scispace - formally typeset
Search or ask a question
Author

G. K. Rajini

Bio: G. K. Rajini is an academic researcher from VIT University. The author has contributed to research in topics: Optical wireless communications & Wavelet transform. The author has an hindex of 2, co-authored 11 publications receiving 16 citations.

Papers
More filters
Journal ArticleDOI
TL;DR: Resilient Propagation algorithm has better prediction accuracy compared to other ANN algorithms for host CPU load prediction and evaluation of their performance compared to actual values.
Abstract: Background/Objectives: To evaluate the prediction accuracy of Neural Network algorithms for host CPU load prediction and evaluate their performance compared to actual values. Methods/Statistical Analysis: The speed of execution of job at the scheduled host is directly proportional to its CPU load. Therefore, target node load prediction plays an important role in job scheduling decisions. It is learnt that Neural Networks are capable of predicting the future values based on the training given on the past data. We designed a multilayer neural network and trained with learning algorithms for the input patterns collected from the load traces and predicted the future load statistics. The Mean and Standard Deviation of the predicted values are computed and analyzed against the Mean and Standard Deviation of actual values for all the ANN algorithms. Findings: We analyzed the prediction accuracy of Back Propagation, Quick Propagation, Back Propagation with Momentum and Resilient Propagation algorithm for the load traces collected from variety of computers connected in a network. Existing reports shows that Back Propagation algorithm exhibits better prediction accuracy compared to statistical approaches like linear regression and polynomial regression. In this paper, we have shown that Resilient Propagation algorithm has better prediction accuracy compared to other ANN algorithms. Application/Improvements: Job scheduling and resource selection algorithms can employ neural network algorithms to predict the load for the sharable resources connected in the network for more accurate and faster scheduling/resource selection decision.

9 citations

Journal ArticleDOI
TL;DR: The imaging modalities play a vital role in acquisition of signals and images from human body which involves invasive and non-invasive methods.
Abstract: Objective: Biomedical signal/image processing and the related imaging modalities is a very vast growing and upcoming field This paper presents the promising image processing techniques used in medical field Methods: Application of image processing techniques has played a vital role in assisting the surgeons and physicians in diagnosing the diseases and performing the surgeries for the patients Clinical medical devices has erupted through combination of hardware and image processing techniques which has a giant leap in medical field Results: Biomedical signals fetching, image formation, processing of image, and image display for medical/clinical diagnosis based on extracted features from the signal (1D), images (2D) and Video (3D) Image processing has proved its significance in medical analysis and health care Conclusion: The imaging modalities play a vital role in acquisition of signals and images from human body which involves invasive and non-invasive methods

9 citations

Book ChapterDOI
01 Jan 2018
TL;DR: A central control framework which utilizes a remote Bluetooth gadget and gives wireless access to smart phones is intended to control electrical gadgets all through the house with ease of installing it, ease of use, and cost-effective design and implementation.
Abstract: Smart home is a practical technique to build the simplicity of life. It can be utilized to give assistance and fulfill the necessities of the elderly and the handicapped at houses. Home automation framework will enhance the ordinary living status at houses. The aim of this paper is to implement a central control framework which utilizes a remote Bluetooth gadget and gives wireless access to smart phones. This framework is intended to control electrical gadgets all through the house with ease of installing it, ease of use, and cost-effective design and implementation.

4 citations

Journal ArticleDOI
TL;DR: A noninvasive technique which includes statistical features to determine and classify normal, benign, and malignant images are identified and created awareness about the breast cancer.
Abstract: Objective: To create awareness about the breast cancer which has become one of the most common diseases among women that leads to death if not recognized at early stage. Methods: The technique of acquiring breast image is called mammography and is a diagnostic and screening tool to detect cancer. A cascade algorithm based on these statistical parameters is implemented on these mammogram images to segregate normal, benign, and malignant diseases. R esults: Statistical features - such as mean, median, standard deviation, perimeter, and skewness - were extracted from mammogram images to describe their intensity and nature of distribution using ImageJ. C onclusion: A noninvasive technique which includes statistical features to determine and classify normal, benign, and malignant images are identified. Ke ywords: Breast cancer, Benign, Malignant , Mammogram image, ImageJ.

3 citations

Book ChapterDOI
01 Jan 2021
TL;DR: In this article, the modified Tustin discretization and Euler Discretization methods are implemented for current controller of the inverter and compared with each other with respect to total harmonic distortion (THD) of the current and voltage signal from the inverters.
Abstract: The Non-Conventional energy sources play a key role in present power markets to meet the electrical energy demand on the grid. These solar modules are connected to the grid through converters for converting the DC to AC power. The quality of the power from these inverters should be good and hence it is required to limit the harmonics from these inverters as much as possible. This can be done with the help of current controller of inverter which controls the quality of the current supplied by the PV Inverter to the grid. One of the most commonly used current controllers is the PI controller. But due to presence of dynamics in the integral term, the PI control has steady-state error in following the sinusoidal reference. Another commonly used current controller is the Proportional Resonant (PR) controller. As most of the controllers are of digital type, the resonant controllers has zero and pole mapping during the conversion of continuous to discrete time domain and hence it is employed in discrete mode. In this work, the modified Tustin discretization and Euler discretization methods are implemented for current controller of the inverter and compared with each other with respect to total harmonic distortion (THD) of the current and voltage signal from the inverter. This work is designed and implemented in MATLAB/Simulink tool.

2 citations


Cited by
More filters
Journal ArticleDOI
01 Jan 2021
TL;DR: Artificial neural networks outperform other machine-learning algorithms in evaluation metrics such as the recall and the F1 score and it is found that prior academic achievement, socioeconomic conditions, and high school characteristics are important predictors of students’ academic performance in higher education.
Abstract: The applications of artificial intelligence in education have increased in recent years. However, further conceptual and methodological understanding is needed to advance the systematic implementation of these approaches. The first objective of this study is to test a systematic procedure for implementing artificial neural networks to predict academic performance in higher education. The second objective is to analyze the importance of several well-known predictors of academic performance in higher education. The sample included 162,030 students of both genders from private and public universities in Colombia. The findings suggest that it is possible to systematically implement artificial neural networks to classify students’ academic performance as either high (accuracy of 82%) or low (accuracy of 71%). Artificial neural networks outperform other machine-learning algorithms in evaluation metrics such as the recall and the F1 score. Furthermore, it is found that prior academic achievement, socioeconomic conditions, and high school characteristics are important predictors of students’ academic performance in higher education. Finally, this study discusses recommendations for implementing artificial neural networks and several considerations for the analysis of academic performance in higher education.

28 citations

Journal ArticleDOI
TL;DR: The authors propose the adaptive forecasting model and corresponding adaptive forecasting methods to apply in the management system of a cloud data center for workload forecasting, ensuring compliance with the service level agreement and power consumption decrease.
Abstract: Forecasting on different levels of the management system of a cloud data center has received increased attention due to its significant impact on the cloud services quality. Making accurate forecasts, however, is challenging due to the non-stationary workload and intrinsic complexity of the management system of a cloud data center. It is possible to prevent excessive resource allocation and service level agreement violations through workload forecasting for virtual machines and containers. In this paper, the authors propose the adaptive forecasting model and corresponding adaptive forecasting methods to apply in the management system of a cloud data center for workload forecasting, ensuring compliance with the service level agreement and power consumption decrease. The authors consider six alternative forecasting methods and 77 training data windows on each management step to determine the best combination of methods and the training set size that generates a most accurate forecast, thereby adapting to the current state of the physical or virtual server in a cloud data center. Through the comprehensive analysis, the authors also evaluate the proposed adaptive forecasting methods using real-world workload traces Bitbrains and demonstrate that combined forecasting methods outperform the individual forecasting methods significantly in terms of forecasting accuracy measured by Mean Absolute Percentage Error.

19 citations

Book ChapterDOI
27 Mar 2019
TL;DR: The implementation of an automatic resource feeding system for vehicle washing using low cost devices, consisting of an Arduino Mega controller, ultrasonic sensors to measure the level of liquids, several actuators, Bluetooth communication devices and a mobile application is presented.
Abstract: Vehicle washing is a profitable business today, but it produces unwanted environmental effects that should be considered; autonomous systems are a viable solution for the optimization of resources in production processes and services. This paper presents the implementation of an automatic resource feeding system for vehicle washing using low cost devices. The system consists of an Arduino Mega controller, ultrasonic sensors to measure the level of liquids, several actuators, Bluetooth communication devices and a mobile application. The results present the consumption of resources in a month of operation, demonstrating the benefits of this proposal.

10 citations

Proceedings ArticleDOI
19 Mar 2020
TL;DR: The main objective of this survey paper is to compare the multiple algorithms used for facial recognition.
Abstract: Facial Recognition System is a computer technology that uses a variety of algorithms that identify the human face in digital images, identify the person and then verify the captured images by comparing them with the facial images stored in the database. Facial recognition is an important topic in computer vision, and many researchers have studied this topic in many different ways; it is important especially in some applications such as surveillance systems. The main objective of this survey paper is to compare the multiple algorithms used for facial recognition.

8 citations

Journal ArticleDOI
TL;DR: In this article , a digital IIR filter-based Proportional-Resonant (PR) current controller is proposed to cancel harmonics while achieving high gain at the resonant frequency (grid frequency).
Abstract: This study proposes a novel technique of cooperative control for a distributed hybrid DC/AC Microgrid (MG) by designing a digital Infinite Impulse Response (IIR) filter-based Proportional-Resonant (PR) current controller. This controller adopts an Adaptive Neuro Fuzzy Inference System (ANFIS) trained by Particle Swarm Optimization (PSO) to control inverter output current while tracking Maximum Power Point (MPP). A hybrid ANFIS-PSO extracts maximum power from both inverter and boost converter-based solar Photovoltaics (PVs) systems quickly and with zero oscillation tracking. The proposed PR controller cancels harmonics while achieving high gain at the resonant frequency (grid frequency). The PR controller offers quick reference signal tracking, grid frequency drift adaptation, easy system design, and no steady-state error. Moreover, this investigation features a PR controller frequency-domain analysis. The proposed technique smooths voltage and improves steady-state and transient responses. Cooperative control is implemented on an IEEE 14-bus MG with distributed communication. The findings indicate that the proposed control technique can regulate MG voltage to obtain a more stable voltage profile. The adopted MG, made up of dispersed resources, is crucial for assessing power flow and quality indicators in a smart power grid. Finally, numerical simulation results are utilized to verify the recommended technique.

7 citations