检索结果-内蒙古大学图书馆

Spatial Correlation Module for Classification of Multi-Label Ocular Diseases Using Color Fundus Images

computers, Materials & Continua 2023年第7期76卷 133-150页

作者： Ali Haider Khan Hassaan Malik Wajeeha Khalil Sayyid Kamran Hussain Tayyaba Anees Muzammil Hussain Department of Software Engineering Faculty of Computer SciencesLahore Garrison UniversityLahorePakistan Department of Computer Science School of Systems and TechnologyUniversity of Management and TechnologyLahore54000Pakistan Department of Computer Science&Information Technology University of Engineering and Technology(UET)PeshawarPakistan Department of Computer Science TIMES InstituteMultan60000Pakistan Department of Software Engineering School of Systems and TechnologyUniversity of Management and TechnologyLahore54000Pakistan

To prevent irreversible damage to one’s eyesight,ocular diseases(ODs)need to be recognized and treated *** fundus imaging(CFI)is a screening technology that is both effective and *** to CFIs,the early stages of the disease are characterized by a paucity of observable symptoms,which necessitates the prompt creation of automated and robust diagnostic *** traditional research focuses on image-level diagnostics that attend to the left and right eyes in isolation without making use of pertinent correlation data between the two sets of *** addition,they usually only target one or a few different kinds of eye diseases at the same *** this study,we design a patient-level multi-label OD(PLML_ODs)classification model that is based on a spatial correlation network(SCNet).This model takes into consideration the relevance of patient-level diagnosis combining bilateral eyes and multi-label ODs ***_ODs is made up of three parts:a backbone convolutional neural network(CNN)for feature extraction i.e.,DenseNet-169,a SCNet for feature correlation,and a classifier for the development of classification *** DenseNet-169 is responsible for retrieving two separate sets of attributes,one from each of the left and right *** then,the SCNet will record the correlations between the two feature sets on a pixel-by-pixel *** the attributes have been analyzed,they are integrated to provide a representation at the patient *** the whole process of ODs categorization,the patient-level representation will be *** efficacy of the PLML_ODs is examined using a soft margin loss on a dataset that is readily accessible to the public,and the results reveal that the classification performance is significantly improved when compared to several baseline approaches.

关键词： Ocular disease multi-label spatial correlation CNN eye disease

来源：评论

学校读者我要写书评

暂无评论

A Secure Framework for WSN-IoT Using Deep Learning for Enhanced Intrusion Detection

引用

computers, Materials & Continua 2024年第10期81卷 471-501页

作者： Chandraumakantham Om Kumar Sudhakaran Gajendran Suguna Marappan Mohammed Zakariah Abdulaziz S.Almazyad School of Computer Science&Engineering Vellore Institute of TechnologyChennai CampusChennai600127India School of Electronics&Engineering Vellore Institute of TechnologyChennai CampusChennai600127India Department of Computer Sciences and Engineering College of Applied ScienceKing Saud UniversityRiyadh11543Saudi Arabia Department of Computer Engineering College of Computer and Information SciencesKing Saud UniversityRiyadh11543Saudi Arabia

The security of the wireless sensor network-Internet of Things(WSN-IoT)network is more challenging due to its randomness and self-organized *** detection is one of the key methodologies utilized to ensure the security of the *** intrusion detection mechanisms have issues such as higher misclassification rates,increased model complexity,insignificant feature extraction,increased training time,increased run time complexity,computation overhead,failure to identify new attacks,increased energy consumption,and a variety of other factors that limit the performance of the intrusion system *** this research a security framework for WSN-IoT,through a deep learning technique is introduced using Modified Fuzzy-Adaptive DenseNet(MF_AdaDenseNet)and is benchmarked with datasets like NSL-KDD,UNSWNB15,CIDDS-001,Edge IIoT,Bot *** this,the optimal feature selection using Capturing Dingo Optimization(CDO)is devised to acquire relevant features by removing redundant *** proposed MF_AdaDenseNet intrusion detection model offers significant benefits by utilizing optimal feature selection with the CDO *** results in enhanced Detection Capacity with minimal computation complexity,as well as a reduction in False Alarm Rate(FAR)due to the consideration of classification error in the fitness *** a result,the combined CDO-based feature selection and MF_AdaDenseNet intrusion detection mechanism outperform other state-of-the-art techniques,achieving maximal Detection Capacity,precision,recall,and F-Measure of 99.46%,99.54%,99.91%,and 99.68%,respectively,along with minimal FAR and Mean Absolute Error(MAE)of 0.9%and 0.11.

关键词： Deep learning intrusion detection fuzzy rules feature selection false alarm rate accuracy wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

A Lightweight, Secure, and Scalable Blockchain-Fog-IoMT Healthcare Framework with IPFS Data Storage for Healthcare 4.0

引用

SN computer science 2024年第1期5卷 1-11页

作者： Mallick, Soubhagya Ranjan Lenka, Rakesh Kumar Tripathy, Pradyumna Kumar Rao, D. Chandrasekhar Sharma, Suraj Ray, Niranjan Kumar Computer Science and Engineering International Institute of Information Technology Odisha Bhubaneswar 751003 India Computer Science and Engineering Silicon Institute of Technology Odisha Bhubaneswar 751024 India Information Technology Veer Surendra Sai University of Technology Odisha Burla 768018 India Computer Science and Engineering Guru Ghasidas Vishwavidyalaya Chhattisgarh Bilaspur 495009 India School of Computer Science and Engineering Kalinga Institute of Industrial Technology Odisha Bhubaneswar 751024 India

The gathering, processing, transmission, sharing, and storage of healthcare data was the core idea behind Healthcare 4.0. Currently, most of the existing solutions for offering smart healthcare services rely on cloud-based platforms. The main issues with current healthcare systems include storage overhead, processing speed, scalability, single points of failure, bandwidth requirements, and device connectivity. The recent challenges in the healthcare system motivated us to develop a system by integrating the Internet of Medical Things (IoMT), Blockchain, fog computing, and InterPlanetary File System (IPFS) to achieve decentralization, scalability, security, immutability, and data privacy. In this paper, we propose a novel IoMT and Blockchain framework with fog node computing to reduce latency and speed up processing, as well as to reduce the network congestion, bandwidth requirements, and the main Blockchain network overload. Untrusted devices are connected to the system using a proxy monitor, which records the device’s activity. In addition, the interplanetary file system (IPFS) is integrated with the Blockchain network to store patient data and files in order to ensure the system’s decentralization, scalability, security, and privacy. Moreover, we evaluate the proposed framework in terms of security, scalability, latency, storage, efficiency, and performance. The experimental analysis shows that the proposed framework makes access, searches, uploads, and downloads faster and more secure. © 2024, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Blockchain Efficiency Fog computing IoMT IPFS Scalability Security

来源：评论

学校读者我要写书评

暂无评论

Chinese Relation Extraction Based on Cross-Attention and Multi-feature Perception

Journal of Network Intelligence

引用

Journal of Network Intelligence 2024年第3期9卷 1837-1853页

作者： Xu, Shiao Sun, Shuihua Zhang, Zhiyuan Zhou, Huan School of Electronics and Information Engineering Jingchu University of Technology Jingmen448000 China School of Computer Science and Mathematics Fujian University of Technology Fuzhou350118 China

Relation extraction aims at extracting semantic relations between given pairs of entities from unstructured textual data and is a critical task in information extraction. A relation extraction model based on cross-attention and multi-feature perception is proposed to address the limitations of Chinese relation extraction models that rely solely on characters, which struggle to capture rich semantic information, and the inability to ful ly utilize the textual structural information during neural network feature extraction. First, the model uses BERT to encode sentences and entities to obtain character vector sequences and word vector sequences of sentences, and uses word cross-attention mechanism to capture the key word and word information in sentences to form character and word cross-fused sentence sequences. Second, uses graph convolutional network and deep separable convolutional network to capture syntactic information between nodes and multi-granularity local semantic information in sentence sequences, respectively, and forms sentence features for classification by attention mechanism. Final ly, combines with Softmax classifier for relation classification. Experimental results on the Chinese SanWen dataset demonstrate the superiority of the proposed method over mainstream neural network-based relation extraction methods, with an F1-score of 71.57%. © 2024, Taiwan Ubiquitous information CO LTD. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Unified Approach Integrating Machine Learning Algorithms for Detection of e-Mail Phishing Attacks 1

Unified Approach Integrating Machine Learning Algorithms for...

引用

1st International Conference on Computing, sciences and Communications, ICCSC 2024

作者： Mathur, Abeer Dubey, Abhinav Sudhakar Mahara, Pranav Singh Gandhi, Usha Devi School of Computer Science & Engineering Vellore Institute of Technology Department of Software Systems Vellore India School of Computer Science Engineering & Information Systems Vellore Institute of Technology Department of Information Technology Vellore India

ISBN: (纸本)9798350353648

With the ever-rising risk of phishing attacks, which capitalize on vulnerable human behavior in the contemporary digital space, requires new cybersecurity methods. This literary work contributes to the solution by novel incorporation of three techniques: Support Vector Machine (SVM), Natural Language Processing (NLP) and Random Forest (RF). Utilizing NLP for deep analysis of text in phishing e-mails, SVM for strong categorization and Random Forest's decision making by group helps in improving detection. This combination of language and pattern analysis along with group learning builds a fortified system. This approach differs from prior work on a variety of factors such as reliability, security, integrity, scalability, interpretability, transparency, and robustness. Thorough evaluation on a reliable dataset aimed to demonstrate the method's effectiveness, which resulted in 98.7 % of accuracy in detection. This majorly aims at showcasing the potential of ensemble techniques to combat against cyber-attacks like phishing for laying a strong foundation for a secure digital environment. © 2024 IEEE.

关键词： Phishing

来源：评论

学校读者我要写书评

暂无评论

Cluster Based Concurrent Data Collection with Fault Tolerance for Shared IoT Applications 16

Cluster Based Concurrent Data Collection with Fault Toleranc...

引用

16th International Conference on COMmunication Systems and NETworkS, COMSNETS 2024

作者： Kumar, Arvind Matam, Rakesh Swain, Srinibas Mukherjee, Mithun Indian Institute of Information Technology Guwahati Department of Computer Science and Engineering India Nanjing University of Information Science and Technology Nanjing China

ISBN: (纸本)9798350383119

Sharing IoT device infrastructure by multiple entities or applications for their respective sensing and monitoring needs is an effective way to reduce the upfront setup cost, ownership costs, and also to prevent over provisioning. Concurrent data collection in such a shared environment is a major challenge, given the number of devices and multiple processes relying on that data. Most of the existing works in this direction typically consider network scenarios where devices can reach the base station(s) directly. As this assumption is not always valid, few other works focused on concurrent data collection over multiple-hops. In such a shared multi-hop environment, the chances of device failures are high, especially considering the power constraints of devices. To address the issue of reliability in data collection, this paper presents a cluster-based fault tolerant network structure for concurrent data collection. The proposed work aims to minimize the delay and handles the topology changes in case of faults, and also lowers the transmission count. The validity of the proposed work is shown via analytical and simulation results. © 2024 IEEE.

关键词： Concurrent Data collection in IoT Network topology Shared IoT device infrastructure

来源：评论

学校读者我要写书评

暂无评论

Liver Tumors Segmentation Using 3D SegNet Deep Learning Approach

引用

computer Systems science & engineering 2023年第5期45卷 1655-1677页

作者： G.Nallasivan V.Ramachandran Roobaea Alroobaea Jasem Almotiri Department of Computer Science and Engineering PSN College of Engineering and TechnologyTirunelveli627152Tamil NaduIndia Department of Computer Science and Engineering Gokaraju Rangaraju Institute of Engineering and TechnologyHyderabadTelangana500090India Department of Computer Science College of Computers and Information TechnologyTaif UniversityP.O.Box 11099Taif21944Saudi Arabia Department of Computer Science College of Computers and Information TechnologyTaif UniversityTaif21974Saudi Arabia

An ultrasonic filter detects signs of malignant tumors by analysing the image’s pixel quality fluctuations caused by a liver *** of malignant growth proximity are identified in an ultrasound filter through image pixel quality variations from a liver’s *** changes are more common in alcoholic liver conditions than in other etiologies of cirrhosis,suggesting that the cause may be alcohol instead of liver *** Two-Dimensional(2D)ultrasound data sets contain an accuracy rate of 85.9%and a 2D Computed Tomography(CT)data set of 91.02%.The most recent work on designing a Three-Dimensional(3D)ultrasound imaging system in or close to real-time is *** this article,a Deep Learning(DL)model is implemented and modified to fit liver CT segmentation,and a semantic pixel classification of road scenes is *** architecture is called semantic pixel-wise segmentation and comprises a hierarchical link of encoder-decoder layers.A standard data set was used to test the proposed model for liver CT scans and the tumor accuracy in the training *** the normal class,we obtained 100%precision for chronic cirrhosis hepatitis(73%),offset cirrhosis(59.26%),and offensive cirrhosis(91.67%)for chronic hepatitis or cirrhosis(73,0%).The aim is to develop a computer-Aided Detection(CAD)screening tool to detect *** results proved 98.33%exactness,94.59%sensitivity,and 92.11%case with Convolutional Neural Networks(CNN)*** the classifier’s performance did not differentiate so clearly at this level,it was recommended that CNN generally perform better due to the good relationship between Area under the Receiver Operating Characteristics Curve(AUC)and accuracy.

关键词： Deep learning liver tumor CNN CT accuracy

来源：评论

学校读者我要写书评

暂无评论

Quality Assessment of Selective Laser Melting Components Using Quantitative Ultrasound Measurements and Image Texture Analysis

引用

IEEE Access 2024年 12卷 71797-71807页

作者： Lin, Chun-Hui Lin, Cheng-Jian Wang, Shyh-Hau National Cheng Kung University Department of Computer Science and Information Engineering Tainan 701 Taiwan National Chin-Yi University of Technology Department of Computer Science and Information Engineering Taichung 411 Taiwan

Successful production of metallic selective laser melting components requires a quality assurance process that can effectively and nondestructively assess internal defects. Ultrasound testing has emerged as a valuable modality for defect identification as well as the characterization of microstructural and material properties. In this study, a comprehensive quality assessment approach was developed, leveraging quantitative ultrasound parameters, images, and image texture analysis. The evaluation focused on Inconel 718 selective laser melting components manufactured using diverse combinations of process parameters. The investigation involved examining the correlation between ultrasound parameters, image texture features, and the overall quality of the fabricated components. To validate the findings obtained through ultrasound testing, micro-computed tomography was employed. The experimental results provided evidence that the ultrasound parameters and image texture features successfully detected nonhomogeneous microstructures present within the selective laser melting components. Notably, the speed of sound and attenuation exhibited a positive correlation of 0.64 and 0.74, respectively, with porosity, indicating their potential as indicators of porosity. Furthermore, image texture features such as entropy, contrast, and homogeneity demonstrated high correlations (R2> 0.7 ) with the quality of the components. Consequently, these identified features hold promising potential for aiding in the selection of optimal process parameters and the prediction of porosity in future research. © 2013 IEEE.

关键词： image texture analysis Quality assessment selective laser melting ultrasound testing

来源：评论

学校读者我要写书评

暂无评论

Multiview EEG signal analysis for diagnosis of schizophrenia: an optimized deep learning approach

引用

Multimedia Tools and Applications 2024年 1-32页

作者： Bhadra, Sweta Kumar, Chandan Jyoti Bhattacharyya, Dhruba Kr Department of Computer Science and Information Technology Cotton University Assam Guwahati781001 India Department of Computer Science and Engineering Tezpur University Assam Tezpur784028 India

Schizophrenia (SZ) is a complex neuropsychiatric disorder affecting approximately 1% of the global population. The early diagnosis of SZ, with electroencephalograph (EEG) signals using deep learning (DL), can help in timely interventions which may mitigate the risk of progression to clinical psychosis. This study introduces five novel machine learning (ML)/DL-based frameworks for identifying SZ using EEG signals. The first framework involves extracting complexity features using discrete wavelet transform (DWT) of the EEG signal. In the second framework, to capture the interrelatedness among the EEG channels the complexity features are computed using multivariate empirical mode decomposition (MEMD). In both of these frameworks, the complexity features extracted are transformed into their 2D representation which uses convolutional neural network (CNN) based model for classification. Various CNN models, including conventional CNN and pretrained models were used for this purpose. In the third framework, to obtain the benefit of multiple view of the EEG signal, the complexity features extracted from DWT and MEMD features in vector representation were fused using concatenation. The combined feature was integrated with a feedforward neural network (FFNN). To obtain the optimized multiview feature set principal component analysis (PCA) was used on the concatenated feature set in the fourth framework. Finally, in the fifth framework, to further optimize the fusion of DWT and MEMD feature set canonical correlation analysis (CCA) based approach was proposed. This study is one of the first to apply a 2D representation of entropy features extracted from DWT and MEMD transformed signals for diagnosis of SZ. Furthermore, this is the first study to propose an optimized multiview feature derived from the fusion of 1D-DWT and 1D-MEMD transformed complexity features using PCA and CCA for identifying SZ from healthy control (HC). The classification performance of various CNN models in

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

CompressionShield: Architectural Adaptations towards Enhancing InceptionV3 for Image Forgery Detection

CompressionShield: Architectural Adaptations towards Enhanci...

引用

2024 IEEE Calcutta Conference, CALCON 2024

作者： Bhowal, Arundhati Naskar, Ruchira Neogy, Sarmistha Jadavpur University Computer Science and Engineering Kolkata India Indian Institute of Engineering Science and Technology Information Technology Shibpur India

ISBN: (纸本)9798331516666

The most popular methods for tampering with visual data integrity are copy-move forgery and splicing. These techniques can be used for several malicious purposes, including the production of false or misleading images and videos. Forgery detection becomes challenging when useful data is lost while maintaining fine details, such as during image compression. Therefore, it is crucial to create reliable techniques that can recognize forgery in compressed images with accuracy. This work proposes a deep learning-based transfer learning technique to detect manipulated images after compression. The proposed approach has the advantage of extracting appropriately nontrivial visual features, as it can quickly adjust to the forgery detection task by using a pre-trained transfer learning model named Inception-V3. Experimental results show that the proposed method can successfully identify forgeries in compressed images with superior accuracy. © 2024 IEEE.

关键词： Image compression

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：