检索结果-内蒙古大学图书馆

10th International Conference on Communication and Signal Processing, ICCSP 2024

作者： Abinay Shri, J. Denisha, M. Karunya Institute of Technology and Sciences Division of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350353068

'Iris Disease Detection' project is a comprehensive approach to iris health assessment that combines deep learning techniques with image processing methodologies. The system consists of a Streamlit-based web application and a Mobile Net V2 and CNN Classifier, which use OpenCV and KMeans clustering for effective image analysis. The dataset, derived from medical imaging platforms, includes hundreds of high-resolution photos of the iris, annotated with detailed diagnostic information about a wide range of iris health problems. The project includes both normal and diseased irises, as well as those with cataracts, glaucoma, and iritis. The Streamlit web application provides a user-friendly interface for uploading iris images, which undergo preprocessing, grayscale conversion, and Gaussian blur before applying the Hough Circles method to detect the iris region. The system generates visualizations, including the original image, identified iris, and segmented representation achieved through KMeans clustering. The machine learning component enhances the accuracy of 95 percentage and reliability of iris detection, offering a holistic solution for iris disease detection. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Quorum-based Tier Approach: Integrating PBFT and PoS in a Hybrid Consensus Mechanism 3

Quorum-based Tier Approach: Integrating PBFT and PoS in a Hy...

引用

3rd International Conference on Automation, Computing and Renewable Systems, ICACRS 2024

作者： Abinivesh, S. Isravel, Deva Priya Dhas, Julia Punitha Malar Division of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore India

ISBN: (纸本)9798331532420

Blockchain technology is an advanced system centered around the concept of a shared and immutable ledger, emphasizing decentralization, security, and transparency. Transactions on a blockchain are securely linked through cryptographic hashes, forming blocks. A fundamental component of blockchain is the consensus mechanism, which comes in various types, each with its own advantages and limitations. For instance, Proof of Work (PoW) faces challenges related to energy consumption, while Proof of Stake (PoS) is susceptible to certain attacks. This paper proposes a hybrid consensus mechanism that integrates Practical Byzantine Fault Tolerance (PBFT) and Proof of Stake (PoS) using a quorum-based tier approach. This new hybrid model combines the refined features of both PoS and PBFT to create a hierarchical structure for reaching consensus. Nodes are categorized into high-tier and low-tier groups, with the consensus process primarily involving high-tier nodes. Low-tier nodes serve as backups in situations like network issues or node failures. Through experimentation it is evident that the hybrid consensus mechanism achieves a balance between decentralization and energy efficiency. The results demonstrate that this newly developed mechanism outperforms several existing consensus algorithms in terms of throughput and latency. © 2024 IEEE.

关键词： Decentralized control

来源：评论

学校读者我要写书评

暂无评论

Stroke Rehabilitation using Virtual Reality 3

Stroke Rehabilitation using Virtual Reality

引用

3rd International Conference on Applied Artificial Intelligence and Computing, ICAAIC 2024

作者： John, Nived Melvin Sangeetha, R. Karunya Institute of Technology and Sciences Division of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350375190

A specialized virtual reality platform, designed for desktop use, has emerged to assist in the recovery of stroke patients' impaired limbs. The proposed system integrates a mixed reality headset for computational power, enabling users to interact within a virtual environment. Inside this setting, two separate rehab protocols have been carefully developed, addressing various facets of hand mobility, including reach, velocity, and power. Through the implementation of performance-based target levels, the proposed system aims to enhance patient motivation and tailor exercises to individual requirements. Initial clinical trials involved the monitoring of movement using these systems, revealing issues related to patient motivation. However, objective evaluations demonstrated notable improvements in the majority of hand parameters for each patient over the course of the training period, corroborated by positive subjective feedback from the patients. This research study offers detailed perspectives on the creation and implementation of this state-of-the-art VR rehabilitation innovation. © 2024 IEEE.

关键词： Mixed reality

来源：评论

学校读者我要写书评

暂无评论

E-voting system using cloud-based hybrid blockchain technology

引用

Journal of Safety Science and Resilience 2024年第1期5卷 102-109页

作者： Beulah Jayakumari S Lilly Sheeba Maya Eapen Jani Anbarasi Vinayakumar Ravi A.Suganya Malathy Jawahar Department of Information Technology Tagore Engineering College Chennai India School of Computer Science and Engineering SRM Institute of Science and Technology Ramapuram ChennaiIndia Department of Information Technology Jerusalem College of Engineering ChennaiIndia School of Computer Science and Engineering Vellore Institute of Technology Chennai India Center for Artificial Intelligence Prince Mohammad Bin Fahd UniversityKhobarSaudi Arabia Leather Process Technology Division CSIR-Central Leather Research Institute ChennaiIndia

With the invention of Internet-enabled devices,cloud and blockchain-based technologies,an online voting system can smoothly carry out election *** pandemic situations,citizens tend to develop panic about mass gatherings,which may influence the decrease in the number of *** urges a reliable,flexible,transparent,secure,and cost-effective voting *** proposed online voting system using cloud-based hybrid blockchain technology eradicates the flaws that persist in the existing voting system,and it is carried out in three phases:the registration phase,vote casting phase and vote counting phase.A timestamp-based authentication protocol with digital signature validates voters and candidates during the registration and vote casting *** smart contracts,third-party interventions are eliminated,and the transactions are secured in the blockchain ***,to provide accurate voting results,the practical Byzantine fault tolerance(PBFT)consensus mechanism is adopted to ensure that the vote has not been modified or ***,the overall performance of the proposed system is significantly better than that of the existing *** performance was analyzed based on authentication delay,vote alteration,response time,and latency.

关键词： E-voting Cloud Blockchain Smart contract Consensus mechanism

来源：评论

学校读者我要写书评

暂无评论

Machine learning Approaches for Autism Spectrum Disorder Prediction 10

Machine learning Approaches for Autism Spectrum Disorder Pre...

引用

10th International Conference on Communication and Signal Processing, ICCSP 2024

作者： Harish Sree Prasanna Kumar, D. Malardhas, Julia Punitha Devapriya, I. Karunya Institute of Technology and Sciences Division of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350353068

The neurodevelopmental illness known as autism spectrum disorder is a lifelong condition marked by a persistent or limited development of social-communication skills, cognitive abilities, activities, and behavior. The symptoms of autism are easier to see and identify in children between the ages of two and three. A prediction system based on traditional machine learning techniques, such as support vector machines, random forests, multiple layer perceptrons, naive Bayes, convolution neural networks, and deep neural networks, accounts for most of the research on autism spectrum disorder. Accuracy, precision, and recall are among the performance indicators used to verify the proposed models. This study investigated and evaluated the prediction of autism spectrum disorders using standard criteria including application type, simulation method, comparison approach, and input data. The purpose of this work is to offer a consolidated framework for autism spectrum disorder prediction to researchers. With the best results, the random forest method performed better than traditional machine learning algorithms. 97.8% accuracy percentage was achieved. Readers can better comprehend the underlying mechanisms and structures of the investigated frameworks with the aid of these work flow representations. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Security Algorithm for Authenticating Mobile Transactions using Wearable Devices and ECC Based Signcryption 10

A Lightweight Security Algorithm for Authenticating Mobile T...

引用

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

作者： Harrish, A. David, Shibin Karunya Institute of Technology and Sciences Division of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350384369

Internet of Things (IoT) devices are intelligent and act as the core component for capturing transactional data, initiating communication with wearable devices. Wearable devices such as smartwatches or smart wristbands serve as the user's payment interface. It aligns with near field communication (NFC) technology which gets connected with payment terminals at a closer range. As these terminals have secure payment gateways like Unified Payment Interface (UPI) and other intermediaries, transactions between the user's bank account and the merchant will be easier. To prove authorization in the transaction, an additional layer of security called vein pattern authentication is invoked. Alongside, elliptic curve cryptography (ECC) based signcryption ensures secure transactions by encrypting and digitally signing the payment data which guarantees confidentiality and non-repudiation. Therefore, a system that adds additional security to the mobile transactions by appending vein pattern and ECC-based signcryption technique. As a result, confidentiality, authorization, and robustness in the transaction is achieved at a higher rate by inculcating forward secrecy, verifiability and non-repudiation. © 2024 IEEE.

关键词： Gateways (computer networks)

来源：评论

学校读者我要写书评

暂无评论

Green Vision: Plant Care Monitoring System 1

Green Vision: Plant Care Monitoring System

引用

1st IEEE International Conference on Cognitive Robotics and Intelligent Systems, ICC - ROBINS 2024

作者： Nithish, M. Denisha, M. Karunya Institute of Technology and Sciences Division of Computer Science and Engineering Coimbatore India

ISBN: (数字)9798350372748

ISBN: (纸本)9798350372748

The entire human development process is dependent on plants, however caring for them can be quite difficult. The occurrence of different type of diseases that are difficult to identify have blended into these plants. This research study has recognized the usage of technology such as mobile applications and Convolutional Neural Networks [CNN] to examine the afflicted plant and to lessen the human efforts whenever scientists or doctors are unable to travel to different locations to examine them. This study has developed an Android smartphone application, which allows users to remotely analyze their plants and determine which diseases they may have entrenched in them and provide cure for it. All it takes is taking a picture of the plant with a camera or importing it from the gallery to receive diagnosis reports and the cures and needs for it with a simple user-interface, which will help all users to use it easily. © 2024 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Analysis of Cancer Category using Bidirectional LSTM from Medical Records 3

Analysis of Cancer Category using Bidirectional LSTM from Me...

引用

3rd International Conference on Applied Artificial Intelligence and Computing, ICAAIC 2024

作者： Dhinakar, Yalla Reyana, A. Karunya Institute of Technology and Sciences Division of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350375190

Analyzing medical data effectively is critical for making educated decisions and providing patient care in this age of quickly improving healthcare technology. Natural language processing methods, particularly text classification and sentiment analysis in cancer patients' medical records is the primary objective of the proposed work. The goal is to help healthcare professionals diagnose and treat patients more effectively by extracting meaningful insights from textual data. Logistic Regression is used as separate text analysis method in the research. In order to get a full picture of patients' histories, these models are trained and tested to see how well they categorize medical information pertaining to cancer into certain predetermined groups. To make sure the input data is good, data preparation is essential. Remove stop words, special letters, and any unnecessary information from the text to make it cleaner. In addition, the dataset is examined to learn about its properties and distribution which understanding of the data that lie underneath. The suggested models are successful, according to the experimental data;the Bidirectional LSTM model had Healthcare practitioners must pay close attention to these results because they pave the way for improved decision support via the accurate and rapid identification of pertinent medical information. This study highlights the value of natural language processing methods in analyzing cancer patients' medical records, which is a contribution to healthcare analytics as a whole. In addition, it highlights how Bidirectional LSTM models may improve medical record classification, which in turn improves patient care and healthcare decision-making. © 2024 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Food Oil Quality and Usage Detection Using AI 10

Food Oil Quality and Usage Detection Using AI

引用

10th International Conference on Communication and Signal Processing, ICCSP 2024

作者： Sanjay, S. Karunya Institute of Technology and Sciences Division of Computer Science and Engineering Coimbatore India

ISBN: (数字)9798350353068

ISBN: (纸本)9798350353068

The proposed system revolutionizes food oil quality assessment through an intelligent integration of Artificial Intelligence (AI) and Convolutional Neural Networks (CNNs). Overcoming the limitations of traditional methods, the system employs a robust CNN model trained on a diverse dataset of labeled food oil images. This innovative approach enables swift and reliable quality classification, addressing the challenges of real-time monitoring in food production and distribution. The system's architecture emphasizes user-friendliness, offering a seamless interface for diverse stakeholders, including food manufacturers and regulatory bodies. Its adaptability and scalability make it applicable across various food oil types and production settings. By leveraging the efficiency of CNNs, the proposed system heralds a paradigm shift in food oil quality assessment, fostering rapid and accurate decision-making in the ever-evolving landscape of the food industry. © 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

Enhancing Retinal Image Analysis through Deep Learning-Based Blood Vessel Segmentation 10

Enhancing Retinal Image Analysis through Deep Learning-Based...

引用

10th International Conference on Communication and Signal Processing, ICCSP 2024

作者： Anandha Prakash, S. Denisha, M. Karunya Institute of Technology and Sciences Division of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350353068

Blood vessel segmentation is the process of identifying and describing blood vessels from retinal pictures, which is required for quantitative analysis and anomaly detection. However, the accuracy and efficiency of the current blood vessel segmentation approach are frequently inadequate. By using deep learning techniques for blood vessel segmentation, it aims to increase retinal analysis's effectiveness and precision. Based on our findings, UNet outperforms FCN (94.02%) and SegNet (95.89%) in terms of accuracy, reaching a whopping 98.89%. UNet is well-suited for biomedical image segmentation tasks because to its symmetric encoder-decoder structure and skip connections, which allow for good feature extraction and spatial preservation. A user interface is used to provide the segmented image when a retinal picture is injected. It helps in the creation of computer-aided diagnostic tools for retinal diseases and showing in the application by providing a trustworthy method for correct blood vessel segmentation, which is essential for early detection and monitoring of various ocular pathologies. © 2024 IEEE.

关键词： User interfaces

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：