Institute of Engineering and Management

Saltlake, India

Institute of Engineering and Management

Saltlake, India
Time filter
Source Type

Dhar P.,Institute of Engineering and Management | Alavi A.,University of Maryland University College
2017 IEEE International Conference on Identity, Security and Behavior Analysis, ISBA 2017 | Year: 2017

Employing Convolutional Neural Networks (CNN) to extract deep features from facial images for the task of recognition, identification and verification is well established. However, features extracted using CNNs have not been thoroughly studied for cross-resolution and blurred face verification. In this paper, we investigate the effectiveness of CNN features, that are primarily trained for matching high resolution images, to verify a pair of images constructed from a high and a low resolution face images. To perform this task, we degrade the image quality of the probe by artificially blurring and down sampling them, before it is passed to the CNN to be verified against high-resolution gallery image. After thorough experimental analysis, we present a pipeline which successfully improves upon the results obtained by raw CNN features, without any prior information of the quality of the degraded probe image. Using this pipeline, we show that the proposed system leads to improving verification accuracy in LFW and CMU-PIE datasets. © 2017 IEEE.

Mukherjee J.,Visva Bharati University | Ray S.,Visva Bharati University | Ghosh P.B.,Institute of Engineering and Management
Ecological Modelling | Year: 2013

Hooghly-Matla estuarine system receives a major load of carbon from adjacent mangrove forest in the form of litterfall throughout the year. Keeping in view, the crucial role of carbon, a seven compartment model has been proposed to study the dynamics of carbon in this estuarine system. Different forms of carbon present in soil (as soil organic carbon (SOC), soil inorganic carbon (SIC)) and in water (as dissolved inorganic carbon (DIC), dissolved carbon dioxide (DCO2), dissolved bicarbonate (DBC), dissolved organic carbon (DOC) and particulate organic carbon (POC)) are taken as state variables. Litter biomass, dissolved oxygen, primary productivity, community respiration, temperature of water, pH of water and soil, air-water exchange of carbon dioxide and conversion rates among different forms of carbon are considered as graph time functions. The data used in the present model are collected for over two years from our own field works and experiments. Other sensitive rate parameters which are not possible to collect from survey or experiment, calibrated following standard procedure. Sensitivity analysis is performed along with calibration. Model simulation results are validated with observed data. Results show seasonal variations of litterfall and which is the main source of SOC pool and ultimately transported to the estuary. Other than litterfall, the death of organisms in soil and water enriches the SOC and POC respectively. pH of water is governing factor and depending on this factor, DIC is converted to DCO2 and DBC, which are taken up by phytoplankton during photosynthesis. Mineralization rate of SOC to SIC and uptake rate of DCO2 and DBC are the sensitive parameters. © 2012 Elsevier B.V.

Hazra J.,Institute of Engineering and Management
2012 International Conference on Computer Communication and Informatics, ICCCI 2012 | Year: 2012

Design of non-uniform circular antenna arrays is one of the important optimization problems in electromagnetic domain. While designing a non-uniform circular array the goal of the designer is to achieve minimum side lobe levels with maximum directivity. In contrast to the single-objective methods that attempt to minimize a weighted sum of the four objectives considered here, in this article we consider these as four distinct objectives that are to be optimized simultaneously in a multi-objective (MO) framework using one of the best known Multi-Objective Evolutionary Algorithms (MOEAs) called NSGA-II. This MO approach provides greater flexibility in design by producing a set of final solutions with different trade-offs among the four objective from which the designer can choose one as per requirements. To the best of our knowledge, other than the single objective approaches, no MOEA has been applied to design a non-uniform circular array before. Simulations have been conducted to show that the best compromise solution obtained by NSGA-II is far better than the best results achieved by the single objective approaches by using the differential evolution (DE) algorithm and the Particle Swarm Optimization (PSO) algorithm. © 2012 IEEE.

Saha S.,Institute of Engineering and Management
International Journal of Systems Science | Year: 2015

We explore the impact of channel structure on the manufacturer, the distributer, the retailer and the entire supply chain by considering three different channel structures in radiance of with and without coordination. These structures include a traditional retail channel and two manufacturer direct channels with and without consistent pricing. By comparing the performance of the manufacturer, the distributer and the retailer, and the entire supply chain in three different supply chain structures, it is established analytically that, under some conditions, a dual channel can outperform a single retail channel; as a consequence, a coordination mechanism is developed that not only coordinates the dual channel but also outperforms the non-cooperative single retail channel. All the analytical results are further analysed through numerical examples. © 2014 Taylor & Francis.

Saha S.,Institute of Engineering and Management | Goyal S.K.,Concordia University at Montréal
International Journal of Production Economics | Year: 2015

In this paper three unlike coordinating contracts namely (i) joint rebate contract (ii) wholesale price discount contract and (iii) cost sharing contract are proposed for two echelon supply chain coordination perspective under stock and price induced demand. It is found analytically that the manufacturer's and the retailer's preferences among three contractual forms are not always aligned. By applying bargaining theory, it is established that stock elasticity plays an important role to select coordination contract and a threshold value stock elasticity is also determined, below which cost sharing contract is not feasible. It is also found that the retailer with higher bargaining power always prefers wholesale price discount contract among considered three contracts. Results are illustrated analytically as well as numerically. © 2015 Elsevier B.V. All rights reserved.

Banerjee S.,Institute of Engineering and Management
Springer Proceedings in Physics | Year: 2015

This paper mainly deals with an efficient method to solve the forward and the backward problem for 2D diffraction tomography. The method described here is a direct method which leads to faster reconstruction of the body’s complex refractive index profile. The method is based upon Born approximation which holds for weakly scattering bodies. The method involves a new type of mapping from real space to K space. The reconstructed image of the body is studied for different noisy environment and for different resolution in K space. Also suitable forward and inverse formula is presented. © Springer India 2015.

Panda S.,Bengal Institute of Technology | Saha S.,Institute of Engineering and Management | Basu M.,Kalyani University
International Journal of Systems Science | Year: 2013

Product perishability is an important aspect of inventory control. To minimise the effect of deterioration, retailers in supermarkets, departmental store managers, etc. always want higher inventory depletion rate. In this article, we propose a dynamic pre-and post-deterioration cumulative discount policy to enhance inventory depletion rate resulting low volume of deterioration cost, holding cost and hence higher profit. It is assumed that demand is a price and time dependent ramp-type function and the product starts to deteriorate after certain amount of time. Unlike the conventional inventory models with pricing strategies, which are restricted to a fixed number of price changes and to a fixed cycle length, we allow the number of price changes before as well as after the start of deterioration and the replenishment cycle length to be the decision variables. Before start of deterioration, discounts on unit selling price are provided cumulatively in successive pricing cycles. After the start of deterioration, discounts on reduced unit selling price are also provided in a cumulative way. A mathematical model is developed and the existence of the optimal solution is verified. A numerical example is presented, which indicates that under the cumulative effect of price discounting, dynamic pricing policy outperforms static pricing strategy. Sensitivity analysis of the model is carried out. © 2013 Copyright Taylor and Francis Group, LLC.

Ahmed F.,Institute of Engineering and Management | Das S.,Indian Statistical Institute
IEEE Transactions on Fuzzy Systems | Year: 2014

Suppression of impulse noise in images is an important problem in image processing. In this paper, we propose a novel adaptive iterative fuzzy filter for denoising images corrupted by impulse noise. It operates in two stages - detection of noisy pixels with an adaptive fuzzy detector followed by denoising using a weighted mean filter on the "good" pixels in the filter window. Experimental results demonstrate the algorithm to be superior to state-of-the-art filters. The filter is also shown to be robust to very high levels of noise, retrieving meaningful detail at noise levels as high as 97%. © 2013 IEEE.

Hazra J.,Institute of Engineering and Management
2012 International Conference on Computer Communication and Informatics, ICCCI 2012 | Year: 2012

This paper proposes a high speed low power circular convolution implementation of two finite length sequences by taking the advantage of fast Vedic Urdhva-Tiryakbhyam multiplication algorithm with a very efficient leakage control technique called Mutilple Channel CMOS (McCMOS) technique. The use of this Vedic formula allows for high speed convolution processing which happens frequently during the treatment of the time domain of signals. In this paper, the circular convolution is approached as a combination of Vedic multiplication unit and transmission gates based adders. The idea for designing the multiplication unit from Vedic Sutra is adopted because the partial sums and products are generated in only a single step. Furthermore McCMOS technique is used having non-minimum length transistors to offer the possibility of achieving excellent leakage control in nano-scale CMOS design with a very modest increase in area and switched capacitance. The simulations have been carried out in Cadence spice spectre using 130nm, 90nm, 65nm and 45nm node technology and presents comparative simulation results indicating the performance of the circuit. Thorough simulations show that the proposed architecture of designing the circular convolution achieves approximately 74-97% better performance in terms of PDP compared to the conventional architecture. The proposed technique will be very useful in different applications of time and space domains in digital image and signal processing. © 2012 IEEE.

Mukherjee A.,University of Engineering and Management | Ghosh K.K.,Institute of Engineering and Management
2013 International Conference on Informatics, Electronics and Vision, ICIEV 2013 | Year: 2013

In this paper we propose an efficient approach to QRS-complex detection using the Continuous Wavelet Transform (CWT). The method described in this paper is not affected by the presence of noise in the ECG signal nor does it depend on the morphology of the ECG waves. The speed of analysis of ECG signals using CWT and the accuracy of QRS-complex detection has been increased. The implementation of this method puts the CWT based peak detection methods at par with the DWT based methods with, same and in some cases, better accuracy of detection than the DWT based methods. © 2013 IEEE.

Loading Institute of Engineering and Management collaborators
Loading Institute of Engineering and Management collaborators