VR Siddhartha Engineering College

Vijayawāda, India

VR Siddhartha Engineering College

Vijayawāda, India
SEARCH FILTERS
Time filter
Source Type

Kiran Kumar R.,Krishna University | Saichandana B.,Gandhi Institute of Technology and Management | Srinivas K.,VR Siddhartha Engineering College
Indonesian Journal of Electrical Engineering and Computer Science | Year: 2016

This paper presents genetic algorithm based band selection and classification on hyperspectral image data set. Hyperspectral remote sensors collect image data for a large number of narrow, adjacent spectral bands. Every pixel in hyperspectral image involves a continuous spectrum that is used to classify the objects with great detail and precision. In this paper, first filtering based on 2-D Empirical mode decomposition method is used to remove any noisy components in each band of the hyperspectral data. After filtering, band selection is done using genetic algorithm in-order to remove bands that convey less information. This dimensionality reduction minimizes many requirements such as storage space, computational load, communication bandwidth etc which is imposed on the unsupervised classification algorithms. Next image fusion is performed on the selected hyperspectral bands to selectively merge the maximum possible features from the selected images to form a single image. This fused image is classified using genetic algorithm. Three different indices, such as K-means Index (KMI) and Jm measure are used as objective functions. This method increases classification accuracy and performance of hyperspectral image than without dimensionality reduction. © 2016 Institute of Advanced Engineering and Science. All rights reserved.


Saichandana B.,Jawaharlal Nehru Technological University Kakinada | Srinivas K.,VR Siddhartha Engineering College | Kiran Kumar R.,Krishna University
Indonesian Journal of Electrical Engineering and Computer Science | Year: 2016

Hyper spectral remote sensors collect image data for a large number of narrow, adjacent spectral bands. Every pixel in hyperspectral image involves a continuous spectrum that is used to classify the objects with great detail and precision. This paper presents hyperspectral image classification mechanism using genetic algorithm with empirical mode decomposition and image fusion used in preprocessing stage. 2-D Empirical mode decomposition method is used to remove any noisy components in each band of the hyperspectral data. After filtering, image fusion is performed on the hyperspectral bands to selectively merge the maximum possible features from the source images to form a single image. This fused image is classified using genetic algorithm. Different indices, such as K-means (KMI), Davies-Bouldin Index (DBI), and Xie-Beni Index (XBI) are used as objective functions. This method increases classification accuracy of hyperspectral image. © 2016 Institute of Advanced Engineering and Science. All rights reserved.


Ravi Kumar P.,PVP Siddhartha Institute of Technology | Mohana Rao K.,VR Siddhartha Engineering College
Materials Today: Proceedings | Year: 2017

Functionally Graded materials have been widely used in engineering applications due to the advantage of smooth and continuous variation in material properties, better fatigue life, less stress concentration, lower thermal stresses and attenuation of stress waves. By intelligently designing material constitutions and gradient distributions of FGMs, structures made of them can have excellent dynamic and thermodynamic characteristics. In the present study Flapwise vibration of rotating functionally graded beam is studied. The effective material properties are determined using Mori Tanaka Method. The natural frequencies are obtained using differential transform method (DTM). The effect of rotating speed, gradient index and hub radius on natural frequency are discussed. © 2017 Elsevier Ltd. All rights reserved.


Vasavi S.,VR Siddhartha Engineering College | Prabhakar Benny S.,Kakatiya University
Advances in Intelligent Systems and Computing | Year: 2018

Social media such as twitter, Facebook are the sources for Stream data. They generate unstructured formal text on various topics containing, emotions expressed on persons, organizations, locations, movies etc. Characteristics of such stream data are velocity, volume, incomplete, often incorrect, cryptic and noisy. Hadoop framework is proposed in our earlier work for recognising and resolving entities within semi structured data such as e-catalogs. This paper extends the framework for recognising and resolving entities from unstructured data such as tweets. Such a system can be used in data integration, de-duplication, detecting events, sentiment analysis. The proposed framework will recognize pre-defined entities from streams using Natural Language Processing (NLP) for extracting local context features and uses Map Reduce for entity resolution. Test results proved that the proposed entity recognition system could identify predefined entities such as location, organization and person entities with an accuracy of 72%. © Springer Nature Singapore Pte Ltd. 2018.


Krishna C.N.,VR Siddhartha Engineering College | Suneetha M.,VR Siddhartha Engineering College
International Conference on Signal Processing, Communication, Power and Embedded System, SCOPES 2016 - Proceedings | Year: 2017

A new era of Business Intelligence Applications has started in-order to solve the problems of Relational Database Management System (RDBMS). If the data is coming from different sources, the data couldn't be sent to any one of the target RDBMS. To overcome this problem BI Apps evolved, i.e. applying ETL (Extraction Transformation and Loading) on different schemas, flat files and many other sources the data need to be transformed into target area. Then the tasks (mappings) were developed and scheduled, the data need to be monitored in-order to load into target area. Finally the data is represented using pictorial representations on the dashboard pages. These dashboard pages consists of statistical representations like pie, pivot, horizontal, vertical bars so that the growth of business can be evaluated by the CEO's. © 2016 IEEE.


Rao B.S.,VR Siddhartha Engineering College
International Journal of Power and Energy Conversion | Year: 2017

This paper presents the application of adaptive clonal selection algorithm to solve single and multi-objective optimal power flow (OPF) problems with the incorporation of wind energy conversion systems. As the wind power is intermittent in nature it requires an appropriate tool for OPF problem. Minimisation of generation cost of thermal as well as wind units, transmission loss and voltage stability index are considered as three conflicting objectives for optimisation. A fast elitist non-dominated sorting and crowding distance techniques have been used to find and manage the Pareto optimal front. Further, a fuzzy-based mechanism has been applied to select a best compromise solution from the Pareto set. The proposed method has been tested on standard IEEE 30-bus test system having three conventional and three wind power generators. The simulation results are compared with three other standard algorithms such as non-dominated sorting genetic algorithm-II, multi-objective particle swarm optimisation and multi-objective differential evolution. Copyright © 2017 Inderscience Enterprises Ltd.


Srinivasa Rao B.,VR Siddhartha Engineering College | Vaisakh K.,Andhra University
International Journal of Electrical Power and Energy Systems | Year: 2013

This paper presents a new multi objective optimization approach based on Adaptive Clonal Selection Algorithm (ACSA) to solve complex Environmental/ Economic Dispatch (EED) problem of thermal generators in power system. The proposed methodology also incorporates the power demand equality constraint and ensures various operating constraint limits while solving EED problem. In this algorithm an adaptive Clonal selection principle with non-dominated sorting technique and crowding distance has been used to find and manage Pareto-optimal set. Clonal selection principle is one of the models used to incorporate the behavior of the artificial immune system. The biological principles of clone generation, proliferation and maturation are mimicked and incorporated into this algorithm. To show the effectiveness of the proposed Multi Objective Adaptive Clonal Selection Algorithm (MOACSA) in solving EED problem two types of test systems have been considered with various objectives. These includes an IEEE 30-bus 6 unit test system and an 82-bus 10 unit Indian utility real life power system network for solving EED problem without and with load uncertainty. Simulation results are compared by implementation of three other standard algorithms such as Non-dominated Sorting Genetic Algorithm-II (NSGA-II), Multi-Objective Particle Swarm Optimization (MOPSO) and Multi-Objective Differential Evaluation (MODE) methods. © 2013 Elsevier Ltd. All rights reserved.


Raj V.N.P.,VR Siddhartha Engineering College | Venkateswarlu T.,Sri Venkateswara University
ICECT 2011 - 2011 3rd International Conference on Electronics Computer Technology | Year: 2011

The Electrocardiogram (ECG) is a technique of recording bioelectric currents generated by the heart which will help clinicians to evaluate the conditions of a patient's heart. So it is very important to get the parameters of ECG signal clear without noise. Many of the wavelet based denoising algorithms use DWT (Discrete Wavelet Transform) in the decomposition stage which is suffering from shift variance. To overcome this in this paper we are proposing the denoising method which uses Undecimated Wavelet Transform to decompose the raw ECG signal and we performed the shrinkage operation to eliminate the noise from the noisy signal. In the shrinkage step we used semi-soft and stein thresholding operators along with traditional hard and soft thresholding operators and verified the suitability of different wavelet families for the denoising of ECG signals. The results proved that the denoised signal using UDWT (Undecimated Discrete Wavelet Transform) have a better balance between smoothness and accuracy than the DWT. © 2011 IEEE.


Ramanaiah K.,VR Siddhartha Engineering College | Ratna Prasad A.V.,VR Siddhartha Engineering College | Hema Chandra Reddy K.,Jawaharlal Nehru Technological University Anantapur
Materials and Design | Year: 2013

The objective of present work is to introduce sansevieria natural fiber as reinforcement in the preparation of partially biodegradable green composites. The effect of fiber content on mechanical properties of composite was investigated and found that tensile strength and impact strength at maximum fiber content were 2.55 and 4.2 times to that of pure resin, respectively. Transverse thermal conductivity of unidirectional composites was investigated experimentally by a guarded heat flow meter method. The thermal conductivity of composite decreased with increase in fiber content and the quite opposite trend was observed with respect to temperature. In addition, the experimental results of thermal conductivity at different volume fractions were compared with theoretical model. The response of specific heat capacity of the composite with temperature as measured by differential scanning calorimeter was discussed. Lowest thermal diffusivity of composite was observed at 90°C and its value is 0.9948E-07m2s-1.Fire behavior of composite was studied using the oxygen consumption cone calorimeter technique. The addition of sansevieria fiber has effectively reduced the heat release rate (HRR) and peak heat release rate (PHRR) of the matrix by 10.4%, and 25.7%, respectively. But the composite ignite earlier, release more amount of carbon dioxide yield and total smoke during combustion, when compared to neat polyester resin. © 2013 Elsevier Ltd.


Ramanaiah K.,VR Siddhartha Engineering College | Ratna Prasad A.V.,VR Siddhartha Engineering College | Hema Chandra Reddy K.,Jawaharlal Nehru Technological University Anantapur
Materials and Design | Year: 2012

The main focus of this study is to utilize waste grass broom natural fibers as reinforcement and polyester resin as matrix for making partially biodegradable green composites. Thermal conductivity, specific heat capacity and thermal diffusivity of composites were investigated as a function of fiber content and temperature. The waste grass broom fiber has a tensile strength of 297.58MPa, modulus of 18.28GPa, and an effective density of 864kg/m3. The volume fraction of fibers in the composites was varied from 0.163 to 0.358. Thermal conductivity of unidirectional composites was investigated experimentally by a guarded heat flow meter method. The results show that the thermal conductivity of composite decreased with increase in fiber content and the quite opposite trend was observed with respect to temperature. Moreover, the experimental results of thermal conductivity at different volume fractions were compared with two theoretical models. The specific heat capacity of the composite as measured by differential scanning calorimeter showed similar trend as that of the thermal conductivity. The variation in thermal diffusivity with respect to volume fraction of fiber and temperature was not so significant. The tensile strength and tensile modulus of the composites showed a maximum improvement of 222% and 173%, respectively over pure matrix. The work of fracture of the composites with maximum volume fraction of fibers was found to be 296Jm-1. © 2012 Elsevier Ltd.

Loading VR Siddhartha Engineering College collaborators
Loading VR Siddhartha Engineering College collaborators