Search

Automatic voltage regulator (AVR) systems plays a vital role in power system. AVR system is normally used to maintain uniform power supply from generating station. This paper introduced a robust Adaptive Neuro Fuzzy Inference System (ANFIS) controller AVR system. ANFIS consists of both neural network and fuzzy system so ANFIS structure has advantages of both neural network and fuzzy system. Fuzzy rules are designed using neural network to get robust and optimized performance from AVR system. We compared the result of ANFIS controller with PID controller for two cases (i) without considering any noise and (ii) considering noise. The robust ANFIS controller outperforms PID controller for AVR system. [ABSTRACT FROM AUTHOR]

A splice joint is a process of combining two sections from end to end. The splice joint is used when the material is not available at the required length. It is a different procedure from the other joints used such as butt joints and scarf joints. Splice joints are far better than the unenforced butt and other joints. Splice joints in the aircraft fuselage helps to resist different internal and external loads when the aircraft is in motion or at rest. Here we compared the splice joints of two Aluminium alloys with different stringers (Z, C, Land omega) by doing the static and dynamic analysis using ANSYS software the optimum design and material is discussed for a fuselage. [ABSTRACT FROM AUTHOR]

Because of the worldwide ongoing situation triggered by the Coronavirus (COVID-19) pandemic, millions of people lost their lives and the economic disturbances, globally billions of people have been directly or indirectly affected. In order to prevent deaths, it is of utmost importance to determine anticipated infected cases and the spread rate of the virus for advance planning to eliminate fatalities in healthcare. Even though vaccination started over the globe, different people had a different perception regarding the vaccination, so preferable solution to fight against it is, by following precautions and by creating awareness about Coronavirus,. In rural areas and even in urban areas there is a lot of panic situations among people, to overcome panic situations, we proposed a model that uses the ARIMA model to forecast nCOVID-2019, and where we will show the death and recovery rate of nCOVID-2019 and also provided prevention and precaution tips to follow. We designed a user-friendly web interface that displays the recovery rate and death rate ratio and can help us to free ourselves from the panic situation. The aim of this paper is to evaluate time series relevant data for the top ten COVID-19 significantly impacted nations to forecast the spread of the epidemic. [ABSTRACT FROM AUTHOR]

India yields many varieties of crops. Among them tomato crop is the vital staple in Indian market. Many farmers produce tomato crop cross India. Many types of diseases will affect the crop due to many reasons. So, it is important to prevent the crop from being affected by those diseases and also curing the affected portion with suitable techniques. Our model is to predict the tomato leaf's health and also identify type of the disease it is affected with. The proposed model targets to reduce the amount of chemical fertilized used without having proper knowledge of the disease affected. Also help the cultivator to grow the tomato plants properly. This model is developed using Deep Convolutional Neural Network (CNN) model called TOMLeNet and Adam optimizer is used to predict the disease in the early stage and to avoid loss to the farmer. Neural network models make use of automatic feature extraction for the classification of the input image into their respective disease classes. The proposed model uses the tomato leaf disease data set publicly available in Kaggle and model generated an average accuracy of 97.42% using the features provide and even in unfavorable conditions. [ABSTRACT FROM AUTHOR]

The proportion of students desire to pursue higher education abroad, especially in United States, is growing every year and they find it hard to looking for the right universities. And therefore, this paper helps in determining the eligibility of Indian student to be admitted to universities based on their test characteristics, such as CGPA, TOEFL, Research papers published predicting the output which helps them to find the possibility of admitting in universities based on their scores, for the PGScore dataset collected from Kaggle and the Logistic regression model out performed among all other model with an accuracy of 93.3%. [ABSTRACT FROM AUTHOR]

Reinforcement Learning (RL) technologies have demonstrated excellent resultsfor a multiple of areas, including such Atari sports, finance & self-driving vehicles. Fortunately, their black-box design complicates its usage, particularly in essential areas like healthcare. Scholars have reported various ways to interpret Reinforcement Learning systems to reduce this issue. A few of these techniques have been used in deep learning, whilst others are specifically developed with RL. This same main purpose of this paper is also to demonstrate and clarify the techniques of Reinforcement Learning interpretation, the measures used to define them, and how certain metrics were being used to consider the internal features of Reinforcement Learning models. [ABSTRACT FROM AUTHOR]

Data de-duplication would greatly reduce the overhead of cloud computing services for storage and transfer, and it has possible applications in this big data-driven environment. Current systems that de-duplication of data are typically designed either to tackle brute-force threats or increase the accessibility of quality and data, but not all situations. In the context of shortening redundant data disclosure in this publication, we tend to evaluate 3-tier cross-domain architecture, degree program suggest an accurate and confidentiality issues saving big data de-duplication in the cloud, we also tend not to be aware of any current theme that attains authority. Both confidentiality and data de-duplication is accomplished by EPCDD and brute-force attacks are countered. In general, we generally take accountability into evaluation for having greater safeguards of privacy than current schemes. We appear to show that, in terms of computing, interactions and warehousing expenses, EPCDD performs better competitive processes. The dynamic operation user may also perform detailed update, data leakage & restoring through this project. Upon accessing it, the file is sent to the local distributor to verify de-duplication when the document is not reproduced, then the file will be saved on the cloud, and the replica file will obtain evidence of copyright. Authentication process and cross-domain de-duplication of big data in the cloud can be accomplished by this method. In addition, that time complexity of the EPCDD replication search is indexed. [ABSTRACT FROM AUTHOR]