Identification of COVID-19 spreaders using 5-Layer Multiple network Approach
Authors: Jafar Ali Ibrahim, T Sravani, G Chaitanya Sai, V Sandhya Rani, R Rakesh, N Sai Sri Harsha
Abstract
Since the onset of COVID-19, radiographic image analysis coupled with artificial intelligence (AI) has become popular due to insufficient RT-PCR test kits. In this paper, an automated AI- assisted COVID-19 diagnosis scheme is proposed utilizing the ensembling approach of multiple convolutional neural networks (CNNs). Two different strategies have been carried out for ensembling: A feature level fusionbasedensembling method and a decision level ensembling method. Several traditional CNN architectures are tested and finally in the ensembling operation, MobileNet, InceptionV3, DenseNet201, DenseNet121 and Xception are used. To handle the computational complexity of multiple networks, transfer learning strategy is incorporated through ImageNet pre-trained weight initialization. For feature-level ensembling scheme, global averages of the convolutional feature maps generated from multiple networks are aggregated and undergo through fully connected layers for combined optimization. Additionally, for decision level ensembling scheme, final prediction generated from multiple networks are converged into a single prediction by utilizing the maximum voting criterion. Both strategies perform better than any individual network. Outstanding performances have been achieved through extensive experimentation on a public database with 96% accuracy on 3-class (COVID- 19/normal/pneumonia) diagnosis and 89.21% on 4- class (COVID-19/normal/viral pneumonia/bacterial pneumonia)diagnosis.
DESIGN OF THERMO ELECTRIC GENERATOR FOR LED STREET LIGHT APPLICATIONS
Authors: Ch Kiran Kumar, S. Supriya, N. Srikanth, T. Viswa Teja, M Reshma, V. Sai Manaswini
Abstract
Generating electricity in present there is a shortage of fossil fuel, oil, gas, etc. burning of these fuels causes environmental problem like radio activity pollution, global warming etc. These (coal, oil, gas) are the limiting resources hence the new technology is needed for electricity generation, by using thermoelectric generators to generate power is environmental free and several advantages in production. This paper gives the thermoelectric energy harvesting devices are used for waste heat harvesting in microscale applications. This chapter presents an overview of the fundamental principles of thermoelectric energy harvesting and their low-power applications. Thermoelectric power generator convert direct waste heat into generate electricity. Thermoelectric power generation offer a potential application in the direct exchange of waste- heat energy into electrical power where it is unnecessary to believe the cost of the thermal energy input .This method will have an maximum outcome. The application of this option green technology in converting waste-heat energy directly into electrical power can too improve the overall efficiencies of energy conversion systems.
Hazard Identification Using Machine Learning Approach
Authors: K .SANTHI RANI, G.RACHEL NIREEKSHITHA, L. DEEPIKA, Y. NIKHITHA, K.LAVANYA
Abstract
Internet surfing has become a crucial piece of our everyday life. So to grab the eye of the clients’ diverse program merchants contend to set up the new usefulness and progressed highlights that become the wellspring of assaults for the gatecrasher and the sites are put at danger. Be that as it may, the existing methodologies are not sufficient to secure the surfers which require an speedy and exact model that can have the option to recognize the begnign or malevolent pages. In this exploration article, we plan another order system to dissect and distinguish the pernicious pages utilizing AI classifiers for example, arbitrary timberland, support vector machine. innocent Bayes, calculated relapse and Some exceptional URL (Uniform Resource Locator) in light of removed highlights the classifiers are prepared to anticipate the malevolent site pages. The exploratory outcomes have shown that the presentation of the arbitrary woods classifier accomplishes better precision of 95% in correlation with other AI classifiers. Catchphrases pernicious page, AI, recognition, URL, pernicious sites.
SPEED CONTROL OF BLDC MOTOR USING ARDUINO & PWM TECHNIQUE
Authors: Dr.B.Venkata Prasanth, V.Venkata Swathi
Abstract
This work deals with the speed control of BLDC motor using Ardunio and PWM Technique. Brush less DC motor plays a vital role in all applications such as ling fans, pumps, automotive driver, robotic Automations etc., Now a days, lot of technologies are available In motor from controlling the speed of the motor as per the designed applications. In this regard, for control of speed in a BLDC motor application, using Ardunio Board with PWM Technique be used Speed Control of BLDC motor with various Techniques such as, using mobile applications,Blue 100th based BMS from mobile phone etc., But for those technologies. there are different mythologies and platforms. Due to there technologies the economic cost of the product will be increased and the poor people Can not be utilized further. For Society benifits, if the product cost will be reduced their utilization also improved.A product were designed to developed with low cost, user friendly, easy to handle etc with an advancetechnology for controlling of speed of BLDC motor.