Christ University

About: Christ University is a education organization based out in Bengaluru, India. It is known for research contribution in the topics: Computer science & Convection. The organization has 2267 authors who have published 2715 publications receiving 14575 citations. The organization is also known as: Christ College & Christ University.

Rough Set Based Ant-Lion Optimizer for Feature Selection

Abstract: As the area of computational intelligence evolves, the dimensionality of any sort of data gets expanded. To solve this issue, Rough Set Theory (RST) has been successfully used for finding reducts as it requires only supplied data and no additional information. This paper investigates a novel search strategy for minimal attribute reduction based on rough sets and Ant Lion Optimization (ALO). ALO is a nature-inspired algorithm that mimics the hunting mechanism of ant lions, and this is inspired to find the minimum reducts. Datasets from the UCI repository are used in this paper. The experimental results show that the features selected by the proposed method are well classified with reasonable accuracy.

Epileptic Seizure Prediction from EEG Signals Using DenseNet

Abstract: Epilepsy is a disorder in which the normal electrical pattern in the brain is disrupted causing seizures or loss of consciousness. Seizure is harmful during various events like swimming or driving. The electroencephalogram (EEG) is the measurement of electrical activity received from the nerve cells of the cerebral cortex. Forthcoming seizures can be predicted from scalp EEG signal to improve the quality of life. The study proposes a method of automatic epileptic seizure prediction from raw EEG signal. The raw EEG signal is converted into EEG signal image for automatic extraction of features and classification of inter-ictal and pre-ictal state using Dense Convolutional Network (DenseNet). This classification process is carried out in a manner similar to the process followed by a medical practitioner without resorting to hand-crafted features. The public CHB-MIT EEG database is used for training, validation, and testing. An EEG signal for 1 second duration is taken as one sample. The accuracy for the classification of inter-ictal and pre-ictal state is achieved up to 94% by using 5-Fold cross validation. However, the accuracy is not up to the mark for the presence of common artifacts caused by eye-blinking and muscle activities during EEG recordings. Hence, a 30 seconds pool based technique is used for decision on correct state identification. The proposed pool based technique provides an average specificity of 95.87% and a false prediction rate of 0.0413/hour. It also provide average sensitivities of 100%, 97%, and 90% for the time slots 0 - 5 minutes, 5 - 10 minutes, and 10 - 15 minutes before the seizure event.

Classification of Vehicle Make Based on Geometric Features and Appearance-Based Attributes Under Complex Background

Abstract: Vehicle detection and recognition is an important task in the area of advanced infrastructure and movement administration. Many researchers are working on this area with different approaches to solve the problem since it has a many challenge. Every vehicle has its on own unique features for recognition. This paper focus on identifying the vehicle brand based on its geometrical features and diverse appearance-based attributes like colour, occlusion, shadow and illumination. These attributes will make the problem very challenging. In the proposed work, system will be trained with different samples of vehicles belongs to the different make. Classify those samples into different classes of models belongs to same make using Neural Network Classifier. Exploratory outcomes display promising possibilities efficiently.