Shri Vishnu Engineering College for Women

Bhīmavaram, India

Shri Vishnu Engineering College for Women

Bhīmavaram, India
SEARCH FILTERS
Time filter
Source Type

Adinarayana S.,Shri Vishnu Engineering College for Women | Ilavarasan E.,Pondicherry Engineering College
International Conference on Signal Processing, Communication, Power and Embedded System, SCOPES 2016 - Proceedings | Year: 2017

The Sentiment discovery from data sources of social media is a challenging task. Since the data is available not only in the structured format but also exists in un structured and semi structured as users are expressing freely their opinions in their desired style. Opinion mining is an important research area for many domains. It has most feasible approaches for business Intelligance. In this review paper, we tried to summarize all the theoretical and practical aspects for efficient implementation of opinion classification for Sentiment discovery. © 2016 IEEE.


Sree P.K.,Shri Vishnu Engineering College for Women | Usha Devi N.,Jawaharlal Nehru Technological University Kakinada
2015 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2015 | Year: 2015

Nowadays predicting the weather is the most vital problem in the recent centaury. It is very difficult to predict the temperature variations, wind speed and amount of rainfall at any given location. In this research we propose a dynamic real time weather prediction system with non uniform cellular automata that use eight neighborhood to predict the normal and abnormal climatic variations. This prediction method is based on dynamic NUH-MAR based climatologically methods, united with discovery of knowledge. This research work is mostly helpful to the farmers and guides the disasters management department to take remedial actions in case of drought. We have used OGD and IMD datasets pertaining to East Godavari, West Godavari and Krishna districts where majority of the people dependent on cultivation. Extensive experimental results are performed to estimate the variations in temperature, speed of wind and amount of rainfall in these locations. We have compared our results with the standard and best techniques reported in the literature survey. The results shows the novelty and strength of our algorithm to predict temperature abnormalities with an accuracy of 92%, wind speed with 91.2% and amount of rainfall with 96%. © 2015 IEEE.


Raju D.N.,Shri Vishnu Engineering College for Women
2015 IEEE UP Section Conference on Electrical Computer and Electronics, UPCON 2015 | Year: 2015

Data Structure is considered as one of the fundamental research area in computer science. Sorting is a foremost issue in data structure which arranges the data in ascending or descending order. Though several sorting algorithms are available, it is necessary to select the best sorting algorithm depends on the situation. These sorting technique are frequently used in a large variety of important applications. This paper presents a new sorting technique, "Mean Sort" which has exclusively been developed to sort the number of elements and also makes the data analysis and data processing very easy by taking the advantage of a computed mean. Like merge sort or quick sort, this algorithm works by single a divide-and-conquer strategy to divide a single unsorted array into two smaller sub-arrays. It uses mean to divide and sort them and time complexity is O(n∗logn). This algorithm is described using C++. The proposed algorithm is analyzed using asymptotic analysis and also using machine-running time and compared with their basic sorting algorithms. © 2015 IEEE.


Pradeep M.,Shri Vishnu Engineering College for Women
Proceedings - 2013 IEEE International Multi Conference on Automation, Computing, Control, Communication and Compressed Sensing, iMac4s 2013 | Year: 2013

This paper represents a approach to implement image fusion algorithm ie LAPLACIAN PYRAMID. In this technique implements a pattern selective approach to image fusion. The basic idea is to perform a pyramid decomposition on each source image and finally reconstruct the fused image by performing an inverse pyramid transform. It offers benefits like resolution, S/N ratio and pixel size. The aim of image fusion, apart from reducing the amount of data, is to create new images that are more suitable for the purposes of human/machine perception, and for further image-processing tasks such as segmentation, object detection or target recognition in applications such as remote sensing and medical imaging Based on this technique finally it reconstructs the fused image from the fused pyramid. © 2013 IEEE.


Malladi S.,Shri Vishnu Engineering College for Women | Yadaiah N.,Jawaharlal Nehru Technological University
2015 International Conference on Industrial Instrumentation and Control, ICIC 2015 | Year: 2015

Proportional Derivative Integral (PID) controllers are extensively used in most of the industrial applications. But often, PID frame work fails to address some serious issues like susceptibility to noise, instability due to integral term etc. On the other hand Active Disturbance Rejection Control (ADRC) addresses these issues quite successfully. The problem considered in this work is to control Automatic Voltage Regulator (AVR) with Linear ADRC (LADRC) under presence of plant parameter uncertainties and sudden load variations.A fifth-order Extended State Observer (ESO) was designed which estimates generalized disturbance which includes both system uncertainties and external disturbances. This information is used to actively cancel the effects of disturbances. The effectiveness of LADRC scheme has been illustrated by comparing with conventional PID tuning method in the presence of plant parameter and sudden load variations. Further to study the frequency response characteristics of control system, transfer function of LADRC has been derived. From the simulations it can be observed that there is significant improvement in system response which can be reconfirmed from the frequency response analysis. © 2015 IEEE.


Kunapuli S.S.,Shri Vishnu Engineering College for Women
International Journal of Applied Engineering Research | Year: 2015

Transceivers based on a direct conversion architecture introduces an unwanted limited image rejection and degrades the accuracy of carrier estimation due to presence of I/Q imbalance. In this paper, we proposed an efficient scheme to compensate IQ imbalance in OFDM receivers. Simulation results confirmed that the proposed scheme performance is very close to the ideal case. © Research India Publications.


Malladi S.,Shri Vishnu Engineering College for Women | Yadaiah N.,Jawaharlal Nehru Technological University
Proceedings of the IEEE International Conference on Control Applications | Year: 2013

This paper proposes a co-ordinate tuning strategy for PID control parameters in achieving both the robustness and better transient characteristics. Modified Ziegler-Nichols, Bode-Integrals and Iso-damping are well known methods for tuning of PID parameters in meeting the desirable. In order to achieve the robustness to gain variations and better transient properties, a new control strategy known as co-ordinate control structure is derived by incorporating the important features of Iso-damping and Bode integral methods. In this process a weightage factor μ is obtained optimally by minimizing Integral Time Absolute Error through Genetic Algorithm (GA). The effectiveness of the proposed scheme has been illustrated with typical systems. © 2013 IEEE.


Kalluri N.V.S.N.,Shri Vishnu Engineering College for Women | Yarlagadda D.V.,Shri Vishnu Engineering College for Women
Proceedings - 6th International Advanced Computing Conference, IACC 2016 | Year: 2016

To solve heterogeneity and gauge problems cloud computing proffer abundance of services to users. Users without percipient how transcendent the service and without any cognizance of Quality of Service (QOS) of services in cloud computing, users use the services and feel perturb, unsatisfied. To avoid user ennui, dissatisfaction, soreness and annoy by using a service it is very important to induce and elucidate awareness of Quality of Service (QOS) of services to users before using the services in cloud. For any cloud service provider to accumulate profit, to cope with other service providers and to perpetuate in the business field successfully it is very much imperative to emolument customer satisfaction, so cloud service provider should ameliorate QOS of service to augment customer satisfaction. How cognizance of QOS of services is useful for users who use services in forthcoming and how improving QOS of service is useful for service providers in cloud is inaugurated and designed in this paper. Knowing about QOS for one service from one user feedback is agile but it is very striving and time conceiving to get awareness of QOS of all services in cloud computing by collecting feedback of users who already used the service, so in order to surmount this predicament clustering technique is used. One of the important task in data mining is clustering which is propitious for profuse users so by using clustering concept users who want to use service in future will dexterously and agilely can get awareness of QOS of services in cloud through Intutionistic Fuzzy C-means clustering algorithm. Multiple Abettors are used to comply and dispose this process so multi Abettor system is inaugurated to transact the work. K-means, Hard C-means and Fuzzy C-means clustering algorithms are not much efficacious, proficient, and conducive for clustering QOS values of services so in this paper for giving awareness of QOS of services in cloud Intutionistic Fuzzy C-means algorithm is used for clustering. As Intutionistic Fuzzy C-means algorithm clustering algorithm abides of both membership function and hesitation function the feedback of QOS of services not given by users who used services is also handled. In the inaugurated process while collecting QOS feedback of services in cloud from future users, security contention from extrinsic people may occur and this predicament is solved by corroboration method in this paper. By the concept prefaced in this paper users can analyze agilely which service is best to use among available services in cloud and feel happy, satisfied by using the best service. By analyzing the output obtained from clustering, service providers can improve their QOS of services by using Pandect technique as customer satisfaction is the primary thing for any service provider to sustain in business, to gain clover and lucre. In this paper the unexpurgated process Awareness of Quality of Service and Convalescent Quality of service of services in cloud is elucidated with help of architecture. © 2016 IEEE.


Peddapati S.,Shri Vishnu Engineering College for Women | Kruthiventi K.K.P.,Shri Vishnu Engineering College for Women
Proceedings - 6th International Advanced Computing Conference, IACC 2016 | Year: 2016

In this paper, multiple solution vector based random search algorithm is presented. The conventional random search method has single solution vector and has difficulties associated with local optima for higher-dimensional numeric problems, this paper introduces multiple solution vector in random search method solving optimization problems. The proposed algorithm is compared with evolutionary algorithm (EA) and particle swarm optimization (PSO) methods using standard test functions and the performance results are presented. © 2016 IEEE.


Purushothama Raju V.,Shri Vishnu Engineering College for Women | Saradhi Varma G.P.,k-Technology
Proceedings of 2014 IEEE International Conference on Advanced Communication, Control and Computing Technologies, ICACCCT 2014 | Year: 2015

Closed sequential pattern mining is an important data mining task because it produces more compact result set and it is more efficient than sequential pattern mining. In general closed sequential patterns are generated from large data sets by applying algorithms like CloSpan and BIDE which require more execution time to compute all the closed sequential patterns. By using genetic algorithms we can reduce the execution time. The advantage of using a genetic algorithm in finding the closed sequential patterns is that it performs global search and it has less time complexity compared to other algorithms.This paper proposes a novel genetic algorithm G-CSPM to find closed sequential patterns. To improve the performance, we develop an effective fitness function and a pruning method. Our algorithm is the first method that utilizes genetic approach for closed sequential pattern mining. The results indicate that the proposed algorithm G-CSPM outperforms CloSpan. © 2014 IEEE.

Loading Shri Vishnu Engineering College for Women collaborators
Loading Shri Vishnu Engineering College for Women collaborators