arXiv subjects

Vinay Kumar

Publications and source records attributed to Vinay Kumar.

34 records · Page 2Linked to original sources

arXiv2022

Variational Approach for Intensity Domain Multi-exposure Image Fusion

Recent innovations shows that blending of details captured by single Low Dynamic Range (LDR) sensor overcomes the limitations of standard digital cameras to capture details from high dynamic range scene. We present a method to produce well-exposed fused image that can be displayed directly on conventional display devices. The ambition is to preserve details in poorly illuminated and brightly illuminated regions. Proposed approach does not require true radiance reconstruction and tone manipulation steps. The aforesaid objective is achieved by taking into account local information measure that select well-exposed regions across input exposures. In addition, Contrast Limited Adaptive Histogram equalization (CLAHE) is introduced to improve uniformity of input multi-exposure image prior to fusion.

cs.CV↗

arXiv2021

From Convolutions towards Spikes: The Environmental Metric that the Community currently Misses

Today, the AI community is obsessed with 'state-of-the-art' scores (80% papers in NeurIPS) as the major performance metrics, due to which an important parameter, i.e., the environmental metric, remains unreported. Computational capabilities were a limiting factor a decade ago; however, in foreseeable future circumstances, the challenge will be to develop environment-friendly and power-efficient algorithms. The human brain, which has been optimizing itself for almost a million years, consumes the same amount of power as a typical laptop. Therefore, developing nature-inspired algorithms is one solution to it. In this study, we show that currently used ANNs are not what we find in nature, and why, although having lower performance, spiking neural networks, which mirror the mammalian visual cortex, have attracted much interest. We further highlight the hardware gaps restricting the researchers from using spike-based computation for developing neuromorphic energy-efficient microchips on a large scale. Using neuromorphic processors instead of traditional GPUs might be more environment friendly and efficient. These processors will turn SNNs into an ideal solution for the problem. This paper presents in-depth attention highlighting the current gaps, the lack of comparative research, while proposing new research directions at the intersection of two fields -- neuroscience and deep learning. Further, we define a new evaluation metric 'NATURE' for reporting the carbon footprint of AI models.

cs.AI↗

arXiv2021

Entropy optimized semi-supervised decomposed vector-quantized variational autoencoder model based on transfer learning for multiclass text classification and generation

Semisupervised text classification has become a major focus of research over the past few years. Hitherto, most of the research has been based on supervised learning, but its main drawback is the unavailability of labeled data samples in practical applications. It is still a key challenge to train the deep generative models and learn comprehensive representations without supervision. Even though continuous latent variables are employed primarily in deep latent variable models, discrete latent variables, with their enhanced understandability and better compressed representations, are effectively used by researchers. In this paper, we propose a semisupervised discrete latent variable model for multi-class text classification and text generation. The proposed model employs the concept of transfer learning for training a quantized transformer model, which is able to learn competently using fewer labeled instances. The model applies decomposed vector quantization technique to overcome problems like posterior collapse and index collapse. Shannon entropy is used for the decomposed sub-encoders, on which a variable DropConnect is applied, to retain maximum information. Moreover, gradients of the Loss function are adaptively modified during backpropagation from decoder to encoder to enhance the performance of the model. Three conventional datasets of diversified range have been used for validating the proposed model on a variable number of labeled instances. Experimental results indicate that the proposed model has surpassed the state-of-the-art models remarkably.

cs.LG↗

arXiv2021

Frequency Aware Face Hallucination Generative Adversarial Network with Semantic Structural Constraint

In this paper, we address the issue of face hallucination. Most current face hallucination methods rely on two-dimensional facial priors to generate high resolution face images from low resolution face images. These methods are only capable of assimilating global information into the generated image. Still there exist some inherent problems in these methods; such as, local features, subtle structural details and missing depth information in final output image. Present work proposes a Generative Adversarial Network (GAN) based novel progressive Face Hallucination (FH) network to address these issues present among current methods. The generator of the proposed model comprises of FH network and two sub-networks, assisting FH network to generate high resolution images. The first sub-network leverages on explicitly adding high frequency components into the model. To explicitly encode the high frequency components, an auto encoder is proposed to generate high resolution coefficients of Discrete Cosine Transform (DCT). To add three dimensional parametric information into the network, second sub-network is proposed. This network uses a shape model of 3D Morphable Models (3DMM) to add structural constraint to the FH network. Extensive experimentation results in the paper shows that the proposed model outperforms the state-of-the-art methods.

cs.CV↗

arXiv2021

Unclonable anti-counterfeiting labels based on microlens arrays and luminescent microparticles

Micron-scale randomness during manufacturing can ensure anti-counterfeiting labels are unclonable. However, this security typically comes at the expense of complex hardware being needed for authentication (e.g., microscopy systems). We demonstrate unclonable labels that can be authenticated using a standard light-emitting diode and smartphone camera. The labels consist of a microlens array laminated to a polymer film that is doped with luminescent microparticles. The micron-scale random overlap of focal volumes and microparticles leads to a pattern of bright points of visible light emission that can be easily imaged by a smartphone camera. 10 000 comparisons of images demonstrate that the labels can be robustly authenticated, and that the probability of a false authentication is on the order of $10^{-15}$. The ability for microlens arrays to simplify the hardware needed for authentication of unclonable labels is generalizable, and attractive for the implementation of unclonable labels in anti-counterfeiting systems.

physics.app-ph↗

arXiv2020

A complete character recognition and transliteration technique for Devanagari script

Transliteration involves transformation of one script to another based on phonetic similarities between the characters of two distinctive scripts. In this paper, we present a novel technique for automatic transliteration of Devanagari script using character recognition. One of the first tasks performed to isolate the constituent characters is segmentation. Line segmentation methodology in this manuscript discusses the case of overlapping lines. Character segmentation algorithm is designed to segment conjuncts and separate shadow characters. Presented shadow character segmentation scheme employs connected component method to isolate the character, keeping the constituent characters intact. Statistical features namely different order moments like area, variance, skewness and kurtosis along with structural features of characters are employed in two phase recognition process. After recognition, constituent Devanagari characters are mapped to corresponding roman alphabets in way that resulting roman alphabets have similar pronunciation to source characters.

cs.CV↗

arXiv2020

Unpredictable basin boundaries in restricted six-body problem with square configuration

The present work deals with the recently introduced restricted six body-problem with square configuration. It is determined that the total number of libration points are twelve and twenty for the mass parameter $0< μ< 0.25$. The multivariate form of Newton-Raphson scheme is used to discuss the basin of attraction. Different aspects of the basin of attraction are investigated and explained in detail. The complex combination of the different basins is found along the boundaries. The concept of basin entropy is used to unveil the nature of the boundaries. For $μ= 0.22$ and $0.23$, the basin of attraction is unpredictable throughout. It is observed that for all values of the mass parameter $μ$, the basin boundaries are highly unpredictable. Further, We have investigated the presence of Wada basin boundary in the basin of attraction.

nlin.CD↗

arXiv2020

Fractal basins of attraction in a binary quasar model

The present paper investigates the binary system of quasars in the framework of the Circular Restricted Three-Body Problem. The parametric evolution of libration points, the geometry of zero-velocity curves are one of the crucial aspects of our study. The multivariate form of NR method is applied to study the basin of attraction connected with libration points. The algorithm for using the Newton-Raphson method is slightly modified in order to avoid the unnecessary delay in the convergence of initial conditions. The impact of parameters on the shape of the basin of attraction and the number of iterations needed for the convergence of initial conditions are explored. We carry out an exhaustive (numerical) study to show the influence of these parameters on converging regions in basins of convergence. We unveil the existence of fractal structure in the basin of attraction using the method of basin entropy. In almost all cases, the existence of fractal structure is found throughout the basins of attraction.

nlin.CD↗

arXiv2017

FogGrid: Leveraging Fog Computing for Enhanced Smart Grid Network

The present manuscript concentrates on the application of Fog computing to a Smart Grid Network that comprises of a Distribution Generation System known as a Microgrid. It addresses features and advantages of a smart grid. Two computational methods for on-demand processing based on shared information resources is discussed. Fog Computing acts as an additional layer of computational and/or communication nodes that offload the Cloud backend from multi-tasking while dealing with large amounts of data. Both Fog computing and Cloud computing hierarchical architecture is compared with respect to efficient utilization of resources. To alleviate the advantages of Fog computing, a Fog computing framework based on Intel Edison is proposed. The proposed architecture has been hardware implemented for a microgrid system. The results obtained show the efficacy of Fog Computing for smart grid network in terms of low power consumption, reduced storage requirement and overlay analysis capabilities.

cs.DC↗

arXiv2017

A Software-equivalent SNN Hardware using RRAM-array for Asynchronous Real-time Learning

Spiking Neural Network (SNN) naturally inspires hardware implementation as it is based on biology. For learning, spike time dependent plasticity (STDP) may be implemented using an energy efficient waveform superposition on memristor based synapse. However, system level implementation has three challenges. First, a classic dilemma is that recognition requires current reading for short voltage$-$spikes which is disturbed by large voltage$-$waveforms that are simultaneously applied on the same memristor for real$-$time learning i.e. the simultaneous read$-$write dilemma. Second, the hardware needs to exactly replicate software implementation for easy adaptation of algorithm to hardware. Third, the devices used in hardware simulations must be realistic. In this paper, we present an approach to address the above concerns. First, the learning and recognition occurs in separate arrays simultaneously in real$-$time, asynchronously $-$ avoiding non$-$biomimetic clocking based complex signal management. Second, we show that the hardware emulates software at every stage by comparison of SPICE (circuit$-$simulator) with MATLAB (mathematical SNN algorithm implementation in software) implementations. As an example, the hardware shows 97.5 per cent accuracy in classification which is equivalent to software for a Fisher$-$Iris dataset. Third, the STDP is implemented using a model of synaptic device implemented using HfO2 memristor. We show that an increasingly realistic memristor model slightly reduces the hardware performance (85 per cent), which highlights the need to engineer RRAM characteristics specifically for SNN.

cs.NE↗

arXiv2016

Significance of Mobility on Received Signal Strength: An Experimental Investigation

In this paper, estimation of mobility using received signal strength is presented. In contrast to standard methods, speed can be inferred without the use of any additional hardware like accelerometer, gyroscope or position estimator. The strength of Wi-Fi signal is considered herein to compute the time-domain features such as mean, minimum, maximum, and autocorrelation. The experiments are carried out in different environments like academic area, residential area and in open space. The complexity of the algorithm in training and testing phase are quadratic and linear with the number of Wi-Fi samples respectively. The experimental results indicate that the average error in the estimated speed is 12 % when the maximum signal strength features are taken into account. The proposed method is cost-effective and having a low complexity with reasonable accuracy in a Wi-Fi or cellular environment. Additionally, the proposed method is scalable that is the performance is not affected in a multi-smartphones scenario.

cs.NI↗

arXiv2013

A Simplified Approach for Quality Management in Data Warehouse

Data warehousing is continuously gaining importance as organizations are realizing the benefits of decision oriented data bases. However, the stumbling block to this rapid development is data quality issues at various stages of data warehousing. Quality can be defined as a measure of excellence or a state free from defects. Users appreciate quality products and available literature suggests that many organization`s have significant data quality problems that have substantial social and economic impacts. A metadata based quality system is introduced to manage quality of data in data warehouse. The approach is used to analyze the quality of data warehouse system by checking the expected value of quality parameters with that of actual values. The proposed approach is supported with a metadata framework that can store additional information to analyze the quality parameters, whenever required.

cs.DB↗

arXiv2013

A simple technique for steganography

A new technique for data hiding in digital image is proposed in this paper. Steganography is a well known technique for hiding data in an image, but generally the format of image plays a pivotal role in it, and the scheme is format dependent. In this paper we will discuss a new technique where irrespective of the format of image, we can easily hide a large amount of data without deteriorating the quality of the image. The data to be hidden is enciphered with the help of a secret key. This enciphered data is then embedded at the end of the image. The enciphered data bits are extracted and then deciphered with the help of same key used for encryption. Simulation results show that Image Quality Measures of this proposed scheme are better than the conventional LSB replacing technique. The proposed method is simple and is easy to implement.

cs.MM↗

arXiv2013

Anisotropic Diffusion for Details Enhancement in Multi-Exposure Image Fusion

We develop a multiexposure image fusion method based on texture features, which exploits the edge preserving and intraregion smoothing property of nonlinear diffusion filters based on partial differential equations (PDE). With the captured multiexposure image series, we first decompose images into base layers and detail layers to extract sharp details and fine details, respectively. The magnitude of the gradient of the image intensity is utilized to encourage smoothness at homogeneous regions in preference to inhomogeneous regions. Then, we have considered texture features of the base layer to generate a mask (i.e., decision mask) that guides the fusion of base layers in multiresolution fashion. Finally, well-exposed fused image is obtained that combines fused base layer and the detail layers at each scale across all the input exposures. Proposed algorithm skipping complex High Dynamic Range Image (HDRI) generation and tone mapping steps to produce detail preserving image for display on standard dynamic range display devices. Moreover, our technique is effective for blending flash/no-flash image pair and multifocus images, that is, images focused on different targets.

cs.MM↗

arXiv2013

Design of One-Dimensional Linear Phase Digital IIR Filters Using Orthogonal Polynomials

In the present paper, we discuss a method to design a linear phase 1-dimensional Infinite Impulse Response (IIR) filter using orthogonal polynomials. The filter is designed using a set of object functions. These object functions are realized using a set of orthogonal polynomials. The method includes placement of zeros and poles in such a way that the amplitude characteristics are not changed while we change the phase characteristics of the resulting IIR filter.

cs.OH↗

arXiv2004

Exploring Core-to-edge Transport in Aditya Tokamak by Oscillations Observed in the edge Radiation

Understanding of the transport in a Tokamak plasma is an important issue. Various mechanisms have been reported in the literature to relate the core phenomenon to edge phenomenon. Sawtooth and Mirnov oscillations caused by MHD instabilities are generally observed in Tokamak discharges. Observation of these effects in the visible radiation from outer edge may offer a possible means to understand the transport.Oscillations in the visible radiation from outer region of the plasma have been observed during recent Aditya discharges. Percentage modulation of these oscillations vary with the Lines of Sight (LOS) of the chords and surfaces on which they terminate. This has been found in both the low frequency (~1 kHz) oscillations that seem to correlate with sawteething in SXR signals and the higher frequency (~10 kHz) oscillations that correlate well with Mirnov signals indicative of m/n=2/1 mode rotation. This suggests that the extent to which the MHD instabilities in the central region of the plasma column are reflected in the edge radiation depends on the interaction of the plasma with the surface at the extremity of the LOS. The release of particle/ energy accompanying the MHD instabilities leads to a large influx of particles from such surfaces. Cross-bispectral analysis suggests that a mode (having frequency of ~20 kHz) is also generated due to the interaction of m/n=1/1 (~10 kHz, seen in SXR) and m/n=2/1 (~10 kHz, seen in Mirnov, Visible & Microwave Interferometer signals). By possible selection rules, this mode seems to be a m/n=3/2 mode. This mode is seen in Mirnov, Visible & Interferometer signals. Behaviour of these oscillations on various LOS and their relation to SXR&Mirnov signals can lead to an understanding of the transport phenomenon. These observations and our interpretations will be presented.

physics.plasm-ph↗