检索结果-内蒙古大学图书馆

2022 International Conference on Advanced Computing Technologies and applications, ICACTA 2022

作者： Sheeba, T.M. Albert Antony Raj, S. Anand, M. SRM Institute of Science and Technology College of Science and Humanities Department of Computer Applications Chennai India SRM Institute of Science and Technology College of Engineering and Technology Department of Networking and Communications Chennai India

ISBN: (纸本)9781665495158

Pigment epithelial detachment(PED) is a disorder in retina that happens when RPE layers of cells at the back side of the eye come apart, or get teared. The bend of layers in the retina, as well as fluid, proteins, tissue, or blood vessels, is a defining feature of PED disease, which occurs most frequently in the macula. PED can disturb the vision of the people which is often depict dark shadow, blurry vision or partial loss of vision. The optical coherence tomography (OCT) is a trend set of high resolution and non-invasive imaging modality that expedite the structure of the retina. OCT non-invasively yields cross-sectional volume of images with tissues. The major objective of this research paper is to study, state of art and to classify the retinal layer segmentation techniques, PED fluid segmentation and classification of diseases in retinal OCT images. The medical industry is suffering with more critical patients and the cases are increasing in eye diseases double the number as of now. The artificial intelligence (AI) techniques help the health sector with a great and accurate automatic detection of disease. The image classification and pattern recognition are transforming the industry with artificial intelligence techniques. Many studies are being conducted employing image processing to aid in the early diagnosis of this disease. Image processing techniques have advanced as a result of the introduction of artificial intelligence and machine learning. In this review paper, the structure classification methods and the image segmentation method that are best available existing research is discussed. This review summarizes all the recent algorithms that suits for the application of machine learning algorithms for predicting retinal diseases in OCT images. The algorithms discussed from existing research paper, produce the readers to identify the best accurate algorithm for retinal classification of infected eye and normal eye, precision and less processing time for la

关键词： Optical tomography

来源：评论

学校读者我要写书评

暂无评论

Survey on Machine Learning Techniques Used for Central Serous Retinopathy Detection

Survey on Machine Learning Techniques Used for Central Serou...

引用

2023 International Conference on Advances in Computation, Communication and Information Technology, ICAICCIT 2023

作者： Suba, M. Rajini, S. Nirmala Sugirtha Anand, M. Dr. Mgr Educational and Research Institute Department of Computer Science Chennai Tamil Nadu Maduravoyal India Dr. Mgr Educational and Research Institute Department of Computer Applications Chennai Tamil Nadu Maduravoyal India Srm Institute of Science and Technology Faculty of Engineering and Technology Department of Networking and Communications Chennai Kattankulathur India

ISBN: (纸本)9798350344387

Central Serous Retinopathy (CSR) is an important health concern affecting millions of people worldwide, leading to vision loss and blindness. This condition is identified by abnormalities in retinal layers and fluid leakage, frequently occurring in the vicinity of the macula. The disease generates pressure inside the retinal layers, resulting in the detachment of retinal walls and subsequently causing impaired vision. As the macula is home to most of the visual sensory organs, including rods and cones, the eyesight undergoes substantial effects. Thus, early detection of CSR permits preventive actions to be taken to avoid any eye damage. While numerous physical approaches for detecting CSR have been devised previously, they have demonstrated inaccuracies and a lack of reliability. This paper examines the different algorithms, imaging modalities, and the outcomes they yield that have been devised over time for the timely detection of CSR. The research reveals that the SVM classifier has achieved a 97% accuracy rate in recognizing central serous retinopathy ailment based on OCT images. © 2023 IEEE.

关键词： Choroid Neovascularization Fundus Autofluorescence Optical Coherence Tomography image Pigment Epithelium Detachment Retinal Pigment Epithelium Support Vector Machine

来源：评论

学校读者我要写书评

暂无评论

SMART: Secured and Mobility Aware Routing Technique for Opportunistic IoT Network in Smart Cities

引用

Journal of Mobile Multimedia 2024年第2期20卷 335-358页

作者： Ajith Kumar, S.P. Thakur, Hardeo Kumar Datta Gupta, Koyel Sharma, Deepak Kumar Manav Rachna University Department of Computer Applications Bhai Parmanand DSEU Shakarpur Campus II India SCSET Bennett University Greater Noida India Department of Computer Science and Engineering Maharaja Surajmal Institute of Technology New Delhi India Department of Information Technology Indira Gandhi Delhi Technical University for Women Delhi India

Transferring data between nodes in the Opportunistic Internet of Things (OppIoT) network may lead to the transmission of multiple copies of each message, which can increase communication costs and jeopardise network security. This necessitates a routing method that is effective and can address both problems. To protect transmitted data and reduce communication overhead, this study suggests a Secured and Mobility Aware Routing Method (SMART) routing algorithm for OppIoT networks in smart cities. With a buffer size of 30 MB and an overhead ratio of 27.9, the delivery probability can be increased by more than 50%. The simulation’s findings demonstrate that, in terms of delivery probability, overhead ratio, and reports, the proposed SMART protocol outperforms more traditional routing methods. © 2024 River Publishers.

关键词： delivery probability Internet of Things ONE simulator opportunistic network routing protocols scheduled energy smart cities time to live

来源：评论

学校读者我要写书评

暂无评论

The HAR-KNN - A novel Prospective for Recommendation System

The HAR-KNN - A novel Prospective for Recommendation System

引用

2024 International Conference on Sustainable Computing and Integrated Communication in Changing Landscape of AI, ICSCAI 2024

作者： Kumar, Rohit Adnan, Myasar Mundher Shrivastava, Anurag Bhadula, Shuchi Dutt, Amit Praveena, K. Bansal, Saloni School of Management Gautam Buddha University Greater Noida India Department of computers Techniques engineering College of technical engineering The Islamic university Najaf Iraq Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamilnadu Chennai India Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun India Lovely Professional University Phagwara India Institute of Aeronautical Engineering Dundigal Hyderabad India Department of Computer Engineering and Applications GLA University Mathura India

ISBN: (纸本)9798350355338

Commercial platforms frequently use the Recommendation System (RS) to offer recommendations to users. Recommendation systems (RS) are extensively employed in diverse domains, especially in e-commerce platforms where RS detects recommended products based on user activity. Some significant problems have emerged as a result of the last decades' significant growth in both users and products.. Additionally, selecting the appropriate product and active user in RS is a challenging procedure. When recommending products, existing works take user preferences and sociodemographic behavior into account. Collaborative filtering (CF) is one of the most often used algorithms in recommendation systems. This algorithm is simple to understand and performs well. Data based on user behavior that is gathered from the Amazon dataset is used for testing. The Amazon product dataset contains 18,501 product reviews. The dataset's data was gathered and integrated with administrative services using Amazon Web *** suggested Deep Neural Network (DNN) method is empirically tested based on metrics like F1-measure, Recall (R), and Precision (P), and it provides the highest value of those metrics when compared to state-of-the-art techniques like K-Nearest Neighbour (K-NN) and Artificial Neural Networks (ANN). © 2024 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

PRACTICING THE RULE-BASED CLASSIFIER USING METAHEURISTICS GRAVITATIONAL SEARCH ALGORITHM TO GENERATE A CREDIT SCORE MODEL TO AVAIL LOANS

PRACTICING THE RULE-BASED CLASSIFIER USING METAHEURISTICS GR...

引用

2024 International Conference on Sustainable Computing and Integrated Communication in Changing Landscape of AI, ICSCAI 2024

作者： Kumar, Rohit Habelalmateen, Mohammed I. Bansal, Saloni Bhadula, Shuchi Reddy, C.H. Vijendar Kansal, Lavish Boob, Nandini Shirish School of Management Gautam Buddha University Greater Noida India Department of Computers Techniques Engineering College of Technical Engineering The Islamic University Najaf Iraq Department of Computer Engineering and Applications GLA University Mathura India Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun India Institute of Aeronautical Engineering Dundigal Hyderabad India Lovely Professional University Phagwara India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamilnadu Chennai India

ISBN: (纸本)9798350355338

Recent times has witnessed a sudden surge in organizations offering micro-loans on digital media in several developing nations. Airtime lending default rates are generally lesser compared to those faced by banks and microfinance institutions (MFIs) but there is possibly more development since the service is provided ubiquitously. In order to provide an appropriate machine learning framework for airtime lending, this paper examines credit scoring methodologies. Over three million loans with a three-month repayment period that were extended to over 41,000 clients are assessed. A brand-new method for creating a fuzzy-rule-based classifier using the Gravitational Search Algorithm (GSA) metaheuristic is presented. It is evaluated for its ability to classify defaulters using a variety of cross-validation techniques, and the latter framework's performance was excellent. The newness of this technique is in the hybridization of data mining algorithms targeted at the dimensionality reduction of the data and accuracy improvement in the future behaviour prediction of corporate loans, so that a highly efficient micro and macro administration of credit risk can be facilitated. All applicants can get loans if the default rate is less than 2%. When default rates are higher, the framework offers a significant boost in profitability. The allowable degree of default rate for exceeding even is quadrupled by the framework, from 8% to 32%. Nonlinear classification methods show significant promise in credit scoring, allowing for a large number of consumers by handling higher levels of default. © 2024 IEEE.

关键词： Dimensionality reduction

来源：评论

学校读者我要写书评

暂无评论

Vision-Based Locomotion Control for Humanoid Robots: A Study on Vision-Guided Walking Strategies

Vision-Based Locomotion Control for Humanoid Robots: A Study...

引用

2023 International Conference on Computational Intelligence and Sustainable engineering Solution, CISES 2023

作者： Pandey, Saroj Kumar Kumar, Lalan Kumar, Gaurav Kumar, Ankit Singh, Kamred Udham Singh, Teekam Gla University Department of Computer Engineering & Applications UP Mathura India Gl Bajaj Institute of Technology and Management Department of Master of Computer Application India School of Computing Graphic Era Hill University Dehradun India Graphic Era Deemed to Be University Department of Computer Science and Engineering Dehradun India

ISBN: (纸本)9798350323917

Recently, there has been a lot of research on using vision to direct humanoid robots as they walk. Focusing on the major methodologies, difficulties, and prospects, this review article presents an overview of the current state of study in the vision-guided walking of humanoid robots. In the first part of the study, we introduce vision-guided walking and go through the several methods that have been developed to execute it, such as visual serving, visual odometer, and visual simultaneous localization and mapping. The difficulties of vision-guided walking are then discussed;these include, but are not limited to, the necessity for accurate and strong computer vision algorithms, the robot's need to have a solid awareness of its own body and how it moves, and the need to maintain balance while walking. This paper provides a detailed review of the research on humanoid robots that use vision to direct their gait. Deep learning for vision-guided walking, tactile and proprioceptive sensing combined with vision, and reinforcement learning for adaptive walking are only a few of the issues covered in this overview. Future directions in vision-guided walking research are discussed in this paper. These include the development of more advanced and reliable computer vision algorithms, the incorporation of other modalities like tactile and auditory sensing, and the investigation of new applications for vision-guided walking in fields like healthcare and rehabilitation. © 2023 IEEE.

关键词： Anthropomorphic robots

来源：评论

学校读者我要写书评

暂无评论

An Overview of Video Tampering Detection Techniques: State-of-the-Art and Future Directions

An Overview of Video Tampering Detection Techniques: State-o...

引用

2023 International Conference on Computational Intelligence and Sustainable engineering Solution, CISES 2023

ISBN: (纸本)9798350323917

In the realm of video processing and forensics, finding video tampering is a critical challenge. The purposeful change or manipulation of video material to conceal or falsely depict the original information is referred to as 'video tampering.' A significant demand for efficient video tampering detection methods has emerged in recent years as a result of the rise in false news, cyberbullying, and other types of criminal behavior. Modern approaches for detecting video manipulation may be generally divided into two categories: passive methods and aggressive methods. Whereas active methods entail putting digital watermarks or other identifiers on the video clip to aid tampering detection, passive methods rely on evaluating the video content for inconsistencies or artifacts generated during tampering. Techniques like sensor noise analysis, splicing detection, and forgery detection based on compression artifacts are examples of passive approaches. To find any discrepancies produced by manipulation, sensor noise analysis examines the noise patterns in the video. Splicing detection entails identifying the borders between several video segments and inspecting the content of each segment for irregularities. Analyzing the compressed video stream for irregularities caused during tampering is required for detecting forgeries based on compression artifacts. Techniques like digital watermarking, digital signatures, and fingerprinting are examples of active procedures. To detect any manipulation efforts, digital watermarking entails putting a digital watermark into the video clip. To confirm the legitimacy of the video clip, a digital signature is applied to it. To do fingerprinting, special characteristics from the video footage are extracted and saved in a database. In addition to the aforementioned methods, machine learning-based systems have also demonstrated promising outcomes in the identification of video manipulation. Using these methods, any tampering attempts in fresh mov

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

An Exploration of Deep Learning-Based Object Detection and Classification in Yakshagana Imagery with YOLOv3

An Exploration of Deep Learning-Based Object Detection and C...

引用

Electronics and Sustainable Communication Systems (ICESC), 2020 International Conference on

作者： Anantha Murthy Prarhwini Sanjeev Kulkarni Department of Master of Computer Applications Karkala and Research Scholar NMAM Institute of Technology Nitte (Deemed to be University) Institute of Computer Science and Information Science Srinivas University India Department of Master of Computer Applications NMAM Institute of Technology Nitte (Deemed to be University) Karkala India Department of Computer Science and Engineering Srinivas University Institute of Engineering and Technology Mangalore India

ISBN: (数字)9798350379945

ISBN: (纸本)9798350379952

The Indian theatrical genre known as yakshagana has its roots in the coastal districts of Karnataka and parts of Kerala. With a distinct style and shape, it is a colorful fusion of dance, music, conversation, clothing, makeup, and stage tactics. This research uses YOLOv3, a cutting-edge object detection framework, to recognize people and crown jewelry in order to tackle the problem of identifying Yakshagana characters. Yakshagana, a traditional Indian theatrical style, is distinguished by its distinctive and ornate headdresses and costumes, which complicates automated identification. In order to do this, three classifications were taken into consideration: “person,” “yedekattu,” and “kireeta”. A carefully annotated dataset was used to train the model, which allowed it to capture all of the fine characteristics of these classifications. With a mean Average Precision (mAP) of 93.83%, our method showed impressive accuracy. With the improvement of picture identification and classification technologies, deep learning approaches have the ability to preserve and promote cultural heritage, as demonstrated by this high accuracy.

关键词： YOLO Deep learning Accuracy Art Clothing Real-time systems Cultural differences Character recognition Object recognition Global communication

来源：评论

学校读者我要写书评

暂无评论

Kohonen Self-Organizable Maps based Classification of Optical Code Division Multiple Access Codes 6

Kohonen Self-Organizable Maps based Classification of Optica...

引用

6th International Conference on Inventive Computation Technologies, ICICT 2023

作者： Shankari, S. Hariharan, G. Kushwaha, Sumit Vidhya, K. Vijaya Kumar Reddy, R. Madan, Parul Department of Computer Science and Engineering R.M.K College of Engineering and Technology Tamil Nadu Puduvoyal601206 India Department of Artificial Intelligence and Machine Learning Malla Reddy University Telangana Hyderabad500043 India Department of Computer Applications University Institute of Computing Chandigarh University Punjab 140413 India Department of Computer Science and Engineering KPR Institute of Engineering and Technology Tamil Nadu Arasur641407 India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram522502 India Department of Computer Science and Engineering Graphic Era Deemed to be University Uttarakhand Dehradun248002 India

ISBN: (纸本)9798350398496

Passive Optical Networks (PONs) are a type of fiber-optic network that use passive components, such as splitters and combiners, to distribute optical signals to multiple end-users. PONs typically consist of an Optical Line Terminal (OLT), and Optical Network Units (ONUs) or Optical Network Terminals (ONTs). PONs is also more energy-efficient and environmentally friendly than traditional networks, as they use passive components that do not require power. Overall, PONs is a cost-effective and efficient way to deliver high-speed broadband services to end-users. They offer several advantages over traditional networks and are expected to play a critical role in the deployment of next-generation broadband services. Optical code division multiple access (OCDMA) is an important candidate for implementing access control in PONs because it provides related features such as higher security and flexible on-demand bandwidth. In this context, this article presents a new method for classifying OCDMA codes using artificial neural networks, in particular Kohonen self-organizing maps (S OM), which is important for higher security of the network management system. for users, improving the quality of service (QoS). The code classification success rate was 87.5%, which justifies pattern identification methods to improve the optical code detection process. © 2023 IEEE.

关键词： Passive optical networks

来源：评论

学校读者我要写书评

暂无评论

Effective Short Packet Communication for Resource Allocation in Wireless Powered Iot Networks 9

Effective Short Packet Communication for Resource Allocation...

引用

9th International Conference on Advanced Computing and Communication Systems, ICACCS 2023

作者： Selvi, K. Kanchana, D. Sankar, R. Princy, B Anni Saravanan, S. Balamurugan, A. R M K Engineering College Department of Information Techology Tamil Nadu India SRM Institute of Science and Technology Department of Computer Applications Tamil Nadu India Chennai Institute of Technology Department of Electrical and Electronics Engineering Tamil Nadu India Panimalar Engineering College Department of Computer and Communication Engineering Tamil Nadu India Jeppiaar Institute of Technology Department of Aritificial Intelligence and Data Science Tamil Nadu India

ISBN: (纸本)9798350397376

The Internet-of-things (IoT) is a technology that might be used to link huge amounts of equipment and gadgets in the future. This research uses a hybrid access point (HAP) to explore short packet communication (SPC), in which the IoT devices broadcast their short data packets to the HAP using the energy they gather. As compared to regular wireless networks, SPC has a lower transmission rate and a higher packet error rate. With unlimited block length codes, the allocation of resources in the literature is no longer the best it could possibly be. Based on a user's unique effective amount of information r, their transmission time and packet error rate are tuned to maximize or decrease total effective throughput or total transmission time. Nonconvex issues need the development of efficient ways for unacceptable solutions. These algorithms outperform current benchmarks and are on par with an exhaustive search for the optimum solution in terms of performance. © 2023 IEEE.

关键词： Resource allocation

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：