Electrical Engineering (EE): Recent submissions
Now showing items 61-80 of 357
-
Acoustic-Articulatory Mapping: Analysis and Improvements with Neural Network Learning Paradigms
Human speech is one of many acoustic signals we perceive, which carries linguistic and paralinguistic (e.g., speaker identity, emotional state) information. Speech acoustics are produced as a result of different temporally ... -
Speaker verification using whispered speech
Like neutral speech, whispered speech is one of the natural modes of speech production, and it is often used by speakers in their day-to-day life. For some people, such as laryngectomees, whispered speech is the only ... -
Degradation Studies on Polymeric Insulators used for EHV and UHV Transmission
High voltage insulators used in overhead power transmission systems are of key im- portance for safe, reliable, and effcient operation of transmission line in transferring huge amount of electrical power. Conventionally, ... -
Multisource Subnetwork Level Transfer in Deep CNNs Using Bank of Weight Filters
The convolutional neural networks (CNNs) have become the most successful models for many pattern recognition problems in the areas of computer vision, speech, text and others. One concern about CNNs has always been their ... -
Stationary diesel exhaust treatment by blending discharge plasma/ozone with industry wastes: a study on abatement of NOx and THC
Increased usage of fossil fuels, especially diesel, has made a large impact on the environment in the form of rise in global temperature, increased acidity in the rain water, decreased yield in vegetation and numerous ... -
Denoising and Refinement Methods for 3D Reconstruction
Capturing raw 3D data from the real world is the initial step for many 3D reconstruction pipelines in different computer vision applications. However, due to inaccuracies in measurement and oversimplification in mathematical ... -
Upper Frequency Bound on Circuit-Based Models for Transformer Windings
The power generation, transmission and utilisation are necessarily being carried out at different voltage levels, and require transformers for performing the voltage level conversions. As a result, transformers form one ... -
Sparsity Driven Solutions to Linear and Quadratic Inverse Problems
The problem of signal reconstruction from inaccurate and possibly incomplete set of linear/non-linear measurements occurs in a variety of signal and image processing applications. In this thesis, we develop reconstruction ... -
Price of Privacy of Smart Meter Data
Smart meter data can be used by the utility for billing the consumers timely along with power theft detection, demand side management, distribution network planning, consumer segmentation, load forecasting, fault detection, ... -
Solving Inverse Problems Using a Deep Generative Prior
In an inverse problem, the objective is to recover a signal from its measurements, given the knowledge of the measurement operator. In this thesis, we address the problems of compressive sensing (CS) and compressive phase ... -
Knowledge-driven training of deep models for better reconstruction and recognition
This thesis aims to efficiently solve many interesting and challenging problems by incorporating appropriate image processing techniques in a deep learning framework. We have proposed, implemented and tested efficient ... -
Speech enhancement using deep mixture of experts
Speech enhancement is at the heart of many applications such as speech com- munication, automatic speech recognition, hearing aids etc. In this work, we consider the speech enhancement under the framework of multiple ... -
Binaural Source Localization using subband reliability and interaural time difference patterns
Machine localization of sound sources is necessary for a wide range of appli- cations, including human-robot interaction, surveillance and hearing aids. Robot sound localization algorithms have been proposed using ... -
Dynamics of a Stratified Population of Optimum Seeking Agents on a Network
Very large scale multi-agent systems occur both naturally and in engineering applications. In many of these systems, the agents are either selfish or act with varying levels of coordination. Understanding the evolution of ... -
Shape-constrained Biomedical Image Segmentation and Applications
The detection, segmentation, and delineation of the targeted regions of interest in biomedical images are fundamental steps for computer-aided assessment and prescreening. In this thesis, we focus on shape-constrained ... -
Modeling, Analysis and Control of Reconfigurable Battery/Grid Tied Solar Photo-Voltaic Inverter
Grid reliability and power outages are key concerns today, due to the ever-increasing energy demand. Traditionally, Uninterruptible Power Supplies (UPS) with battery storage have been employed to contend with grid outages. ... -
Face Recognition in Unconstrained Environment
The goal of computer vision is to provide the ability to machines to understand image data and infer the useful information from it. The inferences highly depend on the quality of the image data. But in many real-world ... -
Hardware Emulation of a Long Transmission Line by High Frequency Power Electronic Converter for the study of Switching Transients
To ensure smooth functioning of the grid, the reliability and robustness of the power system equipment needs to be precisely evaluated during their development process. But direct on- eld tests of most of the equipment ... -
Algorithms for Processing RGBD Images and Videos for Depth-Based 3D Video Systems
In recent times, immersive visual media such as Virtual Reality (VR), Augmented Reality (AR), 3DTV and Free Viewpoint Television (FTV) have garnered tremendous interest. Immersive visual media content typically provides ... -
Content-Based Texture Analysis and Synthesis for Low Bit-Rate Video Coding Using Perceptual Models
Determining perceptually irrelevant and redundant information from human point of view is one of the fundamental problems today that is limiting the performance of current video compression algorithms. The performance of ...