Vignan University

About: Vignan University is a education organization based out in Guntur, Andhra Pradesh, India. It is known for research contribution in the topics: Computer science & Control theory. The organization has 1138 authors who have published 1381 publications receiving 7798 citations.

Automatic text summarization with statistical and linguistic features using successive thresholds

Abstract: Text summarization is an emerging technique for finding out the summary of the text document. Text summarization is nothing but summarizing the content of given text document. Text summarization has got so uses such as Due to the massive amount of information getting increased on internet; it is difficult for the user to go through all the information available on web. Summarization techniques need to be used to reduce the user's time in reading the whole information available on web. In this paper, we propose an automatic text summarization technique using both linguistic and statistical features using successive threshold for finding the summary i.e important sentences from the given input text document. Here the sentences are selected for summary based on the weight of the sentence. The weight of the sentences is calculated based on the statistical and linguistic features. Our approach assigns scores to the sentences by weighting the features like term frequency, word occurrences, and noun weight, phrases etc. In our approach, the number of sentences present in our summary would be equal to the number of paragraphs present in a text document, which can be achieved by using our successive threshold approach.

Feature Extraction and Classification Using Deep Convolutional Neural Networks

Abstract: The impressive gain in performance obtained using deep neural networks (DNN) for various tasks encouraged us to apply DNN for image classification task. We have used a variant of DNN called Deep convolutional Neural Networks (DCNN) for feature extraction and image classification. Neural networks can be used for classification as well as for feature extraction. Our whole work can be better seen as two different tasks. In the first task, DCNN is used for feature extraction and classification task. In the second task, features are extracted using DCNN and then SVM, a shallow classifier, is used to classify the extracted features. Performance of these tasks is compared. Various configurations ofDCNNare used for our experimental studies.Among different architectures that we have considered, the architecture with 3 levels of convolutional and pooling layers, followed by a fully connected output layer is used for feature extraction. In task 1 DCNN extracted features are fed to a 2 hidden layer neural network for classification. In task 2 SVM is used to classify the features extracted by DCNN. Experimental studies show that the performance of υ-SVM classification on DCNN features is slightly better than the results of neural network classification on DCNN extracted features.

High-G drop effect on the creep-fatigue failure of SAC solder joints in BGA packages

Abstract: The purpose of this work is to show the effects of drop impact on the creep-fatigue evolution of solder balls in an electronic device. Finite element method analysis was carried out for evaluation of stress and strain distribution in the solder joints. According to the simulation outcomes, the thermal cycling made an accumulated creep strain in the solder balls. The concentration of creep strain considerably increased with the coupling of drop impact into the thermal cycling. This event was owing to the excessive stress exerted on the samples by drop impacts. The stress analysis also indicated that with the addition of drop impacts into the thermal cycling intensified the stress triaxiality at the interfaces. Moreover, the experimental works were done and determined the elemental heterogeneity phenomenon in the solder joints and crack propagation along the interface.

Improving Performance Through Reputation Based Routing Protocol for Manet

Abstract: In ad hoc networks, nodes act as routers and transmit data packets originating from other nodes to destinations beyond the transmission range of the source node. Traditional routing protocols designed for Mobile Ad hoc Network all nodes in the network are trustworthy. Security of routing protocol is challenging in realistic setting as networks are attacked by untrustworthy nodes which disrupt the communication. In this paper, it is proposed to investigate the performance of dynamic source routing (DSR) routing protocol under untrustworthy environment. A novel fuzzy based model with trust and reputation is proposed to enhance the performance of the network with untrustworthy nodes. Reputation system takes input of previous records of successful transmissions, capability of nodes calculated as total trust value and the node mobility. Trust and reputation parameters are used to identify a secured route for transmission in the network. Simulation results show improved Quality of Service of the proposed technique compared to DSR in untrustworthy environment.