Birla Institute of Technology and Science

About: Birla Institute of Technology and Science is a education organization based out in Pilāni, Rajasthan, India. It is known for research contribution in the topics: Computer science & Population. The organization has 8897 authors who have published 13947 publications receiving 170008 citations.

Detection of major depressive disorder using linear and non-linear features from EEG signals

Abstract: EEG signals are non-stationary, complex and non-linear signals. During major depressive disorder (MDD) or depression, any deterioration in the brain function is reflected in the EEG signals. In this paper, linear features (band power, inter hemispheric asymmetry) and non-linear features [relative wavelet energy (RWE) and wavelet entropy (WE)] and combination of linear and non-linear features were used to classify depression patients and healthy individuals. In this analysis the data set used is publicly available data set contributed by Mumtaz et al. (Biomed Signal Process Control 31:108–115, 2017b). The dataset consisted of 34 MDD patients and 30 healthy individuals. The classifiers used were multi layered perceptron neural network (MLPNN), radial basis function network (RBFN), linear discriminant analysis (LDA) and quadratic discriminant analysis. When linear feature was used, highest classification accuracy of 91.67% was obtained by alpha power with MLPNN classifier. When non-linear feature was used, both RWE and WE provided highest classification accuracy of 90% with RBFN and LDA classifier, respectively. The highest classification of 93.33% was achieved when combining linear and non-linear feature, i.e., combination alpha power and RWE with MLPNN as well as RBFN classifier. This paper also showed that the combination of non-linear features, i.e., RWE and WE also performed the best with highest classification accuracy of 93.33%. The study compared the accuracy, sensitivity and specificity of different classifiers along with linear and non-linear features and combination of both. The results indicated that combination alpha power and RWE showed the highest classification 93.33% accuracy in all the applied classifiers.

Insulator condition analysis for overhead distribution lines using combined wavelet support vector machine (SVM)

Abstract: Condition analysis of overhead power distribution system insulators using combined support vector machine (SVM) and wavelet multi-resolution analysis (MRA) seems to be promising for distribution system monitoring (DSM) automation to cope with the increasing system complexity. Though system well-being analysis for engineering applications has been used mostly for electric power system reliability studies, the same principle has been extended for assessing the condition of insulators in a distribution system based on the extent of their damage. Video surveillance with fixed cameras provide the required images of power lines along with insulators at regular intervals and same is sent to a control room using remote terminal units (RTUs) for analysis. Not only the health of the insulators, but also the sagging of the lines, breakage of both insulators and lines can be captured with such cameras. This paper mainly focuses on application of wavelet-transform based feature extraction for digital image processing and SVM for subsequent condition analysis of insulators. The most significant contribution of the paper is to compute the condition indices for overhead power distribution line insulators to overcome difficulties related to vehicular applications in video surveillance. The results contained in this paper validate the efficacy of the proposed methodology for wide-scale applications in overhead power distribution system monitoring (DSM) automation.

Routing Protocols in Wireless Sensor Networks

Abstract: Due to dynamic topology, resource constraints and the distributed nature of WSNs, several requirements of routing protocols needs to be fulfilled. Wireless sensor networks comprise of huge number of spatially distributed, low-power, low-cost and intelligent autonomous sensors with one or more base stations which cooperatively monitor environment or physical conditions such as pressure, temperature, sound or motion. Efficiency of any routing protocol is governed by two main factors that is network lifetime and energy conservation. Another challenging issue in WSNs is the QoS support and therefore QoS aware routing protocol have gained much attention in the recent few years. In this article we first discuss several challenging factors and issues that affects the WSNs routing protocol design. In this paper we categorize various routing protocols in WSNs into three major categories namely the flat networks routing protocols, the hierarchical networks routing protocols and the QoS aware routing protocols. The article explores the flat networks routing protocols as Re-active, Pro-active and Hybrid Protocols and hierarchical networks routing protocols as chain-based, grid-based, tree-based and area-based protocols. The article also discusses the various types of QoS routing protocols in WSNs. Finally we present certain open issues regarding the design of routing protocols in WSNs.

Optimal Reservoir Operation for Flood Control Using Folded Dynamic Programming

Abstract: Folded Dynamic Programming (FDP) is adopted for developing optimal reservoir operation policies for flood control. It is applied to a case study of Hirakud Reservoir in Mahanadi basin, India with the objective of deriving optimal policy for flood control. The river flows down to Naraj, the head of delta where a major city is located and finally joins the Bay of Bengal. As Hirakud reservoir is on the upstream side of delta area in the basin, it plays an important role in alleviating the severity of the flood for this area. Data of 68 floods such as peaks of inflow hydrograph, peak of outflow from reservoir during each flood, peak of flow hydrograph at Naraj and d/s catchment contribution are utilized. The combinations of 51, 54, 57 thousand cumecs as peak inflow into reservoir and 25.5, 20, 14 thousand cumecs respectively as peak d/s catchment contribution form the critical combinations for flood situation. It is observed that the combination of 57 thousand cumecs of inflow into reservoir and 14 thousand cumecs for d/s catchment contribution is the most critical among the critical combinations of flow series. The method proposed can be extended to similar situations for deriving reservoir operating policies for flood control.