Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
19 results
Search Results
Item Quantum Machine Learning: A Review and Current Status(Springer Science and Business Media Deutschland GmbH, 2021) Mishra, N.; Kapil, M.; Rakesh, H.; Anand, A.; Mishra, N.; Warke, A.; Sarkar, S.; Dutta, S.; Gupta, S.; Prasad Dash, A.; Gharat, R.; Chatterjee, Y.; Roy, S.; Raj, S.; Kumar Jain, V.; Bagaria, S.; Chaudhary, S.; Singh, V.; Maji, R.; Dalei, P.; Behera, B.K.; Mukhopadhyay, S.; Panigrahi, P.K.Quantum machine learning is at the intersection of two of the most sought after research areas—quantum computing and classical machine learning. Quantum machine learning investigates how results from the quantum world can be used to solve problems from machine learning. The amount of data needed to reliably train a classical computation model is evergrowing and reaching the limits which normal computing devices can handle. In such a scenario, quantum computation can aid in continuing training with huge data. Quantum machine learning looks to devise learning algorithms faster than their classical counterparts. Classical machine learning is about trying to find patterns in data and using those patterns to predict further events. Quantum systems, on the other hand, produce atypical patterns which are not producible by classical systems, thereby postulating that quantum computers may overtake classical computers on machine learning tasks. Here, we review the previous literature on quantum machine learning and provide the current status of it. © 2021, Springer Nature Singapore Pte Ltd.Item A Decentralized Nonlinear Control Scheme for Modular Power Sharing in DC-DC Converters(Institute of Electrical and Electronics Engineers Inc., 2021) Roy, S.; Joisher, M.; Hanson, A.J.Modular power conversion systems can have a variety of potential advantages, including high thermal contact area, reliability, repairability, wide operating range, the use of devices with reduced voltage and/or current ratings and better Figure of merit, and overall small parasitics to enable high-frequency operation even at high power. In order to ensure power sharing among modules, most approaches adopt a centralized or distributed approach which require communication with a central controller or among modules, which increases the opportunity for global system failure and impedes modularity. In this paper, we present a truly decentralized control approach (one with no communication between modules) for power sharing in modular converters. Each module's controller implements a nonlinear 'selfish' control algorithm, wherein the increment or decrement in its power at any time instant is a function of its present contribution to the overall output power. That is, modules currently processing high power respond strongly when less power is required, but weakly when more power is required (and vice versa for modules currently processing low power). The successful operation of the proposed control strategy is first verified using simulation results which show its fast convergence and stable operation in IPOP, ISOP, IPOS and ISOS configurations without changing any physical or control parameters. Further validation is presented through the successful operation of a hardware prototype when arranged in different modular configurations, as well as its stable operation over load transients and in the event of module failure. © 2021 IEEE.Item A Low Mismatch Current Steering Charge Pump for High-Speed PLL(Springer Science and Business Media Deutschland GmbH, 2023) Roy, S.; Lad, K.H.; Rekha, S.; Laxminidhi, T.This paper presents the design of a charge pump based on the current steering and positive feedback topology to support application in high-speed PLLs. The primary objective of the design is to counter current mismatch in charging and discharging currents as well as maintain fast operation with the help of positive feedback assisted current steering topology. This charge pump is designed in UMC 65nm CMOS technology and its functionality, characteristics and amount of current mismatch are verified across voltage and temperature variations. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.Item QGAPHnet : Quantum Genetic Algorithm Based Hybrid QLSTM Model for Soil Moisture Estimation(Institute of Electrical and Electronics Engineers Inc., 2024) Sai, S.; Sen, A.; Mallick, C.; Mallik, A.; Sen, U.; Paul, M.; Sutradhar, A.; Roy, S.Soil moisture, pH, soil temperature, humidity among other factors play a pivotal role in affecting the agricultural productivity of a region, influencing factors such as crop yield, organic carbon estimation, and crop growth analysis. This paper introduces a comprehensive investigation into soil moisture and temperature dynamics, employing a dynamic soil moisture dataset. Utilising Quantum Long Short Term Memory (QLSTM), we apply Quantum Genetic Algorithm (QGA) and Particle Swarm Optimisation (PSO) to study and predict patterns within the dataset. Our approach not only enhances the precision of soil moisture estimations but also provides a novel perspective on environmental factors. The findings from this study hold significant implications for understanding and managing soil moisture in diverse contexts, spanning agriculture, hydrology, and ecosystem studies. © 2024 IEEE.Item A Survey of Hyperparameter Selection Methods for Weather Forecasting Using State-of-the-Art Machine Learning Algorithms(Springer Science and Business Media Deutschland GmbH, 2025) Sen, A.; Sen, U.; Paul, M.; Sutradhar, A.; Vankala, T.N.; Mallick, C.; Mallik, A.; Roy, A.; Sai, S.; Roy, S.Weather forecasting is an important aspect across various sectors, but the intricate dynamics of weather systems pose a challenge for conventional statistical models to forecast accurately. Besides auto-regressive time forecasting models like ARIMA, deep learning architectures like ANNs, LSTMs, and GRU networks have been shown to enhance the accuracy of forecasts by considering temporal dependencies. This paper studies various machine learning models like XGBoost, SVR, KNN Regressor, Random Forest Regressor and the application of metaheuristic algorithms, like Genetic Algorithm (GA), Differential Evolution (DE), and Particle Swarm Optimization (PSO), on some deep learning model architectures like ANNs, LSTMs and GRUs, to automate the process of finding the best hyperparameters for the models. Furthermore, this paper explores the Quantum LSTM (QLSTM) network and novel QLSTM Ensemble models. We conduct a comparative study of these model structures, evaluating their effectiveness in weather prediction using measures such as Mean Squared Error (MSE) and Mean Absolute Percentage Error (MAPE). The findings underscore the capabilities of metaheuristic algorithms and innovative quantum methods in enhancing the precision of weather forecasts. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.Item A study about color normalization methods for histopathology images(Elsevier Ltd, 2018) Roy, S.; Kumar Jain, A.K.; Lal, S.; Kini, J.R.Histopathology images are used for the diagnosis of the cancerous disease by the examination of tissue with the help of Whole Slide Imaging (WSI) scanner. A decision support system works well by the analysis of the histopathology images but a lot of problems arise in its decision. Color variation in the histopathology images is occurring due to use of the different scanner, use of various equipments, different stain coloring and reactivity from a different manufacturer. In this paper, detailed study and performance evaluation of color normalization methods on histopathology image datasets are presented. Color normalization of the source image by transferring the mean color of the target image in the source image and also to separate stain present in the source image. Stain separation and color normalization of the histopathology images can be helped for both pathology and computerized decision support system. Quality performances of different color normalization methods are evaluated and compared in terms of quaternion structure similarity index matrix (QSSIM), structure similarity index matrix (SSIM) and Pearson correlation coefficient (PCC) on various histopathology image datasets. Our experimental analysis suggests that structure-preserving color normalization (SPCN) provides better qualitatively and qualitatively results in comparison to the all the presented methods for breast and colorectal cancer histopathology image datasets. © 2018 Elsevier LtdItem A Comprehensive Review on the Use of Wastewater in the Manufacturing of Concrete: Fostering Sustainability through Recycling(Multidisciplinary Digital Publishing Institute (MDPI), 2024) Maddikeari, M.; Das, B.B.; Tangadagi, R.B.; Roy, S.; Priyanka, P.B.; Ramachandra, M.L.The primary aim of this review article is to find the influence of wastewater and its characteristics on recycling as an alternative to potable water for concrete preparation. On the other hand, scarcity, and the demand for freshwater for drinking are also increasing day by day around the globe. About a billion tons of freshwater is consumed daily for concrete preparation for various operations such as mixing and curing, to name a few. The rapid development of certain industries such as textile, casting, stone cutting, and concrete production has caused the water supply to be severely affected. Recycling wastewater in concrete offers various potential benefits like resource conservation, environmental protection, cost savings, and enhanced sustainability. This article reviews the effect of various types of wastewater on various physical and chemical properties of wastewater, rheological characteristics, strength, durability, and microstructure properties of concrete. It also explores the potential effects of decomposing agents on enhancing concrete properties. Currently, limited research is available on the use of various types of wastewater in concrete. Hence, there is a need to develop various methods and procedures to ensure that the utilization of wastewater and treated wastewater is carried out in the production of concrete in a sustainable manner. Although wastewater can reduce the workability of fresh concrete, it can also increase its strength and long-term performance of concrete. The use of various types of wastewater, such as reclaimed water and tertiary-treated wastewater, was found to be superior compared to those using industrial- or secondary-treated wastewater. Researchers around the globe agree that wastewater can cause various detrimental effects on the mechanical and physical properties of concrete, but the reductions were not significant. To overcome limited scientific contributions, this article reviews all the available methods of using various types of wastewater to make concrete economically and environmentally friendly. This research also addresses possible challenges with respect to the demand for freshwater and the water crisis. © 2024 by the authors.Item Rhodamine-based Cu2+-selective fluorosensor: Synthesis, mechanism, and application in living cells(2013) Sikdar, A.; Roy, S.; Haldar, K.; Sarkar, S.; Panja, S.S.A rhodamine B-based fluorescence probe (1) for the sensitive and selective detection of Cu2+ ion has been designed and synthesized using pyridine moiety. The optical properties of this compound have been investigated in acetonitrile-water binary solution (7:3 v/v). Compound 1 is found to be an excellent sensor for a biologically/physiologically very important transition metal ion (Cu2+) using only the two very different modes of measurements (absorption and emission); one case displayed intensity enhancement whereas in other case showed intensity depletion (quenching). A mechanistic investigation has been performed to explore the static nature of quenching process. The sensor has been found to be very effective in sensing Cu 2+ ion inside living cells also. © 2013 Springer Science+Business Media New York.Item Influence of mixed convection in an exponentially decreasing external flow velocity(Elsevier Ltd, 2017) Patil, P.M.; Ramane, H.S.; Roy, S.; Hindasageri, V.; Momoniat, E.This article explores the influence of mixed convection in a steady incompressible laminar boundary layer flow for an exponentially decreasing free stream velocity in presence of surface mass transfer and heat source or sink. The nonlinear partial differential equations governing the flow and thermal fields are expressed in dimensionless form with the help of suitable non-similar transformations. The mathematical complexities in obtaining non-similar solutions at the leading edge of the streamwise coordinate as well as non-similarity variable ? have overcome by using the implicit finite difference scheme in conjunction with Quasi-linearization technique by choosing an appropriate finer step sizes along the streamwise direction. The effects of various dimensionless physical parameters on velocity and thermal fields are analysed. © 2016 Elsevier LtdItem Structure sensitive photocatalytic reduction of nitroarenes over TiO2(Nature Publishing Group Houndmills Basingstoke, Hampshire RG21 6XS, 2017) Challagulla, S.; Tarafder, K.; Ganesan, R.; Roy, S.It is a subject of exploration whether the phase pure anatase or rutile TiO2 or the band alignment due to the heterojunctions in the two polymorphs of TiO2 plays the determining role in efficacy of a photocatalytic reaction. In this work, the phase pure anatase and rutile TiO2 have been explored for photocatalytic nitroarenes reduction to understand the role of surface structures and band alignment towards the reduction mechanism. The conduction band of synthesized anatase TiO2 has been found to be more populated with electrons of higher energy than that of synthesized rutile. This has given the anatase an edge towards photocatalytic reduction of nitroarenes over rutile TiO2. The other factors like adsorption of the reactants and the proton generation did not play any decisive role in catalytic efficacy. © 2017 The Author(s).