检索结果-内蒙古大学图书馆

Congruent Feature Selection Method to Improve the Efficacy of Machine Learning-Based Classification in Medical Image Processing

引用

computer Modeling in engineering & sciences 2025年第1期142卷 357-384页

作者： Mohd Anjum Naoufel Kraiem Hong Min Ashit Kumar Dutta Yousef Ibrahim Daradkeh Department of Computer Engineering Aligarh Muslim UniversityAligarh202002India College of Computer Science King Khalid UniversityAbha61413Saudi Arabia School of Computing Gachon UniversitySeongnam13120Republic of Korea Department of Computer Science and Information Systems College of Applied SciencesAlMaarefa UniversityRiyadh13713Saudi Arabia Department of Computer Engineering and Information College of Engineering in Wadi AlddawasirPrince Sattam bin Abdulaziz UniversityAl-Kharj16273Saudi Arabia

Machine learning(ML)is increasingly applied for medical image processing with appropriate learning *** applications include analyzing images of various organs,such as the brain,lung,eye,etc.,to identify specific flaws/diseases for *** primary concern of ML applications is the precise selection of flexible image features for pattern detection and region *** of the extracted image features are irrelevant and lead to an increase in computation ***,this article uses an analytical learning paradigm to design a Congruent Feature Selection Method to select the most relevant image *** process trains the learning paradigm using similarity and correlation-based features over different textural intensities and pixel *** similarity between the pixels over the various distribution patterns with high indexes is recommended for disease ***,the correlation based on intensity and distribution is analyzed to improve the feature selection ***,the more congruent pixels are sorted in the descending order of the selection,which identifies better regions than the ***,the learning paradigm is trained using intensity and region-based similarity to maximize the chances of ***,the probability of feature selection,regardless of the textures and medical image patterns,is *** process enhances the performance of ML applications for different medical image *** proposed method improves the accuracy,precision,and training rate by 13.19%,10.69%,and 11.06%,respectively,compared to other models for the selected *** mean error and selection time is also reduced by 12.56%and 13.56%,respectively,compared to the same models and dataset.

关键词： computer vision feature selection machine learning region detection texture analysis image classification medical images

来源：评论

学校读者我要写书评

暂无评论

HoloStream: a GPU-powered high-speed user interface for holographic microscopy imaging

引用

Optics Express 2025年第7期33卷 15648-15660页

作者： Morales, Johan Obando-Vásquez, Sofia Doblas, Ana Trujillo, Carlos Applied Optics Group School of Applied Science and Engineering EAFIT University Medellin Colombia Optical Imaging Research Lab Electrical and Computer Engineering Department University of Massachusetts Dartmouth DartmouthMA United States

This paper presents HoloStream, a GPU-powered high-speed user interface designed for holographic microscopy imaging. The platform reconstructs quantitative phase images rapidly for off-axis digital holographic microscopy (DHM) systems operating in the telecentric regime. By optimizing critical computational procedures, the HoloStream app reconstructs phase maps of 1280 × 960 pixels up to 11 frames per second (FPS) in live visualization and 90 fps for pre-recorded holographic videos. This real-time phase compensation is performed by upgrading the semi-heuristic phase compensation (SHPC) algorithm through GPU acceleration via PyCUDA. The interface also offers a user-friendly experience with flexible control over acquisition modes, visualization formats, and 3D tracking functionalities. Experimental validation demonstrates the platform’s capability to achieve fast and accurate phase imaging for live microscopy applications. The HoloStream app advances DHM technology by combining high-speed processing with ease of use, making it suitable for a wide range of DHM imaging applications. © 2025 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement.

关键词： computer graphics equipment

来源：评论

学校读者我要写书评

暂无评论

Addressing Imbalance in Health Datasets: A New Method NR-Clustering SMOTE and Distance Metric Modification

引用

computers, Materials & Continua 2025年第2期82卷 2931-2949页

作者： Hairani Hairani Triyanna Widiyaningtyas Didik Dwi Prasetya Afrig Aminuddin Department of Electrical Engineering and Informatics Faculty of EngineeringUniversitas Negeri MalangMalang65145Indonesia Department of Computer Science Universitas BumigoraMataram83127Indonesia Department of Computer Graphic and Multimedia Faculty of ComputingCollege of Computing and Applied SciencesUniversiti Malaysia Pahang Al-Sultan AbdullahPekan26600Malaysia

An imbalanced dataset often challenges machine learning, particularly classification methods. Underrepresented minority classes can result in biased and inaccurate models. The Synthetic Minority Over-Sampling Technique (SMOTE) was developed to address the problem of imbalanced data. Over time, several weaknesses of the SMOTE method have been identified in generating synthetic minority class data, such as overlapping, noise, and small disjuncts. However, these studies generally focus on only one of SMOTE’s weaknesses: noise or overlapping. Therefore, this study addresses both issues simultaneously by tackling noise and overlapping in SMOTE-generated data. This study proposes a combined approach of filtering, clustering, and distance modification to reduce noise and overlapping produced by SMOTE. Filtering removes minority class data (noise) located in majority class regions, with the k-nn method applied for filtering. The use of Noise Reduction (NR), which removes data that is considered noise before applying SMOTE, has a positive impact in overcoming data imbalance. Clustering establishes decision boundaries by partitioning data into clusters, allowing SMOTE with modified distance metrics to generate minority class data within each cluster. This SMOTE clustering and distance modification approach aims to minimize overlap in synthetic minority data that could introduce noise. The proposed method is called “NR-Clustering SMOTE,” which has several stages in balancing data: (1) filtering by removing minority classes close to majority classes (data noise) using the k-nn method;(2) clustering data using K-means aims to establish decision boundaries by partitioning data into several clusters;(3) applying SMOTE oversampling with Manhattan distance within each cluster. Test results indicate that the proposed NR-Clustering SMOTE method achieves the best performance across all evaluation metrics for classification methods such as Random Forest, SVM, and Naїve Bayes, compared t

关键词： SMOTE modification Clustering-SMOTE manhattan distance

来源：评论

学校读者我要写书评

暂无评论

Enhanced Emotion Recognition Using a Hybrid Autoencoder-LSTM Model Optimized with a Hybrid ACO-WOA Algorithm for Hyperparameter Tuning

引用

International Journal of Advanced computer science and Applications 2025年第4期16卷 861-876页

作者： Waiker, Vinod Ramesh, Janjhyam Venkata Naga Bala, Ms Kiran Krishnaiah, V.V. Jaya Rama Jackulin, T. Muniyandy, Elangovan Shahin, Osama R. Datta Meghe Institute of Management Studies Maharashtra Nagpur India Department of CSE Graphic Era Hill University Dehradun248002 India Department of CSE Graphic Era Deemed To Be University Uttarakhand Dehradun248002 India Department of Computer Science College of Engineering and Computer Science Jazan University Jazan Saudi Arabia Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram India Department of CSE Panimalar Engineering College Tamil Nadu Chennai India Department of Biosciences-Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai602 105 India Applied Science Research Center Applied Science Private University Amman Jordan Department of Computer Science College of Computer and Information Sciences Jouf University Saudi Arabia Physics and Mathematics Department Faculty of Engineering Helwan University Helwan Egypt

Emotion recognition is vital in the human computer interaction because it improves interaction. Therefore, this paper proposes an improved method for emotion recognition regarding the Hybrid Autoencoder-Long Short-Term Memory (LSTM) model and the newly developed hybrid approach of the Ant Colony Optimization (ACO) and Whale Optimization Algorithm (WOA) for hyperparameters tuning. In this case, Autoencoder can reduce input data dimensionality for input data and find the features relevant for the model’s work. In addition, LSTM is able to work with temporal structures of sequential inputs like speech and videos. The contribution of this research lies in the novel combination method of ACO-WOA which aims at tweaking hyperparameters of Autoencoder-LSTM model. Global aspect of ACO and WOA thereby improve the search efficiency and the accuracy of the proposed emotion recognition system and its generalization capacity. In context with the benchmark dataset for the experimentations of emotion recognition, it has established the efficiency of the proposed model in terms of the conventional methods. Recall rates in recognitive intended various emotions and different modalities were also higher in the hybrid Autoencoder-LSTM model. The optimization algorithms like the ACO-WOA also supported in reducing the computational cost which arose due to hyperparameters tuning. The implementation of this paper is done through Python Software. This implementation shows a high accuracy of 94.12% and 95.94% for audio datasets and image datasets respectively when compared with other deep learning models of Conv LSTM and VGG16. Therefore, the research shows that the presented hybrid approach can be a useful solution for successfully employing emotion recognition for enhancing the creation of the empathetic AI systems and for improving user interactions within various fields including healthcare, entertainment, and customer support. © (2025), (science and Information Organization). All rights

关键词： Ant colony optimization

来源：评论

学校读者我要写书评

暂无评论

An optical vortex-based asymmetric cryptosystem using QZ modulation for the double image encryption in the gyrator transform

引用

Iran Journal of computer science 2024年第4期7卷 829-842页

作者： Singh, Hukum Yadav, Poonam Department of Applied Sciences The NorthCap University Gurugram India Department of Computer Science Engineering The NorthCap University Gurugram India

The current study proposes a new nonlinear cryptosystem that employs complex phase masks named as optical vortices (OVs) which are obtained from the phases of the radial Hilbert mask (RHM) and Toroidal Fresnel lens (TFL). The security keys used in classical optical cryptosystems are often random phase masks (RPMs), which are vulnerable to various forms of attacks including brute force attacks. To create complex images in the frequency domain with the current encryption, the amplitude images are first phase encoded, after which the OV phase mask is used to modulate them. The complex images are further processed with QZ decomposition resulting in two upper quasi-triangular matrices, two unitary matrices, and decryption keys in the gyrator transform (GT). The use of OVs, QZ decomposition and gyrator transform settings provides additional keys to expand the key space. The proposed method is asymmetric, and the decryption process requires the private keys generated during encryption. The performance of the scheme has been evaluated in terms of mean-squared-error (MSE), peak signal-to-noise ratio (PSNR), SSIM, histograms, entropy analysis, correlation analysis, noise and occlusion attacks. Numerical simulations are presented to validate the proposed encryption method in terms of its strength and reliability. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Entropy Gyrator transform Occlusion and noise attacks Optical vortex QZ modulation

来源：评论

学校读者我要写书评

暂无评论

Resource Allocation in Edge Computing Environment Using Deterministic Policy Gradient Algorithm 10

Resource Allocation in Edge Computing Environment Using Dete...

引用

10th International Conference on Advanced Computing and Communication Systems, ICACCS 2024

作者： Shabariram, C.P. Shanthi, N. Ponnuswamy, P. Priya Subramaniyaswamy, V. Sathana, V. Psg Institute of Technology and Applied Research Department of Computer Science and Engineering Coimbatore India Kongu Engineering College Department of Computer Science and Engineering Erode India School of Computing Sastra University Department of Computer Science and Engineering Thanjavur India

ISBN: (纸本)9798350384369

In recent years, the edge computing paradigm enables the movement of processing units and storage nearer to the data available locations. The mechanism completes the computation in a short span of time in minimum bandwidth. Edge ecosystem is a type of distributed computing that is sensitive to topology and geography;the Internet of Things is a prime instance of this. Rather than referring to a single technology, Edge computing refers to an architecture. This paper proposes a resource allocation methodology that will enliven the situation between users and edge servers. By creating continuous control at the edge servers to determine resource allocation, edge computing improves reaction time, provides high security with decreased risk, scalability, lowers transmission costs, and versatility (offload targets, migration bandwidth and computing resources). The Deterministic Policy Gradient, Deep learning and Quality Network concepts are combined in the proposed system. The continuous action space is achieved by a deterministic policy gradient. The experience relay includes a quality network. In the proposed system, the actor-critic network produces a single continuous action instead of resulting probability based actions. The critic-part uses Q-value from a quality network based on current status and activity. The goal of the proposed system is to develop a Deep Deterministic Policy Gradient methodology to allocate servers for mobile users with the help of the Edge computing while taking computation resources, offloading goals and migration bandwidth into consideration. The simulation result indicates that deterministic policy gradients integrated deep learning models improve the system performance compared with Game theory. © 2024 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Revisiting 30 years of the Network Time Protocol 24

Revisiting 30 years of the Network Time Protocol

引用

33rd Companion of the ACM World Wide Web Conference, WWW 2023

作者： Woo, Simon S. Computer Science and Engineering Department Applied Data Science Department Department of Artificial Intelligence Sungkyunkwan University Suwon Korea Republic of

ISBN: (纸本)9798400701726

Since the inception of the Internet and WWW, providing the time among multiple nodes on the Internet has been one of the most critical challenges. David Mills is the pioneer to provide time on the Internet, inventing the Network Time Protocol (NTP), and synchronizing the clocks in computer systems. Now, the NTP is predominantly used on the Internet and WWW. In this paper, we revisit the NTP, and present the overview of the NTP. In particular, we highlight the advanced research effort, the SpaceNTP, to synchronize the clocks among assets and entities in space. The SpaceNTP designed for space environments will be the fundamental medium and enabling block to provide the future web services in space. © 2024 Copyright held by the owner/author(s).

关键词： Web services

来源：评论

学校读者我要写书评

暂无评论

ProspectCV: LLM-Based Advanced CV-JD Evaluation Platform

ProspectCV: LLM-Based Advanced CV-JD Evaluation Platform

引用

2024 IEEE Students Conference on engineering and Systems, SCES 2024

作者： Vagale, Ghanashyam Bhat, Shashidhar Y Padma Priya Dharishini, P. Gk, Prajwal Ramaiah University of Applied Sciences Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350374711

This paper presents a novel framework that utilizes Google's Gemini Pro Vision large language model (LLM) and natural language processing (NLP) techniques to analyze and compare resumes or CVs with job descriptions. The framework not only evaluates the compatibility between the resume and job description but also provides personalized feedback and suggestions for improvement. By identifying potential gaps in skills and qualifications, and recommending relevant resources, the framework assists both human resources professionals in streamlining candidate shortlisting and empowers candidates to enhance their CVs. Gemini processes a resume as a Base64-encoded string and cleans up the job description using NLP. It then generates a personalized report with insights, including a compatibility score, skills analysis, improvement suggestions, and resource recommendations. Initial results demonstrate the framework's effectiveness in accurately assessing candidate suitability and providing valuable feedback. Future work will focus on expanding the framework to analyze multiple resumes simultaneously and developing more sophisticated algorithms for enhanced accuracy and reliability. This framework has the potential to revolutionize the recruitment process by streamlining candidate selection, empowering candidates to improve their CVs, and ultimately leading to better candidate job matches and a more efficient and equitable hiring landscape. © 2024 IEEE.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Smart Traffic Management System for Efficient Mobility and Emergency Response

Smart Traffic Management System for Efficient Mobility and E...

引用

2024 International Conference on Knowledge engineering and Communication Systems, ICKECS 2024

作者： Sultana, Farhain Bhardwaj, Ritika Kumar, Rohan N. Gaur, Ruchir Shankar, Sahana.P. Bharadwaj, Aryan Ramaiah University of Applied Sciences Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350359688

This research addresses the critical issue of urban trafficcongestion exacerbated by the inadequacies of traditional traffic management systems. Inefficient adaptation to real-time traffic conditions by static traffic light timers leads to wasted time, and fuel, increased pollution, and compromised safety during peak hours and emergencies. To mitigate these challenges, this study proposes a novel Smart Traffic Management (STM) system that leverages cutting-edge technologies such as the Internet of Things (IoT) and Artificial Intelligence (AI). The STM framework dynamically adjusts traffic flow in response to real-time data, optimizing efficiency and enhancing emergency response mechanisms. Through comprehensive simulations and case studies, this research demonstrates the potential of the STM system to alleviate urban congestion and improve overall traffic management in diverse urban settings. © 2024 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

computer Vision assisted Deep Learning based Sitting Posture Suggestion System 3

Computer Vision assisted Deep Learning based Sitting Posture...

引用

3rd International Conference for Innovation in Technology, INOCON 2024

作者： Vagale, Ghanashyam Prajwal, G.K. Kumar, Rohit Dharishini, P. Padma Priya Ramaiah University of Applied Sciences Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350381931

This paper presents an innovative framework that employs camera-captured visual data to detect and suggest optimal sitting postures. The framework consists of two crucial components: a video capture object and an object detection system that incorporates Deep Learning to enhance efficiency and reliability. The camera initially captures the user's posture image, which is then subjected to video processing to extract video metadata. Subsequently, the object is created by extracting the image from the video, and the object detection algorithm is applied to provide posture recommendations. The algorithm continually monitors posture correctness and provides suggestions to improve it as necessary, ultimately benefiting the user's daily life and mitigating potential long-term problems. Additionally, the algorithm can be further developed to recognize posture patterns and suggest corrective exercises or techniques. Furthermore, the algorithm's efficiency can be enhanced by optimizing landmark detection for more effective outcomes. This cutting-edge framework offers immense potential for improving posture and overall health, and its development can significantly enhance the quality of life for individuals. © 2024 IEEE.

关键词： Cameras

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：