Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
8 results
Search Results
Item Fog-Based Intelligent Machine Malfunction Monitoring System for Industry 4.0(IEEE Computer Society, 2021) Natesha, B.V.; Guddeti, R.M.R.There is an exponential increase in the use of Industrial Internet of Things (IIoT) devices for controlling and monitoring the machines in an automated manufacturing industry. Different temperature sensors, pressure sensors, audio sensors, and camera devices are used as IIoT devices for pipeline monitoring and machine operation control in the industrial environment. But, monitoring and identifying the machine malfunction in an industrial environment is a challenging task. In this article, we consider machines fault diagnosis based on their operating sound using the fog computing architecture in the industrial environment. The different computing units, such as industrial controller units or micro data center are used as the fog server in the industrial environment to analyze and classify the machine sounds as normal and abnormal. The linear prediction coefficients and Mel-frequency cepstral coefficients are extracted from the machine sound to develop and deploy supervised machine learning (ML) models on the fog server to monitor and identify the malfunctioning machines based on the operating sound. The experimental results show the performance of ML models for the machines sound recorded with different signal-to-noise ratio levels for normal and abnormal operations. © 2021 IEEE.Item Machine Learning for Vortex Flowmeter Design(Institute of Electrical and Electronics Engineers Inc., 2022) Thummar, D.; Reddy, Y.J.; Venugopal, V.Vortex flowmeters are one of the broadly used flow measurement devices in various industrial applications. The shape of the bluff body is the most critical parameter in the design of vortex flowmeter. The conventional approach of bluff body design relies on parametric shape optimization of a bluff body using experimentation and computational fluid dynamics simulations, which are expensive and time-consuming. In this study, we propose a novel machine learning (ML)-based approach to design bluff body shapes. Two ML models are developed using supervised ML using an artificial neural network (ANN). The first model predicts new optimum bluff body shapes for a given input flow characteristic. The second model predicts the deviation in Strouhal number for a given bluff body to determine its optimality. Data from the literature on the geometry of bluff bodies and fluid flow properties such as blockage ratio, Reynolds number, and Strouhal number are used for training ML models. The obtained ML results are in close agreement (±3.0%) compared with the computational fluid dynamics simulation results. This approach may find broad applicability for designing other fluid flowmeters. © 1963-2012 IEEE.Item Numerical modeling of straight and helical elastic rods under fluid flow using immersed boundary method(Elsevier Ltd, 2022) Maniyeri, R.This paper presents a three-dimensional computational model built using immersed boundary finite volume method to explore the dynamics of straight and helical elastic rods rotating under an applied fluid flow in a channel. Numerical simulations are done for low and high rotational frequencies of a base motor attached at one fixed end of the rods. Simulations reveal that under low rotational frequency, a straight rod (bend at free end) always performs stable twirling motion and eventually attains straight state (mechanical equilibrium) under an applied fluid flow. But on the other hand, for the same conditions a helical rod always keeps its helical shape during interaction with fluid and never attains stable straight state. For the case of high rotational frequency, the straight rod executes whirling motion in which it attains helical shape during all the time. Whirling motion is also observed for helical rod under high rotational frequency. For similar conditions, the instantaneous shapes obtained by straight and helical rods are different which indicates that the initial configuration of the rod as well as rotational frequency have significant impact in deciding the dynamics of the elastic rod under fluid flow. In the biological realm, these elastic rods represent flagellum of monotrichous bacteria which helps for propulsion in fluid. Hence, the present simulation results will help to develop efficient bacteria inspired artificial microrobot for biomedical applications. © 2022Item DPPNet: An Efficient and Robust Deep Learning Network for Land Cover Segmentation From High-Resolution Satellite Images(Institute of Electrical and Electronics Engineers Inc., 2023) Sravya, N.; Priyanka; Lal, S.; Nalini, J.; Chintala, C.S.; Dell’Acqua, F.Visual understanding of land cover is an important task in information extraction from high-resolution satellite images, an operation which is often involved in remote sensing applications. Multi-class semantic segmentation of high-resolution satellite images turned out to be an important research topic because of its wide range of real-life applications. Although scientific literature reports several deep learning methods that can provide good results in segmenting remotely sensed images, these are generally computationally expensive. There still exists an open challenge towards developing a robust deep learning model capable of improving performances while requiring less computational complexity. In this article, we propose a new model termed DPPNet (Depth-wise Pyramid Pooling Network), which uses the newly designed Depth-wise Pyramid Pooling (DPP) block and a dense block with multi-dilated depth-wise residual connections. This proposed DPPNet model is evaluated and compared with the benchmark semantic segmentation models on the Land-cover and WHDLD high-resolution Space-borne Sensor (HRS) datasets. The proposed model provides DC, IoU, OA, Ka scores of (88.81%, 78.29%), (76.35%, 60.92%), (87.15%, 81.02%), (77.86%, 72.73%) on the Land-cover and WHDLD HRS datasets respectively. Results show that the proposed DPPNet model provides better performances, in both quantitative and qualitative terms, on these standard benchmark datasets than current state-of-art methods. © 2017 IEEE.Item FedCure: A Heterogeneity-Aware Personalized Federated Learning Framework for Intelligent Healthcare Applications in IoMT Environments(Institute of Electrical and Electronics Engineers Inc., 2024) Sachin, D.N.; Annappa, B.; Hegde, S.; Abhijit, C.S.; Ambesange, S.The advent of the Internet of Medical Things (IoMT) devices has led to a healthcare revolution, introducing a new era of smart applications driven by Artificial Intelligence (AI). These advanced technologies have greatly influenced the healthcare industry and have played a crucial role in enhancing the quality of life globally. Federated Learning (FL) has become popular as a technique to create models that can be shared universally using the vast datasets collected from IoMT devices while maintaining data privacy. However, the complex variations in IoMT environments, including diverse devices, data characteristics, and model complexities, create challenges for the straightforward application of traditional FL methods. Consequently, it is not well-suited for deployment in such contexts. This paper introduces FedCure, a personalized FL framework tailored for intelligent IoMT-based healthcare applications operating within a cloud-edge architecture. FedCure is adept at addressing the challenges within IoMT environments by employing personalized FL techniques that can effectively mitigate the impact of heterogeneity. Furthermore, the integration of edge computing technology enhances processing speed and minimizes latency in intelligent IoMT applications. Lastly, this research showcases several case studies encompassing IoMT-based applications, such as Eye Retinopathy Detection, Diabetes Monitoring, Maternal Health, Remote Health Monitoring, and Human Activity Recognition. These case studies provide a means to assess the effectiveness of the proposed FedCure framework and showcase exceptional performance with accuracy and minimal communication overhead, especially in addressing the challenges posed by heterogeneity. © 2013 IEEE.Item Driving Cycle-Based Design Optimization and Experimental Verification of a Switched Reluctance Motor for an E-Rickshaw(Institute of Electrical and Electronics Engineers Inc., 2024) Bhaktha, B.S.; Jose, N.; Vamshik, M.; Pitchaimani, J.; Gangadharan, K.V.This article deals with the design and optimization of a 2 kW switched reluctance motor (SRM) for an electric rickshaw (E-rickshaw). Previously published research on SRM optimization has mostly focused on the optimization of their design and control variables only at the rated conditions. In electric vehicle (EV) applications, the load operating points (LOPs) of a traction motor are dynamic and spread widely across the torque speed envelope. To enhance their overall performance, it is vital to include them in the design optimization process; therefore, in this article, a novel procedure for implementing the multiobjective design optimization (MODO) of an SRM based on a driving cycle has been demonstrated. Higher starting torque and torque density with reduced electromagnetic losses throughout the driving cycle are established as the design objectives, subject to practical restrictions on current density and slot fill factor. The design objectives have been accurately evaluated through transient finite element analysis (FEA) and a computationally efficient SRM drive model (developed in MATLAB/Simulink) with consideration of the excitation control parameters. Kriging models have been constructed to reduce the computation cost of FEA during the optimization process. Then, a nondominated sorting genetic algorithm II (NSGA II) based multiobjective optimization coupled with the constructed Kriging models is conducted to generate a Pareto front. An optimal design that offers the best balance between the design objectives is selected from the Pareto-optimal set, and the dimensions of corresponding design variables are used to build a prototype. Finally, the static and dynamic performance of the SRM prototype are experimentally evaluated and validated with the FEA simulations. © 2024 IEEE.Item Downscaled XCO2 Estimation Using Data Fusion and AI-Based Spatio-Temporal Models(Institute of Electrical and Electronics Engineers Inc., 2024) Pais, S.M.; Bhattacharjee, S.; Anand Kumar, M.; Chen, J.One of the well-known greenhouse gases (GHGs) produced by anthropogenic human activity is carbon dioxide (CO2). Understanding the carbon cycle and how negatively it affects the ecosystem requires analysis of the rise in CO2 concentration. This work aims to map CO2 concentration for the entire surface, making it useful for regional carbon cycle analysis. Here, column-averaged CO2 dry mole fraction, called XCO2, measured by the orbiting carbon observatory-2 (OCO-2) satellite, is used. Because of spectral interference by the clouds and aerosols, there are many missing footprints in the Level-2 swath of OCO-2, making it disruptive to understand any assessment related to the carbon cycle. The objective of this work is to predict 1 km2 XCO2 using data resampling and machine learning models. This work achieves a minimum mean absolute error (MAE) and root mean square error (RMSE) of 0.3990 and 0.8090 ppm, using the monthly models. © 2004-2012 IEEE.Item Channel Pruning of Transfer Learning Models Using Novel Techniques(Institute of Electrical and Electronics Engineers Inc., 2024) Pragnesh, P.; Mohan, B.R.This research paper delves into the challenges associated with deep learning models, specifically focusing on transfer learning. Despite the effectiveness of widely used models such as VGGNet, ResNet, and GoogLeNet, their deployment on resource-constrained devices is impeded by high memory bandwidth and computational costs, and to overcome these limitations, the study proposes pruning as a viable solution. Numerous parameters, particularly in fully connected layers, contribute minimally to computational costs, so we focus on convolution layers' pruning. The research explores and evaluates three innovative pruning methods: the Max3 Saliency pruning method, the K-Means clustering algorithm, and the Singular Value Decomposition (SVD) approach. The Max3 Saliency pruning method introduces a slight variation by using the three maximum values of the kernel instead of all nine to compute the saliency score. This method is the most effective, substantially reducing parameter and Floating Point Operations (FLOPs) for both VGG16 and ResNet56 models. Notably, VGG16 demonstrates a remarkable 46.19% reduction in parameters and a 61.91% reduction in FLOPs. Using the Max3 Saliency pruning method, ResNet56 shows a 35.15% reduction in parameters and FLOPs. The K-Means pruning algorithm is also successful, resulting in a 40.00% reduction in parameters for VGG16 and a 49.20% reduction in FLOPs. In the case of ResNet56, the K-Means algorithm achieved a 31.01% reduction in both parameters and FLOPs. While the Singular Value Decomposition (SVD) approach provides a new set of values for condensed channels, its overall pruning ratio is smaller than the Max3 Saliency and K-Means methods. The SVD pruning method prunes 20.07% parameter reduction and a 24.64% reduction in FLOPs achieved for VGG16, along with a 16.94% reduction in both FLOPs and parameters for ResNet56. Compared with the state-of-the-art methods, the Max3 Saliency and K-Means pruning methods performed better in Flops reduction metrics. © 2024 The Authors.