Browsing by Author "Parida, S."

Now showing 1 - 4 of 4

Attention Assisted Patch-Wise CNN forÂ theÂ Segmentation ofÂ Fluids fromÂ theÂ Retinal Optical Coherence Tomography Images
(Springer Science and Business Media Deutschland GmbH, 2024) Anoop, B.N.; Parida, S.; Ajith, B.; Girish, G.N.; Kothari, A.R.; Kavitha, M.S.; Rajan, J.
Optical Coherence Tomography (OCT) is an important imaging modality in ophthalmology to visualize the abnormalities present in the retina. One of the major reasons for blindness is the accumulation of fluids in the various layers of the retina called retinal cysts. Accurate estimation of the type of cyst and its volume is important for effective treatment planning. In this paper, we propose attention assisted convolutional neural network-based architecture to detect and quantify three types of retinal cysts namely the intra-retinal cyst, sub-retinal cyst and pigmented epithelial detachment from the OCT images of the human retina. The proposed architecture has an encoder-decoder structure with an attention and a multi-scale module. The qualitative and quantitative performance of the model is evaluated on the publicly available RETOUCH retinal OCT fluid detection challenge data set. The proposed model outperforms the state-of-the-art methods in terms of precision, recall, and dice coefficient. Furthermore, the proposed model is computationally efficient due to its less number of model parameters. Â© Springer Nature Switzerland AG 2024.
Enhancing safety in surface mine blasting operations with IoT based ground vibration monitoring and prediction system integrated with machine learning
(Nature Research, 2025) Mangalpady, M.; Vardhan, H.; Tripathi, A.K.; Parida, S.; RajaSekhar Reddy, N.V.; Sivalingam, K.M.; Yingqiu, L.; Elumalai, P.V.
Monitoring and predicting ground vibration levels during blasting operations is essential to safeguard mining sites and surrounding communities. This study introduces an IoT-based ground vibration monitoring device specifically designed for limestone mining operations, combined with machine learning algorithms to predict ground vibration intensity. The primary aim is to provide an efficient predictive tool for anticipating hazardous vibration levels, enabling proactive safety measures. A comparative analysis with the industry-standard Minimate Blaster indicates high accuracy of the IoT device, with percentage errors as low as 0.803% across multiple blasts. The study also employed Support Vector Regression (SVR), Gradient Boosting Regression (GBR), and Random Forest (RF) algorithms to predict Peak Particle Velocity (PPV) values. Among these, the Random Forest model outperformed the others, achieving an R2 score of 0.92, Mean Absolute Error (MAE) of 0.21, and Root Mean Squared Error (RMSE) of 0.31. These findings underscore the reliability and predictive accuracy of the IoT-integrated Random Forest model, suggesting that it can significantly contribute to enhancing safety and operational efficiency in mining. The research highlights the potential of IoT and machine learning technologies to transform ground vibration monitoring, promoting safer and more sustainable mining practices. © The Author(s) 2025.
Integrated smart dust monitoring and prediction system for surface mine sites using IoT and machine learning techniques
(Nature Research, 2024) Tripathi, A.K.; Mangalpady, M.; Parida, S.; Durgesh Nandan, D.; Elumalai, P.V.; Prakash, E.; Joshua Ramesh Lalvani, J.S.C.; Koppula, K.S.
The mining industry confronts significant challenges in mitigating airborne particulate matter (PM) pollution, necessitating innovative approaches for effective monitoring and prediction. This research focuses on the design and development of an Internet of Things (IoT)-based real-time monitoring system tailored for PM pollutants in surface mines, specifically PM 1.0, PM 2.5, PM 4.0, and PM 10.0. The novelty of this work lies in the integration of IoT technology for real-time measurement and the application of machine learning (ML) techniques for accurate prediction based on recorded dust pollutants data. The study's findings indicate that PM 1.0 pollutants exhibited the highest concentration in the atmosphere of the ball clay surface mine sites, with the stockyard site registering the maximum levels of PM pollutants (28.45 µg/m3, 27.89 µg/m3, 26.17 µg/m3, and 27.24 µg/m3, respectively) due to the dry nature of clay materials. Additionally, the research establishes four ML models—Decision Tree (DT), Gradient Boosting Regression (GBR), Random Forest (RF), and Linear Regression (LR)—for predicting PM pollutant concentrations. Notably, Random Forest demonstrates superior performance with the lowest Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) at 1.079 and 1.497, respectively. This comprehensive solution, combining IoT-based monitoring and ML-based prediction, contributes to sustainable mining practices, safeguarding worker well-being, and preserving the environment. © The Author(s) 2024.
Laboratory investigation of photovoltaic panel performance under the shaded condition
(Institute of Electrical and Electronics Engineers Inc., 2020) Tripathi, A.K.; Mangalpady, M.; Ray, S.; Parida, S.
The most encouraging use of solar energy is its conversion into electrical energy by using solar photovoltaic (PV) panel. The performance of solar-based PV panel is undoubtedly influenced by the quantity of solar radiation, which is reaching on the panel surface. The occurrence of shading over the panel surface is a vital environmental phenomenon which affects the penetration of solar radiation to reach the overall surface area of photovoltaic cells. The shading on PV panels may happen due to trees, the formation of mists, accumulation of dirt elements on the panel surface, close by long-standing structures, shadows of different panels in its region, neighbouring structures and so on. This paper is mainly focused on the study of shading impact on the panel performance. Further, this paper also observed the influence of shading on the variation of surface temperature of the PV panel. The present study shown a significant reduction of 41.40% in the maximum power output (Pmax) of the panel due to 25% shading strength of the single cell in the panel. Moreover, it was also observed that the increase in the percentage shading strength over the panel surface shifts the maximum power point (MPP), of the panel characteristics, towards the lower output voltage, which affects the effective operation of the charge controller. Further, it was seen that the shading impact degrades the performance of the panel as well as in charge of the rise of the surface temperature of the panel. In the present investigation, it was observed that the temperature of the unshaded cell rises at the rate of 1.753%, due to the shading phenomena over the panel surface. Â© 2020 IEEE.