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

Comparative Analysis of Camera Calibration Algorithms for Football Applications 4

Comparative Analysis of Camera Calibration Algorithms for Fo...

引用

4th International Workshop on information Technologies: Theoretical and Applied Problems, ITTAP 2024

作者： Sorokivskyi, Oleksandr Hotovych, Volodymyr Nazarevych, Oleg Shymchuk, Grygorii Department of Computer Science Faculty of Computer Information Systems and Software Engineering Ternopil Ivan Puluj National Technical University Ternopil Ukraine

In solving the problem of automated analysis of football match video recordings, special video cameras are currently used. This work presents a comparative characterization of known algorithms and methods for video camera calibration, including those utilizing machine learning and neural networks, with the aim of identifying their shortcomings and forming a theoretical foundation for developing modern, more effective methods and algorithms. Specifically, it examines both algorithms that require more input data but operate quickly [1, 2] and more accurate algorithms using machine learning [3, 4, 5, 6, 5]. It is demonstrated that their main drawback is either accuracy or speed. More accurate algorithms using machine learning often do not specify the algorithm's operational speed, which precludes their use in real-time applications. The examined works that emphasize speed frequently lack the accuracy necessary for practical use in real-life scenarios. Copyright © 2024 for this paper by its authors.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Fine-grained Energy-efficient Data Center Traffic Scheduling Mechanism Based on Hierarchical Control

Journal of Network Intelligence

引用

Journal of Network Intelligence 2023年第3期8卷 742-757页

作者： Niu, Tianyu Li, Honghui Li, Weidong Por, Lip Yee College of Computer and Information Engineering Inner Mongolia Agricultural University Inner Mongolia Hohhot China Department of Computer System and Technology Faculty of Computer Science and Information Technology Universiti Malaya Kuala Lumpur50603 Malaysia

With the continuous expansion of the data center, its energy consumption is also increasing. Aiming at the problem that the high redundancy of modern data center network causes low energy-consumption utilization, this paper proposes an energy-saving traffic scheduling algorithm (IMV-MLF) based on improved multi-layer-virtual-topology combined with maximum link-utilization path priority, which realizes more fine-grained control of each layer of virtual topology in data center network. Firstly, the relevant shap-ing linear programming mathematical model is established according to the optimization goal of energy conservation, which can minimize the energy consumption of the whole network as far as possible under the premise of meeting all network-flow requirements;Then, according to the optimization goal, the existing SDN based energy saving multi-layer-virtual-topology (EMV-SDN) method is improved. Whether the network devices in other layers are enabled is determined by the overall traffic level rather than the traffic level of a single link. On the basis of the opened level, the newly arrived network flows are preferentially allocated to the path with the highest link utilization, and overload link set is introduced, we can effectively use the available link routes with sufficient residual bandwidth to reduce congestion when the topology changes by marking the links whose link utilization reaches the critical value, and further count and close the links and switches which no network flows pass through. The experimental results show that the performance of IMV-MLF algorithm is better than multi-layer virtual topology energy saving (EMV-SDN) algorithm and the equivalent multipath (ECMP) algorithm in saving network energy. This result is helpful to provide another new idea for energy conservation of data center. © 2023, Journal of Network Intelligence.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Trees Disease Recognition and Classification Using Hyperspectral Data

引用

computers, Materials & Continua 2023年第10期77卷 681-697页

作者： Uzair Aslam Bhatti Sibghat Ullah Bazai Shumaila Hussain Shariqa Fakhar Chin Soon Ku Shah Marjan Por Lip Yee Liu Jing College of Information and Communication Engineering Hainan UniversityHaikou570228China Department of Computer Engineering Balochistan University of Information TechnologyEngineeringand Management Sciences(BUITEMS)QuettaPakistan Department of Computer Science Sardar Bahadur Khan Women’s UniversityQuettaPakistan Department of Computer Science Universiti Tunku Abdul RahmanKampar31900Malaysia Department of Software Engineering Balochistan University of Information TechnologyEngineeringand Management Sciences(BUITEMS)QuettaPakistan Faculty of Computer Science and Information Technology University of MalayaKuala Lumpur50603Malaysia

Crop diseases have a significant impact on plant growth and can lead to reduced *** methods of disease detection rely on the expertise of plant protection experts,which can be subjective and dependent on individual experience and *** address this,the use of digital image recognition technology and deep learning algorithms has emerged as a promising approach for automating plant disease *** this paper,we propose a novel approach that utilizes a convolutional neural network(CNN)model in conjunction with Inception v3 to identify plant leaf *** research focuses on developing a mobile application that leverages this mechanism to identify diseases in plants and provide recommendations for overcoming specific *** models were trained using a dataset consisting of 80,848 images representing 21 different plant leaves categorized into 60 distinct *** rigorous training and evaluation,the proposed system achieved an impressive accuracy rate of 99%.This mobile application serves as a convenient and valuable advisory tool,providing early detection and guidance in real agricultural *** significance of this research lies in its potential to revolutionize plant disease detection and management *** automating the identification process through deep learning algorithms,the proposed system eliminates the subjective nature of expert-based diagnosis and reduces dependence on individual *** integration of mobile technology further enhances accessibility and enables farmers and agricultural practitioners to swiftly and accurately identify diseases in their crops.

关键词： Plant disease Inception v3 CNN crop diseases

来源：评论

学校读者我要写书评

暂无评论

An Approach for Early Detection of Schizophrenia 15

An Approach for Early Detection of Schizophrenia

引用

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

作者： Paranagama, Sachin Uditha, Isiwara Daundasekara, Pamodya Hettiarachchi, Shehani Weerasinghe, Lokesha Kasthurirathna, Dharshana Sri Lanka Institue Of Information Technology Faculty Of Computing Department of Computer Science and Software Engineering Malabe Sri Lanka

ISBN: (纸本)9798350370249

Schizophrenia is a chronic mental disorder with distorted thinking, hallucinations, and social difficulties. Early diagnosis is vital, but current methods are limited. This research proposes a web-based application integrating machine learning, emotion recognition, and game-based elements to track symptoms and aid in early diagnosis. Interactive exercises focus on specific symptoms like cognitive evaluation, emotional analysis, and memory assessment. By combining computer science, psychology, and machine learning, the project aims to improve early detection and ultimately enhance the quality of life for affected individuals. Key components include using Deep Convolutional Neural Network (DCNN) architecture for recognizing facial and physical expressions associated with schizophrenia with an 87% accuracy rate, and utilizing Vector Regressor (SVR) with a 93% accuracy rate, along with Vision Transformer (ViT) and Custom CNN models for cognitive assessment, achieving accuracy rates of 99% and 98%, respectively. © 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

Exploring Deep Insights from Vast Data: An Overview of Deep Learning Techniques for Big Data 4

Exploring Deep Insights from Vast Data: An Overview of Deep ...

引用

4th International Conference on Electrical engineering and computer science, ICECOS 2024

作者： Baez Hasan, Sarhad Kareem, Shahab Wahhab Ameen, Didar Dlshad Hamad Soran University Faculty of Science Computer Science Department Soran Iraq Erbil Polytechnic University College of Engineering Knowledge University Department of Information System Engineering Department of Computer Engineering Erbil Iraq

ISBN: (纸本)9798350368253

Big data has emerged very fast, and this has brought both opportunities and problems that are related to the application of deep learning. This paper explores how deep learning can be implemented using big data and in particular the Apache Mahout library. Unlike most other machine learning tools, Mahout can perform distributed computation, especially while using the MapReduce frameworks including Apache Hadoop and Apache Spark. However, this study does not only focus on the explanation of the need for Mahout's integration and employment but also carries out a high-fidelity argument on how deep learning algorithms can be incorporated in the Mahout framework to optimize the manipulation of large and complicated datasets. Mahout-based contributions include the comparative analysis of key deep learning paradigms including distributed processing, parallel processing and transfer learning. This paper also includes examples of the Mahout deep learning integration use and its application in real contexts. This article describes the challenges that currently organizations face in handling big data and indeed, the potential threats these challenges pose to the success of deep learning techniques when used in organizations' big data processing and analysis. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of 3D Rendering Method on Web-Based Augmented Reality Application Using WebGL and OpenGL Shading Language 23

Performance Analysis of 3D Rendering Method on Web-Based Aug...

引用

8th International Conference on Sustainable information engineering and Technology, SIET 2023

作者： Hamzaturrazak, Multohadi Jonemaro, Eriq Muhammad Adams Pinandito, Aryo Informatics Engineering Department Universitas Brawijaya Faculty of Computer Science Indonesia Information System Department Universitas Brawijaya Faculty of Computer Science Indonesia

ISBN: (纸本)9798400708503

In recent years, web programming has increased to the extent where it is capable of rendering 3D objects on the web. Its rendering performance varied depending on where it ran and what library was used to render the objects. This study aims to investigate the rendering performance of several 3D renderer libraries that render 3D objects in an augmented reality application. WebGL is one of the APIs that uses the Javascript programming language to render 3D objects in web applications. To create augmented reality on the web, a JavaScript library called *** is needed, which allows developers to create augmented reality on the web without the need to use additional plugins. *** supports various types of augmented reality, i.e., bookmarks, images, and location-based types. It also allows developers to incorporate visual and audio effects into augmented reality. This study aims to investigate the rendering performance of WebGL raw shaders and GLSL shaders in an HTML-based augmented reality application. The results suggested that both WebGL and GLSL could render low-poly and medium-poly 3D objects well. However, according to the test, WebGL performance drops significantly when rendering high-polygon 3D objects. Nonetheless, the GLSL library could render the same high-poly 3D objects at a similar level with native library rendering performance. Thus, suggest GLSL shaders as the recommended library to render 3D objects on the web. © 2023 ACM.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Enhanced Steganalysis for Color Images Using Curvelet Features and Support Vector Machine

引用

computers, Materials & Continua 2024年第1期78卷 1311-1328页

作者： Arslan Akram Imran Khan Javed Rashid Mubbashar Saddique Muhammad Idrees Yazeed Yasin Ghadi Abdulmohsen Algarni Faculty of Computer Science and Information Technology Department of Computer ScienceSuperior UniversityLahore54000Pakistan Machine Learning Code(MLC)Lab Meharban HouseHouse Number 209Zafar ColonyOkara56300Pakistan Information Technology Services University of OkaraOkara56310Pakistan Department of Computer Science&Engineering University of Engineering&Technology LahoreNarowal CampusNarowal51601Pakistan Department of Computer Science and Software Engineering Al Ain UniversityAl Ain11671Abu Dhabi Department of Computer Science King Khalid UniversityAbha61421Saudi Arabia

Algorithms for steganography are methods of hiding data transfers in media *** machine learning architectures have been presented recently to improve stego image identification performance by using spatial information,and these methods have made it feasible to handle a wide range of problems associated with image *** with little information or low payload are used by information embedding methods,but the goal of all contemporary research is to employ high-payload images for *** address the need for both low-and high-payload images,this work provides a machine-learning approach to steganography image classification that uses Curvelet transformation to efficiently extract characteristics from both type of *** Vector Machine(SVM),a commonplace classification technique,has been employed to determine whether the image is a stego or *** Wavelet Obtained Weights(WOW),Spatial Universal Wavelet Relative Distortion(S-UNIWARD),Highly Undetectable Steganography(HUGO),and Minimizing the Power of Optimal Detector(MiPOD)steganography techniques are used in a variety of experimental scenarios to evaluate the performance of the *** WOW at several payloads,the proposed approach proves its classification accuracy of 98.60%.It exhibits its superiority over SOTA methods.

关键词： Curvelets fast fourier transformation support vector machine high pass filters steganography

来源：评论

学校读者我要写书评

暂无评论

Improving information Delivery Effectiveness and Efficiency Using WebVR Technology 23

Improving Information Delivery Effectiveness and Efficiency ...

引用

8th International Conference on Sustainable information engineering and Technology, SIET 2023

作者： Pratama, Ardiyan Nur Akbar, Muhammad Aminul Pinandito, Aryo Informatics Engineering Department Universitas Brawijaya Faculty of Computer Science Indonesia Information System Department Universitas Brawijaya Faculty of Computer Science Indonesia

ISBN: (纸本)9798400708503

In this digital era, attracting new students from outside the region to enter a college or university is difficult. This problem can be solved with good marketing and information dissemination techniques. information is a type of data that has been processed and organized so that it has relevant meaning for the recipient. Useful information can be used to help make decisions, gain new knowledge, or solve problems. One medium for providing information is by using videos that can be uploaded to YouTube for dissemination. However, problems arise when the information depends on the point of view of the video content creator, who may not provide enough information sought by users in their videos. Virtual reality (VR) technology can be pursued as one of the solutions to overcome the lack of detail and control in videos for users to get the expected information. One of the technologies in VR that allows people to explore a three-dimensional virtual world on a web platform is the 360° WebVR technology. Since users have full control over what can be seen using WebVR, it is expected that this technology can assist users in getting deeper and detailed information related to their needs. This study aims to determine the effectiveness and efficiency of using YouTube videos and WebVR in distributing information and delivering detailed information to users. The results show that WebVR technology has the potential to provide greater control over more detailed information to users who use it, in contrast to traditional two-dimensional video playback technology. © 2023 ACM.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Enhancing the Efficiency of Navigation systems: Dijkstra Algorithm Optimization Through Integration of Douglas-Peucker Line Simplification Technique 23

Enhancing the Efficiency of Navigation Systems: Dijkstra Alg...

引用

8th International Conference on Sustainable information engineering and Technology, SIET 2023

作者： Haq, Muhammad Yasir Anshari Sianturi, Riswan Septriayadi Pinandito, Aryo Informatics Engineering Department Universitas Brawijaya Faculty of Computer Science Indonesia Information System Department Universitas Brawijaya Faculty of Computer Science Indonesia

ISBN: (纸本)9798400708503

Smartphones have grown popular in the current digital era among people. Map-based applications are one of many that are used daily by people to acquire information about specific locations. Google Maps and Waze are two popular examples of map-based applications for travel and navigation, as they provide detailed information while the user navigates from one point to another. One of the most commonly used algorithms in map-based applications is the Dijkstra algorithm. Although the Dijkstra algorithm can determine the shortest route between two points, there is an issue when the selected route involves a large number of data points that need to be processed. The more data points involved, the longer it takes to do a route calculation in the Dijkstra algorithm. This can lead to a degradation in system performance, especially on smartphones with limited resources. To address this issue, the Douglas-Peucker algorithm is proposed as a solution to reduce the number of points involved in the calculation using the line simplification technique. Line simplification means reducing unnecessary points that are considered unimportant. This study suggested that integrating the Douglas-Peucker line simplification technique before Dijkstra could improve the system performance more than the system without integrating line simplification in terms of reducing both memory usage and the time required to compute the solution. © 2023 ACM.

关键词： Navigation systems

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：