2023 World Conference on Communication & Computing (WCONF)最新文献_第9页

Harnessing the Strength of ResNet50 to Improve the Ocular Disease Recognition 利用ResNet50的优势提高眼部疾病的识别

2023 World Conference on Communication & Computing (WCONF) Pub Date : 2023-07-14 DOI: 10.1109/WCONF58270.2023.10234986

Gunjan Sharma, Vatsala Anand, Sheifali Gupta

{"title":"Harnessing the Strength of ResNet50 to Improve the Ocular Disease Recognition","authors":"Gunjan Sharma, Vatsala Anand, Sheifali Gupta","doi":"10.1109/WCONF58270.2023.10234986","DOIUrl":"https://doi.org/10.1109/WCONF58270.2023.10234986","url":null,"abstract":"Among the most prevalent eye conditions, cataract is the leading cause of blindness, impairing vision. A cataract is a condition that means clouding of the lens of the eye. Cataract-related blindness can be mainly prevented with early detection and prompt treatment. Artificial intelligence systems that grade cataracts based on fundus pictures are a practical way to help clinicians detect cataracts more accurately. For early detection of cataracts, Convolutional neural networks, also referred to as CNNs, have been reported to have a great deal of promise in several different domains, including the identification of many eye illnesses. In this research, a deep CNN model based on ResNet50 architecture has been proposed to classify the images into cataract-infected and normal classes. For fulfilling this task Ocular Disease Intelligent Recognition dataset has been chosen. This dataset contains real-time patient reports of both eyes. The model has shown a very good accuracy of 95.63% and 90.37% of validation accuracy while using SGD optimizer. The loss was 0.64 which is nominal and this model has shown very promising results in classifying the images. This model has a very innovative approach in the medical field so it can be used as a tool in the biomedical or healthcare field.","PeriodicalId":202864,"journal":{"name":"2023 World Conference on Communication & Computing (WCONF)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127867296","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

System Implementation at CED Paint Shop for Cost and Quality Improvement 涂装车间成本和质量改进的系统实施

2023 World Conference on Communication & Computing (WCONF) Pub Date : 2023-07-14 DOI: 10.1109/WCONF58270.2023.10235236

R. A. Mule, Dr. P. V. Paratwar

引用次数: 0

Retinal Fundus Image Classification Using Hybrid Deep Learning Model 基于混合深度学习模型的视网膜眼底图像分类

2023 World Conference on Communication & Computing (WCONF) Pub Date : 2023-07-14 DOI: 10.1109/WCONF58270.2023.10235233

Shobhana Lakhera, Amit Garg

{"title":"Retinal Fundus Image Classification Using Hybrid Deep Learning Model","authors":"Shobhana Lakhera, Amit Garg","doi":"10.1109/WCONF58270.2023.10235233","DOIUrl":"https://doi.org/10.1109/WCONF58270.2023.10235233","url":null,"abstract":"Diabetic retinopathy (DR) is a disease related with diabetes. DR causes lesions on the eye retina that can affect the human vision. DR needs to be detected at its earlier stage, otherwise in the worst situation patients suffer from DR may lead to blindness. Currently, DR is diagnosed using fundus images of the retina using manual methods by medical practitioners. Automated methods are more reliable, cost-effective, and time savers as compared to their manual counterpart. In this work, a deep learning (DL) model is proposed to automatically recognize DR images by classifying retinal fundus images into five different classes. A hybrid DL model of three different DL pretrained models AlexNet, VGGNet, and ResNet-18 is used. Then the performance of the combined proposed model is enhanced using the AdaBoost algorithm. AdaBoost algorithm is used to exploit dependency among different DL models. It can handle missing values and outliers. The APTOS and Messidor-2 dataset are used for the training of all pre-trained models and proposed model. Then performance of the proposed hybrid DL model along with three other pretrained DL models is evaluated based on performance metrics accuracy, sensitivity, specificity, and F1score. From the obtained results it is to be noted that performance metric values for the proposed hybrid model are at higher side as compared to the other pretrained DL models. Hence, the proposed method is a potential method for the DR image classification.","PeriodicalId":202864,"journal":{"name":"2023 World Conference on Communication & Computing (WCONF)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115953508","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Cyber Attack Risk Estimation Technique in Intelligent Cyber Physical System for Pharmaceutical Care Services 面向药学服务的智能网络物理系统网络攻击风险评估技术

2023 World Conference on Communication & Computing (WCONF) Pub Date : 2023-07-14 DOI: 10.1109/WCONF58270.2023.10235133

Swati Devliyal, H. Goyal, Sachin Sharma

引用次数: 0

Automation of FaaS Serverless Frameworks OpenFaaS and OpenWhisk in Private Cloud 私有云中FaaS无服务器框架OpenFaaS和OpenWhisk的自动化

2023 World Conference on Communication & Computing (WCONF) Pub Date : 2023-07-14 DOI: 10.1109/WCONF58270.2023.10235008

Pankaj Tiwari, Sangeeta Sharma

{"title":"Automation of FaaS Serverless Frameworks OpenFaaS and OpenWhisk in Private Cloud","authors":"Pankaj Tiwari, Sangeeta Sharma","doi":"10.1109/WCONF58270.2023.10235008","DOIUrl":"https://doi.org/10.1109/WCONF58270.2023.10235008","url":null,"abstract":"A methodology for cloud-native development called serverless facilitates the creation and execution of programmes by developers without worrying about maintaining servers. As no automation is available to implement FaaS serverless frameworks in private clouds and manual implementation is a tedious job. If the same tasks are performed manually, there is a greater risk of human error as well as an increase in cognitive strain that can take up to 4-5 hours for installation and configuration. Therefore, we are going to provide a command line tool to automate the process to implement FaaS serverless frameworks Open-FaaS and OpenWhisk in private clouds, which is easy to configure and straight forward to use. The proposed tool has the potential to save significant time and cost for customers compared to hiring a DevOps engineer to manually perform the installation and configuration. Additionally, the potential revenue generated from the tool’s use in the financial industry alone suggests a promising market for this type of automation tool. Overall, this paper highlights the usefulness and importance of automation in facilitating the adoption and implementation of serverless architecture in private clouds.","PeriodicalId":202864,"journal":{"name":"2023 World Conference on Communication & Computing (WCONF)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115653775","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Teeth Staining from Tobacco Consumption as an Indicator to Chronic Illness: A Data Analytics and Machine Learning Application 牙齿染色从烟草消费作为慢性疾病的指标:数据分析和机器学习的应用

2023 World Conference on Communication & Computing (WCONF) Pub Date : 2023-07-14 DOI: 10.1109/WCONF58270.2023.10234993

Koel Bajaj, Reetu Jain

{"title":"Teeth Staining from Tobacco Consumption as an Indicator to Chronic Illness: A Data Analytics and Machine Learning Application","authors":"Koel Bajaj, Reetu Jain","doi":"10.1109/WCONF58270.2023.10234993","DOIUrl":"https://doi.org/10.1109/WCONF58270.2023.10234993","url":null,"abstract":"Tobacco consumption is a major public health concern because it is associated with a range of serious health problems, including lung cancer, heart disease, stroke, respiratory disease, and many others. Tobacco consumption is a leading cause of preventable death and disease worldwide, and it is estimated to be responsible for over 7 million deaths each year. The primary active ingredient in tobacco products is nicotine, which is highly addictive. People who use tobacco products can become physically dependent on nicotine, which can make it very difficult to quit using tobacco. Too much of nicotine consumption can cause the staining of the dental enamel. The aim of this study is to develop machine learning (ML) model to classify chronic diseases in person based on their dental staining. The study is divided into two phases. In the first phase involves the development of a smart system to detect and categorize the dental stain as high, average and low. This phase also involves the collection of demographic data and its analysis to derive valuable insights from it. The second phase involves training of the different ML models to recognize the hidden pattern in them. The parameters of the ML models are optimized by tuning and then the tuned ML models are employed for classifying the chronic illness. The Grid Searched Logistic Regression (GSLR) showed the best prediction out of all the ML models. The GSLR model showed training and testing accuracy of 64% and 60% respectively. The applicability of the model is ascertained by applying the model to the test data. The GSLR model is able to correctly classify 7 out of the 31 cases of no chronic diseases and 38 out of 44 cases of chronic diseases. Based on the applicability of the model, it can be concluded that the model is capable of detecting chronic diseases with dental enamel staining as an indicator.","PeriodicalId":202864,"journal":{"name":"2023 World Conference on Communication & Computing (WCONF)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114537796","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Indian Sign Language (ISL) Recognition And Translation using Mediapipe and LSTM 使用Mediapipe和LSTM的印度手语识别和翻译

2023 World Conference on Communication & Computing (WCONF) Pub Date : 2023-07-14 DOI: 10.1109/WCONF58270.2023.10235113

Tanmay Nehra, D. Saisanthiya, Anshu Modi

引用次数: 0

Utilization of Parallel Transmission in the Network Using MAC Protocol With Back Off Algorithm in WSN 基于MAC协议的WSN网络并行传输的应用

2023 World Conference on Communication & Computing (WCONF) Pub Date : 2023-07-14 DOI: 10.1109/WCONF58270.2023.10235204

Saksham Sood

{"title":"Utilization of Parallel Transmission in the Network Using MAC Protocol With Back Off Algorithm in WSN","authors":"Saksham Sood","doi":"10.1109/WCONF58270.2023.10235204","DOIUrl":"https://doi.org/10.1109/WCONF58270.2023.10235204","url":null,"abstract":"Parallel transmission is a general concept in networking that involves the simultaneous sending of multiple data streams to increase the amount of data that can be transferred in a given time period. In this technique, the data is divided into several small parts and each part is sent along multiple paths in parallel to reduce latency and improve the total data throughput of the network. The Media Access Control (MAC) protocol is used to mediate communication between nodes in an Ethernet network. It allocates bandwidth between the nodes and guarantees that multiple nodes can communicate simultaneously without any collision. The MAC protocol also plays a critical role in the utilization of parallel transmission in a network as it is used to achieve efficient and reliable delivery of bits along multiple paths. By using parallel transmission, MAC protocol ensures reliable, low latency, and high throughput communication. Furthermore, it helps to reduce the chances of data loss by increasing the number of available paths for transmission. In order to improve network performance, modern networks are now using parallel transmission in combination with other technologies such as Quality of Service (QoS) and Adaptive Multi-Rate (AMR). These technologies are designed to provide more efficient use of communication channels and increase the data rate of networks in general. Additionally, parallel transmission is being used in various wireless communication networks to improve the efficiency of data transmission. All in all, parallel transmission is becoming increasingly popular in networking due to its ability to significantly improve transmission speed and reduce latency. The MAC protocol is an important part of this technology as it facilitates reliable transmission of packets along multiple paths through careful allocation of bandwidth. As a result, the utilization of parallel transmission and MAC protocol in networking has become a popular way to significantly improve the data rate and quality of service of a network.","PeriodicalId":202864,"journal":{"name":"2023 World Conference on Communication & Computing (WCONF)","volume":"11 7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116295860","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Water Potability Prediction Model Based on Machine Learning Techniques 基于机器学习技术的饮用水预测模型

2023 World Conference on Communication & Computing (WCONF) Pub Date : 2023-07-14 DOI: 10.1109/WCONF58270.2023.10235096

Vaibhav Singh, Navpreet Kaur Wallia, Animesh Kudake, Aniket Raj

引用次数: 0

Response Surface Methodology to Optimize the Screen Brightness and Duration of Laptop Usage Based on the Eye Blink Rate 基于眨眼频率优化笔记本电脑屏幕亮度和持续时间的响应面方法

2023 World Conference on Communication & Computing (WCONF) Pub Date : 2023-07-14 DOI: 10.1109/WCONF58270.2023.10235030

Kush Agrawal, Reetu Jain

{"title":"Response Surface Methodology to Optimize the Screen Brightness and Duration of Laptop Usage Based on the Eye Blink Rate","authors":"Kush Agrawal, Reetu Jain","doi":"10.1109/WCONF58270.2023.10235030","DOIUrl":"https://doi.org/10.1109/WCONF58270.2023.10235030","url":null,"abstract":"During the lockdown caused by the COVID-19 pandemic, the average screen time of a person saw a drastic increase. Laptops and personal computers were used throughout the pandemic for entertainment and work, and many jobs shifted to the online medium. Thus the use of laptops and personal computers for entertainment and work continued even after the pandemic. But, long hours of work combined with the use of screens lead to many people staring at a screen for a large part of their day leading to eye-related problems like digital eye syndrome. This became a widespread problem of its own as more and more people began to heavily rely on their digital devices. A low blink rate is also a prominent cause of digital eye strain. A healthy human at rest blinks around 17 times per minute while a human using a screen blinks around 12–15 times per minute. The aim and objective of the present study are to determine the optimal level of brightness and duration of usage for the most comfort of computer screen usage. In order to achieve the aims and objectives of the study, the data collected are analyzed using the response surface methodology (RSM) and contour plot method. The RSM optimizer is employed to compute the optimal brightness level and duration of usage. The data is collected by a python code built using the openCV, CVzone, and FaceMesh libraries. The data collected at different levels of brightness ranging from 50 to 100 at intervals of 10 and the duration of usage is ranged from 10 to 30 minutes at an interval of 10 minutes. Full factorial design of experiment (DOE) is employed to plan the experiments. The data were collected from 50 participants for 6 days from 10 AM to 3 PM.","PeriodicalId":202864,"journal":{"name":"2023 World Conference on Communication & Computing (WCONF)","volume":"3 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125605968","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0