Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
Search Results
Item Anomalous Electrical Power Consumption Detection in Household Appliances via Micro-Moment Classification(Institute of Electrical and Electronics Engineers Inc., 2025) Nayak, R.; Jaidhar, C.D.The detection of anomalous power consumption is critical for improving energy efficiency, particularly with the increasing demand in buildings. This study explores Convolutional Neural Network-based models by transforming 1-dimensional micro-moment labeled data into 2-dimensional matrices to capture both temporal and spatial consumption patterns. Three architectural variants are investigated: a conventional Deep Convolutional Neural Network (DCNN), a Depthwise Separable Convolutional Neural Network (DS-CNN), and a Depthwise Separable Residual Convolutional Neural Network (DSR-CNN). Unlike earlier studies, this work incorporates hyperparameter tuning, statistical validation, and cross-validation, resulting in the evaluation of over 450 model configurations. The results indicate that while the DCNN consistently achieves the highest accuracy, the DS-CNN achieves comparable performance with significantly reduced parameters and computational cost, making it suitable for real-time and resource-constrained environments. Model complexity analysis and statistical tests confirm the robustness of the findings. Finally, a systematic model selection strategy is presented, identifying the DS-CNN as the most balanced solution for effective and efficient anomaly detection in smart grid applications. © 2020 IEEE.Item Multistage Image Reconstruction and Attention-Based Semi-Supervised Learning for Medical Image Segmentation(SAGE Publications Ltd, 2025) Gawas, P.; Kamath S, S.; Singh, A.; Gurupur, V.Automated segmentation of medical images is critical in detecting and diagnosing various conditions. In recent years, supervised deep learning (DL) techniques have been widely researched. However, their application is often limited by the availability of annotated data in the medical domain. To address this, recent studies have explored semi-supervised techniques, though very few of these works focus on skin-lesion segmentation. In addition, they struggle to effectively capture contextual features to delineate the region of interest from the surrounding tissues in the image, which is crucial for accurate segmentation. In this article, a semi-supervised approach for medical image segmentation called MIRA (Medical Image Reconstruction and Analysis) is proposed, which uses adaptive-attention U-Net (AA-U-Net) trained on pseudo-labels generated with a lightweight feature-consistent encoder-decoder network (FCED-Net) to address these challenges. A case study focusing on the precise segmentation of malignant skin lesions is considered for our experiments, as the scarcity of extensive annotated dermatology data limits the effectiveness of traditional DL models. The proposed pipeline is validated and tested using two standard datasets, ISIC2016 and PH2. With only 50% annotated samples, the proposed approach demonstrated promising performance with DSC, IoU, and accuracy of 0.96, 0.92, and 0.85 on ISIC2016 and 0.93, 0.88, and 0.93 on cross-data testing with PH 2 dataset. When benchmarked against leading edge models trained on 100% labeled data, MIRA achieved promising results and even outperformed in some cases. These findings show that it can significantly reduce manual annotation requirements while achieving segmentation performance comparable to models trained on fully annotated skin lesion data. © The Author(s) 2025