Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
15 results
Search Results
Item A hybrid approach for nucleus stain separation in histopathological images(Institute of Electrical and Electronics Engineers Inc., 2017) Bhat, H.; Kanakatte, A.; Nayak, R.; Gubbi, J.Difficulties in automation of histology image analysis are caused due to varying stain colors in the histology slides and the interaction of stains. Incorrect stain separation results in incorrect nucleus segmentation. A new hybrid algorithm has been proposed combining de-staining and wedge separation algorithms, which provides better stain separation and maintains color integrity of the input image. The proposed algorithm is tested on 36 histopathological images covering varying tissues and compared with popular methods in the area with excellent results in high nuclei density category. © 2017 IEEE.Item Micro-Moment Classification for Anomalous Power Consumption Detection using 1D CNN(Institute of Electrical and Electronics Engineers Inc., 2023) Nayak, R.; Jaidhar, C.D.Identifying anomalous power consumption is essential in improving energy efficiency in buildings. With the help of sensors and other intelligent systems installed in buildings (including smart homes), identifying anomalous power consumption becomes easy. In this work, 1 Dimensional Convolutional Neural Network (1D CNN)-based classification model is proposed to classify the micro-moments to identify the anomalous power consumption in the presence and absence of the consumer. The SimDataset values are normalized, and each instance with ten features is given as input to the 1D CNN. The robustness of the proposed model is defined by experimenting with varying the hyperparameter to obtain the best performance in the standard performance evaluation metrics. The results depicted that the suggested model outperformed the state-of-the-art, producing an accuracy of 96.4% and a weighted average F1-score of 0.962. © 2023 IEEE.Item Classification of Micro-Moment-Based Anomalous Power Consumption Using Transfer Learning(Institute of Electrical and Electronics Engineers Inc., 2023) Nayak, R.; Jaidhar, C.D.The identification of unusual power usage in buildings is crucial for improving energy efficiency. Using an electrical consumption monitoring system can help with energy conservation by identifying unusual energy consumption patterns. This paper suggests a micro-moment-based methodology for detecting abnormal power use. This study makes use of a benchmark dataset called SimDataset, which is used in most of the micro-moment classification-related works. On the images created from the dataset labeled with two classes and five classes, binary and multi-class classifications have both been used. Transfer learning is used by employing pre-trained CNN models, namely DenseNet121, ResNet50V2, and Xception model. The results depicted that the DenseNet121 model has outperformed all other models by giving the best accuracy of 99% and F1-score of 0.984. © 2023 IEEE.Item Smart Appliance Abnormal Electrical Power Consumption Detection(Springer Science and Business Media Deutschland GmbH, 2024) Nayak, R.; Jaidhar, C.D.Potential cyber threats now have an immensely larger attack surface due to the widespread use of smart devices and smart environments. Smart home appliances build a network of linked objects that exchange information and communicate with each other. Detecting abnormal electrical power consumption becomes a first line of protection for bolstering the security of smart homes. Using Machine Learning (ML), anomalous electrical power consumption of the Smart Appliance can be identified. This work proposes an ML-based anomalous electrical power consumption detection to identify the security breach of the Smart Appliances. SimDataset is used for anomalous power consumption detection as a proof of concept for experimentation, and results depicted that Random Forest (RF) classifier outperformed other ML-based classifiers while detecting the abnormal electrical power usage. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.Item Experimental Study on Detection of Household Electrical Appliance Energy Consumption Deviation(Springer Science and Business Media Deutschland GmbH, 2024) Nayak, R.; Jaidhar, C.D.The energy efficiency of buildings is compromised due to the wastage of power and the unidentified abnormal power consumption. Identifying the patterns within a dataset that drastically vary from the usual pattern or behavior is known as anomaly detection. With anomalous power consumption detection, it is possible to respond quickly to problems like malfunctioning appliances, energy waste, or unusual usage patterns, improving energy management, reducing costs, and improving safety. This work is an experimental study on detecting electrical appliance energy consumption deviation using a micro-moment labeled appliance power consumption dataset named ‘SimDataset’. Two sets of experiments were conducted: the first was by using the original dataset without removing any features, and in the second experiment, highly correlated redundant features were removed from the original dataset. Experiments are conducted based on an 80:20 split of the dataset and also on tenfold cross-validation. Experimental results depicted that the Random Forest (RF) classifier performed best, and its performance is consistent among different experiments. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.Item Experimental Study on Impact of Appliance ID-Based Normalization on SimDataset for Anomalous Power Consumption Classification(Institute of Electrical and Electronics Engineers Inc., 2024) Nayak, R.; Jaidhar, C.D.In terms of annual worldwide energy consumption, buildings use more energy than any other sector. Enhancing buildings' energy efficiency and ensuring security of the appliances requires iden-tifying abnormal power usage. Identifying anomalous power usage is essential for energy conservation. This study suggests an experimental analysis of SimDataset used for detecting micro-moment-based abnormal power usage. Five machine learning-based classifiers-Random Forest (RF), Support Vector Ma-chine (SVM), K Nearest Neighbors (KNN), Naive Bayes (NB), and Decision Tree (DT)-are used to detect unusual consumption of electricity. The Sim-Dataset has undergone binary and multi-class classi-fication. Effect on the performance of the classifiers after the inclusion of new features is examined. Computational complexity of the classifiers is also analyzed. Experimental results showed, the binary and multi-class classification using the RF model with the original dataset, with Min-Max Normalized Power feature and Appliance Id-based Normalized Power feature, produced identical and maximum accuracy, precision, recall, and F1-Score. © 2024 IEEE.Item Taguchi's technique in machining of metal matrix composites(Brazilian Society of Mechanical Sciences and Engineering, 2009) Shetty, R.; Pai B, R.B.; Rao, S.S.; Nayak, R.This paper presents the study on Taguchi's optimization methodology, which is applied to optimize cutting parameters in turning of age hardened Al6061-15% vol. SiC 25 ?m particle size metal matrix composites with Cubic boron nitride inserts (CBN) KB-90 grade using steam as cutting fluid. Analysis of variance (ANOVA) is used to study the effect of process parameters on the machining process. This procedure eliminates the need for repeated experiments, time and conserves the material by the conventional procedure. The turning parameters evaluated are speed, feed, depth of cut, nozzle diameter and steam pressure. A series of experiments are conducted using PSG A141 lathe (2.2 KW) to relate the cutting parameters on surface roughness, tool wear, cutting force, feed force, and thrust force. The measured results were collected and analyzed with the help of the commercial software package MINITAB15. As well, an orthogonal array, signal-to-noise ratio is employed to analyze the influence of these parameters. The method could be useful in predicting surface roughness, tool wear, cutting force, feed force and thrust force as a function of cutting parameters. From the analysis using Taguchi's method, results indicate that among the all-significant parameters, steam pressure is the most significant parameter. © 2009 by ABCM.Item Application of response surface methodology on surface roughness in grinding of aerospace materials (6061Al-15Vol%SiC25P)(2010) Dayananda Pai, D.; Rao, S.S.; Shetty, R.; Nayak, R.In this paper, the effects and the optimization of machining parameters on surface roughness in the grinding of 6061Al-SiC25P (MMCs) specimen are investigated. In the grinding process, a machining parameter, such as hardness of the specimen, flow rate of the coolant and depth of cut while machining were chosen for evaluation by the response surface methodology. By response surface methodology, a complete realization of the process parameters and their effects were achieved. The variation of surface roughness with machining parameters was mathematically modeled using response surface methodology. Finally, experimentation was carried out to identify the effectiveness of the proposed method. © 2006-2010 Asian Research Publishing Network (ARPN). All rights reserved.Item Employing Feature Extraction, Feature Selection, and Machine Learning to Classify Electricity Consumption as Normal or Electricity Theft(Springer, 2023) Nayak, R.; Jaidhar, C.D.One of the main causes of revenue loss in the energy sector across the globe has been non-technical losses. Electricity theft is a non-technical loss that affects the power supply’s quality. Detecting electricity theft is crucial for conserving energy and making use of it effectively. This research proposes a method through which higher accuracy in electricity theft detection can be obtained using fewer features. Different feature extraction and feature selection techniques are examined to find the best method for selecting the features that are more relevant in electricity theft detection. Various experiments are carried out using feature selection and feature extraction methods, such as mutual information, low variance filtering, and Principal Component Analysis. Various machine learning-based classifiers are used that include Random Forest, Support Vector Machine, K-Nearest Neighbours, Naive Bayes, and Decision Tree. Results of the experiments are tabulated based on standard performance measures, namely accuracy, precision, recall, and Area Under the Receiver Operating Characteristic Curve (AUC-ROC) score. According to experimental findings, the Random Forest classifier with 30 components for PCA outperformed other methods by producing the best accuracy of 95.82%, recall of 0.938, and AUC-ROC-score of 0.989. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.Item Enhancing Anomaly Detection in Critical Systems Using Household Appliance Power Consumption Data(Institute of Electrical and Electronics Engineers Inc., 2024) Nayak, R.; Jaidhar, C.D.It is crucial to detect anomalous use of electrical power in critical systems to prevent malfunctions or hazards, ensure operational security, and optimize the energy economy. Since anomalies in critical systems can serve as early warning systems for potential issues or threats that could lead to severe failures, it becomes strategically crucial to discover them as soon as possible. This study proposes and suggests a novel technique for anomaly identification in industrial critical systems using a household appliance's electrical power consumption dataset in the absence of a dedicated critical system or industrial equipment dataset. The study looks at the ability of a deep learning (DL) model trained on household data to identify anomalous patterns in large-scale industrial equipment's power use. Convolutional neural network (CNN) is used in this work to analyze anomalous electrical power use based on micro-moments. In this work, an appliance-level dataset is employed for experimentation. 10 × 10 appliance-wise grayscale images are generated from numeric dataset with and without the instance-wise N-gram approach. The effectiveness of the proposed approach is evaluated and compared it with other ML and DL models used earlier. The experimental findings showed that the proposed approach worked better than other models. Compared to images created without the instance-wise N-gram approach, the performance of the proposed approach with images created with N-gram is superior. © 2001-2012 IEEE.