Kavita Thakur

Pt. Ravishankar Shukla University, School of Studies in Electronics and Photonics, Faculty Member

Followers

Following

Co-authors

Public Views

Interests

Uploads

Papers by Kavita Thakur

Integration of ML and IoT for Healthcare Systems

Advances in medical technologies and clinical practice book series, Apr 8, 2022

Comparative Investigation of Different Classification Techniques for Epilepsy Detection Using EEG Signals

Classification of working memory loads using hybrid EEG and fNIRS in machine learning paradigm

Electronics Letters, 2020

Performance Evaluation of Spectrogram Based Epilepsy Detection Techniques Using Gray Scale Features

Journal of Ravishankar University (PART-B), 2020

Electroencephalogram (EEG) is most common instrument for treatment and diagnosis of brain related... more Electroencephalogram (EEG) is most common instrument for treatment and diagnosis of brain related diseases. Analysis of EEG signals for treatment of patient is time consuming and not easy task for neurologist. There is always a chance of human error. The purpose of this paper is to present an automatic detection model for epileptic seizure from EEG signals. To fulfill this objective, EEG signals are preprocessed and converted into spectrogram images using Short Time Fourier Transform (STFT). From this spectrogram images gray scale features are extracted. Support Vector Machine (SVM) with six different kernel functions and three data division protocols are utilized for performance evaluation of proposed model. Results show that quadratic SVM classifier has achieved highest classification accuracy.

Optimal quantization table generation for efficient satellite image compression using teaching learning based optimization technique

2017 International Conference on Big Data Analytics and Computational Intelligence (ICBDAC), 2017

Communication of the satellite images plays a crucial role in many important applications such as... more Communication of the satellite images plays a crucial role in many important applications such as change detection, land cover classification, weather prediction etc. The increase in the demand of satellite images over the band limited channel requires good quality compression tools. Currently, the compression standard developed by Joint Photographic Experts Group (JPEG) is the widely used product for the compression of satellite images. Moreover, one of the important elements which influence the performance of JPEG compression standard is the nature of quantization table. The compression ratio and the decompressed image quality are determined all-together by the quantization table, and hence, the table strongly influences the whole compression performance. The author aims to generate better quantization tables to enhance the compression performance to achieve higher compression ratios while preserving high reconstruction quality for satellite images. A Teaching Learning based Optimization (TLBO) technique is employed to promote higher compression performance for satellite images. The aim is to identify optimal quantization tables that contribute to better compression efficiency in terms of image quality indexes Peak Signal to Noise Ratio (PSNR) and Mean Square Error (MSE). The TLBO based optimization strategy is proposed because it is free from the algorithmic parameters. Experiments were carried out on the three different satellite images. The results demonstrate that the identified optimal quantization tables offer average PSNR gain of about 0.5 dB with the average reduction in MSE of about 10 against the available JPEG quantization table.

Majority voting-based hybrid feature selection in machine learning paradigm for epilepsy detection using EEG

International Journal of Computational Vision and Robotics, 2021

Quality Assessment of Compressed MR Medical Images using General Regression Neural Network

Medical imaging plays a major role in contemporary health care, both as a tool in primary diagnos... more Medical imaging plays a major role in contemporary health care, both as a tool in primary diagnosis and as a guide for surg ical and therapeutic procedures. Compression of radiological images is an effective mechanism for storage and transmission. The use of such images for teleradiol ogy is of increasing importance, with one of the main reasons being the ability to c all upon remotely located diagnostic experts. Whilst many researchers have ad dressed the problem of how the degradation of image quality with compression ratio affects observer-based diagnostic accuracy. In this work, we propose a qua ntitative analysis of quality for lossy compressed magnetic resonance (MR) images, an d their influence in automatic tissue classification. Peak Signal to Noise Ratio ( PSNR), as quality measurement, is not enough if we have medical images. So we need to find out new quality measurements not based in perception to make a quan titative analysis for medical image compression. This paper pr...

High-Quality Medical Image Compression Using Discrete Orthogonal Cosine Stockwell Transform and Optimal Integer Bit Allocated Quantization

Communication of the medical image and videos has now raised as a vital concern for the telediagn... more Communication of the medical image and videos has now raised as a vital concern for the telediagnosis of critical diseases. Currently, JPEG and JPEG2k codecs are the default compression tool to facilitate their communication over band-limited channels. However, most often, the performance of these existing codecs is found poor particularly at the higher compression levels. Hence, this paper presents a new medical image compression codec to achieve high-quality compression of the medical images, especially at the higher compression levels. The proposed codec utilizes Discrete Orthogonal Cosine Stockwell Transform (DOCST) for the higher pixel decorrelation and the optimal integer bit allocation based quantization strategy for the efficient quantization of the DOCST coefficients. Further, to justify and validate the performance of the proposed codec an extensive performance analysis has been presented for six medical images of two different modalities. It is reported that the proposed ...

Extraction of phonetic parameters for status recognition of pregnant woman using linguistic segmentals

Assessment of Stressed Lungs Using the FIR Filters

The vocal apparatus consist of different parts some of which belongs the alimentary tract and oth... more The vocal apparatus consist of different parts some of which belongs the alimentary tract and other to the respiratory organs. The whole respiratory apparatus is active in the sound producing mechanism of speech. The thoracic cavity can be expanded and contracted by the respiratory muscles, thus prouducing a current of compressed air from the lungs in case of any utterance (speech). Infact, the production of speech is a supplementary activity to the respiration; this means that, in particular these two functions have a considerable influence on each other. The compressed air from the lungs to larynx, reducing the phonetic quality is a function of lungs healthy/stressed status. Thus the analysis of speech will be a status symbol indicating the lungs stressed/unstressed condition. In present work the stressed condition of lungs is assessed using the FIR filter in which the side lobe configuration is utilized having the same bandwidth of the filter. It is concluded that the shifting of...

Need of Automated System for Climatic Control and Irrigation

Journal of Microcontroller Engineering and Applications, 2019

Abstract India is an agricultural country. Agriculture affects the economy of India. For better p... more Abstract India is an agricultural country. Agriculture affects the economy of India. For better production, irrigation system must be well designed and auto-controlled. Irrigation is a technique used to supplement the rainwater of dry land. Irrigation is a technique for providing water supply to plants at needed interval. Irrigation of different regions of the country is done through different means, such as wells, reservoirs, canals, rivers, etc. There are various types of irrigation system namely surface, localized, drip, sprinkler, center pivot, lateral, sub and manual irrigation. According to World Bank collection of development indicators, India has 60.45% agriculture land. Agriculture contributes 17% of the total GDP of Indian economy. Agriculture plays a vital role in the Indian economy. 70% of the rural households depend on agriculture. Irrigation sector faces lots of issues and challenges viz regional imbalance of rainfall and water availability, faulty ground water policy, water resources face irregular climate change challenge, water shortage due to urbanization and industrialization, heavy subsidies provided by government intended to wasteful use of water. So, it is very essential to supply water in a controlled way. Lots of techniques have been developed to provide controlled automated irrigation system. This paper basically explores the requirements of automated system and various latest techniques for controlling irrigation and climate. Keywords: Irrigation, climate control, smart agriculture system, soil sensor, temperature sensor Cite this Article P Vyas, K Thakur. Need of Automated System for Climatic Control and Irrigation. Journal of Microcontroller Engineering and Applications. 2019; 6(3): 1–4p.

Social Impact of Biometric Technology: Myth and Implications of Biometrics: Issues and Challenges

Advances in Biometrics, 2019

Biometric system which is based on human physical and behavioral traits is implemented in a versa... more Biometric system which is based on human physical and behavioral traits is implemented in a versatile field especially national security, wage control, access control, intruder detection and verification, forensic science, etc. Biometrics is more reliable and capable than conventional methods like PIN, token system, etc. because of its unique identity whether physical or behavioral trait verification of each and every person. In recent times, the awareness of biometrics for common man had been limited to its use in spy thrillers or fear instilling instruments of state of corporate surveillance in speculative fiction, forensic or as investigative tools; and was supposed to be ultimate in areas where it was applied. There has been a drastic change in areas where biometrics can be applied. A good biometrics is characterized by use of a feature that is highly unique, so that the chance of any two people having the same characteristic will be minimal; is stable, so that the feature does not change over time; and can be easily captured, in order to provide convenience to the user and prevent misrepresentation of the feature. Biometric identifications are harder to steal than other traditional traits.

Improved Optimum Nonnegative Integer Bit Allocation Algorithm Using Fuzzy Domain Variance Estimation and Refinement for the Wavelet-Based Image Compression

Circuits, Systems, and Signal Processing, 2019

Optimum nonnegative integer bit allocation (ONIBA) is a conspicuous technique, which usually prov... more Optimum nonnegative integer bit allocation (ONIBA) is a conspicuous technique, which usually provides the solution of optimal quantization issues for the transform coders (TCs). In order to obtain the optimum bits for a specific quantizer, all the existing ONIBA algorithms strongly rely on the variance characteristics of transform coefficients. Typically, in the wavelet-based TCs, the sub-band variances are directly estimated in the wavelet domain. This direct variance estimation is not supposed to be the best way to obtain the exact variance information, because the practical values of the wavelet coefficients may not be precise and therefore constitute an uncertain environment for the accurate variance estimation. Consequently, all the existing ONIBA algorithms often exhibit poor quantization performance in the presence of entropy coder. Hence, this paper presents a new fuzzy domain variance estimation and refinement (FDVER)-based ONIBA algorithm to attain the real optimum quantization of the wavelet coefficients in the presence of entropy coder. The outcome shows that the proposed FDVER-ONIBA algorithm outperforms and provides high-quality image compression along with the significant bitrate savings by the efficient quantization of the wavelet coefficients as compared to the existing common sub-band coding technique and the recent ONIBA algorithms. Keywords Transform coding • Image compression • Discrete wavelet transform (DWT) • Quantization • ONIBA algorithm • Fuzzy logic • Image quality • BD-PSNR • BD-rate Publisher's Note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Download

Hybrid WPT‐BDCT transform for high‐quality image compression

IET Image Processing, 2017

The image compression performance of transform coders highly depends on the energy compaction (EC... more The image compression performance of transform coders highly depends on the energy compaction (EC) capability of transforms. The popular transforms such as discrete cosine transform (DCT) and discrete wavelet transform (DWT) provide decent EC; however, their capability is not enough to deliver good quality image reconstruction for higher compression levels (CLs). In this study, the authors propose a new hybrid transform which is a fusion of wavelet packet transform (WPT) and block-DCT (BDCT) transform to achieve high-quality image compression. This new hybrid WPT-BDCT transform is able to attain higher EC than the existing transforms. Further, the authors have found a new energy compaction index (ECI) to evaluate the energy compactness of the image transforms. The proposed hybrid transform has been extensively evaluated, based on proposed ECI parameter, the visual quality assessment of reconstructed images and with the standard image quality indexes peak-signal-to-noise ratio and structural similarity index measure. It is reported that the proposed hybrid transform provides higher EC and outperforms the transforms namely DCT, DWT, WPT, multi-wavelet transform and existing hybrid transforms for all the CLs.

Download

A Highly Efficient Gray Image Compression Codec using Neuro Fuzzy Based Soft Hybrid JPEG Standard

ABSTRACT

First degree heart block determination from speech analysis

2013 International Conference on Signal Processing , Image Processing & Pattern Recognition, 2013

ABSTRACT The proposed work describes the method of determination of first degree heart block cond... more ABSTRACT The proposed work describes the method of determination of first degree heart block condition of a human heart from the speech analysis of the particular. In an Electrocardiogram (ECG), the PR interval represents the time taken for the depolarization to spread from the SA node to the ventricular muscle. If PR interval is found greater than 0.2s, first degree heart block or AV Block is detected in the heart. As Formant Frequency is the speech feature which represents the physiological and psychological condition of a human body. Formant analysis describes various heart parameters which are obtained through an ECG and so the detection of various heart diseases can be possible from speech analysis.

Artificial intelligence-based classification of breast cancer using cellular images

RSC Advances, 2014

ABSTRACT Detection and classification of breast cancer at the cellular level is one of the most c... more ABSTRACT Detection and classification of breast cancer at the cellular level is one of the most challenging problems. Since the morphology and other cellular features of cancer cells are different from normal heathy cells, it is possible to classify cancer cells and normal cells using such features. Although various artificial intelligence (AI) techniques including least square support vector machine (LS-SVM) have been used for pattern recognition, their use in classifying breast cancer from cellular images has yet not been established. In this communication, we developed an alternative approach using various AI techniques to classify breast cancer and normal cells using cellular image texture features extracted from cell images of various breast cancer cell lines like MCF-7, MDAMB-231 and the human normal breast cell line MCF-10A. Applying pattern recognition techniques upon various human breast cancer/normal cell images, we successfully performed cellular image segmentation, texture based image feature extraction and subsequent classification of cancer and normal breast cells. Four different AI techniques: K th nearest neighbour (KNN), artificial neural network (ANN), support vector machine (SVM) and LS-SVM were applied to classify cancer using optimal features obtained from cell segmented images. Our results demonstrated that LS-SVM with both radial basis function (RBF) and linear kernel classifier had the highest classification rate of 95.34% among all. Thus, our LS-SVM classifier was found to be a suitable trained model that could classify the cancer and normal cells using cell image features in a short time unlike other approaches reported so far.

Appropriate Windowing in Speech Parameter Extraction

2010 International Conference on Advances in Recent Technologies in Communication and Computing, 2010

... asymptotic decay. Kamil K. W´ojcicki and Kuldip K. Paliwal (2007) investigate the effect that... more

Design and Implementation of a Highly Efficient Three-Level T-Type Converter for Low-Voltage Applications

IEEE Transactions on Power Electronics, 2013

ABSTRACT The demand for lightweight converters with high control performance and low acoustic noi... more ABSTRACT The demand for lightweight converters with high control performance and low acoustic noise led to an increase in switching frequencies of hard switched two-level low-voltage 3-phase converters over the last years. For high switching frequencies, converter efficiency suffers and can be kept high only by employing cost intensive switch technology such as SiC diodes or CoolMOS switches; therefore, conventional IGBT technology still prevails. In this paper, the alternative of using three-level converters for low-voltage applications is addressed. The performance and the competitiveness of the three-level T-type converter (3LT2C) is analyzed in detail and underlined with a hardware prototype. The 3LT2 C basically combines the positive aspects of the two-level converter such as low conduction losses, small part count and a simple operation principle with the advantages of the three-level converter such as low switching losses and superior output voltage quality. It is, therefore, considered to be a real alternative to two-level converters for certain low-voltage applications.

An Efficient Fuzzy Logic Based Edge Detection Algorithm for Gray Scale Image

Various Edge detection algorithm has been proposed in the literature for extracting the edges fro... more Various Edge detection algorithm has been proposed in the literature for extracting the edges from the image. After emerging the fuzzy logic concept, a lot of Researcher of image processing shifted their attention towards the fuzzy logic concept and its applicability in the field of image processing. This paper presents a fuzzy rule base algorithm which is capable of detecting edges efficiently from the gray scale images. The performance of the proposed method is demonstrated through computer simulation in comparison with the existing sobel and prewitt edge detector.

Download

Kavita Thakur

Uploads

Papers by Kavita Thakur

Log In