检索结果-内蒙古大学图书馆

Deep feature-support vector machine based hybrid model for multi-crop leaf disease identification in Corn, Rice, and Wheat

引用

Multimedia Tools and Applications 2025年第8期84卷 4751-4771页

作者： Bhola, Amit Kumar, Prabhat Department of Computer Science and Engineering National Institute of Technology Patna Bihar India

Corn, Rice, and Wheat serve as primary staple foods globally, playing a pivotal role in the economies of numerous countries. Despite their paramount importance, these cereal crops face susceptibility to various diseases, posing a significant threat to production. Timely and accurate disease diagnosis is imperative to mitigate these risks. In response, a range of Machine Learning (ML) and Deep Learning (DL) models have been devised to automate the identification of diseases impacting cereal crops. While DL excels with abundant data, traditional ML may outperform DL with limited data. This study proposes a hybrid model integrating deep transfer learning and ML techniques for identifying crop diseases. The model utilizes pre-trained DenseNet201 weights to extract features, which are subsequently fed into a Support Vector Machine (SVM) for identification. Experimental results show that the hybrid model outperforms several benchmark counterparts. The DenseNet201 deep feature combined with SVM exhibits superior performance, achieving an impressive accuracy score of 87.23% with just 20.2M parameters. The model underwent comprehensive performance assessment using precision, recall, F1 score, and overall accuracy metrics. It effectively classifies healthy and diseased categories for each crop, achieving accuracies of 99.82%, 98.75%, and 84.15% for Corn, Wheat, and Rice, respectively. Moreover, the model’s remarkable performance and lightweight nature make it a practical and efficient real-time crop disease detection solution, emphasizing its relevance and significance for farmers and researchers in the agricultural community. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

LightDD: A lightweight model for disaster detection from aerial imagery

引用

Multimedia Tools and Applications 2025年 1-25页

作者： Gaur, Samta Kumar, J. Sathish Department of Computer Science and Engineering MNNIT Allahabad UP Prayagraj211004 India

Natural disasters disrupt both human habitats and vital infrastructures, leading to significant damage and sometimes permanent alterations to the environment. Such disasters can arise from diverse natural phenomena, such as earthquakes, cyclones, floods and wildfires. Despite various efforts by researchers to use Deep Learning (DL) for disaster identification and classification, the complexity and imbalance of image data present ongoing challenges. In response to these challenges, a new LightDD (Lightweight Deep Disaster Detection) model is proposed to streamlined deep Convolutional Neural Network (CNN) tailored for disaster detection. Notably, the proposed LightDD model is lightweight, comprising just 0.11 million parameters. The model is divided into two main segments: the first employs three convolutional modules for feature extraction, with filters sizes in descending order (128, 64, and 32), capped by average global pooling. This configuration allows the model to extract complex features using high-level filters and efficiently condense them in subsequent layers, preserving a rich feature representation while reducing the overall number of parameters. The second segment is dedicated to disaster classification and consists of a singular module of fully connected layers. The LightDD model was evaluated on a disaster dataset, achieving an accuracy rate of 91.44%. © 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

An Improved Graph Partitioning Algorithm Based Approach for Workflow Offloading in a Fog Environment

引用

Journal of The Institution of Engineers (India): Series B 2025年第2期106卷 623-634页

作者： Mahajan, Neetu Narang Kaur, Parmeet Department of Computer Science and Engineering Jaypee Institute of Information Technology Noida India

The paper addresses the critical problem of application workflow offloading in a fog environment. Resource constrained mobile and Internet of Things devices may not possess specialized hardware to run complex workflows locally and hence, need to offload these tasks to fog nodes. As compared to cloud-based servers, fog nodes can provide responses in a more-timely manner and are preferred for latency-sensitive applications. Workflow applications are characterized by inter-task dependencies and hence, can be readily represented as directed acyclic graphs. Therefore, the proposed offloading solution approach utilizes an improved graph partitioning algorithm based on the Louvain community detection algorithm. The aim of the algorithm is to partition the workflow graph in such a manner that the workflow tasks having high communication costs between them are transferred or offloaded to the same fog node. The benefits of the proposed algorithm have been verified by simulation experiments where it was observed that it results in a lower makespan as compared to the related approaches. © The Institution of Engineers (India) 2024.

关键词： Fog

来源：评论

学校读者我要写书评

暂无评论

Multi-source ECG Signal-Based Cardiac-Abnormality Pattern Classification with Fast–Slow Learning DNNs

引用

Journal of The Institution of Engineers (India): Series B 2025年 1-10页

作者： Samant, Sandhya Baloni, Dev Department of Computer Science and Engineering Quantum University Uttarakhand Roorkee247667 India

The classification of cardiac-abnormality patterns with ECG data plays a crucial role in the diagnosis as well as treatment and prognosis of diseases related to the human heart. With the advent of deep learning techniques, particularly convolutional, recurrent, and generative neural networks, there has been a significant advancement in the accuracy and efficiency of cardiac-abnormality pattern classification with electrocardiogram (ECG) data. However, with the availability of multitudes of freely available multi-source ECG data today, more attempts are required to develop new models that can handle and perform well on these datasets simultaneously. In this study, an attempt is made to develop a novel deep learning classification model with multi-source ECG dataset for cardiac abnormality pattern classification. The model uses the power of Transformer networks in their ability to produce low inductive bias towards learning representations and the power of Recurrence networks to memorize a compressed representation of a sequence is that it is beneficial for generalization. The transformers are the fast-stream component due to their sensitivity to sensory input and the RNs are slow-stream component due to their long-term memory sustenance. The multi-source ECG dataset is composed of 4 different and popular 12-lead ECG datasets available publicly for research purposes. The proposed model performed satisfactorily overall on a 27-class classification scenario. © The Institution of Engineers (India) 2025.

关键词： Electrocardiography

来源：评论

学校读者我要写书评

暂无评论

BEFF-SIGS: blockchain-enhanced fog framework- securing IoT data integrity and green sustainability through scalable authentication-authorization

引用

International Journal of computers and Applications 2025年第3期47卷 293-311页

作者： Khan, Neelam Saleem Mir, Roohie Naaz Chishti, Mohammad Ahsan Department of Computer Science & Engineering NIT Srinagar J&K India

This paper introduces a comprehensive framework designed to address security concerns in the Internet of Things (IoT) environment while contributing to the global Green Environment Initiative. The proposed mechanism utilizes a secure and scalable Authentication-Authorization system, employing JSON Web Token (JWT) and Casbin to ensure that only authorized entities access critical data. data processing is strategically offloaded to the fog layer to enhance scalability and reduce latency, optimizing IoT data handling. The framework actively supports environmental sustainability by promoting eco-friendly practices within industrial setups. Industries are incentivized to embrace environmentally responsible approaches through tax incentives, fostering a greener future. Our model is a robust mechanism to guarantee the consistency and authenticity of the data stored in the cloud environment, offering assurance against potential tampering attempts by securing data integrity. This holistic approach demonstrates how governments can leverage cutting-edge technology to incentivize industries and promote a sustainable and eco-friendly future. Utilizing blockchain technology ensures unparalleled transparency, robust security, and tamper-resistant record-keeping. We evaluate the impact on network consumption, latency, and energy consumption for analyzing the performance of the proposed system. The proposed framework offers better latency, network efficiency, and distributed computational power as major benefits over depending exclusively on cloud resources in IoT deployments. © 2024 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Limits of Depth: Over-Smoothing and Over-Squashing in GNNs

引用

Big data Mining and Analytics 2024年第1期7卷 205-216页

作者： Aafaq Mohi ud din Shaima Qureshi Department of Computer Science and Engineering National Institute of Technology SrinagarSrinagar 190006India

Graph Neural Networks(GNNs)have become a widely used tool for learning and analyzing data on graph structures,largely due to their ability to preserve graph structure and properties via graph representation ***,the effect of depth on the performance of GNNs,particularly isotropic and anisotropic models,remains an active area of *** study presents a comprehensive exploration of the impact of depth on GNNs,with a focus on the phenomena of over-smoothing and the bottleneck effect in deep graph neural *** research investigates the tradeoff between depth and performance,revealing that increasing depth can lead to over-smoothing and a decrease in performance due to the bottleneck *** also examine the impact of node degrees on classification accuracy,finding that nodes with low degrees can pose challenges for accurate *** experiments use several benchmark datasets and a range of evaluation metrics to compare isotropic and anisotropic GNNs of varying depths,also explore the scalability of these *** findings provide valuable insights into the design of deep GNNs and offer potential avenues for future research to improve their performance.

关键词： Graph Neural Networks(GNNs) learning on graphs over-smoothing over-squashing isotropic-GNNs anisotropic-GNNs

来源：评论

学校读者我要写书评

暂无评论

L3Buddy: a location-aware academic content-recommendation system through machine learning based cache techniques

引用

Multimedia Tools and Applications 2025年第5期84卷 2633-2649页

作者： Guddadmani, Ashwini Chougale, Supriya Gokanvi, Megha Tapale, Manisha Pattar, Santosh Department of Computer Science and Engineering KLE Technological University Belagavi Campus India

At present, recommendation systems have become pivotal in personalized education learning management systems, where there is a growing need for location-based suggestions. Our problem addresses the inefficiency of current systems in integrating real-time location data, leading to latency and irrelevant content delivery. We propose L3Buddy, a context-aware system leveraging machine learning for location-specific video recommendations. This approach enhances accuracy and reduces latency, improving the user experience by delivering timely, relevant content. Our results demonstrate significant improvements in both recommendation precision and system responsiveness. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Blockchain enabled MediVault for healthcare system

引用

Multimedia Tools and Applications 2025年第15期84卷 14805-14825页

作者： Chaurasia, Brijesh Kumar Department of Computer Science and Engineering Pranveer Singh Institute of Technology Kanpur India

The management of healthcare data has significantly benefited from the use of cloud-assisted MediVault for healthcare systems, which can offer patients efficient and convenient digital storage services for storing their medical records. Nevertheless, there are security risks associated with the current digital healthcare data, as malicious parties may work with cloud storage service providers to alter patient records or to directly disclose health record content to other adversaries for monetary advantage. In this paper, a blockchain-enabled MediVault for healthcare systems is proposed not only to provide safe storage of healthcare data in digital form but also secure access for authenticated entities such as patients, doctors, and pharmacists. In this MediVault, we introduced NFT generation and storage over the cloud using Interplanetary File System (IPFS) and FireBase as per user adaptability, Ehtereum Blockchain for immutability, and encryption and decryption using asymmetric keys for confidentiality. The empirical results and the performance evaluation demonstrate that the proposed MediVault is secure, simple, and efficient with a limited computation overhead. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

EPDTNet + -EM: Advanced Transfer Learning and SubNet Architecture for Medical Image Diagnosis

引用

Cognitive Computation 2025年第2期17卷 1-22页

作者： K, Dhivya K, Sangamithrai S, Indra Priyadharshini M, Vedaraj Department of Electronics and Communication Engineering SRM Institute of Science and Technology Tamilnadu Kattankulathur India Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R & d Institute of Science and Technology Tamilnadu Chennai India School of Computer Science and Engineering Vellore Institute of Technology Chennai India Department of Computer Science and Engineering R.M.D. Engineering College RSM Nagar Tamilnadu Kavaraipettai Thiruvallur601206 India

This paper presents a novel medical imaging framework, Efficient Parallel Deep Transfer SubNet+-based Explainable Model (EPDTNet + -EM), designed to improve the detection and classification of abnormalities in medical images. The model integrates Enhanced Exponential Transfer Learning (En-ETL) and the Parallel SubNet (PSNet +) architecture, addressing challenges like overfitting, high computational cost, and limited generalization across complex datasets. En-ETL accelerates learning and enhances precision, while PSNet + balances computational efficiency and performance through parallel convolutional layers and an axis attention mechanism. The proposed framework preprocesses medical images using resizing, noise removal, and contrast enhancement, ensuring high-quality inputs for analysis. For classification, the PSNet + model categorizes medical images into normal and abnormal cases. Explainable AI (XAI) is applied to highlight key features in classified images, improving interpretability and clinical decision-making. Experimental results validate the framework on various datasets, including MRI, CT, X-ray, and mammography images. The proposed model achieves a classification accuracy of 98.83%, a false positive rate of 2%, and an execution time of 5.3 ms. Comparative Analysis show superior performance over existing approaches in classification accuracy and efficiency. Ablation studies confirmed the significant contributions of the proposed model using each component in enhancing performance. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Product Quality Enhancement in Social Media using Emotion-Enhanced Bert (EE-BERT) Model 2

Product Quality Enhancement in Social Media using Emotion-En...

引用

2nd International Conference on Self Sustainable Artificial Intelligence Systems, ICSSAS 2024

作者： Raj Kumar, V.S. Kumaresan, T. Mythily, V. Raghavendran, N. Bannari Amman Institute of Technology Department of Artificial Intelligence and Data science Sathyamangalam India Bannari Amman Institute of Technology Department of Computer Science and Engineering Sathyamangalam India Nandha Engineering College Department of Computer Science and Engineering Erode India Rmk college of Engineering and Technology Department of Artificial Intelligence and Data science Chennai India

ISBN: (纸本)9798350368413

Twitter plays an important role in understanding the consumer sentiment about the products. The advanced analytics and Natural Language Processing (NLP) are used to extract actionable insights from this data and useful for a business to improve features and address issues on time for better customer satisfaction and brand loyalty. Most of the current models suffer from a lack of effective ways to handle subtle sentiment analysis because of a lack of contextual understanding and proper feature extraction. Most traditional models cannot combine and optimize features that lead to obtaining sentiments. This leads to overfitting and problems caused by local minima. The proposed Emotion-Enhanced BERT (EE-BERT) model is an extension of the standard BERT to learn contextual embeddings in user sentiment. In this work, data preprocessing includes text cleaning, tokenization, dealing with emojis and emoticons, and lemmatization with the best quality data. The proposed work is basically a dual-stream architecture extended with butterfly optimizer. First, the advanced tokenization and semantic understanding techniques is used for extracting textual features. Second, the emotion-enhanced features extracted through emotion-hash vectorization to enhance the model's contextual awareness in social media data. This provides a unified framework that combines the feature extraction methods to enhance the accuracy in sentiment analysis. It demonstrated with an impressive accuracy of 98.2% on sentiment in posts and comments with 0.15 losses. The proposed work is free from overfitting and local minima in product quality enhancement. © 2024 IEEE.

关键词： Tweets

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：