M Rajesh Kumar

Bio: M Rajesh Kumar is an academic researcher from VIT University. The author has contributed to research in topic(s): Feature extraction & Statistical classification. The author has an hindex of 4, co-authored 26 publication(s) receiving 61 citation(s).

Sentiment analysis on speaker specific speech data

Abstract: Sentiment analysis has evolved over past few decades, most of the work in it revolved around textual sentiment analysis with text mining techniques. But audio sentiment analysis is still in a nascent stage in the research community. In this proposed research, we perform sentiment analysis on speaker discriminated speech transcripts to detect the emotions of the individual speakers involved in the conversation. We analyzed different techniques to perform speaker discrimination and sentiment analysis to find efficient algorithms to perform this task.

Multi-objective generation dispatch using Particle Swarm Optimisation

Abstract: The advancement in power systems has led to the development of generation dispatch (GD) that is difficult to solve by classical optimisation method. The proposed paper work is to evolve simple and effective method for optimum generation dispatch to minimise the fuel cost, environmental cost and security requirement of power networks. The approach is based on the bi-criterion global optimisation and particle swarm optimisation (PSO) technique. The proposed technique is tested on 3-area interconnected and longitudinal system. The effectiveness of the proposed optimisation is verified in simulation studies using MATLAB software. The PSO based approach has been extended to evaluate the trade-off curve between the fuel cost of power production and the environmental cost according to the bi-criterion objective function.

A text-independent speaker verification model: A comparative analysis

Abstract: The most pressing challenge in the field of voice biometrics is selecting the most efficient technique of speaker recognition. Every individual's voice is peculiar, factors like physical differences in vocal organs, accent and pronunciation contributes to the problem's complexity. In this paper, we explore the various methods available in each block in the process of speaker recognition with the objective to identify best of techniques that could be used to get precise results. We study the results on text independent corpora. We use MFCC (Mel-frequency cepstral coefficient), LPCC (linear predictive cepstral coefficient) and PLP (perceptual linear prediction) algorithms for feature extraction, PCA (Principal Component Analysis) and t-SNE for dimensionality reduction and SVM (Support Vector Machine), feed forward, nearest neighbor and decision tree algorithms for classification block in speaker recognition system and comparatively analyze each block to determine the best technique.

Source camera identification using SPN with PRNU estimation and enhancement

Abstract: The sensor pattern noise is associated with digital images, due to imperfection in the chip of image sensor manufacturing process and it causes pixel sensitivity variation in the imaging sensor. The distinct property of these pattern noises makes it unique to that image sensor. Therefore, it acts as ‘fingerprint’ of that particular imaging sensor. The main contributor of sensor pattern noise is Photo Response Non-Uniformity noise (PRNU). In this proposed work, we analyse the PRNU estimation and enhance the content of the PRNU for better accurate identification of the source camera. The PRNU extraction consists of three stages: filtering, estimation and enhancement stage. Each stage consists of various techniques incorporated for the PRNU extraction. The experiments were conducted on natural images taken from the different camera models. For our experiment, 300 images from 6 different camera models are used and identification of source camera of a given image is done by correlating the PRNU reference pattern with the noise residual model obtained from the test image.

Efficient License Plate Recognition System with Smarter Interpretation Through IoT

Abstract: Vehicles play a vital role in modern-day transportation systems. Number plate provides a standard means of identification for any vehicle. To serve this purpose, automatic license plate recognition system was developed. This consisted of four major steps: preprocessing of obtained image, extraction of license plate region, segmentation, and character recognition. In earlier research, direct application of Sobel edge detection algorithm or applying threshold was used as key steps to extract the license plate region, which do not produce efficient results when captured image is subjected to high intensity of light. The use of morphological operations causes deformity in the characters during segmentation. We propose a novel algorithm to tackle the mentioned issues through a unique edge detection algorithm. It is also a tedious task to create and update the database of required vehicles frequently. This problem is solved by the use of ‘Internet of things’ where an online database can be created and updated from any module instantly. Also, through IoT, we connect all the cameras in a geographical area to one server to create a ‘universal eye’ which drastically increases the probability of tracing a vehicle over having manual database attached to each camera for identification purpose.

Impact of price penalty factors on the solution of the combined economic emission dispatch problem using cubic criterion functions

Abstract: Thermal power plants play a major role in power production. The impacts of the various pollutants such as sulphur dioxide (SO2), Nitrogen oxide (NOx) and carbon dioxide (CO2) affects the environmental issues. The fuel cost of the generator in an economic dispatch problem can be presented by any order polynomial. The literature review reported that most of the papers consider the single pollutant using the second order polynomial function. The paper formulates the dispatch problem using a cubic function for both fuel cost and emission values. The impacts of various pollutants and price penalty factors such as Max-Max, MinMax, Average, and Common are considered in the multi-objective dispatch problem. The dispatch problem is solved using Lagrange's method and the simulation results are provided for IEEE 30 bus system. It concludes that Min-Max Price penalty factor provides minimum fuel cost and minimum emission values in comparison to the other price penalty factors.

Lateralization of temporal lobe epilepsy based on resting-state functional magnetic resonance imaging and machine learning

Abstract: Lateralization of temporal lobe epilepsy (TLE) is critical for successful outcome of surgery to relieve seizures. TLE affects brain regions beyond the temporal lobes and has been associated with aberrant brain networks, based on evidence from functional magnetic resonance imaging. We present here a machine learning-based method for determining the laterality of TLE, using features extracted from resting-state functional connectivity of the brain. A comprehensive feature space was constructed to include network properties within local brain regions, between brain regions, and across the whole network. Feature selection was performed based on random forest and a support vector machine was employed to train a linear model to predict the laterality of TLE on unseen patients. A leave-one-patient-out cross validation was carried out on 12 patients and a prediction accuracy of 83% was achieved. The importance of selected features was analyzed to demonstrate the contribution of resting-state connectivity attributes at voxel, region, and network levels to TLE lateralization.

Combined Economic Emission Dispatch Problem using Particle Swarm Optimization

Abstract: This paper deals with particle swarm optimization (PSO) method to solve Combined Economic emission Dispatch Problem (CEEDP)of thermal units while satisfying the constraints such as generator capacity limits, power balance and line flow limits. PSO is a stochastic optimization process based on the movement and intelligence of swarms. The objective is to minimize the total fuel cost of generation and environmental pollution caused by fossil based thermal generating units. The bi-objective problem is converted into single objective problem by introducing price penalty factor to maintain an acceptable system performance in terms of limits on generator real power outputs, transmission losses with minimum emission dispatch. The proposed approach has been evaluated on an IEEE 30-bus test system with six generators. The results obtained with the proposed approach are compared with results of genetic algorithm and other technique. Keywords

A Quantum-Like multimodal network framework for modeling interaction dynamics in multiparty conversational sentiment analysis

Abstract: Sentiment analysis in conversations is an emerging yet challenging artificial intelligence (AI) task. It aims to discover the affective states and emotional changes of speakers involved in a conversation on the basis of their opinions, which are carried by different modalities of information (e.g., a video associated with a transcript). There exists a wealth of intra- and inter-utterance interaction information that affects the emotions of speakers in a complex and dynamic way. How to accurately and comprehensively model complicated interactions is the key problem of the field. To fill this gap, in this paper, we propose a novel and comprehensive framework for multimodal sentiment analysis in conversations, called a quantum-like multimodal network (QMN), which leverages the mathematical formalism of quantum theory (QT) and a long short-term memory (LSTM) network. Specifically, the QMN framework consists of a multimodal decision fusion approach inspired by quantum interference theory to capture the interactions within each utterance (i.e., the correlations between different modalities) and a strong-weak influence model inspired by quantum measurement theory to model the interactions between adjacent utterances (i.e., how one speaker influences another). Extensive experiments are conducted on two widely used conversational sentiment datasets: the MELD and IEMOCAP datasets. The experimental results show that our approach significantly outperforms a wide range of baselines and state-of-the-art models.

Multimodal sentimental analysis for social media applications: A comprehensive review

Abstract: The analysis of sentiments is essential in identifying and classifying opinions regarding a source material that is, a product or service. The analysis of these sentiments finds a variety of applications like product reviews, opinion polls, movie reviews on YouTube, news video analysis, and health care applications including stress and depression analysis. The traditional approach of sentiment analysis which is based on text involves the collection of large textual data and different algorithms to extract the sentiment information from it. But multimodal sentimental analysis provides methods to carry out opinion analysis based on the combination of video, audio, and text which goes a way beyond the conventional text‐based sentimental analysis in understanding human behaviors. The remarkable increase in the use of social media provides a large collection of multimodal data that reflects the user's sentiment on certain aspects. This multimodal sentimental analysis approach helps in classifying the polarity (positive, negative, and neutral) of the individual sentiments. Our work aims to present a survey of recent developments in analyzing the multimodal sentiments (involving text, audio, and video/image) which involve human–machine interaction and challenges involved in analyzing them. A detailed survey on sentimental dataset, feature extraction algorithms, data fusion methods, and efficiency of different classification techniques are presented in this work.