检索结果-内蒙古大学图书馆

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Kumar, Boddu Manoj Rajeswari, G. Duraipandian, Kavitha David, Shiela Dept. of Computer Science and Engineering with specialization in Blockchain Technology Sathyabama Institute of Science and Technology Tamil Nadu Chennai India Dept. of Computer Science and Engineering Sathyabama Institute of Science and Technology Tamil Nadu Chennai600119 India

ISBN: (纸本)9798331527549

Blockchain technology has become more widespread in our lives revolutionizing various industries through improved security, transparency, and operational efficiency. Its decentralized ledger system is particularly effective in areas like finance and supply chain management ensuring data integrity and reducing the need for middlemen. This study explores how blockchain technology is used in the process of buying vehicles highlighting its benefits compared to methods. Traditional vehicle purchases involve a network of dealers, banks and regulators leading to inefficiencies, higher costs and potential fraud. The usual process involves steps like financing checking vehicle history and changing ownership. Each requiring extensive paperwork and third-party intervention. In contrast using blockchain for vehicle purchases can simplify things through contracts that automate tasks like verifying history securely transferring ownership instantly settling payments. The unchangeable nature of records ensures that all transaction data remains secure against tampering fostering trust between buyers and sellers. Furthermore, blockchain can cut costs significantly by removing the need for middlemen such, as escrow services and title companies while reducing burdens. The advanced security elements built into technology help reduce the chances of fraudulent actions like altering odometer readings or selling stolen cars. This study showcases a comparison illustrating how blockchain can simplify the process of buying vehicles offering an economical and secure experience. © 2025 IEEE.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

VGGAE-Net: A Two Stream Ensemble CNN for Diabetes Retinopathy Classification 4

VGGAE-Net: A Two Stream Ensemble CNN for Diabetes Retinopath...

引用

4th International Conference on Intelligent Technologies, CONIT 2024

作者： Girepunje, Shashank Singh, Pradeep National Institute of Technology Dept. of Computer Science and Engineering Raipur India

ISBN: (纸本)9798350349900

Diabetic retinopathy is a retinal disease that leads to vision impairment in people suffering from diabetes mellitus. Early detection of disease requires expert supervision and computer diagnosis systems to avoid vision loss. Diabetic Retinopathy grading is suffering from small lesions and data imbalance problems. In this work, we proposed a VGG based attentive ensemble Network (VGGAE-Net) for the classification of diabetes Retinopathy. We have also utilized the two attention blocks channel attention module and class attention module with extracted feature maps from the CNN. Then their prediction outputs are combined to provide the final output for the classification task. The experiment shows that the ensemble approach of two attention blocks with VGG model gives 96.66% accuracy as compared to the existing recent models. © 2024 IEEE.

关键词： class attention module diabetes retinopathy global attention module

来源：评论

学校读者我要写书评

暂无评论

Image Recognition-Based Indoor Positioning System Using Federated Learning 100

Image Recognition-Based Indoor Positioning System Using Fede...

引用

100th IEEE Vehicular technology Conference, VTC 2024-Fall

作者： Yu, Heng-Shao Jhuang, Yu-Chiao Leu, Jenq-Shiou University of Science and Technology Dept. of Electronic and Computer Engineering Taipei Taiwan

ISBN: (纸本)9798331517786

With the advancement of artificial intelligence (AI), indoor positioning systems have become increasingly important for various applications, leading to the development of diverse indoor positioning methods. Among various approaches, image-based indoor positioning methods have demonstrated relatively good positioning accuracy. However, maintaining user privacy continues to be a significant challenge. To tackle this issue, we propose a Federated Learning (FL) approach and develop an FL-based indoor image recognition positioning system. We conducted experiments to validate our method using two real-world datasets and compare the results to a Non-FL approach. Furthermore, we evaluated the accuracy of our method across various communication rounds, the number of client devices, and the amount of data per client device. Our experimental results indicate that the proposed method effectively preserves client privacy while achieving accuracy similar to the Non-FL approach. By employing FedAvg and FedOpt algorithms with the MobileNet model, our system ultimately reaches 94% accuracy. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Recognition of American sign language using modified deep residual CNN with modified canny edge segmentation

引用

Multimedia Tools and Applications 2025年 1-28页

作者： Hariharan, U. Devarajan, Devikanniga Kumar, P. Santhosh Rajkumar, K. Meena, M. Akilan, T. Department of Computer Science and Engineering Apex Institute of Technology Chandigarh University Punjab Mohali140413 India Department of Computer Science and Engineering GITAM University Karnataka Bengaluru561203 India Department of Information Technology Faculty of Engineering and technology SRM Institute of Science and Technology Ramapuram Tamil Nadu Chennai600089 India Department of Data Science and Business Systems School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamil Nadu Chennai603203 India Department of Computer Science and Engineering Sri Sairam Engineering College Tamil Nadu Tambaram602109 India Research Coordinator Dept. of IQAC Amity University Kolkata West Bengal 700135 India

American Sign Language (ASL) recognition aims to recognize hand gestures, and it is a crucial solution to communicating between the deaf community and hearing people. However, existing sign language recognition algorithms still have some drawbacks, such as difficulty recognizing hand movements and low recognition accuracy for most sign language recognition. A Modified Convolutional Neural Network (MCNN) deep residual 101 classifier-based American Sign Language identification system has been developed to address this problem. There are three main parts presents in the method. The first part is pre-processing the images to remove the noise, enhance the contrast of the picture, adjust the contrast level and smoothen the picture using various filters. The second part is the segmentation, and it’s used to partition the image using a modified canny edge detection method by removing all weak edges present in the image. Finally, classification will be done using the Modified CNN deep residual 101 classifiers. By classifying the image, the American Sign Language is accurately identified. This process is conducted through images. The outcome shows that the suggested approach has a 0.97% accuracy and a 0.05% False Positive Rate. Other CNN architectures such as resNet 50 and resNet 18 reached 0.90% and 0.80% accuracy, respectively, which is lower than our proposed method. In addition, the resNet 101 classifier effectively recognizes the difficult hand gestures through the image data. It obtains high recognition accuracy for 36 signs is 0 to 9 numbers and a to z alphabets from American Sign Language. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Campus Surveillance: Deep Learning-Based Rules Violation Detection 14

Campus Surveillance: Deep Learning-Based Rules Violation Det...

引用

14th International Conference on Cloud Computing, Data Science and engineering, Confluence 2024

作者： Deepalakshmi, R. Senthil Murugan, K.R. Arunnachalam, R.S. Mohamed Asif, B. Velammal College of Engineering and Technology Dept of Computer Science Tamil Nadu India

ISBN: (纸本)9798350344837

Cutting edge Innovation had made big affect in areas in Technical, Trade and Mechanical Sectors. Deep learning calculations had created those innovation into great enhancement for the quick, exactness and effectiveness in information. Deep learning Methods could executed in Campus Areas to moves forward its headway in innovation. The paper proposes Deep Learning in college camera which recognizes run the rule violators successfully. Wear ID Card and Wearing Shoes is one of the important rules in Campus, but in today's world limited datasets for the recognizing identity card and shoes. For this issue, Dataset for recognizing the Rule Violators have been made with 5000 pictures. Enhanced deep learning calculations like YOLO for object recognition and Convolutional neural networks to facial detection. YOLO verifies the identity card and Shoes from Pictures and Video. It gives about 80.6% mAP,90.3% precision, and 76.5% recall. © 2024 IEEE.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

TrustCaller- Voice-based Fraud Prevention System 4

TrustCaller- Voice-based Fraud Prevention System

引用

4th International Conference on Intelligent Technologies, CONIT 2024

作者： Sonwane, Rushikesh Patil, Mansi Chauhan, Purva Jain, Anushka Nandwalkar, Bhushan Awate, Ashish Shahade, Makarand SVKM's Institute of Technology Dept. of Computer Engineering Dhule India

ISBN: (纸本)9798350349900

An innovative project called 'TrustCaller' aims to improve call security. With the goal of establishing caller verification and building trust in incoming calls, the project makes use of state-of-the-art technologies for voice feature extraction, processing, and pattern matching. Utilizing React Native only for the Android application, 'TrustCaller' assumes a key function in boosting the security of phone communications when combined with Machine Learning (ML) and Speech Synthesis. This program is a vital step in protecting people from possible dangers and promoting safer phone communication. Moreover, it provides scalable security settings to guarantee users' privacy and control over communication. © 2024 IEEE.

关键词： Secure communication

来源：评论

学校读者我要写书评

暂无评论

Linear Irrational Unit (LIU): An Activation Function For Convolutional Neural Network 5

Linear Irrational Unit (LIU): An Activation Function For Con...

引用

5th IEEE International Conference on Communication, Computing and Industry 6.0, C2I6 2024

作者： Nanda, Pranamita Duraipandian, N. Behera, Sagarika R.M.K College of Engineering and Technology Dept. of Computer Sc. and Engineering Tamilnadu 601206 India Rajalakshmi Engineering College Dept. of Computer Sc. and Engineering Tamilnadu Chennai602105 India Cmr Institute of Technology Dept. of Computer Sc. and Engineering Bengaluru560037 India

ISBN: (纸本)9798350379884

In a convolutional neural network (CNN), the output is produced by passing the input through an activation function (AF). The traditional AFs like sigmoid and tanh suffer from disappearing gradient problems. The disappearing gradient issue was solved by the ReLU AF, but the negative region issue still exists. This study introduces a non-monotonic, nonlinear AF dubbed the Linear Irrational Unit (LIU). The function is continuously differentiable in both the positive and negative regions, which overcomes the disappearing gradient problem. As the proposed function has a non-zero value in the negative region, it does not suffer from the negative region problem. The effectiveness of the proposed LIU activation function was assessed using MNIST, CIFAR-10 and Chest X-ray datasets. With our proposed CNN model, the LIU activation function can reach an accuracy of 85.26% on the Chest X-ray dataset, 99.52% on the MNIST dataset, and 83.15% on the CIFAR dataset, which is better than the performance of other modern activation functions. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Personalized Movie Recommendation Based on User Preferences Using Optimized Sequential Transformer Model

Personalized Movie Recommendation Based on User Preferences ...

引用

2024 International Conference on Artificial Intelligence and Emerging technology, Global AI Summit 2024

作者： Ravikumar, R.N. Jain, Sanjay Sarkar, Manash Amity University Rajasthan Dept. of Computer Science and Engineering Jaipur India Atria Institute of Technology Dept. of Computer Science and Engineering Banglore India

ISBN: (纸本)9798350379716

This study explores the application of a Transformer based model to the 'MovieLens 1M' and 'MovieLens 10M' datasets provided by GroupLens, which includes one million and ten movie ratings. The Transformer model, known for its proficiency in handling sequence-to-sequence tasks, employs multi-head self-attention mechanisms and position-wise feed-forward networks. Our implementation, developed in PyTorch, benefits from its capacity for automatic differentiation and GPU acceleration, which significantly enhances the training efficiency. The model underwent rigorous hyperparameter tuning and optimization to adapt optimally to the characteristics of the dataset. Performance evaluation using the Normalized Discounted Cumulative Gain (NDCG) metric demonstrates that the Transformer model substantially outperforms a conventional popular recommendation system across various top-K rankings. Specifically, for the MovieLens 1M dataset, the Transformer model achieved NDCG scores of 0.0455, 0.0805, 0.0995, and 0.1273 at top 1, 3, 5, and 10, respectively. Comparatively, the popular recommendation system scored 0.0023, 0.0044, 0.0061, and 0.0091 at these same rankings. This trend of superior performance by the Transformer model is also consistent across the MovieLens 10M dataset, further confirming its effectiveness in ranking highly relevant items at the top of the list. Also, to address quality and utility of recommendations, MAP, Precision, Recall, F1 Score, Coverage and Serendipity metrics evaluated. These results underscore the effectiveness of Transformer models in extracting and leveraging complex patterns in sequence data, demonstrating a clear superiority over traditional methods in recommendation systems. This study highlights the potential of deep learning architectures to revolutionize fields reliant on understanding user preferences and sequential data interactions. © 2024 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Converging Diagnostic Paths: A Unified Approach to Acid-Base Imbalances in COPD Patients 2

Converging Diagnostic Paths: A Unified Approach to Acid-Base...

引用

2nd IEEE International Conference on Interdisciplinary Approaches in technology and Management for Social Innovation, IATMSI 2024

作者： Kinikar, Atharva Shah, Manan Pune Institute of Computer Technology Dept. Information Technology Pune India Dwarkadas J Sanghvi Coe Dept. Computer Engineering Mumbai India

ISBN: (纸本)9798350360523

Chronic Obstructive Pulmonary Disease (COPD) significantly impacts patient quality of life and is a leading cause of morbidity and mortality. This paper introduces an innovative algorithm for diagnosing acid-base disorders in COPD patients, incorporating traditional and advanced methodologies like the Henderson-Hasselbalch equation and Bedside Stewart Method. The algorithm enhances the accuracy and speed of Arterial Blood Gas (ABG) analysis, crucial for COPD management. We present a comprehensive approach that includes a Gamblegram for visualizing acid-base balance and a sophisticated system architecture employing Optical Character Recognition (OCR) for efficient ABG report processing. Our findings demonstrate the algorithm's efficacy in providing rapid, detailed analysis, markedly reducing treatment initiation time. This advancement holds significant potential in revolutionizing COPD patient care by improving diagnostic accuracy and treatment strategies for acid-base disorders. © 2024 IEEE.

关键词： Gases

来源：评论

学校读者我要写书评

暂无评论

Frequency Response Deterioration due to Surface Ridge Abrasion of Tactile Sensors 13

Frequency Response Deterioration due to Surface Ridge Abrasi...

引用

13th IEEE Global Conference on Consumer Electronic, GCCE 2024

作者： Yanwari, Muhammad Irwan Okamoto, Shogo Polines Dept. Computer Engineering Technology Japan Tokyo Metropolitan University Dept. Computer Science Tokyo Japan

ISBN: (纸本)9798350355079

Epidermal ridges are crucial for tactile sensing in both human fingers and synthetic sensors. These ridges are made of compliant materials and susceptible to abrasion damage after iterative use. This study focuses on examining the impact of sensor ridge damage on the acquired signal, which encompasses a broad range of frequency components. We compared the frequency responses of a tactile sensor scanning sandpaper with both intact and damaged sensors. The degradation of signal levels was evident across the 0-1,000 Hz range, with particularly prominent suppression of the peak frequency component. This study demonstrates the frequency-dependent influence of ridge abrasion. © 2024 IEEE.

关键词： Friction

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：