检索结果-内蒙古大学图书馆

A Lightweight CNN Based on Transfer Learning for COVID-19 Diagnosis

computers, Materials & Continua 2022年第7期72卷 1123-1137页

作者： Xiaorui Zhang Jie Zhou Wei Sun Sunil Kumar Jha Wuxi Research Institute Nanjing University of Information Science&TechnologyWuxi214100China Engineering Research Center of Digital Forensics Ministry of EducationJiangsu Engineering Center of Network MonitoringSchool of Computer and SoftwareNanjing University of Information Science&TechnologyNanjing210044China Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology(CICAEET) Nanjing University of Information Science&TechnologyNanjing210044China School of Automation Nanjing University of Information Science&TechnologyNanjing 210044 China IT Fundamentals and Education Technologies Applications University of Information Technology and Management in RzeszowRzeszow Voivodeship100031Poland

The key to preventing the COVID-19 is to diagnose patients quickly and *** have shown that using Convolutional Neural Networks(CNN)to analyze chest Computed Tomography(CT)images is helpful for timely COVID-19 ***,personal privacy issues,public chest CT data sets are relatively few,which has limited CNN’s application to COVID-19 ***,many CNNs have complex structures and massive *** if equipped with the dedicated Graphics Processing Unit(GPU)for acceleration,it still takes a long time,which is not conductive to widespread *** solve above problems,this paper proposes a lightweight CNN classification model based on transfer *** the lightweight CNN MobileNetV2 as the backbone of the model to solve the shortage of hardware resources and computing *** order to alleviate the problem of model overfitting caused by insufficient data set,transfer learning is used to train the *** study first exploits the weight parameters trained on the ImageNet database to initialize the MobileNetV2 network,and then retrain the model based on the CT image data set provided by *** results on a computer equipped only with the Central Processing Unit(CPU)show that it consumes only 1.06 s on average to diagnose a chest CT *** to other lightweight models,the proposed model has a higher classification accuracy and reliability while having a lightweight architecture and few parameters,which can be easily applied to computers without GPU ***:***/ZhouJie-520/paper-codes.

关键词： Convolutional neural networks chest computed tomography image COVID-19 transfer learning mobileNetv2

来源：评论

学校读者我要写书评

暂无评论

A Review on Content Based Image Retrieval Techniques

A Review on Content Based Image Retrieval Techniques

引用

2023 International Conference on Circuit Power and Computing Technologies, ICCPCT 2023

作者： Suresh Kumar, J.S. Maria Celestin Vigila, S. Noorul Islam Centre for Higher Education Kumaracoil Department of Computer Science and Engineering Tamilnadu Kanyakumari India Noorul Islam Centre for Higher Education Kumaracoil Department of Information Technology Tamilnadu Kanyakumari India

ISBN: (纸本)9798350333244

Significant interest in Content-Based Image Retrieval (CBIR) has been identified over the last two decades, which utilizes image and video perception to find adequate images. The availability of graphical and multimedia data, as well as the expansion of the Internet, demands field matching. Because of the lack of visual content as a ranking clue, methodologies for visual retrieval that use text search methods may suffer from lack of consistency between full texts and visual content. Many programmers and tools have been developed to help users develop, implement, and conduct research on visual or audio content, as well as to browse large multimedia repositories. A benchmark for transmission model has been established DICOM, and patient data can be ended up saving along with the images, although there are still a few issues with standardization. Several papers have proposed content-based access to medical images to aid clinical decision-making and simplify medical evidence, and instances for integrating based on their content access methods into images and communication systems have been developed. This work provides a thorough evaluation of current advancements in the fields of CBIR. This investigation utilizes key characteristics of numerous retrieval methods for images and frameworks, ranging from basic identification of features from images to current deep-learning approaches. © 2023 IEEE.

关键词： Hospital data processing

来源：评论

学校读者我要写书评

暂无评论

Integrating Digital Twins with AI for Real-Time Intrusion Detection in Smart Infrastructure Networks

Integrating Digital Twins with AI for Real-Time Intrusion De...

引用

2024 International Conference on Intelligent Algorithms for Computational Intelligence Systems, IACIS 2024

作者： Sasikala, M. Mahaboob John, Y.M. Jothi, B. Nandhini, S. Senthil Kumar, S. Sona College of Technology Department of Information Technology Salem India Mahendra College of Engineering Ece Department Salem India Srm Institute of Science and Technology Department of Computational Intelligence Kattankulathur India Karpagam Academy of Higher Education Computer Science and Engineering Coimbatore India R.M.K. College of Engineering and Technology Department of Mechanical Engineering Thiruvallur India

ISBN: (纸本)9798350360660

The integration of Digital Twins with Artificial Intelligence (AI) represents a revolutionary approach to enhancing real-time intrusion detection in smart infrastructure networks. Digital Twins, as virtual replicas of physical assets, enable continuous monitoring and predictive analysis, while AI provides advanced analytical capabilities for identifying and mitigating potential security threats. This paper presents a comprehensive framework that leverages Digital Twins in conjunction with AI algorithms to detect and respond to intrusions in smart infrastructure networks. By simulating network behavior and employing machine learning models to analyze data patterns, the proposed system ensures robust security measures. One of the proposed techniques involves the use of a hybrid anomaly detection algorithm combining Autoencoders and Recurrent Neural Networks (RNN). The Autoencoder is utilized to learn a compact representation of the normal network behavior by reducing dimensionality and reconstructing inputs, while the RNN captures temporal dependencies and sequences within the network data. This hybrid model enhances the detection of both known and unknown intrusion patterns by focusing on deviations from the learned normal behavior. The integration of these AI components with Digital Twins enables a more nuanced and accurate understanding of network anomalies, thereby improving the system's ability to detect and respond to intrusions promptly. Experimental results demonstrate the efficacy of this approach in real-time threat detection, showcasing significant improvements in response times and accuracy. This integration not only enhances the resilience of smart infrastructure but also paves the way for future advancements in secure and intelligent network management. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Robust Method for Embedding an Image Inside Cover Image Based on Least Significant Bit Steganography

引用

Informatica (Slovenia) 2022年第9期46卷 53-60页

作者： Almola, Sahera A.S. Qasim, Najat H. Ali Abed Alasadi, Hamid Department of Information System College of Computer Sciences and Information Technology University of Basrah Iraq Department of Computer Science College of Education for Pure Sciences University of Basrah Iraq Communications Engineering Department Iraq University College Istqlal Street Basra61004 Iraq

According to the enormous evolution of the internet and communications, the security of private or sensitive information has become the important issue. The private information can be passed between a sender and a receiver with high security using Cryptography and Steganography. By the cryptography, as the information can be secured with the cipher key for encryption. By the Steganography, the secret information can hide within usual data such as images, videos, audios. In this paper we proposed the robust method that includes two phases. The first phase consists of two stages. In the first stage we encrypt a secret image using encryption algorithm in order of increasing security of information. In the second stage, we complete the first stage for embedding the most significant bits (MSB) of the encrypted image into the least significant bits (LSB) of the cover image for instituting the stego image. The second phase is the obverse of the first phase, where, the encrypted image is retrieved from the stego image and then, decrypted process construct the secret image. The proposed method is efficient in terms of security compare with the other methods. Where, both encryption and embedding algorithms have an efficient role for embedding the secret image and preserving the good visual quality of stego images. Furthermore, extraction algorithms obtained better and faster results to a restoration of the secret image. © 2022 Slovene Society Informatika. All rights reserved.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

DDoS Attack Detection using Enhanced Long-Short Term Memory with Hybrid Machine Learning Algorithms 3

DDoS Attack Detection using Enhanced Long-Short Term Memory ...

引用

3rd International Conference on Smart Electronics and Communication, ICOSEC 2022

作者： Sinthuja, M. Suthendran, K. Kalasalingam Academy of Research and Education Department of Computer Science and Engineering India Kalasalingam Academy of Research and Education Department of Information Technology India

ISBN: (数字)9781665497640

ISBN: (纸本)9781665497640

The Internet of Things (IoT) environment's heterogeneous components make the distributed denial-of-service (DDoS) attack a security challenge. The dependency on the network topology is one of the various drawbacks of the DDoS detection techniques currently in use. In this research work, a new variant of long-short term memory (LSTM) is proposed to detect DDoS attacks in the IoT environment. The proposed method uses a new hybrid method for optimizing the parameters of LSTM based on bacterial foraging optimization (BFO) with a firefly algorithm (FA) called BFOFA-LSTM. The performance of comparison algorithms is examined using two types of datasets including BoT-IoT and CICDDoS2019 and four different performance indicators are considered such as sensitivity, specificity, accuracy, and F-Measure. The proposed BFOFALSTM detection method produced a high detection rate when compared with other literature algorithms. © 2022 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

An Software Defined Networking (SDN) Enhanced Edge Computing Framework for Internet of Healthcare Things (IoHT)

An Software Defined Networking (SDN) Enhanced Edge Computing...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Anh, Dang Van Chehri, Abdellah Quy, Nguyen Minh Hue, Chu Thi Minh Nguyen, Dinh C. Quy, Vu Khanh Hung Yen University of Technology and Education Faculty of Information Technology Hungyen Viet Nam Royal Military College of Canada Department of Mathematics and Computer Science Kingston Canada Fpt University Faculty of Software Engineering Hanoi Viet Nam The University of Alabama Department of Electrical and Computer Engineering HuntsvilleAL United States

ISBN: (纸本)9798350351255

The rapid proliferation of intelligent Internet of Health Things (IoHT) applications within the context of the COVID-19 pandemic has exerted significant strain on the backhaul network infrastructure. This paper aims to introduce a novel framework that leverages software-defined networking (SDN) to enhance edge computing capabilities. This framework will expect to facilitate dynamic and adaptable communication between edge and cloud servers, specifically designed to support real-time Internet of Health Things applications. Through the establishment of a connection between servers and the Software-Defined Networking controller, the system is expected to facilitate load balancing, network optimization, and the utilization of resources in an efficient manner. This, in turn, enables the provision of real-time healthcare services. Ultimately, the efficacy of the suggested framework is assessed by analyzing its impact on service response time. The research results indicate that the proposed framework significantly benefits IoHT systems' service response times across various workloads and traffic. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Semantic Segmentation for Image Understanding 15

Semantic Segmentation for Image Understanding

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Thangarasu, N. Sohal, Jagmeet Umamaheswari, B. Singh, Jagtej Manjunatha, R. Shelke, Ganesh C. Department of Computer Science Karpagam Academy of Higher Education Coimbatore641021 India Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Department of Computer Science and Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai127 India Chitkara Centre for Research and Development Chitkara University Himachal Pradesh 174103 India Karnataka Bangalore India Department of Information Technology Vishwakarma Institute of Information Technology Pune India

ISBN: (纸本)9798350370249

Semantic segmentation is a way of photo knowhow that entails labeling the objects in a picture on the pixel degree and assigning every pixel within the photograph a category label. This method is utilized in PC imaginative and prescient programs to construct a representation of a scene from digital photographs. It may be used to correctly phase discrete items consisting of vehicles, pedestrians, and timber, as well as more summary standards, which include shadows and reflections. On the way to achieve success, semantic segmentation algorithms require a large amount of designated labeling and accurate pixel-degree statistical analysis. Latest advances in deep mastering strategies have allowed for the improvement of more sophisticated algorithms that could achieve incredible effects on hard-picture segmentation datasets. Those strategies have progressed the accuracy and efficiency of the photograph know-how algorithms, allowing them to carry out duties that include scene understanding, item identification, scene type, and pixel-stage segmentation. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Real-time 3D Human Pose Estimation Through Augmented Reality technology and Transpose Model 3

Real-time 3D Human Pose Estimation Through Augmented Reality...

引用

3rd International Conference on Artificial Intelligence, Internet of Things and Cloud Computing technology, AIoTC 2024

作者： Cheng, Chen Xu, Huahu Kang, Jian School of Computer Engineering and Science Shanghai University Shanghai200444 China Languages and Information Technology Ministry of Education Northwest Minzu University Key Laboratory of China's Ethnic Lanzhou730030 China

ISBN: (纸本)9798331530280

With the rapid development of virtual reality and augmented reality technologies, real-time 3D human pose estimation plays a key role in various interactive applications. This paper proposes a real-time 3D human pose estimation method based on augmented reality technology and the Transpose model. This method significantly improves the pose estimation accuracy in complex scenes by combining the scene perception module and the spatiotemporal feature module. We conducted extensive experimental verification on the Human3.6M dataset, and the results showed that the proposed method performed well in different activities and multiple perspectives. Through ablation experimental analysis, we further confirmed the contribution of each module to the overall performance. The final experimental results show that the complete model achieved the best performance in terms of MPJPE, MPVE and Angular error, verifying the effectiveness and stability of our method. This study provides an important reference for real-time human pose estimation in augmented reality and demonstrates its great potential in practical applications. © 2024 IEEE.

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

LESaET: Low-Dimensional Embedding Method for Link Prediction Combining Self-Attention and Enhanced-TuckER

LESaET: Low-Dimensional Embedding Method for Link Prediction...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Ding, Lichao Zhao, Jing Lu, Kai Hao, Zenghao Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (纸本)9781665410205

Knowledge graphs (KGs) provide a structured representation of the real world through entity-relation triples. However, current KGs are often incomplete, typically containing only a small fraction of all possible facts. This involves inferring missing content from existing information, a task known as link prediction. Existing methods in the field of link prediction struggle with controlling the dimensionality of embedding vectors or suffer from overly complex models. In order to tackle these challenges, we introduce a method in this paper, named Low-Dimensional Embedding Method for Link Prediction Combining Self-Attention and Enhanced-TuckER (LESaET). LESaET leverages both self-attention mechanisms and tensor factorization to learn expressive contextual-enhanced representations of KGs. Specifically, LESaET employs the multi-head self-attention mechanism of Transformer as an encoder to capture the mutual information between entities and relationships, and utilizes Enhanced-TuckER as a decoder, ultimately achieving expressive low-dimensional embeddings for link prediction tasks. LESaET demonstrates competitive performance compared to advanced methods on standard datasets. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

ConvBLS: An Effective and Efficient Incremental Convolutional Broad Learning System Combining Deep and Broad Representations

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第10期5卷 5075-5089页

作者： Lei, Chunyu Guo, Jifeng Chen, C. L. Philip South China University of Technology Guangdong Provincial Key Laboratory of Computational Intelligence and Cyberspace Information School of Computer Science and Engineering Guangzhou510006 China Pazhou Lab Brain and Affective Cognitive Research Center Guangzhou510335 China Engineering Research Center of the Ministry of Education on Health Intelligent Perception and Paralleled Digital-Human Guangzhou510006 China

Broad learning system (BLS) has to undergo a vectorization operation before modeling image data, which makes it challenging for BLS to learn local semantic features. Thus, various convolutional-based broad learning systems (C-BLSs) have been introduced to address these challenges. Regrettably, the existing C-BLS variants either lack an efficient training algorithm and incremental learning capability or suffer from poor performance. To this end, we propose a novel convolutional broad learning system (ConvBLS) based on the spherical K-means (SKM) algorithm and two-stage multiscale (TSMS) feature fusion, which consists of the convolutional feature layer (CFL), convolutional enhancement layer (CEL), TSMS feature fusion layer, and output layer. First, unlike the current C-BLS, the simple yet efficient SKM algorithm is utilized to learn the weights of CFLs. Compared with random filters, the SKM algorithm enables the CFL to learn more comprehensive spatial features. Second, to further mine the local semantic features, CELs are established to expand the feature space. Third, the TSMS feature fusion layer is proposed to extract more effective multiscale features by integrating deep and broad representations. Thanks to the above elaborate design and the pseudoinverse calculation of the output layer weights, our proposed ConvBLS method is unprecedentedly efficient and effective. Finally, the corresponding incremental learning algorithms are presented for rapid remodeling if the model deems to expand. Experiments and comparisons demonstrate the superiority of our method. © 2024 IEEE.

关键词： Image classification

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：