Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
49 results
Search Results
Item Big Data Analytics for Industry 5.0(wiley, 2025) Hegde, A.; Bhowmik, B.The steam engine's power, the assembly line's efficiency, and the computer's processing speed: these disruptive new technologies were the driving forces behind the first three industrial revolutions. The fourth industrial revolution, also known as Industry 4.0, is propelled by intelligent technologies. Industry 5.0, the fifth industrial revolution, fosters collaboration between humans and robots, thereby enhancing Industry 4.0 technologies. It is anticipated that this will generate employment that is more valuable, thereby allowing individuals to engage in more creative and design-oriented activities. It is possible for factories to remain competitive and adjust to the changing requirements of their customers by implementing this change. With the implementation of suitable investments, Industry 5.0 has the potential to foster economic growth and establish a more sustainable, collaborative future for both humans and machines. Finance, healthcare, retail, and manufacturing are among the sectors that have already experienced this transformation. Industries 5.0 has been rendered feasible by technologies including blockchain, cloud computing, Big Data Analytics (BDA), Internet of Things (IoT), and 6G networks. The administration of substantial quantities of data is facilitated by BDA, in particular. To optimize the utilization of human resources and minimize waste and inefficiency, sophisticated big data management and analysis systems implement artificial intelligence and machine learning techniques. Furthermore, the enhanced customization, precision, and productivity of Industry 5.0, which is a component of the IoT, are ensured by the increased use of intelligent devices and sensors. This chapter outlines the current trends, design principles, and applications of Industry 5.0. This chapter outlines the fundamentals of Industry 5.0, its emergence, and the significance of BDA as a technology. Furthermore, this chapter outlines the architecture, design principles, and opportunities that are linked to Industry 5.0, including optimization of human efficiency, personalized services, enhanced automation, and higher-value employment. In this chapter, Industry 5.0 faces a variety of obstacles, such as a scarcity of qualified workers, a time-consuming process, a substantial budget requirement, and security and privacy concerns. Furthermore, this chapter provides a comprehensive analysis of the most recent developments in the field, the paradigm shift toward Industry 5.0, and a diverse array of prospective futures. This chapter outlines the primary challenges, interests, and problems of Industry 5.0 in relation to BDA. © 2025 by John Wiley & Sons Inc. All rights reserved.Item Electrodeposited Ni-P alloy thin films for alkaline water splitting reaction(Institute of Physics Publishing michael.roberts@iop.org, 2016) Elias, L.; Damle, V.H.; Hegde, A.Ni-P alloy thin films was developed as a robust electrode material for alkaline water splitting for hydrogen evolution reaction (HER) and oxygen evolution reaction (OER), through electrodeposition technique. The influence of alloy composition, achieved through induced codeposition of the reluctant non-metal, i.e. phosphorous (P) on its electrocatalytic activity was studied, and arrived at the best composition of alloy for HER and OER. The water splitting efficacy of the alloy films was tested in 1.0 M KOH using electrochemical methods such as cyclic voltammetry and chronopotentiometry. The experimental observation shows that the alloy thin film with 9.0 wt.% of P and 4.2 wt.% of P are the best electrode materials for HER and OER, respectively. The electrocatalytic performance of alloy films towards HER and OER were related to its surface topography, composition and crystal structure through field emission scanning electron microscopy (FESEM), energy dispersive spectroscopy (EDS) and X-ray diffraction (XRD) analyses, respectively. © Published under licence by IOP Publishing Ltd.Item Synthesis of Ni-W-Graphene oxide composite coating for alkaline hydrogen production(Elsevier Ltd, 2018) Elias, L.; Hegde, A.Nickel-Tungsten-Graphene oxide (Ni-W-GO) composite coating was developed through direct electrolysis method, and its electrocatalytic activity for alkaline water splitting reaction was studied. The development of composite coating with a homogeneous dispersion of GO was achieved using an optimal Ni-W plating bath loaded with GO. The electrocatalytic efficacy of the coating for hydrogen evolution reaction (HER) was tested using cyclic voltammetry and chronopotentiometry techniques in 1.0 M KOH medium. The variation in electrocatalytic activity with the addition of GO was studied. A significant increase in the electrocatalytic activity towards HER was found. The improvement in electrocatalytic activity of Ni-W-GO composite coating was ascribed to the intersticed GO nanoparticles in the alloy matrix, evidenced by different advanced methods of analyses, like Scanning electron microscopy (SEM), Energy dispersive spectroscopy (EDS) and X-ray diffraction (XRD). © 2018 Elsevier Ltd.Item A comparative study on the electrocatalytic activity of electrodeposited Ni-W and Ni-P alloy coatings(Elsevier Ltd, 2018) Elias, L.; Hegde, A.Bright Ni-W and Ni-P alloy coatings were synthesized through direct electrolysis from an aqueous alkaline citrate bath. The effect of alloying elements, W and P, on the electrocatalytic activity of Ni was studied, based on their induced codeposition behavior and related to the composition, structure and surface morphology of the developed coatings. The electrocatalytic activity of the alloy coatings towards hydrogen evolution reaction (HER) was studied using electrochemical techniques such as cyclic voltammetry (CV) and chronopotentiometry (CP), in 1. M KOH medium. A comparison of the electrocatalytic efficiencies of these Ni-based alloys was made in consideration with its physical and electrochemical characteristics. The obtained results showed that the alloying of Ni with W gives superior properties towards HER, attributed by its better hydrogen adsorption energy than in Ni-P alloy. The surface appearance, chemical composition and phase structure of the coatings were studied using SEM, EDS and XRD analyses, respectively. © 2018 Elsevier Ltd. All rights reserved.Item Prediction of reflection coefficient of a perforated Quarter Circle Breakwater using artificial neural network (ann)(Institute of Physics Publishing helen.craven@iop.org, 2019) Ramesh, N.; Hegde, A.; Rao, S.A breakwater is structure which is generally adopted in not only protecting the shoreline, but also in creating tranquil zone on the lee side of the structure minimizing the various movements on the anchored ships / vessels due to the wave / tidal action in the region resulting in easy handling of goods. Over the years, breakwater was generally constructed using rubble mounds. Due to the increase in demand for the coastal development all over the world, many innovative Breakwater were evolved as against the rubble mound. In the recent times, in order to economize the innovative breakwater construction, Semi Circular caisson type Breakwater has been studied. Based on Semi circularBreakwater (SBW), Quarter circular Breakwater (QBW) has been evolved. The hydrodynamic performance of a coastal structure is important, because it involves many parameters to be considered while designing a safe and economical structure. The hydro-dynamic performance of a Quarter circular breakwater is studied in a monochromatic wave flume in the Department of Applied Mechanics and Hydraulics, National Institute of Technology, Surathkal Karnataka, India. In the present paper reflection coefficient (Kr) of a perforated Quarter circular Breakwater (QBW) with various S/D ( spacing to diameter ratio) values is predicted applying Artificial Neural Network (ANN) technique using MATLAB. Four networks were constructed by varying the number of hidden layers based on the input parameters, which affects the performance of the breakwater. The predicted values of reflection coefficient using ANN, are compared with the experimental results. © Published under licence by IOP Publishing Ltd.Item Overview of the Shared Task on Machine Translation in Dravidian Languages(Association for Computational Linguistics (ACL), 2022) Anand Kumar, A.M.; Hegde, A.; Banerjee, S.; Chakravarthi, B.R.; Priyadarshini, R.; Shashirekha, H.L.; Mccrae, J.P.This paper presents an outline of the shared task on translation of under-resourced Dravidian languages at DravidianLangTech-2022 workshop to be held jointly with ACL 2022. A description of the datasets used, approach taken for analysis of submissions and the results have been illustrated in this paper. Five sub-tasks organized as a part of the shared task include the following translation pairs: Kannada to Tamil, Kannada to Telugu, Kannada to Sanskrit, Kannada to Malayalam and Kannada to Tulu. Training, development and test datasets were provided to all participants and results were evaluated on the gold standard datasets. A total of 16 research groups participated in the shared task and a total of 12 submission runs were made for evaluation. Bilingual Evaluation Understudy (BLEU) score was used for evaluation of the translations. © 2022 Association for Computational Linguistics.Item A Study of Machine Translation Models for Kannada-Tulu(Springer Science and Business Media Deutschland GmbH, 2023) Hegde, A.; Shashirekha, H.L.; Anand Kumar, M.; Chakravarthi, B.R.Over the past ten years, neural machine translation (NMT) has seen tremendous growth and is now entering a phase of maturity. Despite being the most popular solution for machine translation (MT), it performs sub-optimally on under-resourced language pairs due to lack of parallel corpora as compared to high-resourced language pairs. The implementation of NMT techniques for under-resourced language pairs is receiving the attention of researchers and has resulted in a significant amount of research for many under-resourced language pairs. In view of the growth of MT, this paper describes a set of practical approaches for investigating MT between Kannada and Tulu. These two languages belong to the family of Dravidian languages and are under-resourced due to lack of tools and resources particularly the parallel corpus for MT. Since there are no parallel corpora for the Kannada-Tulu language pair for MT, this work aims to construct a parallel corpus for this language pair. As manual construction of parallel corpus is laborious, data augmentation is introduced to enhance the size of the parallel corpus along with suitable preprocessing techniques. Different NMT schemes such as recurrent neural network (RNN) baseline, bidirectional recurrent neural network (BiRNN), transformer-based NMT with and without subword tokenization, and statistical machine translation (SMT) models are implemented for MT of Kannada-Tulu and Tulu-Kannada language pairs. Empirical results reveal that the impact of data augmentation increases the bilingual evaluation understudy (BLEU) score of the proposed models. Transformer-based models with subword tokenization outperformed the other models with BLEU scores 41.82 and 40.91 for Kannada-Tulu and Tulu-Kannada MT, respectively. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.Item Effective Resource Utilization in Hadoop Using Ganglia(Institute of Electrical and Electronics Engineers Inc., 2024) Srungarapati, B.; Pamarthi, M.; Vakada, V.; Hegde, A.; Bhowmik, B.The exponential growth of big data has led to the widespread adoption of Hadoop clusters for storing and processing large volumes of data. Efficient management of resources within these clusters is crucial for achieving optimal performance and cost efficiency. This research paper explores the use of Hadoop and Ganglia for monitoring and optimizing resource utilization in Hadoop clusters. The study demonstrates that leveraging Hadoop and Ganglia is an effective strategy for improving cluster performance and resource efficiency. Results show significant enhancements in cluster performance and resource utilization, highlighting the importance of proactive resource management in Hadoop environments. © 2024 IEEE.Item Advancements in Credit Scoring, Profit Scoring, and Portfolio Optimization for P2P Lending(Institute of Electrical and Electronics Engineers Inc., 2024) Nayaka, P.; Hegde, A.; Bhowmik, B.The Peer-to-peer (P2P) lending platform allows borrowers to connect directly with lenders outside traditional banking systems. Therefore, for the sustainability of these platforms, they must accurately assess the credit risk and profitability of the loans. Various credit scoring techniques, including Logistic Regression, neural networks, and ensemble methods, can be used to estimate the likelihood of borrower default. It is imperative to analyze the profit the lenders generated and enhance the credit scoring so that the investors face minimum loss. Once the profit analysis is done, then it is crucial to advise the investors about the portfolio of loans. This paper presents recent credit scoring, profit scoring, and portfolio optimization trends for P2P lending. We highlight the significant issues in incorporating machine learning models into credit scoring systems. The analysis emphasizes the need for a data-driven approach to perfecting lending practices, thus benefiting both borrowers and investors in the rapidly changing P2P landscape. © 2024 IEEE.Item Optimizing Feature Selection in Big Data: A Hybrid Spark and Fuzzy Approach(Institute of Electrical and Electronics Engineers Inc., 2024) Hada, A.S.; Sahoo, G.S.; Vamsi, C.K.; Hegde, A.; Bhowmik, B.The exponential growth of big data presents both immense opportunities and significant challenges. While vast datasets hold the key to unlocking groundbreaking insights, efficiently extracting value requires sophisticated feature selection techniques. Traditional methods often struggle with the sheer volume and complexity of big data. This paper addresses this challenge by proposing a novel hybrid feature selection algorithm by leveraging Apache PySpark's distributed computing power. Combining a robust feature selection technique with a novel weighting scheme, our method outperforms existing hypercuboid and fuzzy Rough Set methods. The hybrid approach achieves superior accuracy of 72.1% with a reduced feature set, demonstrating its effectiveness in identifying salient features for big data analysis. © 2024 IEEE.