检索结果-内蒙古大学图书馆

Autoencoder-based conditional optimal transport generative adversarial network for medical image generation

Visual Informatics 2024年第1期8卷 15-25页

作者： Jun Wang Bohan Lei Liya Ding Xiaoyin Xu Xianfeng Gu Min Zhang School of Software Technology Zhejiang UniversityNingboZhejiangChina College of Computer Science&Technology Zhejiang UniversityHangzhouZhejiangChina Department of Pathology Sir Run Run Shaw HospitalZhejiang University School of MedicineHangzhouZhejiangChina College of Biomedical Engineering&Instrument Science Zhejiang UniversityHangzhouZhejiangChina Department of Computer Science State University of New York at Stony BrookStony BrookNYUSA

Medical image generation has recently garnered significant interest among ***,the primary generative models,such as Generative Adversarial Networks(GANs),often encounter challenges during training,including mode *** address these issues,we proposed the AECOT-GAN model(Autoencoder-based Conditional Optimal Transport Generative Adversarial Network)for the generation of medical images belonging to specific *** training process of our model comprises three fundamental *** training process of our model encompasses three fundamental ***,we employ an autoencoder model to obtain a low-dimensional manifold representation of real ***,we apply extended semi-discrete optimal transport to map Gaussian noise distribution to the latent space distribution and obtain corresponding labels *** procedure leads to the generation of new latent codes with known ***,we integrate a GAN to train the decoder further to generate medical *** evaluate the performance of the AE-COT-GAN model,we conducted experiments on two medical image datasets,namely DermaMNIST and *** model’s performance was compared with state-of-the-art generative *** show that the AE-COT-GAN model had excellent performance in generating medical ***,it effectively addressed the common issues associated with traditional GANs.

关键词： Medical image generation Mode collapse Mode mixing Optimal transport Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Automated Intracranial Hemorrhage Detection Using Deep Learning in Medical Image Analysis 2

Automated Intracranial Hemorrhage Detection Using Deep Learn...

引用

2nd IEEE International Conference on Data science and Network Security, ICDSNS 2024

作者： Kar, Naresh Kumar Jana, S. Rahman, Abdur Ashokrao, Patil Rahul Indhumathi, G. Mangai, R. Alarmelu Gitam Deemed to Be University Department of Cse Hyderabad India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Ece Chennai India School of Business & Technology Emporia State University Science in Information Technology Department of Accounting and Technology United States Kthm College Department of Computer Science Nashik India Rajalakshmi Engineering College Department of Ece Chennai India Dr. Sns Rajalakshmi College of Arts and Science Department of Computer Science Coimbatore India

ISBN: (纸本)9798350373110

The research work introduces a novel approach to automatically detect intracranial hemorrhage (ICH) using advanced deep learning algorithms. The method being examined efficiently extracts and localizes information from computed tomography (CT) brain data by utilizing attention processes that are connected to convolutional neural networks (CNNs). The results achieved through training and evaluating the model using a dataset of CT images was highly impressive. The model showed accuracy value of 99.76% and has an AUC-score of 0.9976. Through the incorporation of attention strategies into the CNN framework, the interpretability of the model can be enhanced, allowing for the identification of the most relevant regions for ICH detection. The findings of the paper highlight the potential of AI-driven medical diagnostics to enhance the speed and accuracy of neuroimaging analysis, leading to better patient outcomes. Significant advancements have been achieved in the automated diagnosis of cerebral hemorrhage through the utilization of deep learning algorithms with the proposed method. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Explainable AI for Leukemia Diagnosis: Modified ResNet with Hard Attention Mechanisms 1

Explainable AI for Leukemia Diagnosis: Modified ResNet with ...

引用

1st International Conference on Intelligent systems and Computational Networks, ICISCN 2025

作者： Ramanujam, E. Sekar, K. Bavashree, G.S. Prabakar, Shreya Sai National Institute of Technology Department of Computer Science and Engineering Silchar India Rajalakshmi Engineering College Department of Aiml Chennai India

ISBN: (纸本)9798331529246

Leukemia is a highly complex and aggressive form of cancer, necessitating accurate and timely diagnosis for effective treatment. This study investigates the use of Explainable Artificial Intelligence (XAI) techniques to enhance computer-aided diagnosis (CAD) systems for leukemia. A modified ResNet architecture, integrated with a hard attention mechanism, is proposed to improve model performance and interpretability. The approach emphasizes robust segmentation of white blood cell (WBC) nuclei, utilizing advanced image processing techniques and U-Net models for precise feature extraction. Model evaluation focuses on both accuracy and interpretability, employing Grad-CAM and clustering space analysis to assess network focus and transparency in decision-making. The results underscore the strengths and limitations of the proposed architecture, offering insights into further advancements in XAI to improve the reliability and transparency of CAD systems. This work ultimately aims to advance clinical outcomes in leukemia diagnosis by providing more reliable and interpretable diagnostic tools. The proposed model produces 99.7% of accuracy for detection and classification of leukemia. © 2025 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

A Novel Capability of Object Identification and Recognition Based on Integrated mWMM

引用

computers, Materials & Continua 2023年第4期75卷 959-976页

作者： MZeeshan Sarwar Mohammed Hamad Alatiyyah Ahmad Jalal Mohammad Shorfuzzaman Nawal Alsufyani Jeongmin Park Department of Computer Science Air UniversityIslamabadPakistan Department of Computer Science College of Sciences and Humanities in AflajPrince Sattam Bin Abdulaziz UniversityAl-KharjSaudi Arabia Department of Computer Science College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia Department of Computer Engineering Tech University of Korea237 Sangidaehak-roSiheung-siGyeonggi-do15073Korea

In the last decade,there has been remarkable progress in the areas of object detection and recognition due to high-quality color images along with their depth maps provided by RGB-D *** enable artificially intelligent machines to easily detect and recognize objects and make real-time decisions according to the given *** cues can improve the quality of object detection and *** main purpose of this research study to find an optimized way of object detection and identification we propose techniques of object detection using two RGB-D *** proposed methodology extracts image normally from depth maps and then performs clustering using the Modified Watson Mixture Model(mWMM).mWMM is challenging to handle when the quality of the image is not ***,the proposed RGB-D-based system uses depth cues for segmentation with the help of *** it extracts multiple features from the segmented *** selected features are fed to the Artificial Neural Network(ANN)and Convolutional Neural Network(CNN)for detecting *** achieved 92.13%of mean accuracy over NYUv1 dataset and 90.00%of mean accuracy for the Redweb_v1 ***,their results are compared and the proposed model with CNN outperforms other state-of-the-art *** proposed architecture can be used in autonomous cars,traffic monitoring,and sports scenes.

关键词： Artificial intelligence convolutional neural network depth images interactive-object detection machine learning

来源：评论

学校读者我要写书评

暂无评论

Improved optimizer with deep learning model for emotion detection and classification

引用

Mathematical Biosciences and Engineering 2024年第7期21卷 6631-6657页

作者： Joseph, Willson C. Kathrine, G. Jaspher Willsie Shanmuganathan, Vimal Sumathi, S. Pelusi, Danilo Valencia, Xiomara Patricia Blanco Verdú, Elena Department of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore India Department of Computer Science and Engineering Adi Shankara Institute of Engineering and Technology Kerala India Department of Artificial Intelligence and Data Science Sri Eshwar College of Engineering Coimbatore India Sri Eshwar College of Engineering Coimbatore India Communication Sciences University of Teramo Coste Sant’agostino Campus Teramo Italy Universidad Internacional de La Rioja La Rioja Logroño Spain

Facial emotion recognition (FER) is largely utilized to analyze human emotion in order to address the needs of many real-time applications such as computer-human interfaces, emotion detection, forensics, biometrics, and human-robot collaboration. Nonetheless, existing methods are mostly unable to offer correct predictions with a minimum error rate. In this paper, an innovative facial emotion recognition framework, termed extended walrus-based deep learning with Botox feature selection network (EWDL-BFSN), was designed to accurately detect facial emotions. The main goals of the EWDL-BFSN are to identify facial emotions automatically and effectively by choosing the optimal features and adjusting the hyperparameters of the classifier. The gradient wavelet anisotropic filter (GWAF) can be used for image pre-processing in the EWDL-BFSN model. Additionally, SqueezeNet is used to extract significant features. The improved Botox optimization algorithm (IBoA) is then used to choose the best features. Lastly, FER and classification are accomplished through the use of an enhanced optimization-based kernel residual 50 (EK-ResNet50) network. Meanwhile, a nature-inspired metaheuristic, walrus optimization algorithm (WOA) is utilized to pick the hyperparameters of EK-ResNet50 network model. The EWDL-BFSN model was trained and tested with publicly available CK+ and FER-2013 datasets. The Python platform was applied for implementation, and various performance metrics such as accuracy, sensitivity, specificity, and F1-score were analyzed with state-of-the-art methods. The proposed EWDL-BFSN model acquired an overall accuracy of 99.37 and 99.25% for both CK+ and FER-2013 datasets and proved its superiority in predicting facial emotions over state-of-the-art methods. ©2024 the Author(s), licensee AIMS Press.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Redundant Data Detection and Deletion to Meet Privacy Protection Requirements in Blockchain-Based Edge Computing Environment

引用

China Communications 2024年第3期21卷 149-159页

作者： Zhang Lejun Peng Minghui Su Shen Wang Weizheng Jin Zilong Su Yansen Chen Huiling Guo Ran Sergey Gataullin Cyberspace Institute Advanced Technology Guangzhou UniversityGuangzhou 510006China College of Information Engineering Yangzhou UniversityYangzhou 225127China School Math&Computer Science Quanzhou Normal UniversityQuanzhou 362000China Computer Science Department City University of Hong KongHong Kong 999077China School of Computer and Software Nanjing University of Information Science and TechnologyNanjing 21004China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and TechnologyAnhui UniversityHefei 230601China Department of Computer Science and Artificial Intelligence Wenzhou UniversityWenzhou 325035China Guangzhou University Library Guangzhou UniversityGuangzhou 510006China Central Economic and Mathematics Institute Russian Academy of Sciences MIREA-Russian Technological University Moscow RegionRussia

With the rapid development of information technology,IoT devices play a huge role in physiological health data *** exponential growth of medical data requires us to reasonably allocate storage space for cloud servers and edge *** storage capacity of edge nodes close to users is *** should store hotspot data in edge nodes as much as possible,so as to ensure response timeliness and access hit rate;However,the current scheme cannot guarantee that every sub-message in a complete data stored by the edge node meets the requirements of hot data;How to complete the detection and deletion of redundant data in edge nodes under the premise of protecting user privacy and data dynamic integrity has become a challenging *** paper proposes a redundant data detection method that meets the privacy protection *** scanning the cipher text,it is determined whether each sub-message of the data in the edge node meets the requirements of the hot *** has the same effect as zero-knowledge proof,and it will not reveal the privacy of *** addition,for redundant sub-data that does not meet the requirements of hot data,our paper proposes a redundant data deletion scheme that meets the dynamic integrity of the *** use Content Extraction Signature(CES)to generate the remaining hot data signature after the redundant data is *** feasibility of the scheme is proved through safety analysis and efficiency analysis.

关键词： blockchain data integrity edge computing privacy protection redundant data

来源：评论

学校读者我要写书评

暂无评论

Railway Track Fault Detection Using Mel Frequency Cepstral Coefficient from Acoustic Data using Chi Square

引用

Chinese Journal of Electronics 2023年

作者： Furqan Rustam Abid Ishaq Muhammad Shadab Alam Hashmi Hafeez-Ur-Rehman Siddiqui Imran Ashraf School of Computer Science University College Dublin Faculty of Computer Science and Information Technology Khawaja Fareed University of Engineering and Information Technology Department of Information and Communication Engineering Yeungnam University

Spatial, temporal, and weather elements like ballast, loose nuts, misalignment, and cracks due to rain, snow, and earthquakes may lead to railway accidents and cause human and financial loss. Manual inspection is erroneous, labor-intensive, and *** automatic inspection provides a fast, reliable, and unbiased solution in this regard, however, ensuring high accuracy for fault detection is challenging due to the lack of public datasets, noisy data, high computer processing requirements, and inefficient models. This study presents an approach that uses Mel frequency cepstral coefficient features from the acoustic data. The dataset gathered using a customized railway cart from our previous research is used for experiments. The focus of the study is to increase the fault detection performance using selective features from the acoustic data. This study employs Chisquare(Chi2) for the selection of important features and involves performance analysis of machine learning and deep learning models using selected features. Experimental results suggest that using 60 features, 40 original features, and 20 Chi2 features, produces optimal results both regarding accuracy and computational complexity. A 100%accuracy can be obtained using the proposed approach with machine learning models. Moreover, this performance is significantly better than existing approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Honey Badger Optimization Algorithm-Based RSU Deployment for Improving Network Coverage in VANETs 1

引用

6th International Conference on Microelectronics and Telecommunication Engineering, ICMETE 2022

作者： Sengathir, J. Deva Priya, M. Christy Jeba Malar, A. Sam Peter, S. Department of Information Technology CVR College of Engineering Mangalpally Vastunagar Telangana Hyderabad India Department of Computer Science and Engineering Sri Eshwar College of Engineering Tamilnadu Coimbatore India Department of Information Technology Sri Krishna College of Technology Tamilnadu Coimbatore India Department of Computer Science and Engineering Sri Krishna College of Technology Tamilnadu Coimbatore India

ISBN: (数字)9789811995125

ISBN: (纸本)9789811995118

Road Side Units (RSUs) installed in roadside, and intersections in Vehicular Ad hoc NETwork (VANET) play an anchor role in aggregating and exploring intelligent data associated with vehicle traffic. These RSUs help in exchanging information among vehicles and obtaining early warning messages to ensure safety driving of vehicles. However, determining the number of RSUs and position over which they must be deployed are vital due to high cost incurred in implementing and maintaining them in the network. This problem of determining the number of RSUs along with their positions of deployment is a multi-objective problem, since it necessitates maximized coverage of network with minimized number of RSUs in the network. In this paper, Honey Badger Optimization Algorithm-based RSU Deployment (HBOA-RSUD) scheme is proposed with a multi-objective fitness function for improving network coverage in VANETs. This HBOA-RSUD initially establishes a static model for determining the complexity involved during the deployment of RSUs in the urban road. Then, a multi-objective HBOA algorithm with sigmoid function is applied over individual discrete values of fitness for identifying the position of RSU deployment. It determines the new positions of RSUs for enhancing the performance of the population and convergence speed. Experimental results of HBOA-RSUD confirm a maximized throughput by 21.38%, maximized network coverage by 28.95%, minimized delay by 19.42% and reduced energy consumption by 21.98% for varying number of RSUs in contrast to the existing intelligent RSU deployment approaches. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Vehicular ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

An Infrastructure-Less Communication Platform for Android Smartphones Using Wi-Fi Direct

An Infrastructure-Less Communication Platform for Android Sm...

引用

International Conference on IoT, Intelligent Computing and Security, IICS 2021

作者： Malar, A. Christy Jeba Kanmani, R. Priya, M. Deva Nivedhitha, G. Divya, P. Surya, T. S. Pavith Department of Information Technology Sri Krishna College of Technology Tamilnadu Coimbatore India Department of Computer Science and Engineering Sri Krishna College of Technology Tamilnadu Coimbatore India Department of Computer Science and Engineering Sri Eshwar College of Engineering Tamilnadu Coimbatore India Department of Electronics and Communication Engineering SNS college of Technology Tamilnadu Coimbatore India

ISBN: (纸本)9789811981357

Real-time indoor positioning systems provide information about localization of devices required for communication. This paper focuses on Device-to-Device (D2D) communication among smartphones for device discovery and communication. Wi-Fi Direct (Wi-FiDi) is a type of Wi-Fi where a smartphone can connect with another without internet or Access Point (AP). There is no demand for an infrastructure, and this peer-to-peer network doesn’t permit multi-hop communication like ad-hoc network. In a Wi-FiDi network, each device acts as an AP for connecting with other devices. Wi-FiDi allows devices to communicate without Wi-Fi routers. Each AP in the WLAN network is configured with its location in geospatial coordinates (latitude, longitude and altitude) and civic address. Fine Time Measurement (FTM) protocol is implemented and Round Trip Time (RTT) is measured. FTM determines accurate position of a mobile device from an AP. New version of Android OS supports FTM protocol. It allows a mobile device to make a request either in scheduled or immediate measurement mode. WiDiSi simulator is used for implementing Wi-FiDi networks. Devices at proximity can be discovered and connected at higher speed when compared to other wireless technologies. The speed of communication is improved and can be used to locate devices that are few meters away with greater accuracy. The range can also be extended to 1 km covering the entire smart building. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Indoor positioning systems

来源：评论

学校读者我要写书评

暂无评论

An empirical IoT and cloud-based customizable healthcare surveillance system

引用

International Journal of Information technology (Singapore) 2024年第8期16卷 5317-5323页

作者： Meti, Subhash Razauddin, S. Nallakumar, R. Mansingh, P. M. Benson Sameen, Aws Zuhair Pandey, Sakshi Bhatt, Sanjeev Kumar Jayabalan, Bhuvana Department of Electronics and Communication Engineering SKSVMACET Lakshmeshwar Karnataka Gadag India College of Computer Science and Engineering University of Hail Hail Saudi Arabia Department of Artificial Intelligence and Data Science Karpagam Institute of Technology Coimbatore India Department of Advanced Computer Science and Engineering Vignan’s Foundation for Science Technology and Research Andhra Pradesh Guntur India College of Medical Techniques Al-Farahidi University Baghdad Iraq Centre of Interdisciplinary Research in Business and Technology Chitkara Institute of Engineering and Technology Chitkara University Punjab Rajpura India Software Architect and Research Scholar Digital Innovation College PDM University Bahadurgarh India Department of Computer Science and Information Technology JAIN (Deemed-to-Be University) Karnataka Bengaluru India

In certain emergencies, patients must be continuously monitored and cared for. However, visiting the hospital to do such activities is difficult because of time constraints. To modernize the healthcare sector, the study in question presents an empirical Internet of Things and cloud-based, customizable healthcare monitoring system. Initially, a cloud-based algorithm called particle swarm intelligence (PGI) is used in the proposed healthcare monitoring system to group recorded data, hence increasing the prediction rate. Subsequently, features are selected and extracted, and back propagation neural networks (BPNN) are employed to classify healthcare for humans. In the end, the effectiveness of the suggested system is evaluated using a healthcare dataset and contrasted with current deep learning/machine learning classifiers. The suggested surveillance system performs better than the methods employed in the previous research, according to the findings. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： BPNN Cloud computing Healthcare surveillance IoT Particle swarm intelligence (PSI)

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：