Thapar University

About: Thapar University is a education organization based out in Patiāla, Punjab, India. It is known for research contribution in the topics: Computer science & Cloud computing. The organization has 2944 authors who have published 8558 publications receiving 130392 citations.

A Decision Support System for Classification of Normal and Medical Renal Disease Using Ultrasound Images: A Decision Support System for Medical Renal Diseases

Abstract: Early detection of medical renal disease is important as the same may lead to chronic kidney disease which is an irreversible stage. The present work proposes an efficient decision support system for detection of medical renal disease using small feature space consisting of only second order GLCM statistical features computed from raw renal ultrasound images. The GLCM mean feature vector and GLCM range feature vector are computed for inter-pixel distance d varying from 1 to 10. These texture feature vectors are combined in various ways yielding GLCM ratio feature vector, GLCM additive feature vector and GLCM concatenated feature vector. The present work explores the potential of five texture feature vectors computed using GLCM statistics exhaustively for differential diagnosis between normal and MRD images using SVM classifier. The result of the study indicates that GLCM range feature vector computed with d = 1 yields the highest overall classification accuracy of 85.7% with individual classification accuracy values of 93.3% and 77.9% for normal and MRD classes respectively.

Benzimidazole-biologically attractive scaffold for protein kinase inhibitors

Abstract: Great advances in elucidating molecular structures allow the precise determination of the interactions between a protein and a therapeutic agent. Enzyme inhibitors are used as a therapeutic agent with organic molecules, that interact with their targets through the weak linkages of hydrogen bonding and van der Waals interactions. These reduce the undesirable side effects and allow more non-specific interactions with non-target molecules. Benzimidazole acts as an enzyme inhibitor that may interact with different proteins and enzymes and has inspired chemists to carry out various structural variations of it. This review discusses the development of distinct benzimidazoles with an array of enzyme inhibitors viz., aurora kinase inhibitors, cyclin-dependent kinase inhibitors, mitogen activated protein kinase inhibitors, polo like kinase inhibitors, Tie kinase inhibitors, lymphocyte specific kinase inhibitors etc., also highlighting the molecular interaction with enzyme inhibitors. Various derivatives of benzimidazole, with different inhibitory activities, have been described on the basis of substitution around the central moiety, with an aim to help medicinal chemists to develop structure–activity relationships. The reviews in the literature till now are focused only on the biological activities of benzimidazole viz., antiviral, anticancer and antifungal, but the present review focuses on the latest work, describing the inhibitor aspects and the potential of the benzimidazole ring. This discussion will further help in the development of novel benzimidazole compounds.

Fuzzy decision-making in stochastic multiobjective short-term hydrothermal scheduling

Abstract: In the multiobjective framework, fuzzy decision-making methodology is exploited to decide the generation schedule of a short-range fixed-head hydrothermal problem. The multiobjective problem is formulated considering five objectives: (i) cost, (ii) NO/sub x/ emission, (iii) SO/sub 2/ emission, (iv) CO/sub 2/ emission and (v) variance of generation mismatch with the explicit recognition of statistical uncertainties in the thermal generation cost, NO/sub x/, SO/sub 2/ and CO/sub 2/ emission curves and power demand, which are random variables. The solution set of such formulated problems is non-inferior due to contradictions among the objectives taken. The weighting method is used to simulate the trade-off relation between the conflicting objectives in the non-inferior domain. Once the trade-off has been obtained, fuzzy set theory helps the system operator to choose the weighting pattern and thus the operating point that maximises the satisfaction of all the objectives. The results are demonstrated on three sample systems.

Deep Learning Based Sentiment Analysis Using Convolution Neural Network

Abstract: Sentiment analysis (SA) of natural language text is an important and challenging task for many applications of Natural Language Processing. Till now, researchers have used different types of SA techniques such as lexicon based and machine learning to perform SA for different languages such as English, Chinese. Inspired by the gain in popularity of deep learning models, we conducted experiments using different configuration settings of convolutional neural network (CNN) and performed SA of Hindi movie reviews collected from online newspapers and Web sites. The dataset has been manually annotated by three native speakers of Hindi to prepare it for training of the model. The experiments are conducted using different numbers of convolution layers with varying number and size of filters. The CNN models are trained on 50% of the dataset and tested on remaining 50% of the dataset. For the movie reviews dataset, the results given by our CNN model are compared with traditional ML algorithms and state-of-the-art results. It has been observed that our model is able to achieve better performance than traditional ML approaches and it has achieved an accuracy of 95%.