2021 2nd International Conference on Communication, Computing and Industry 4.0 (C2I4)最新文献_第2页

Real-time Face Mask Detection System on Edge using Deep Learning and Hardware Accelerators 基于深度学习和硬件加速器的边缘实时人脸检测系统

2021 2nd International Conference on Communication, Computing and Industry 4.0 (C2I4) Pub Date : 2021-12-16 DOI: 10.1109/C2I454156.2021.9689421

Stavan Ruparelia, Monil Jethva, Ruchi Gajjar

{"title":"Real-time Face Mask Detection System on Edge using Deep Learning and Hardware Accelerators","authors":"Stavan Ruparelia, Monil Jethva, Ruchi Gajjar","doi":"10.1109/C2I454156.2021.9689421","DOIUrl":"https://doi.org/10.1109/C2I454156.2021.9689421","url":null,"abstract":"Real-time face mask detection with the use of Artificial Intelligence is one of the most advanced ways of detecting face masks and their wearing condition in public or private areas. In this work, a system based on Object Detection models is proposed which can detect and classify the type of mask wearing conditions in real-time. The system is implemented with two latest deep convolutional neural networks; YOLOv5s and YOLOv5l. The proposed system can efficiently detect and classify face masks based on their wearing condition as well as count them and store the count into a CSV file format with a timestamp. To perform real-time inference, the deep learning models were deployed on Nvidia Jetson Nano and Jetson Xavier NX which are embedded solutions inspired by Edge AI. The detection algorithms achieved mAP of 86.43 and 92.49 for YOLOv5s and YOLOv5l respectively. Comparing the mAP of both detection models, YOLOv5l achieved higher mAP than YOLOv5s while comparing fps on both hardware, Nvidia Jetson Xavier NX provides more fps than Nvidia Jestion Nano for realtime inference.","PeriodicalId":190895,"journal":{"name":"2021 2nd International Conference on Communication, Computing and Industry 4.0 (C2I4)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133959653","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: 2

Employee Attrition System Using Tree Based Ensemble Method 基于树的集成方法的员工流失系统

2021 2nd International Conference on Communication, Computing and Industry 4.0 (C2I4) Pub Date : 2021-12-16 DOI: 10.1109/C2I454156.2021.9689398

Vimoli Mehta, S. Modi

{"title":"Employee Attrition System Using Tree Based Ensemble Method","authors":"Vimoli Mehta, S. Modi","doi":"10.1109/C2I454156.2021.9689398","DOIUrl":"https://doi.org/10.1109/C2I454156.2021.9689398","url":null,"abstract":"Employee attrition has become a vital problem across the world. It is one of the crucial issues faced by business leaders within companies where they lose the most talented employees. A good employee is always an asset to the organization and their resignation can lead to various problems like financial losses, overall performance, and loss of acquired knowledge. Furthermore, hiring new employees is far exorbitant, taxing, and time-consuming in comparison to recruiting the existing one. It is very time-consuming to recruit a new employee as it takes him months for training, adjusting to the culture, rules, and environment. Therefore, upcoming trends and technology using Machine Learning Algorithms must be exploited for the benefit of business organizations. Knowing the reason beforehand for the employee attrition, companies can mitigate this loss. This paper provides a conclusive review of employee attrition using the tree-based Ensemble Machine Learning Model from the dataset ‘IBM HR Analytics Employee Attrition Performance’.A collection of statistically significant factors which connect to an employee's decision to leave are identified. The paper evaluates the tree-based ensemble to get the best results from the existing tree methods.","PeriodicalId":190895,"journal":{"name":"2021 2nd International Conference on Communication, Computing and Industry 4.0 (C2I4)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133962280","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: 6

BER Analysis Using NOMA System over Various Fading Channels 不同衰落信道下NOMA系统的误码率分析

2021 2nd International Conference on Communication, Computing and Industry 4.0 (C2I4) Pub Date : 2021-12-16 DOI: 10.1109/C2I454156.2021.9689385

M. Ranjeeth, V. Manohar, A. Supriya, M. Vinay, M. Bhargav

引用次数: 1

A Real Time Application for Lung Cancer Prediction using Machine Learning 使用机器学习进行肺癌预测的实时应用

2021 2nd International Conference on Communication, Computing and Industry 4.0 (C2I4) Pub Date : 2021-12-16 DOI: 10.1109/C2I454156.2021.9689442

U. B. Mahadevaswamy, Sharayu R Siddhanti, B. M, Mounashree B

引用次数: 0

Stacked Graph Transformer for HIV Molecular Prediction HIV分子预测的堆叠图转换器

2021 2nd International Conference on Communication, Computing and Industry 4.0 (C2I4) Pub Date : 2021-12-16 DOI: 10.1109/C2I454156.2021.9689399

Yogesh Raisinghani, Aagam Shah, Mrugendrasinh L. Rahevar

{"title":"Stacked Graph Transformer for HIV Molecular Prediction","authors":"Yogesh Raisinghani, Aagam Shah, Mrugendrasinh L. Rahevar","doi":"10.1109/C2I454156.2021.9689399","DOIUrl":"https://doi.org/10.1109/C2I454156.2021.9689399","url":null,"abstract":"A Neural Network(NN) is a tool that is modeled after the human brain's neuron system and is used to learn from data and produce the required results. NNs have shown themselves to be highly effective in a variety of domains so far. Graph-structured data or non-euclidean data (non-grid/non-text) growth has, however, constrained the applications of traditional Neural Networks. Graph Neural Networks (GNNs) have recently entered the game, which can efficiently learn representations from Graph Structure. GNNs come in a variety of flavors and quickly gained popularity. Various approaches from other ML domains have been included in GNNs in an effort to improve their performance. One such approach is the Transformer architecture that has become well-known and famous in the NLP field thanks to its admirable attention mechanism. Recently, academics have attempted to use an amalgamation of Graph Neural Networks with Transformers on a variety of problem statements. In our work, for instance, we have tried to incorporate the same philosophy into the molecular field that has had fewer contributions with Transformers. We have narrowed our focus on HIV inhibitor classifications for this study. With a few more details covered further, this paper suggests a novel way to use a stacked transformer method that makes use of multiple transformer blocks to alleviate the limitations of traditional methodologies and achieve great performance. The proposed methods produce results that are comparable or slightly better in some cases to those achieved by current approaches.","PeriodicalId":190895,"journal":{"name":"2021 2nd International Conference on Communication, Computing and Industry 4.0 (C2I4)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128395166","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

Novel Fluorescent Finger Print Monitoring System for Car Drivers and Passengers 新型汽车驾驶员和乘客荧光指纹监测系统

2021 2nd International Conference on Communication, Computing and Industry 4.0 (C2I4) Pub Date : 2021-12-16 DOI: 10.1109/C2I454156.2021.9689392

Jai Deo Tiwari, I. Pandey

{"title":"Novel Fluorescent Finger Print Monitoring System for Car Drivers and Passengers","authors":"Jai Deo Tiwari, I. Pandey","doi":"10.1109/C2I454156.2021.9689392","DOIUrl":"https://doi.org/10.1109/C2I454156.2021.9689392","url":null,"abstract":"Road crash is major risk in automobile sectors. Drugged and drunken drivers are major cause for this crash. As per published report in National institute of Drug Abuse 2019, more than 20 million drunken drivers or drugged drivers are lost their lives. These drivers can be classified as high risk drivers putting their lives in risk but also others such as pedestrians and passengers. The main focus of this work is to develop the alert system that can give real time data of alcohol or cocaine level in sweat and exhaled breath of drunken/drugged drivers and prohibiting them to drive the vehicles. Here novel fluorescence boron nitrogen co doped carbon quantum dots sensors are developed with high selectivity of alcohol and cocaine in breath as well as sweat. With only fluorescence boron nitrogen co doped carbon quantum dots, the senor could quantitatively simultaneously detection alcohol (4–235 μM) and (10–395 μM) cocaine in exhaled breath. The developed sensor shows high sensitivity in the range of 0.22 ${mu AmM-^{1},cm^{2}}$ range with 95% confidence limits. These sensors are flexible, mechanically stable and easily integrated on steering, seat belts and car cabinets. The sensors response time is less than 60 secs and have capability to monitor drunken/drugged driver physiology and prevent the access of vehicles. Deviation of fluorescence is directly related to level of alcohol and cocaine in sweat and exhaled breath. The output signals of sensor decide and grant permission to drivers to drive or not to drive. Thus implementing this sensors in autonomous vehicles safe person life and prevent the damage of public properties.","PeriodicalId":190895,"journal":{"name":"2021 2nd International Conference on Communication, Computing and Industry 4.0 (C2I4)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129496706","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

Autonomous Application in Requirements Analysis of Information System Development for Producing a Design Model 设计模型生成在信息系统开发需求分析中的自主应用

2021 2nd International Conference on Communication, Computing and Industry 4.0 (C2I4) Pub Date : 2021-12-16 DOI: 10.1109/C2I454156.2021.9689440

Prasath R, Rajesh George Rajan

{"title":"Autonomous Application in Requirements Analysis of Information System Development for Producing a Design Model","authors":"Prasath R, Rajesh George Rajan","doi":"10.1109/C2I454156.2021.9689440","DOIUrl":"https://doi.org/10.1109/C2I454156.2021.9689440","url":null,"abstract":"The main technology of traditional information security is firewall, intrusion detection and anti-virus software, which is used in the first anti-outer defence, the first anti-service terminal defence terminal passive defence ideas, the complexity and complexity of these security technologies not only increase the complexity of the autonomous system, reduce the efficiency of the system, but also cannot solve the security problem of the information system, and cannot satisfy the security demand of the information system. After a significant stretch of innovative work, individuals utilize the secret word innovation, network security innovation, set forward the idea “confided in figuring” in view of the equipment security module support, Trusted processing from changing the customary protection thoughts, center around the safety efforts taken from the terminal to forestall framework assaults, from the foundation of the stage, the acknowledgment of the security of data frameworks. Believed figuring is chiefly worried about the security of the framework terminal, utilizing a progression of safety efforts to ensure the protection of clients to work on the security of independent frameworks. Its principle plan thought is implanted in a typical machine to oppose altering the equipment gadget - confided in stage module as the base of the trust, the utilization of equipment and programming innovation to join the trust of the base of trust through the trust bind level to the entire independent framework, joined with the security of information stockpiling insurance, client validation and stage respectability of the three significant safety efforts guarantee that the terminal framework security and unwavering quality, to guarantee that the terminal framework is consistently in a condition of conduct anticipated.","PeriodicalId":190895,"journal":{"name":"2021 2nd International Conference on Communication, Computing and Industry 4.0 (C2I4)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127546598","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: 3

Implementation of An Energy-Efficient Binary Square Rooter Using Reversible Logic By Applying The Non-Restoring Algorithm 利用可逆逻辑实现节能二进制平方根的非还原算法

2021 2nd International Conference on Communication, Computing and Industry 4.0 (C2I4) Pub Date : 2021-12-16 DOI: 10.1109/C2I454156.2021.9689438

S. Swathi, S. Sushma, V. Bindusree, L. Babitha, G. Sukesh, S. Venkateswarlu, V. Vijay, Rajeev Ratna Vallabhuni

{"title":"Implementation of An Energy-Efficient Binary Square Rooter Using Reversible Logic By Applying The Non-Restoring Algorithm","authors":"S. Swathi, S. Sushma, V. Bindusree, L. Babitha, G. Sukesh, S. Venkateswarlu, V. Vijay, Rajeev Ratna Vallabhuni","doi":"10.1109/C2I454156.2021.9689438","DOIUrl":"https://doi.org/10.1109/C2I454156.2021.9689438","url":null,"abstract":"Calculation of square root will be an essential mathematical operation that will have broad applications. In Hardware, the square root will be designed in order to gain power which will be quite low. Similarly, there are also other advantages that comes with gaining of low power that is high speed and also low area. A trade-off will also occur with the three metrics which is quite natural. As we know that the present technology is very advanced so it will aim for low power and architectural modification will be required by the relative designs. This sheet represents an energy efficient square rooter by using reversible logic. (RCSM) Reversible Controlled Subtract Multiplexer will be designing and it also plays an important part in implementing the binary square rooter. Saimur Rahman Gate will also be implementing the binary square rooter in order to improve and develop it. The Improvements such as cost of the quanta, inputs given by constants and also garbage outputs. The approaches such as conventional approach and SRG are used for designing the binary square rooter and it will be completed using non-restoring algorithm. Xilinx Software will be responsible for carrying out simulations and Synopsys Design Compiler will be the factor for obtaining power. The gate count which has been 75 will be decreased to 35. There will be an improvement of 20% in terms of power which will be obtained in this paper.","PeriodicalId":190895,"journal":{"name":"2021 2nd International Conference on Communication, Computing and Industry 4.0 (C2I4)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122444321","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

Piezoelectric Energy Harvesting for Wearables 可穿戴设备的压电能量收集

2021 2nd International Conference on Communication, Computing and Industry 4.0 (C2I4) Pub Date : 2021-12-16 DOI: 10.1109/C2I454156.2021.9689417

Shilpa D R, Rajith Kumar B. K, Apoorva Raghunandan

引用次数: 0

Effect of Feature selection on the performance of Liver Tumor classification using Neural Networks 特征选择对神经网络肝脏肿瘤分类性能的影响

2021 2nd International Conference on Communication, Computing and Industry 4.0 (C2I4) Pub Date : 2021-12-16 DOI: 10.1109/C2I454156.2021.9689266

Munipraveena Rela, Nagaraja Rao Suryakari, P. Reddy

引用次数: 1