer vision problem because vehicle images usually contain a list of adverse factors, such as viewpoint variations, blurs, and ***, how to design an effective vehicle re-identification method has received increasing attention.

关键词： vehicle re-identification spatial strutural simialrity triplet loss deep learning video surveillance system

来源：评论

学校读者我要写书评

暂无评论

Enhanced accuracy of deep learning method for fruit images classification 25

Enhanced accuracy of deep learning method for fruit images c...

引用

25th International Arab Conference on Information Technology, ACIT 2024

作者： Arabiat, Mohammad Abuowaida, Suhaila Alshdaifat, Nawaf Aburomman, Ahmad Al Henawi, Esraa Dmour, Mohmmad Elrashidi, Ali Zarqa University Faculty of Information Technology Department of Computer Science Zarqa Jordan Al al-Bayt University Faculty of Information Technology Department of Computer Science Mafraq Jordan Applied Science Private University Faculty of Information Technology Amman Jordan Zarqa University Faculty of Information Technology Department of Data Science and Ai Zarqa Jordan University of Business and Technology Department of Electrical Engineering Jeddah21432 Saudi Arabia

ISBN: (纸本)9798331540012

In the last few years, artificial intelligence has shown its importance and ability in computer vision due to its high level of accuracy and wide acceptance. The main goal of the research is to look into a better way to separate different types of fruits. Although deep learning is used, the standard classification methods for different types of fruit don't work very well. The main steps of the recommended better multiple fruit classification method are: 1) Making changes to the filter's size. Selecting the most suitable number of repeats is part of the process of improving the ResNet-101 block. 3) It is proposed that there be one more convolutional layer. Exists support for the suggested method after collecting and labeling 27,000 pictures as part of an actual study. The dataset with many fruits is split into two parts: 80% is used for training and 20% is used for testing. These pictures were used to train an application based on deep learning (DL) to help successfully determine multiple fruit objects in images. Then and then possible to compare the results of this method to the most current methods in the area of object division. The application being studied at does better than expected in terms of accuracy AP in a range of levels. The values always go farther than the equivalent measures of three widely used methods. Compared to the other methods, the suggested one takes less time to train. There are higher numbers for the thresholds than there are for the state of the art method's thresholds © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Next-Generation Cyber Defense: Deep Q-Learning-Based Adversarial Detection and Prevention in Autonomous Vehicle Networks

Next-Generation Cyber Defense: Deep Q-Learning-Based Adversa...

引用

Mobile Networks and Wireless Communications (ICMNWC), IEEE International Conference on

作者： Shubhi Srivastava Bhargav H K Vijayakumar Gurani Arpana Chaturvedi Ankita Gandhi Yogesh Dharangutti Department of Information Science and Engineering New Horizon College of Engineering Bangalore India Department of Computer Science and Engineering Shridevi Institute of Engineering and Technology Tumakuru India Department of Computer Science Karnatak University Dharwad India Department of IT/AI/ML New Delhi Institute of Management New Delhi India Department of Computer science and Engineering Parul Institute of Engineering and Technology Gujarat India Faculty of Law Symbiosis Law School Pune Symbiosis International (Deemed University) Pune India

ISBN: (数字)9798331528348

ISBN: (纸本)9798331528355

This paper presents a novel ai-powered super-resolution technique for real-time video processing, which significantly enhances the visual quality of low-resolution video frames. The proposed framework employs a hybrid deep learning model that integrates Convolutional Neural Networks (CNNs) with Generative Adversarial Networks (GANs) to reconstruct high-resolution frames with minimal computational overhead. Experimental results on benchmark video datasets show that the proposed method achieves a peak signal-to-noise ratio (PSNR) of 34.56 dB and a structural similarity index (SSIM) of 0.94, outperforming state-of-the-art methods by 12.3% in PSNR and 8.7% in SSIM. Additionally, the system demonstrates an average processing speed of 30 frames per second (fps) on a GTX 1080Ti GPU, making it suitable for real-time applications. The qualitative and quantitative results validate the effectiveness of the proposed method in preserving fine details, reducing artifacts, and enhancing visual clarity in various real-time video processing scenarios.

关键词： Interpolation Visualization PSNR Superresolution Streaming media Mathematical models Real-time systems Hybrid power systems Kernel Faces

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：