Papers by Soni Chaturvedi
International Journal of Next-Generation Computing, 2021
With minimal resources and trained labour, digital image processing techniques can be used for di... more With minimal resources and trained labour, digital image processing techniques can be used for diagnostic support system in illness identification at an early stage. These methods can also aid doctors during clinical evaluations by removing the need for invasive pathological investigations. By just viewing the colour content of the image of the pallor site, various blood components such as hemoglobin and billirubin can be analysed and classed in terms of the colour properties of the image. This research effort is an attempt to propose an image based method of quantifying hemoglobin(Hb) by examining the brightness, red component and texture of the patient's palpebral conjunctiva image after image super resolution. According to WHO recommendations, a computational model based on network of neurons is employed to relate the hemoglobin level to be measured with the level measured by the conventional invasive technique. Furthermore, based on the models’ testing results, patients with...
Abstract- In this paper we focus on how spiking neural networks can be used to identify a class o... more Abstract- In this paper we focus on how spiking neural networks can be used to identify a class of an input image by LIF model. We address the problem of identifying English alphabet character image By Artificial Neural Network which are mathematical computational models inspired by biological Neurons. An English alphabet character images (“A to z”) are first analyzed with Feed Forward Neural Network which belongs to Artificial Neural Network (ANN). Classes K1&K2 are considered for Capital letter and small letter respectively. The whole Recognition process is divided into four steps-Preprocessing, Classification, Post-Processing, and finally the comparison of
Edge Detection Techniques: Analysis for Contrasting Recent and Conventional Approach Prof. Soni C... more Edge Detection Techniques: Analysis for Contrasting Recent and Conventional Approach Prof. Soni Chaturvedi, Mr. Jayantkumar Dorave, Prof. Aleefia A.Khurshid Electronics & Comm. Engg , P.I. E.T. Nagpur ,INDIA 2 Electronics & Comm. Engg. M.Tech. IV Semester, P.I.E.T. Nagpur, INDIA. Electronics Engg. R.C.O.E M. Nagpur, INDIA. _____________________________________________________________________________________ Abstract— This paper depicts three methods for edge detection. The first method is one of the promising method for edge detection based on canny edge detection. In the second method neural network has been used for edge detection. Third method is inspired by the behavior of biological receptive fields and the human visual system. A network model based on spiking neuron is proposed to detect edges in visual image. SNN is able to perform edge detection within a processing time which is consistent with human visual system. SNNs improve the representation capacity and the processing ...
Mobile Operators see an unending growth of data traffic generated by their customers on their mob... more Mobile Operators see an unending growth of data traffic generated by their customers on their mobile data networks. As the operators start to have a hard time carrying all this traffic over 3G or 4G networks, offloading to Wi-Fi is being considered. Present study proposes method to handover between two WiFi. To achieve aforesaid objectives, the make before break (MBB) technique has been used. Feasibility of using Wi-Fi handover in the current Internet has been proved experimentally by using Network simulator 2 (NS2).
Digital Image Processing, 2014
This paper depicts pattern classification of uppercase and lower case English character, using Le... more This paper depicts pattern classification of uppercase and lower case English character, using Leaky integrated and fire neuron model and Izhikevich neuron model of spiking neural network. Spiking neural network is one of the best artificial neural networks, which are widely used in the field of neuron science. In this paper we focused on spiking mechanism of both models and compare them in terms of accuracy and simulation time. Leaky integrate and fire neuron model which is one of the simple and efficient model of spiking neural network that analyze and simulate efficiently. On the other hand Izhikevich model is one of the powerful models which can simulate thousands of neurons in real time. Using these two models simulation results are obtained for recognition of uppercase and lower case English characters. Finally we report on simulation results of both models and discuss their performance, in terms of recognition rate and speed.
In wireless sensor network reliable data transport is one of the most important requirements wher... more In wireless sensor network reliable data transport is one of the most important requirements where different applications have different reliability requirements. The characteristic of wireless sensor network, especially dense deployment, limited processing ability, memory and power supply, provide unique design challenges at transport protocol. A reliable protocol in wireless sensor network must allow data transfer reliably from source to destination with reasonable packet loss. To prolong the lifetime of wireless sensor network efficient transport protocol need to provide congestion control. This paper presents Agent-based Congestion Control Protocol (ACCP) for wireless sensor networks. The traffic rate analysis on each node is based on the priority index and the congestion degree of the node. The parameter such as latency and throughput are investigated. _________________________________________________________________________________________
Gender and gesture recognition has been a topic of research for many researchers for more than a ... more Gender and gesture recognition has been a topic of research for many researchers for more than a decade. Researchers have worked on gender recognition and gesture recognition as two separate entities, and have achieved optimum results in both the domains. But, very few have worked on improving the quality of gender and gesture detection together in videos. In this paper, we propose a framework for improving accuracy of gender and gesture recognition, which can be used in visual surveillance systems as a tool to measure the irregularities in user behaviour of a particular gender. We have used daubichies based wavelets & spiking neural network (SNN) for gesture recognition and viola-jones cascade object detection combined with support vector machine (SVM) and facial geometry features in order to improve the quality of gender detection from faces. Our results when compared with k-Nearest Neighbour and Hidden Markov Models (HMMs) provides a 10% improvement in accuracy of gender recognit...
Field Programmable Gate Arrays (FPGA) are increasingly being used to design highend computational... more Field Programmable Gate Arrays (FPGA) are increasingly being used to design highend computationally intense microprocessors capable of handling both fixed and floatingpoint mathematical operations. Addition is the most complex operation in a floating-point unit and offers major delay while taking significant area. Over the years, the VLSI community has developed many floating-point adder algorithms mainly aimed to reduce the overall latency. The Objective of this paper to implement the 32 bit binary floating point adder with minimum time. Floating point numbers are used in various applications such as medical imaging, radar, telecommunications Etc. Here pipelined architecture is used in order to increase the performance and the design is achieved to increase the operating frequency. The logic is designed using VHDL. This paper discusses in detail the best possible FPGA implementation will act as an important design resource. The performance criterion is latency in all the cases. The...
The paper depicts pattern recognition of Digits and Special Character using Artificial Neural Net... more The paper depicts pattern recognition of Digits and Special Character using Artificial Neural Network’s model Feed Forward Neural Network using Back Propagation Algorithm and Spiking Neural Network’s model Izhikevich Neuron model. Artificial Neural network is the second generation model and Spiking Neural Network is third generation model of Neural Networks. In this paper we have focused on recognizing the patterns and comparing the results of the two models Feed forward Neural Network and Izhikevich model by following the main steps of pattern recognition which are, Scanned handwritten Images, Pre-Processing of image, Feature Extraction of image, Training the network, Recognition/Classification of images. Feed Forward Neural Network consists of three layers and this network is trained by Back propagation Algorithm. On the other hand, we have Izhikevich model which is well known for producing all known firing rates pattern. It is a combination of Hodgkin-Huxley model and computation...
This paper presents a new approach for image segmentation by applying k-means algorithm. In image... more This paper presents a new approach for image segmentation by applying k-means algorithm. In image segmentation, clustering algorithms are very popular as they are intuitive and are also easy to implement. The K-means clustering algorithm is one of the most widely used algorithm in the literature, and many authors successfully compare their new proposal with the results achieved by the k-Means. This paper proposes a color-based segmentation method that uses K-means clustering technique . The k-means algorithm is an iterative technique used to partition an image into k clusters. The standard K-Means algorithm produces accurate segmentation results only when applied to images defined by homogenous regions with respect to texture and color since no local constraints are applied to impose spatial continuity. At first, the pixels are clustered based on their color and spatial features, where the clustering process is accomplished. Then the clustered blocks are merged to a specific number ...
Neural network concepts and principles appear to have great potential for solving problems arisin... more Neural network concepts and principles appear to have great potential for solving problems arising in pattern recognition. Over the last decade, various spiking neural network models have been proposed, along with a similarly increasing interest in spiking models of computation in computational neuroscience. In this paper, for Pattern Recognition of Handwritten Characters, Spiking Neural Network's Izhikevich Neuron Model is used. Here for large scale simulations of the Izhikevich model we explore the expediency of using FPGAs. It has been observed that due to the accuracy, efficiency, power and simulation time; the Izhikevich spiking neuron model is best suited for large scale simulations.
In this paper we focus on how spiking neural networks can be used to identify a class of an input... more In this paper we focus on how spiking neural networks can be used to identify a class of an input image by LIF model. We address the problem of identifying English alphabet character image By Artificial Neural Network which are mathematical computational models inspired by biological Neurons. An English alphabet character images (“A to z”) are first analyzed with Feed Forward Neural Network which belongs to Artificial Neural Network (ANN). Classes K1&K2 are considered for Capital letter and small letter respectively. The whole Recognition process is divided into four steps-Preprocessing, Classification, Post-Processing, and finally the comparison of Feed Forward Neural Network and Leaky-Integrate Firing Neuron Model is presented. In Proposed work, we have used Neural Network tool box and Image Processing Tool box in MATLAB software. Key WordsFeed Forward Neural Network, Leaky-Integrate Firing Neuron Model, Pattern Recognition, SNN, ANN. ______________________________________________...
A Biological Neural Network or simply BNN is an artificial abstract model of different parts of t... more A Biological Neural Network or simply BNN is an artificial abstract model of different parts of the brain or nervous system, featuring essential properties of t hese systems using biologically realistic models. The process of segmenting images is one of the most critical ones in automati c image analysis whose goal can be regarded as to find what objects are presented in images. This paper depicts the image p rocessing algorithms that treat the problem of image segmentation. Spiking Neuron Networks (SNNs) are often referred to as the 3rd generation of neural networks which have potential to solve problems related to biological stimuli. Spiki ng neural networks (SNNs) exhibit interesting properties that make them particularly suitable for applications that require fast and efficient computation and where the timing of input -output signals carries important information. However, the use of such networks in practical, goal-oriented applicati ons has long been limited by the lack of ap...
Pattern recognition basically assigns a label to a given input image. Pattern recognition is done... more Pattern recognition basically assigns a label to a given input image. Pattern recognition is done on the basis of classes to which an input image belongs. A pattern could be a fingerprint image, a handwritten cursive word, a human face, or a speech signal. In this paper we consider to analyze back propagation algorithm and feed forward algorithm used for recognizing patterns. We also try to implement Leaky integrate and fire neuron model which belongs to a category of Spiking neural networks. KeywordsBack propogation Algorithm, Feed Forward Algorithm, LIF-model, Spiking Neural Network.
Pattern recognition basically assigns a label to a given input image. Pattern recognition is done... more Pattern recognition basically assigns a label to a given input image. Pattern recognition is done on the basis of classes to which an input image belongs. A pattern could be a fingerprint image, a handwritten cursive word, a human face, or a speech signal. In this paper we consider to analyze back propagation algorithm and feed forward algorithm used for recognizing patterns. We also try to implement Leaky integrate and fire neuron model which belongs to a category of Spiking neural networks.
2013 6th International Conference on Emerging Trends in Engineering and Technology, 2013
ABSTRACT
2014 International Conference on Electronic Systems, Signal Processing and Computing Technologies, 2014
ABSTRACT
2014 International Conference on Electronic Systems, Signal Processing and Computing Technologies, 2014
ABSTRACT
2014 International Conference on Electronic Systems, Signal Processing and Computing Technologies, 2014
ABSTRACT
Emerging Trends in Engineering …, 2011
... Feature Extraction and Dimensionality Reduction Mrs.Soni Chaturvedi Dr.(Mrs.) AAKhurshid Dept... more ... Feature Extraction and Dimensionality Reduction Mrs.Soni Chaturvedi Dr.(Mrs.) AAKhurshid Deptt. Of E&C Engg. Deptt. ... Rather, realistic and complex neural models have been used since long to simulate real networks, but always with the emphasis on spike rate. ...
Uploads
Papers by Soni Chaturvedi