检索结果-内蒙古大学图书馆

ResdenseNet: a lightweight dense ResNet enhanced with depthwise separable convolutions and its applications for early plant disease classification

引用

Neural Computing and Applications 2025年第8期37卷 6305-6326页

作者： Nagpal, Jyoti Goel, Lavika Department of Computer Science & Engineering The NorthCap University Gurugram122017 India Department of Computer Science and Engineering Malaviya National Institute of Technology Rajasthan Jaipur302017 India

In recent years, artificial intelligence has undergone robust development, leading to the emergence of numerous autonomous AI applications. However, a crucial challenge lies in optimizing computational efficiency and reducing training time while maintaining high accuracy with limited hardware resources. This paper introduces ResdenseNet, a model built upon the MobileNet, DenseNet, and ResNet architectures. ResdenseNet combines dense blocks and residual blocks from the DenseNet and ResNet architectures. In these dense blocks, the standard convolutional units are replaced by depthwise separable convolutional units, a significant part of the MobileNet architecture. The experimental outcomes are contrasted with established models and their iterations, including ResNet-50, ResNet-101, MobileNet-V1, MobileNet-V2, DenseNet-121, and DenseNet-169. The proposed model is tested on benchmark and proposed datasets, showcasing its efficiency in reducing computations and accelerating the training process. Emphasizing hyperparameter importance, ResdenseNet, optimized with a growth rate of 64, 6 layers, and ReLU activation, achieves an accuracy of (98.73%) and a F1-score of (98.20%) on the wheat and barley dataset. The results indicate that ResdenseNet significantly decreases the number of parameters to 0.72M and efficiently shortens training time to 5983.54 s. Particularly noteworthy is ResdenseNet’s superiority over other models in terms of having the fewest parameters, the shortest training time, and the highest accuracy, especially when dealing with wheat, barley, and maize datasets. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Plant diseases

来源：评论

学校读者我要写书评

暂无评论

From Centralization to Decentralization: Blockchain's Role in Transforming Social Media Platforms

引用

IEEE Access 2025年 13卷 80478-80507页

作者： Diba, Bidita Sarkar Plabon, Jayonto Dutta Tasnim, Nishat Hossain, Mehjabin Mistry, Durjoy Sarker, Sourav Mridha, M.F. Okuyama, Yuichi Shin, Jungpil Department of Computer Science and Engineering University of Asia Pacific Dhaka1215 Bangladesh Department of Computer Science and Engineering American International University of Bangladesh Dhaka1229 Bangladesh Department of Civil Engineering Chittagong University of Engineering and Technology Bangladesh Department of Computer Science and Engineering University of Aizu AizuWakamatsu Fukushima956-8580 Japan

Blockchain is influencing the social media platforms by promising to solve the biggest issues of today, such as privacy concerns and content moderation, and the ability to provide a decentralized system for the management of social media platforms through cryptographic techniques and distributed structures. Conventionally, social media systems are based on central architectures that may indirectly solve the problems of data privacy and platform responsibility since there are increased threats, including identity theft and fake news spread across such systems. Blockchain has stepped up as an anti-centralized platform that allows multiple numbers of users to transact securely and authentically through P2P channels without a middleman. Here in this survey, we introduce a brief overview of the latest trends of the blockchain protocols and the interactions with the social media platforms, as well as present a systematic review of the related area. Specifically, the use case we consider and elaborate on is how blockchain can be applied to various types of social media services: smart contract-based content moderation platforms, user incentives using token economics, social media governance through decentralized autonomous organizations, and cross-chain connections. We then go further and offer a comprehensive literature review of blockchain incorporating main social media applications that cutting across them include identity, tokenization, and self-governance. The key points that can be derived from this review of the blockchain-enabled social media services and applications are also underlined here. We conclude this survey by listing the existing issues in the field, including scalability and compliance with the existing regulations, and suggesting the possible areas of research in this ever-evolving field. © 2013 IEEE.

关键词： Distributed ledger

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

A mathematical multi-objective optimization model and metaheuristic algorithm for effective advertising in the social internet of things

引用

Neural Computing and Applications 2025年第6期37卷 4797-4821页

作者： Molaei, Reza Rahsepar Fard, Kheirollah Bouyer, Asgarali Department of Computer Engineering and Information Technology University of Qom Qom Iran Department of Software Engineering Azarbaijan Shahid Madani University Tabriz Iran Department of Software Engineering Faculty of Engineering and Natural Science Istinye University Istanbul Turkey

The integration of social networks with the Internet of Things (IoT) has been explored in recent research, giving rise to the Social Internet of Things (SIoT). One promising application of SIoT is viral marketing, which plays a critical role in modern advertising. However, current solutions proposed for viral marketing are often impractical in real-world scenarios, and there has been limited investigation into viral marketing within the context of SIoT. To address this issue, we present a multi-objective integer linear programming model named ILP-ASoT that facilitates advertising through SIoT. Our approach introduces two realistic parameters: the node sociality rate and the node appropriateness rate as an advertising destination. By balancing the cost of selecting a seed set with the number of users who receive the advertisement, our model offers an appropriate trade-off. Since this is proven as an NP-hard problem, A PSO-based metaheuristic algorithm is proposed to provide near-optimal solutions for advertising in SIoT, called PSO-ASoT. Through simulations, we show that our PSO-ASoT algorithm outperforms state-of-the-art algorithms in several metrics, such as influence spread, advertising cost, and duplicated advertising rate. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Enhancing link prediction in graph data augmentation through graphon mixup

引用

Neural Computing and Applications 2025年第8期37卷 6267-6282页

作者： Sultana, Tangina Hossain, Md. Delowar Morshed, Md. Golam Lee, Young-Koo Department of Electronics and Communication Engineering Hajee Mohammad Danesh Science and Technology University Dinajpur Bangladesh Department of Computer Science and Engineering Kyung Hee University Yongin Korea Republic of Department of Computer Science and Engineering Hajee Mohammad Danesh Science and Technology University Dinajpur Bangladesh

Link prediction in complex networks is a fundamental problem with applications in diverse domains, from social networks to biological systems. Traditional approaches often struggle to capture intricate relationships in graphs, leading to suboptimal predictions. To address this, we introduce a novel method called graphon mixup (GM), which leverages the power of graphons to enhance link prediction. The augmentation strategy involves generating a synthetic graph by combining the original graph with a graphon-based synthetic graph. This process, expressed as a weighted combination of adjacency matrices, strategically blends real and synthetic information, enriching the training dataset. GM formulates link prediction as a joint optimization problem, aligning the characteristics of the synthetic graph with the true underlying structure. The objective is to minimize cross-entropy loss between predicted and true edge probabilities. A detailed computational complexity analysis evaluates the time and space requirements, aiding in understanding the efficiency and scalability of GM across different datasets and network sizes. Empirical validation on benchmark datasets demonstrates GM’s effectiveness in consistently improving average precision across diverse network types. The proposed method enhances the generalization capabilities of link prediction models, providing a more robust framework capable of accurate predictions even in the presence of noise or unseen patterns. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

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

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

Hybrid optimization assisted deep ensemble classification framework for skin cancer detection

引用

Multimedia Tools and Applications 2025年第1期84卷 63-94页

作者： Pukhta, Irfan Rashid Rout, Ranjeet Kumar Department of Computer Science and Engineering National Institute of Technology Srinagar190006 India

In 2018, there were 1 million occurrences of non-melanoma cancer and 288,000 occurrences of malignant skin cancer (MM) recorded worldwide. Given the aging of the population and limited resources for medical care, a complete strategy to prevent skin cancer must include both practical detection and accurate diagnosis. Dermatologists and family physicians may find it challenging to identify skin cancer, particularly MM, at an early phase. The purpose of this paper is to suggest a paradigm for skin cancer detection, where pre-processing is the initial step for which median filter (MF) is employed. The pre-processed image undergoes segmentation, which is done by an Improved DBSCAN approach. Once the segmentation is over, features like "GLCM, Local Binary pattern (LBP), Local Vector Pattern (LVP), and Improved Center Symmetric Local Ternary Pattern (CSLTP)" are extracted. This is the final phase, where an ensemble classifier (EC) that combines the models like "Convolutional Neural network (CNN), Long Short Term Memory (LSTM), and Bidirectional Gated Recurrent Unit (Bi-GRU)" is deployed. Further, weights of CNN, Bi-GRU, and LSTM are tuned by Hawks Updated Blue Monkey Algorithm with Gaussian Map Randomness (HUBM-GMR) based hybrid optimization. The study will ultimately validate the HUBM-GMR model. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

ECG Signal Classification of Cardiovascular Disorder using CWT and DCNN

引用

Journal of Biomedical Physics and engineering 2025年第1期15卷 77-92页

作者： Rahman, Tawfikur Ahommed, Rasel Deb, Nibedita Das, Utpal Kanti Moniruzzaman, Md. Bhuiyan, Md. Alamgir Sultana, Farzana Kausar, Md. Kamruzzaman Department of Electrical and Electronic Engineering Faculty of Engineering International University of Business Agriculture and Technology Uttara Dhaka 1230 Bangladesh Department of Agriculture International University of Business Agriculture and Technology Uttara Dhaka 1230 Bangladesh Department of Computer Science and Engineering Faculty of Engineering International University of Business Agriculture and Technology Uttara Dhaka 1230 Bangladesh

Background: Cardiovascular Diseases (CVD) requires precise and efficient diagnostic tools. The manual analysis of Electrocardiograms (ECGs) is labor-intensive, necessitating the development of automated methods to enhance diagnostic accuracy and efficiency. Objective: This research aimed to develop an automated ECG classification using Continuous Wavelet Transform (CWT) and Deep Convolutional Neural Network (DCNN), and transform 1D ECG signals into 2D spectrograms using CWT and train a DCNN to accurately detect abnormalities associated with CVD. The DCNN is trained on datasets from PhysioNet and the MIT-BIH arrhythmia dataset. The integrated CWT and DCNN enable simultaneous classification of multiple ECG abnormalities along-side normal signals. Material and Methods: This analytical observational research employed CWT to generate spectrograms from 1D ECG signals, as input to a DCNN trained on di-verse datasets. The model is evaluated using performance metrics, such as precision, specificity, recall, overall accuracy, and F1-score. Results: The proposed algorithm demonstrates remarkable performance metrics with a precision of 100% for normal signals, an average specificity of 100%, an average recall of 97.65%, an average overall accuracy of 98.67%, and an average F1-score of 98.81%. This model achieves an approximate average overall accuracy of 98.67%, highlighting its effectiveness in detecting ***: The integration of CWT and DCNN in ECG classification improves accuracy and classification capabilities, addressing the challenges with manual analy-sis. This algorithm can reduce misdiagnoses in primary care and enhance efficiency in larger medical institutions. By contributing to automated diagnostic tools for cardiovascular disorders, it can significantly improve healthcare practices in the field of CVD detection. © Journal of Biomedical Physics and engineering.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Enhancing the efficiency of lung cancer screening: predictive models utilizing deep learning from CT scans

引用

Neural Computing and Applications 2025年 1-19页

作者： Tawfeek, Medhat A. Alrashdi, Ibrahim Alruwaili, Madallah Shaban, Warda M. Talaat, Fatma M. Department of Computer Science Faculty of Computers and Information Menoufia University Shebin Elkom32511 Egypt Department of Computer Science College of Computer and Information Sciences Jouf University Sakakah Saudi Arabia Department of Computer Engineering and Networks College of Computer and Information Sciences Jouf University Sakakah Saudi Arabia Department of Communication and Electronics Engineering Nile Higher Institute for Engineering and Technology Mansoura Egypt Faculty of Artificial Intelligence Kafrelsheikh University Kafrelsheikh Egypt Faculty of Computer Science and Engineering New Mansoura University Gamasa35712 Egypt

Lung cancer is the most lethal form of cancer. This paper introduces a novel framework to discern and classify pulmonary disorders such as pneumonia, tuberculosis, and lung cancer by analyzing conventional X-ray and CT scan images called lung cancer risk prediction (LCRP) model. LCRP has four modules, namely data collection and preprocessing, data augmentation module, image segmentation module, and prediction module. Actually, LCRP employs three deep learning models;sequential model, functional model, and transfer model on publicly available training datasets. Convolutional neural networks (CNNs) have emerged as a highly effective field in machine learning, particularly for image datasets in the field of biomedical applications. The primary goal is to validate these models by comparing their performance with other models in order to determine their effectiveness in addressing challenging datasets. Our research has revealed a noteworthy enhancement in the efficiency of binary and multi-class classification using mask R-CNN image segmentation. During the model training process, a combination of Adam and stochastic gradient descent dual optimizers has been used to improve performance. LCRP have outperformed current pre-trained models by minimizing training parameters, computational costs, and overhead. It introduces 98.5% accuracy, 88.7% specificity, 89% sensitivity, 89.2% precision, and 89.09% F-measure. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Lung cancer

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：