检索结果-内蒙古大学图书馆

A cancelable biometric authentication scheme based on geometric transformation

Multimedia Tools and Applications 2025年第15期84卷 15407-15428页

作者： Champaneria, Vivek H. Patel, Sankita J. Zaveri, Mukesh A. Department of Computer Science And Engineering Sardar Vallabhbhai National Institute of Technology Icchanath Gujarat Surat395007 India

In digital identification technologies, fingerprint-based biometric systems are extensively utilized for authentication. Fingerprint authentication systems usually store the original minutiae points as user templates in the database which consist of minutiae bifurcation and ridge end points. Storing original minutiae points in the database can create a potential security risk to a person’s identity. An adversary might attack the database and compromise the user template. Various studies have demonstrated the feasibility of reconstructing the original fingerprint by utilizing the minutiae points. Existing research methods still need to be improved, and therefore, it is essential to provide security and robustness to fingerprint-based biometric systems. In this paper, a novel template protection technique using non-invertible transformation is proposed to create a secure and robust template. The transformation function uses the original minutiae positions, orientation details, and user key set values. The results demonstrated equal error rates of 1.5%, 0.85%, and 2.71% for the FVC2002 DB1, DB2, and DB3 fingerprint databases. The proposed method has demonstrated noteworthy performance improvement compared to other notable contributions. The outcome of the proposed method demonstrates practicality and effectiveness. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

Analyzing functional, technical and bibliometric trends of blockchain applications in education: A systematic review

引用

Multimedia Tools and Applications 2025年第8期84卷 4003-4048页

作者： Choudhary, Ankita Chawla, Meenu Tiwari, Namita Department of Computer Science and Engineering Maulana Azad National Institute of Technology Madhya Pradesh Bhopal462003 India

In an educational ecosystem, accurate and complete management of student’s records is a complex and error-prone process. Blockchain is a promising solution to add substantial value around enhanced efficiency, privacy protection, technological advancement, access control, and secure exchange of student course records. This work presents a systematic literature review to analyze the applications of blockchain technology in the educational domain addressing the gaps identified in the previous reviews. The technical papers published in English were searched by key terms related to blockchain and education on IEEE Xplore, science Direct, and six other databases. The risk of bias was assessed by considering all the crucial search terms preventing the accidental exclusion of any article. Many blockchain frameworks in the educational domain have been proposed;including some prototypes and implementations. The PRISMA framework was used for the evaluation of 150 distinct models, 124 of which were prototypes, pilots, or full implementation and the remaining 26 were only proposals. This work contributes a structured bibliometric, functional, and technical examination of these articles, assessing privacy, cost, performance, security, architecture, and standards to identify and bridge gaps. The study concludes an avalanche of proposals, with approximately half of them being prototypes, indicating that implementation and proof-of-concept pilots are expected. Blockchain is found to solve various record management issues at significant trade-offs between performance, storage, and cost. However, scalability issues, poor overall performance, and increased price are major limitations for implementing blockchain in education solutions. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Records management

来源：评论

学校读者我要写书评

暂无评论

COVID-19 detection from Chest X-ray images using a novel lightweight hybrid CNN architecture

引用

Multimedia Tools and Applications 2025年第13期84卷 11295-11317页

作者： Pradeep Dalvi, Pooja Reddy Edla, Damodar Purushothama, B.R. Dharavath, Ramesh Department of Computer Science and Engineering National Institute of Technology Farmagudi Goa Ponda403401 India Dhanbad India

The pandemic of COVID-19 has affected worldwide population. Diagnosing this highly contagious disease at an initial stage is essential for controlling its spread. In this paper, we propose a novel lightweight hybrid convolutional neural network to identify COVID-19-positive patients from Chest X-ray images using building blocks of MobileNet and ResNet50. This model shows improvement over the base models when applied to the same dataset independently. The proposed model is trained and tested on same configuration and dataset as that of its base models, for better performance analysis and comparison. It also has fewer parameters as compared to MobileNet and ResNet50, which makes it lightweight, adding to its better performance. It achieves an accuracy of 98.47 % with very few false negative predicted samples, which is extremely beneficial in medical diagnosis. Concerning the parameters, this model is built with only 200,034 trainable parameters, which marks a parameter reduction percentage of 99.15 % concerning ResNet50 and 93.82% compared to MobileNet. The generalisation performance of our proposed model is evaluated using stratified 5-fold cross validation technique. Our model achieved very good accuracy with very less parameters as compared to various state-of-the-art models. The model also classified Pneumonia images from Normal ones with an accuracy of 98.9 %. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Emotion detection in text using a legendre memory unit based deep learning framework

引用

Multimedia Tools and Applications 2025年 1-16页

作者： Khan, Abrar Kumar, Prabhat Department of Computer Science and Engineering National Institute of Technology Patna Ashok Rajpath Bihar Patna800005 India

Emotion detection stands as a pivotal approach for extracting unbiased insights from textual documents. This process empowers business experts to identify areas of improvement and bolster key facets of their operations. Given that every online customer post holds the potential to influence the market and consumer behaviour, the significance of emotion recognition has surged. This article introduces a cutting-edge deep learning (DL) approach for emotion detection, specifically focusing on analyzing tweet text sourced from the CARER dataset. The proposed method employs a two-step process, utilizing sentence-transformer for text embedding and Legendre Memory Unit (LMU) based DL framework for emotion classification. The LMU is a novel memory cell designed for recurrent neural networks (RNNs). The key innovation of LMU lies in its ability to achieve "orthogonalization" of its continuous-time history. This means that the memory unit effectively processes input data in a way that retains important patterns while reducing interference from irrelevant or noisy information. The study has undertaken an exhaustive comparison with various state-of-the-art classification models, including RNN, long short term memory (LSTM), bidirectional-long short term memory (Bi-LSTM), gated recurrent unit (GRU), and bidirectional gated recurrent unit (Bi-GRU). Notably, the proposed method distinguishes itself by demonstrating superior performance, surpassing established benchmarks in the field. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Advanced skin lesion detection via efficientNetB0 and vision transformer model with spatial-aware attention

引用

Multimedia Tools and Applications 2025年 1-19页

作者： Shaheen, Hera Singh, Maheshwari Prasad Singh, Amit Kumar Department of Computer Science and Engineering National Institute of Technology Patna Ashok Rajpath Bihar Patna800005 India

Due to the high incidence and possibly fatal nature of skin cancer, early identification is crucial for enhancing patient results. This paper presents a unique deep learning network, EfficientNetB0 ViT, to accurately classify skin lesions. The proposed method encompasses the scalability and efficiency of EfficientNetB0 with the global pattern recognition capabilities of Vision Transformers (ViT), strengthened by the Spatial-Aware Squeeze and Excitation (SASE) attention mechanism. This innovative technique improves classification performance by enabling the model to dynamically highlight the image’s most pertinent elements. SASE attention successfully recalibrates feature importance, reducing overfitting and improving generalization. This research highlights the effectiveness of SASE attention mechanism enhances skin lesion classification, providing a valuable tool for dermatologists in early diagnosis. The model outperformed numerous methods, achieving a high accuracy of 94.64% as well as average precision of 95%, average recall of 95%, and F1-scores of 95% on HAM10000 dataset. It achieves an accuracy of 93% © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

DyPSS: Dynamic Priority Signalling System for Emergency Vehicles using Fog and YOLOv8 17

DyPSS: Dynamic Priority Signalling System for Emergency Vehi...

引用

17th International Conference on COMmunication Systems and NETworkS, COMSNETS 2025

作者： Kakde, Anuj Nath, Shubha Brata Ghosh, Soumya K. Indian Institute of Technology Department of Computer Science and Engineering Kharagpur India Indian Institute of Information Technology Department of Computer Science and Engineering Guwahati India

ISBN: (纸本)9798331531195

Efficient navigation of emergency response vehicles (ERVs) through urban congestion is crucial to life-saving efforts, yet traditional traffic systems often slow down their swift passage. In this work, we introduce Dynamic Priority Signalling System (DyPSS), an intelligent, multi-layered traffic management solution designed to minimize ERV delays by creating "green corridors"at traffic signals. Using technologies like fog computing, cloud computing, global positioning system and deep learning, DyPSS adjusts traffic lights instantly to clear congestion as an ERV approaches. Simulation testing was conducted using SUMO and it demonstrated DyPSS's potential to significantly reduce ERV travel time in dense urban settings with minimal disruption to general traffic flow. This system could drastically improve emergency response by reducing delays and helping responders reach their destinations faster, potentially saving more lives. © 2025 IEEE.

关键词： Emergency vehicles

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of EfficientNet Models in Grape Leaf Disease Classification 1

Performance Evaluation of EfficientNet Models in Grape Leaf ...

引用

1st International Conference on Intelligent Systems and Computational Networks, ICISCN 2025

作者： Subramanya, S.G. Parkavi, A. Nitte Meenakshi Institute of Technology Department of Computer Science and Engineering Bengaluru India Ramaiah Institute of Technology Department of Computer Science and Engineering Bengaluru India

ISBN: (数字)9798331529246

ISBN: (纸本)9798331529246

Grape farming is a globally significant agricultural practice, but grapevines frequently encounter viral, fungal, and bacterial infections that compromise crop quality and yield. Conventional disease detection methods are labor-intensive and require significant expertise. This study investigates deep learning techniques, focusing on EfficientNet models, to automate grape leaf disease identification and classification. The transfer learning approach was applied to train and fine-tune EfficientNet models on a publicly available dataset with four classes: black rot, leaf blight, esca, and healthy leaves. A model performance was measured through accuracy and loss metrics. EfficientNetB0 achieved accuracy of 92.45% and 96.73%, and loss of 0.197 and 0.098, on training and validation data, respectively. However, EfficientNetB5 and EfficientNetB7 gave validation accuracies of 96.07% and 96.39%, respectively. The accuracy and loss trends demonstrate that EfficientNetB0 outperforms the other two counterparts. This approach highlights the potential of EfficientNetB0 for accurate, efficient grape disease detection and classification. © 2025 IEEE.

关键词： Plant diseases

来源：评论

学校读者我要写书评

暂无评论

Message Priority Classification Framework for Autonomous Vehicles in Supply Chain Management 2

Message Priority Classification Framework for Autonomous Veh...

引用

2nd International Conference on Computational Intelligence, Communication technology and Networking, CICTN 2025

作者： Virani, Mili Kansara, Drashti Pathak, Lakshit Gupta, Rajesh Tanwar, Sudeep Sawhney, Sahil Department of Computer Science and Engineering Institute of Technology Nirma University Ahmedabad India Department of Computer Science and Engineering Model Institute of Engineering & Technology J&K India

ISBN: (纸本)9798331530389

In modern supply chain management, efficient communication and timely decision-making are essential to ensuring smooth operations and avoiding descriptions. This is ensured by efficient communication and timely decision-making. Prioritizing essential messages with these systems becomes essential as autonomous technologies become more integrated. This work presents a message priority classification framework formulated to refine communication processes within autonomous vehicles (AVs). This plays a growing role in supply chain logistics. Our framework uses machine learning (ML) models such as Support Vector Machines (SVM), K-Nearest Neighbors (KNN), Random Forest (RF), and Logistic Regression (LR) which are implemented to classify message priorities in real-time, assuring efficient and uninterrupted communication. The experimental outcomes show that the RF model outperformed other models and achieved the highest accuracy of 0.9714. Further, the proposed framework enhances the modularity of AV communication systems and supports efficiency in decision making in complex and variable supply chains. This study emphasizes the significance of ML in optimizing communication leading to more dependable and efficient supply chain operations for AVs. © 2025 IEEE.

关键词： Supply chain management

来源：评论

学校读者我要写书评

暂无评论

An Assessment Towards 2D and 3D Human Pose Estimation and its Applications to Activity Recognition: A Review

引用

SN computer science 2025年第2期6卷 1-24页

作者： Verma, Pratishtha Srivastava, Rajeev Tripathy, Santosh Kumar Department of Computer Engineering National Institute of Technology Haryana Kurukshetra India Computer Science and Engineering IIT BHU Varanasi India Department of Computing Science and Engineering National Institute of Technology Patna Bihar Patna India

Human pose estimation (HPE) from images or video is not only a major issue of computer vision, but also it plays a vital role in many real-world applications. The most challenging problems of human pose estimation are the disparity of poses, disturbing background clutter, different camera views, changes in scene lighting conditions, and occlusion. To solve these issues, a significant amount of research effort has been considered in the past. In this paper, we explore various vision-based activity recognition using 2D and 3D human pose estimations. We explore the conventional system, which includes both statistical and deep learning-based approaches for HPE, and then explore the current progress of each one in comparison to existing ones. At last, we also present various current state-of-the-art human activity recognition (HAR) techniques that use HPE for recognition. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Human activity recognition (HAR) Human body model (HBM) Human pose estimation (HPE)

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

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：