检索结果-内蒙古大学图书馆

Efficient and lightweight CNN model for COVID-19 diagnosis from CT and X-ray images using customized pruning and quantization techniques

引用

Neural Computing and Applications 2025年 1-20页

作者： Sriwiboon, Nattavut Department of Computer Science and Information Technology Faculty of Science and Health Technology Kalasin University Kalasin Thailand

The coronavirus disease 2019 (COVID-19) has posed significant challenges globally, with image classification becoming a critical tool for detecting COVID-19 from chest X-ray and CT images. Convolutional neural network (CNN) architectures are widely employed for this purpose, yet many previous models have struggled to balance high accuracy with low storage requirements, limiting their applicability in resource-constrained environments. This paper introduces an efficient and lightweight CNN model optimized for COVID-19 diagnosis through pruning and quantization techniques, addressing these limitations. Our approach significantly reduces storage size and parameter count while maintaining high accuracy. We customized several CNNs, particularly EfficientNetV2 and MobileNetV2, to achieve these goals. We specifically selected EfficientNetV2 and MobileNetV2 due to their superior balance of accuracy and efficiency, making them well-suited for lightweight medical applications. EfficientNetV2’s storage size has been reduced from 568 to 142 KB through customized pruning, achieving 98.9% accuracy for 2-class and 98.28% for 3-class X-ray classification, as well as 98.3% and 98.05% for 2-class and 3-class CT classification, respectively. MobileNetV2, after hybrid pruning and quantization, achieved a remarkably low storage size of 70 KB, making it highly effective for deployment in environments with limited resources. Despite a slight accuracy decrease of 0.9 to 1.58%, both models have maintained robust performance suitable for COVID-19 diagnosis. The results demonstrate that our pruning and quantization techniques are effective in developing lightweight, high-performance CNN models, making them suitable for broader applications in medical imaging where both efficiency and accuracy are critical. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Enhancing Arabic Cyberbullying Detection with End-to-End Transformer Model

引用

computer Modeling in engineering & sciences 2024年第11期141卷 1651-1671页

作者： Mohamed A.Mahdi Suliman Mohamed Fati Mohamed A.G.Hazber Shahanawaj Ahamad Sawsan A.Saad Information and Computer Science Department College of Computer Science and EngineeringUniversity of Ha’ilHa’il55476Saudi Arabia Information Systems Department College of Computer and Information SciencesPrince Sultan UniversityRiyadh11586Saudi Arabia Software Engineering Department College of Computer Science and EngineeringUniversity of Ha’ilHa’il55476Saudi Arabia Computer Engineering Department College of Computer Science and EngineeringUniversity of Ha’ilHa’il55476Saudi Arabia

Cyberbullying,a critical concern for digital safety,necessitates effective linguistic analysis tools that can navigate the complexities of language use in online *** tackle this challenge,our study introduces a new approach employing Bidirectional Encoder Representations from the Transformers(BERT)base model(cased),originally pretrained in *** model is uniquely adapted to recognize the intricate nuances of Arabic online communication,a key aspect often overlooked in conventional cyberbullying detection *** model is an end-to-end solution that has been fine-tuned on a diverse dataset of Arabic social media(SM)tweets showing a notable increase in detection accuracy and sensitivity compared to existing *** results on a diverse Arabic dataset collected from the‘X platform’demonstrate a notable increase in detection accuracy and sensitivity compared to existing methods.E-BERT shows a substantial improvement in performance,evidenced by an accuracy of 98.45%,precision of 99.17%,recall of 99.10%,and an F1 score of 99.14%.The proposed E-BERT not only addresses a critical gap in cyberbullying detection in Arabic online forums but also sets a precedent for applying cross-lingual pretrained models in regional language applications,offering a scalable and effective framework for enhancing online safety across Arabic-speaking communities.

关键词： Cyberbullying offensive detection Bidirectional Encoder Representations from the Transformers(BERT) continuous bag of words Social Media natural language processing

来源：评论

学校读者我要写书评

暂无评论

Contactless and Real-time Hand Gesture Recognition using Inductive Proximity Technique for Wrist-worn Wearables

引用

IEEE Sensors Journal 2025年第11期25卷 20474-20485页

作者： Lin, Pei-Jung Shih, Chi-Huang Weng, Tzu-Hsuan Feng Chia University Department of Information Engineering and Computer Science Taichung407 Taiwan National Chin-Yi University of Technology Department of Computer Science and Information Engineering Taichung411 Taiwan

This study proposes a contactless and real-time hand gesture recognition system suitable for smartwatches. The proposed system adopts inductive proximity sensing to collect Mechanomyography (MMG) signals induced by finger-based gestures above the wrist. After the signal processing and feature extraction stages, machine-learning models can be built for gesture classification. Compared with the Electromyography (EMG)-based method generally deployed in the forearm, inductive MMG applies an electromagnetic field to the body surface and is suitable for use on the wrist. Compared to the existing contact methods, such as EMG and accelerometer-based MMG, the inductive MMG method does not require contact with the body surface to collect muscle action signals and can avoid interference from environmental factors such as sweat and dust. The main contributions of this study are (1) a watch-type prototype with inductive MMG sensing technique, including hardware and firmware;(2) a lightweight and efficient signal processing mechanism that can capture the inductive signal characteristics of gestures for the above-mentioned embedded system (i.e., watch-type prototype);and (3) the tempo-spatial feature extraction method to improve the accuracy of gesture recognition. The experiment results show that for six common machine learning models, the gesture recognition accuracy of the proposed system is above 95%, with a maximum of 97.47%. In the briefing control application for verification purposes, the average accuracy of the inductive gesture recognition system can achieve 98.26%, and the average processing time is 14.37 ms. According to the experimental results, the inductive MMG system can provide a feasible gesture recognition solution for wrist-worn wearable devices. © 2001-2012 IEEE.

关键词： Firmware

来源：评论

学校读者我要写书评

暂无评论

Abnormal event detection in surveillance videos through LSTM auto-encoding and local minima assistance

引用

Discover Internet of Things 2025年第1期5卷 1-25页

作者： Sengonul, Erkan Samet, Refik Abu Al-Haija, Qasem Alqahtani, Ali Alsemmeari, Rayan A. Alghamdi, Bandar Alturki, Badraddin Alsulami, Abdulaziz A. Department of Computer Engineering Ankara University Ankara06100 Turkey Department of Cybersecurity Faculty of Computer & Information Technology Jordan University of Science and Technology PO Box 3030 Irbid22110 Jordan Department of Networks & Communications Engineering College of Computer Science & Information Systems Najran University Najran61441 Saudi Arabia Department of Information Technology Faculty of Computing and Information Technology King Abdulaziz University Jeddah21589 Saudi Arabia Department of Information Systems Faculty of Computing and Information Technology King Abdulaziz University Jeddah21589 Saudi Arabia

Abnormal event detection in video surveillance is critical for security, traffic management, and industrial monitoring applications. This paper introduces an innovative methodology for anomaly detection in video data, encompassing three primary stages: preprocessing, feature learning, and anomaly detection. We employ background subtraction and noise reduction during preprocessing to refine the data. The feature-learning stage involves training an LSTM autoencoder to capture the essential features of normal video sequences. For anomaly detection, we map video data to a lower-dimensional space (latent code) and compare it against the distribution of codes from normal sequences. We determine regularity scores and identify local minima points exceeding a specified threshold while scrutinizing shadows between adjacent maxima to confirm and pinpoint anomalies. When tested on the CUHK Avenue and UMN datasets, our methodology demonstrated performance with AUCs of 93.8% and 94.1%, respectively, outperforming several baseline models. Our results show the high precision of our method that can detect anomalies, highlighting its potential advantages that it can achieve for enhancing systems of surveillance. © The Author(s) 2025.

关键词： Noise abatement

来源：评论

学校读者我要写书评

暂无评论

Hybrid harris hawk-arithmetic optimization with deep learning-driven object detection and classification for surveillance video analysis

引用

Multimedia Tools and Applications 2024年第11期84卷 9023-9044页

作者： Saikrishnan, V. Karthikeyan, M. Department of Computer and Information Science Faculty of Science Annamalai University Tamil Nadu Chidambaram India

Video surveillance has played a pivotal role in ensuring the safety and security of the public across different sectors, including retail, transportation, and urban environments. Object detection (OD) in surveillance videos includes identifying and localizing certain objects, namely vehicles, persons, or suspicious items. Conventional approaches often struggle with variations in complex backgrounds, lighting conditions, and occlusions. Deep learning (DL)-based techniques, particularly convolutional neural network (CNN), have shown outstanding performance in attaining accurate OD and handling these challenges. Despite the success of DL-based OD in surveillance videos, various challenges exist such as dealing with variations in camera viewpoints, recognizing small objects, ensuring robustness to adverse weather conditions, and handling occlusions. This study presents a Hybrid Harris Hawk-Arithmetic Optimization with Deep Learning-Driven Object Detection and Classification (HHAODL-ODC) method for Surveillance Video Analysis. The purpose of the study is to develop a HHAODL-ODC technique for object detection and classification. To accomplish this, the HHAODL-ODC technique follows two major components namely object detector and object classifier. Primarily, the HHAODL-ODC technique employs a YOLO-v5 object detector with EfficientNet as a backbone network. Next, the classification of objects takes place using the Spatial Angular-Stacked Sparse Autoencoder (SA-SSAE) model. The HHAO algorithm has been applied for the hyperparameter tuning process to improve the object classification results of the EfficientNet model. The stimulation validation of the HHAODL-ODC method is tested using a benchmark surveillance video dataset. The experimental outcomes highlighted the superior performance of the HHAODL-ODC algorithm over other DL techniques under various measures. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Object detection

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

Integration of data science with the intelligent IoT(IIoT): Current challenges and future perspectives

引用

Digital Communications and Networks 2025年第2期11卷 280-298页

作者： Inam Ullah Deepak Adhikari Xin Su Francesco Palmieri Celimuge Wu Chang Choi Department of Computer Engineering Gachon University University of Electronic Science and Technology of China College of Information Science and Engineering Hohai University Department of Computer Science University of Salerno Graduate School of Informatics and Engineering The University of Electro-Communications

The Intelligent Internet of Things(IIoT) involves real-world things that communicate or interact with each other through networking technologies by collecting data from these “things” and using intelligent approaches, such as Artificial Intelligence(AI) and machine learning, to make accurate decisions. Data science is the science of dealing with data and its relationships through intelligent approaches. Most state-of-the-art research focuses independently on either data science or IIoT, rather than exploring their integration. Therefore, to address the gap, this article provides a comprehensive survey on the advances and integration of data science with the Intelligent IoT(IIoT) system by classifying the existing IoT-based data science techniques and presenting a summary of various characteristics. The paper analyzes the data science or big data security and privacy features, including network architecture, data protection, and continuous monitoring of data, which face challenges in various IoT-based systems. Extensive insights into IoT data security, privacy, and challenges are visualized in the context of data science for IoT. In addition, this study reveals the current opportunities to enhance data science and IoT market development. The current gap and challenges faced in the integration of data science and IoT are comprehensively presented, followed by the future outlook and possible solutions.

关键词： Data science Internet of things (IoT) Big data Communication systems Networks Security Data science analytics

来源：评论

学校读者我要写书评

暂无评论

Component adaptive sparse representation for hyperspectral image classification

引用

Soft Computing 2024年第20期28卷 11911-11925页

作者： Bortiew, Amos Patra, Swarnajyoti Bruzzone, Lorenzo Department of Computer Science and Engineering Tezpur University Assam Tezpur India Department of Information Engineering and Computer Science University of Trento Trento Italy

Techniques that exploit spectral-spatial information have proven to be very effective in hyperspectral image classification. Joint sparse representation classification (JSRC) is one such technique which has been extensively used for this purpose. However, the use of a single fixed-sized window has limited its ability to incorporate spatial information. Several techniques such as multiscale superpixels based sparse representation classification (MSSRC), multiscale adaptive sparse representation classification (MASRC) and Discriminant Subdictionary Learning (DSDL) have tried to overcome this drawback by fusing information from different scales. However, their inability to simultaneously consider the correlated information at different scales and appropriate spatial neighbourhoods limits their performance. In order to better model contextual information, in this paper, we propose a modified max-tree and modified min-tree to represent the connected components of the image. Then, by exploiting these connected components, adaptive multiscale windows are defined. The potentiality of the proposed technique is validated by performing a comparative analysis with four state-of-the-art sparse representation methods using three real hyperspectral datasets. For a fixed training and test sets of University of Pavia and Indian Pines dataset, our proposed technique provides at least 3% and 2%, respectively higher classification results than the best state-of-the-art method. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Segmentation and Classification of Skin Cancer Diseases Based on Deep Learning: Challenges and Future Directions

引用

IEEE Access 2025年 13卷 90163-90184页

作者： Khalaf, Abdulrahman Dira Hamdan, Hazlina Halin, Alfian Bin Abdul Manshor, Noridayu Faculty of Computer Science and Information Technology Department of Computer Science Selangor Malaysia University of Fallujah Department Computer Centre Department Anbar Iraq Faculty of Computer Science and Information Technology Department of Multimedia Serdang Malaysia

Deep Learning (DL) techniques have significantly improved the diagnostic accuracy in healthcare, particularly for detecting and classifying skin cancer. These advancements are expected to assist healthcare professionals in delivering more accurate, efficient, and timely diagnosis, ultimately improving patient outcomes and facilitating early detection and treatment of skin cancer. Additionally, medical imaging technologies, such as magnetic resonance imaging (MRI) and computed tomography (CT) scans remain critical tools for diagnosing dermatological conditions. However, interpreting these images can be challenging because of the overlapping structures and varying image quality. This study explored the application of DL in skin cancer diagnosis, with a particular focus on advances in image segmentation and classification. It reviews the development of DL-based models, including Convolutional Neural Networks (CNNs), and evaluates their effectiveness in skin lesion detection. This study examined the critical challenges associated with deploying DL models in clinical practice, including dataset diversity, model interpretability, and the feasibility of real-world implementation. It explores essential factors such as the selection of network architectures and data preprocessing techniques, emphasizing their influence on model performance. Additionally, this study identifies research gaps and suggests future directions for optimizing DL models for dermatological applications. © 2013 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhanced MADM Strategy with Heptapartitioned Neutrosophic Distance Metrics

引用

Neutrosophic Sets and Systems 2025年 78卷 74-96页

作者： Eassa, Mohamed Myvizhi, M. Elkholy, Mohamed Abdelhafeez, Ahmed Elbehiery, Hussam Computer Science Department Faculty of Information System and Computer Science October 6 University Giza12585 Egypt Applied Science Research Center Applied Science Private University Amman Jordan Department of Mathematics KPR Institute of Engineering and Technology Tamilnadu Coimbatore India Faculty of Computer Science& Engineering Alamein International University Egypt

In this work, a novel methodological approach to multi-attribute decision-making problems is developed and the notion of Heptapartitioned Neutrosophic Set Distance Measures (HNSDM) is introduced. By averaging the Penta-Partitioned Neutrosophic Distance Measures under particular conditional criteria, the suggested technique ranks the options. Additionally, we explore the fundamental characteristics of HNSDM and provide several illustrative theorems. The Heptapartitioned Neutrosophic Set Distance Measures are formulated based on the Hepta Neutrosophic Set. Lastly, a practical numerical example is provided to illustrate the efficacy of the suggested methodology. © 2025, University of New Mexico. All rights reserved.

关键词： Heptapartitioned Neutrosophic set Heptapartitioned Neutrosophic set and MADM strategy Heptapartitioned set Neutrosophic sine distance measure

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：