Kishore Babu S.,ALIET |
Vasavi S.,VRSEC |
Nagarjuna K.,II M.Tech
Proceedings - 7th IEEE International Advanced Computing Conference, IACC 2017 | Year: 2017
Cloud computing offers service delivery models that facilitate users during development, execution and deployment of workflows. In this Big-data era, Organizations require value out of big data. For this they need not have to deploy complex infrastructure, but can use services that provide value. As such there is a need for a flexible and scalable service called Predictive Analytics as a Service (PAaaS). Predictive analytics can forecast trends, determines statistical probabilities and to act upon fraud and security threats for big data applications such as business trading, fraud detection, crime investigation, banking, insurance, enterprise security, government, healthcare, e-commerce, and telecommunications Prediction algorithms can be supervised or unsupervised with different configurations, and the optimal one may be different for each kind of data. This paper summarizes existing service frameworks for big data and proposes PAaaS framework that can be used by business to deal with prediction in big data. This proposed framework is based upon ensemble model that uses best out of prediction algorithms such as Artificial Neural Networks (ANN), Auto Regression algorithm(ARX) and Gaussian process(GP). © 2017 IEEE.
Rakesh Y.,SRKIT |
Sri Rama Krishna K.,VRSEC
Advances in Intelligent Systems and Computing | Year: 2018
In the field of Computer vision, dependable assessment of visual saliency permits suitable processing of pictures deprived of earlier learning of their substance, and therefore sustains as an imperative stride in numerous errands including segmentation, object identification, and Compression. In this paper, we present a novel saliency recognition model for 3D pictures in view of highlight difference from luminance, color, surface texture, and depth. Difference of the stereo pair is extricated utilizing sliding window strategy. Then we present a contrast based saliency identification method that assesses global contrast divergences and spatial lucidness at the same time. This calculation is straightforward, proficient, and produces full determination saliency maps by combination of the considerable number of elements removed. Our calculation reliably performed better than existing saliency discovery strategies, yielding higher accuracy. We likewise show how the extricated saliency guide can be utilized to make top notch division covers for ensuing picture handling. © Springer Nature Singapore Pte Ltd. 2018.
Koppati N.,VRSEC |
Pavani K.,VRSEC |
Sharma D.,VRSEC |
AIP Conference Proceedings | Year: 2017
MIMO means multiple inputs multiple outputs. As it refers MIMO is a RF technology used in many new technologies these days to increase link capacity and spectral efficiency. MIMO is used in Wi-Fi, LTE, 4G, 5G and other wireless technologies. This paper describes the earlier history of MIMO-OFDM and the antenna beam forming development in MIMO and types of MIMO. Also this treatise describes several decoding algorithms. The MIMO combined with OFDM increases the channel capacity. But the main problem is in estimating the transmitted signal from the received signal. So the channel knowledge is to be known in estimating the channel capacity. The advancement in MIMO-OFDM is Massive MIMO which is beneficial in providing additional data capacity in the increased traffic environment is described. In this memoir various application scenarios of LS-MIMO which increases the capacity are discussed. © 2017 Author(s).
Sridevi K.,Gandhi Institute of Technology and Management |
International Conference on Electrical, Electronics, Signals, Communication and Optimization, EESCO 2015 | Year: 2015
This paper focuses on comparison of Particle Swarm Optimization (PSO) and Genetic Algorithms (GA) that are applied to obtain beam forming of an adaptive Uniform Circular Array (UCA). UCA geometry is targeted because of its symmetry in configuration which enables the adaptive array to scan azimuthally with minimum changes in its beam width and side lobe levels. PSO and GA are used to calculate the complex weights of the antenna elements in order to adapt the antenna to the changing environment. Comparisons are made in the context of performance of PSO and GA algorithms.PSO is less complex and has a very fast convergence over GA. The Particle Swarm Optimizer shares the ability of GA to handle arbitrary cost functions but with much simple implementation it clearly demonstrates better possibilities for its wide use in electromagnetic optimization. © 2015 IEEE.
Padmavathi K.,GRIET |
Sri Ramakrishna K.,VRSEC
International Journal of Electrical and Computer Engineering | Year: 2015
Atrial fibrillation (AF) is the common arrhythmia that causes death in the adults. We measured AR coefficients using Burgs method for each 15 second segment of ECG. These features are classified using the different statistical classifiers: kernel SVM and KNN classifier. The performance of the algorithm was evaluated on signals from MIT-BIH Atrial Fibrillation Database. The effect of AR model order and data length was tested on the classification results. This method shows better results can be used for practical use in the clinics. Copyright © 2015 Institute of Advanced Engineering and Science. All rights reserved.
Padmavathi K.,GRIET |
International Journal of Systems, Control and Communications | Year: 2015
Atrial fibrillation (AF) is a type of heart ailment that occurs when atria beats quicker than normal to move blood from atria to the ventricles. Our present study proposes a technique to detect AF ECG patterns with the use of continuous wavelet transform (CWT), wavelet coherence (WTC) is presented. The wavelet coherence function finds common frequencies between two signals and evaluates similarity of the two signals. The mother wavelet used is db4. The ECG variation of atrial fibrillation (AF) is observed in lead II of ECG. For the detection of normal and AF beats, WTC output values are given as the input features for the Levenberg-Marquardt neural network (LMNN) classifier. The data was collected from MIT/BIH AF database. Copyright © 2015 Inderscience Enterprises Ltd.
Kora P.,GRIET |
Sri Ramakrishna K.,VRSEC
ARPN Journal of Engineering and Applied Sciences | Year: 2015
This paper conveys a technique for the detection of Bundle Branch Block (BBB) ECG patterns using Magnitude Squared Coherence (MSC) function. The MSC function finds common frequencies between two signals and evaluate the similarity of the two signals. The ECG variation in BBB can observed through the changes in the ECG signal. MSC technique uses Welch method for calculating t h e PSD. For the detection of Normal and BBB beats, MSC output values are given as the input features for the LMNN classifier. Overall accuracy of LMNN classifier is 98.5 percent. The data was collected from MIT/BIH arrhythmia database. © 2006-2015 Asian Research Publishing Network (ARPN).
Kora P.,GRIET |
Sri Rama Krishna K.,VRSEC
Smart Innovation, Systems and Technologies | Year: 2016
Abnormal Cardiac beat identification is a key process in the detection of heart ailments. This work proposes a technique for the detection of Bundle Branch Block (BBB) using Bat Algorithm (BA) technique in combination with Levenberg Marquardt Neural Network (LMNN) classifier. BBB is developed when there is a block along the electrical impulses travel to make heart to beat. The Bat algorithm can be effectively used to find changes in the ECG by identifying best features (optimized features). For the detection of normal and Bundle block beats, these Bat feature values are given as the input for the LMNN classifier. © Springer International Publishing Switzerland 2016.
Prasad R.S.,Acharya Nagarjuna University |
2014 International Conference on Circuits, Power and Computing Technologies, ICCPCT 2014 | Year: 2014
To assess the software reliability by statistical means yields efficient results. In this paper, for an effective monitoring of failure process we have opted Sequential Probability Ratio Test (SPRT) over the time between every rth failure (r is a natural number >=2) instead of inter-failure times. This paper projects a controlling framework based on order statistics of the cumulative quantity between observations of time domain failure data using mean value function of Inflection S-Shaped Model. The two unknown parameters can be estimated using the Maximum Likelihood Estimation (MLE). © 2014 IEEE.
Manne S.,VRSEC |
Kotha S.K.,VRSEC |
Sameen Fatima S.,Osmania University
Advances in Intelligent and Soft Computing | Year: 2012
World Wide Web is the store house of abundant information available in various electronic forms. In the past two decades, the increase in the performance of computers in handling large quantity of text data led researchers to focus on reliable and optimal retrieval of information already exist in the huge resources. Though the existing search engines, answering machines has succeeded in retrieving the data relative to the user query, the relevancy of the text data is not appreciable of the huge set. It is hence binding the range of resultant text data for a given user query with appreciable ranking to each document stand as a major challenge. In this paper, we propose a Query based k-Nearest Neighbor method to access relevant documents for a given query finding the most appropriate boundary to related documents available on web and rank the document on the basis of query rather than customary Content based classification. The experimental results will elucidate the categorization with reference to closeness of the given query to the document. © 2012 Springer-Verlag GmbH Berlin Heidelberg.