Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
7 results
Search Results
Item Ensemble RDLR Architecture for Short-Term Solar Power Forecasting(Institute of Electrical and Electronics Engineers Inc., 2024) Ayappane, H.; Kashyap, Y.Given the drastic shift of global sentiment towards renewable energy, it becomes incredibly important to match supply with demand. However the highly variable nature of weather makes it difficult to accurately predict the output of a solar power plant. Through this paper, we will approach this problem by using an ensemble model consisting of both machine learning and neural networks (NN) as base models to forecast the amount of energy that needs to be produced by a solar plant over a short-term time horizon, which in our case will be 0 minute (immediate), 5 minute, 30 minute and 90 minute. Each base model is fine tuned to encourage high diversity and low correlation to improve prediction accuracy. The expected stability or generalization from RF-DNN combined with the memory retention capability of the LSTM network should provide an ideal predictor for time series forecasting of a stochastic process like weather. © 2024 IEEE.Item Stacking Deep learning and Machine learning models for short-term energy consumption forecasting(Elsevier Ltd, 2022) Sujan Reddy, A.; Akashdeep, S.; Harshvardhan, R.; Kamath S․, S.Accurate prediction of electricity consumption is essential for providing actionable insights to decision-makers for managing volume and potential trends in future energy consumption for efficient resource management. A single model might not be sufficient to solve the challenges that result from linear and non-linear problems that occur in electricity consumption prediction. Moreover, these models cannot be applied in practice because they are either not interpretable or poorly generalized. In this paper, a stacking ensemble model for short-term electricity consumption is proposed. We experimented with machine learning and deep models like Random Forests, Long Short Term Memory, Deep Neural Networks, and Evolutionary Trees as our base models. Based on the experimental observations, two different ensemble models are proposed, where the predictions of the base models are combined using Gradient Boosting and Extreme Gradient Boosting (XGB). The proposed ensemble models were tested on a standard dataset that contains around 500,000 electricity consumption values, measured at periodic intervals, over the span of 9 years. Experimental validation revealed that the proposed ensemble model built on XGB reduces the training time of the second layer of the ensemble by a factor of close to 10 compared to the state-of-the-art, and also is more accurate. An average reduction of approximately 39% was observed in the Root mean square error. © 2022 Elsevier LtdItem Micro Expression Recognition Using Delaunay Triangulation and Voronoi Tessellation(Taylor and Francis Ltd., 2023) Adyapady R, R.; Annappa, B.Facial Expression Recognition is a visual cue used for conveying emotions and intentions between human beings. The micro-expressions (MEs) are not visible to the human eye, making it challenging to capture the minute changes in the facial areas as the expressions change. As a result, automating the detection of ME is a challenging task. This work utilizes Delaunay Triangulation and Voronoi Diagram properties to segment Region of Interest (ROI) based on Action Unit indexes. The ROI-based feature extraction aided in improving the performance of the Micro-Expression Recognition (MER) system. The Cross-Database Evaluation (CDE) and Holdout Database Evaluation (HDE) are performed on three publicly available datasets CASMEII, SAMM, and SMIC (HS). The proposed approach resulted in an improved Unweighted Average Recall (UAR) and Unweighted F1 (UF1) scores by 6.09% and 4.36%, respectively. The results obtained with CDE and HDE demonstrate that the proposed model is robust compared to earlier studies. © 2023 IETE.Item An ensemble approach using a frequency-based and stacking classifiers for effective facial expression recognition(Springer, 2023) Adyapady R, R.; Annappa, B.Facial Expression Recognition is an essential aspect of human behavior to communicate effectively. A more profound understanding of human behavior, accurate analysis, and interpretation of the emotional content is essential. Hence, facial features play a crucial role as they contain beneficial information about facial expressions. A baseline architecture belonging to the EfficientNet family of models is explored for feature extraction. In this work, two novel strategies, the ensemble model using the frequency-based voting approach (FV-EffNet) and the stacking classifier (SC-EffNet), are proposed to enhance classification results’ performance. The proposed system deals with both profile and frontal pose variations. The combination of deep learning models with a stacking classifier gave the best results of 98.35% and 98.06%, and the frequency-based approach used with the ensemble classifier achieved superior performance of 98.71% and 98.56% on Oulu-CASIA and RaFD datasets, respectively. The experiment results with the proposed methodology showed better performance than previous studies on Oulu-CASIA and RaFD datasets, making it more robust to pose variations. © 2022, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.Item MSDNet: a deep neural ensemble model for abnormality detection and classification of plain radiographs(Springer Science and Business Media Deutschland GmbH, 2023) Karthik, K.; Kamath S․, S.S.Modern medical diagnostic techniques facilitate accurate diagnosis and treatment recommendations in healthcare. Such diagnostics procedures are performed daily in large numbers, thus, the clinical interpretation workload of radiologists is very high. Identification of abnormalities is a predominantly manual task that is performed by radiologists before the medical scans are available to the patient’s referring doctor for further recommendations. On the other hand, for a radiologist to delineate the imaging study’s findings/observations as a textual report is also a tedious task. Automated methods for radiographic image examination for identifying abnormalities and generating reliable radiology report are thus a fundamental requirement in clinical workflow management applications. In this work, we present an automated approach for abnormality classification, localization and diagnostic report retrieval for identified abnormalities. We propose MSDNet, an ensemble of Convolutional Neural models for abnormality classification, which combines the features of multiple CNN models to enhance abnormality classification performance. The proposed model also is designed to localize and visualize the detected abnormality on the radiograph image, based on an abnormal region detection algorithm to further optimize the diagnosis quality. Furthermore, the extracted features generated by MSDNet are used to automatically generate the diagnosis text report using an automatic content-based report retrieval algorithm. The upper extremity musculo-skeletal images from the MURA dataset and chest X-ray images from Indiana dataset were used for the experimental evaluation of the proposed approach. The proposed model achieved promising results, with an accuracy of 82.69%, showing its significant impact on alleviating radiologists’ cognitive load, thus improving the overall efficiency. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.Item Enhanced Malicious Traffic Detection in Encrypted Communication Using TLS Features and a Multi-class Classifier Ensemble(Springer, 2024) Kondaiah, C.; Pais, A.R.; Rao, R.S.The use of encryption for network communication leads to a significant challenge in identifying malicious traffic. The existing malicious traffic detection techniques fail to identify malicious traffic from the encrypted traffic without decryption. The current research focuses on feature extraction and malicious traffic classification from the encrypted network traffic without decryption. In this paper, we propose an ensemble model using Deep Learning (DL), Machine Learning (ML), and self-attention-based methods. Also, we propose novel TLS features extracted from the network and perform experimentation on the ensemble model. The experimental results demonstrated that the ML-based (RF, LGBM, XGB) ensemble model achieved a significant accuracy of 94.85% whereas the other ensemble model using RF, LSTM, and Bi-LSTM with self-attention technique achieved an accuracy of 96.71%. To evaluate the efficacy of our proposed models, we curated datasets encompassing both phishing, legitimate and malware websites, leveraging features extracted from TLS 1.2 and 1.3 traffic without decryption. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.Item High-Spatial-Resolution Estimation of XCO2 Using a Stacked Ensemble Model(Multidisciplinary Digital Publishing Institute (MDPI), 2025) Pais, S.M.; Bhattacharjee, S.; Anand Kumar, M.; Balamurugan, V.; Chen, J.Highlights: What are the main findings? The study develops a customized stacked ensemble model that generalizes (Formula presented.) predictions across multiple country, such as Germany, France, and Japan. It produces gap-filled high-resolution monthly, seasonal, and yearly maps, highlighting vegetation dynamics and seasonal cycles. What is the implication of the main finding? The customized stacked ensemble model provides reliable cross-country (Formula presented.) predictions at 1 (Formula presented.) resolution, validated against TCCON and CAMS, supporting large-scale environmental monitoring. Seasonal and yearly analyses show vegetation dynamics and photosynthetic activity significantly influence (Formula presented.), enhancing the model’s adaptability for agriculture, different climate assessments, and future global mapping. One of the leading causes of climate change and global warming is the rise in carbon dioxide ((Formula presented.)) levels. For a precise assessment of (Formula presented.) ’s impact on the climate and the creation of successful mitigation methods, it is essential to comprehend its distribution by analyzing (Formula presented.) sources and sinks, which is a challenging task using sparsely available ground monitoring stations and airborne platforms. Therefore, the data retrieved by the Orbiting Carbon Observatory-2 (OCO-2) satellite can be useful due to its extensive spatial and temporal coverage. Sparse and missed retrievals in the satellite make it challenging to perform a thorough analysis. This work trains machine learning models using the Orbiting Carbon Observatory-2 (OCO-2) (Formula presented.) retrievals and auxiliary features to obtain a monthly, high-spatial-resolution, gap-filled (Formula presented.) concentration distribution. It uses a multi-source aggregated (MSD) dataset and the generalized stacked ensemble model to predict country-level high-resolution (1 (Formula presented.)) (Formula presented.). When evaluated with TCCON, this country-level model can achieve an RMSE of 1.42 ppm, a MAE of 0.84 ppm, and (Formula presented.) of 0.90. © 2025 by the authors.