Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
9 results
Search Results
Item Hybrid Approach for Intrusion Detection System(Institute of Electrical and Electronics Engineers Inc., 2018) Singh, P.; Venkatesan, M.In the recent research, Intrusion Detection sys- tem in Machine Learning has been giving good detection and high accuracy on novel attacks. The major purpose of this study is implementing a method that combines Random-Forest classification technique and K-Means clustering Algorithms. In misuse-detection, random-forest algorithm will build a patterns of intrusion over a training data. And in anomaly-detection, intrusions will be identified by the outlier-detection mechanism in the random-forest algorithm. This hybrid-detection system will combine the advantage of anomaly and mis-use detection and improves the performance of detection. This paper mainly focused on evaluating the performance of hybrid approaches namely Gaussian Mixture clustering with Random Forest Classifiers and K-Means clustering with Random Forest Classifiers in-order to detect intrusion. These algorithms were evaluated for the four categories of attacks based on accuracy, false-alarm-rate, and detection-rate. From our experiments conducted, K-Means clustering with Random Forest Classifiers outperformed over the Gaussian Mixture clustering with Random Forest Classifiers. © 2018 IEEE.Item Automated Detection of Maize Leaf Diseases in Agricultural Cyber-Physical Systems(Institute of Electrical and Electronics Engineers Inc., 2022) Verma, A.; Bhowmik, B.R.Agricultural cyber-physical systems (ACPS) are an ever-increasing sector that affects the quality and quantity of agricultural products as the population increases rapidly. Maize, also known as 'corn,' is one of the world's old food crops, consumed every part of Bharat with 1.4 billion masses across the globe. But a disease, whether on seeds, leaves, or other parts of a crop plant, poses a significant risk to food security. For example, a Maize leaf experiences three diseases-blight, common rust, and gray leaf spot. Early detection and correct identification of these diseases can help restrict the spread of infection and ensure crop quality for long-Term health. This paper proposes a deep convolutional neural network (DCNN) framework for Maize leaves named "MDCNN"that detects these diseases. The proposed MDCNN model undergoes training and is tuned to detect four prevalent classes of the conditions. The proposed model exercises a voluminous dataset of the diseases. Experimental results demonstrate that the proposed model achieves a training and test accuracy up to 95.51% and 99.54%, respectively. Furthermore, it outperforms many existing methods and delivers a superior disease control solution for Maize leaf diseases. © 2022 IEEE.Item Measuring Robustness of Side Channel Analysis in the Detection of Hardware Trojans in Encryption Modules(Institute of Electrical and Electronics Engineers Inc., 2022) Masand, S.; Fernandes, K.R.; Bhat, M.S.The hardware, software, and the data present in any electronic system predominantly determine the system's security. Just like software, hardware is equally prone to attacks leading to malfunction. Altering the circuit design via different techniques to create a secret channel that maliciously affects the functionality of the system is called Hardware Trojan (HT) insertion and can cause significant harm. Therefore, it is necessary to efficiently detect the presence of Hardware Trojans in any system. This paper presents the use of a well known Hardware Trojan detection technique called Side-Channel Analysis (SCA) to detect Trojans in encryption modules like AES and RSA. The availability of a golden circuit to compare against the Circuit Under Test (CUT) is assumed to detect Trojans through side-channel analysis. For the same, Xilinx Vivado is used to program the Intellectual Properties (IPs) on the Nexys 4 DDR FPGA. It is shown that the above- mentioned technique is not accurate in certain cases especially when the size of the Trojan is not large enough. So, an alternative technique is proposed that uses machine learning algorithms - that provide an accuracy of at least 93.06% while using the side channel data-sets, thereby significantly increasing the Trojan detection accuracy. © 2022 IEEE.Item Stress Detection Using Deep Learning Algorithms(Institute of Electrical and Electronics Engineers Inc., 2023) Angalakuditi, H.; Bhowmik, B.Stress has become a prevalent issue in modern society, with various negative impacts on mental and physical health. Stress in people is a physiological and psychological reaction to an imagined threat or difficulty. Several things, including employment, relationships, income, health problems, and significant life transitions, can cause stress. Depending on the person and the circumstance, stress symptoms can vary. They frequently include emotions of worry, irritation, and restlessness, as well as physical symptoms like headaches and muscle strain. Early stress detection is crucial for effective intervention and prevention of stress-related health issues. Detecting stress in real-time can be valuable in various domains such as healthcare, mental health, human-computer interaction, and workplace performance. This paper proposes a method for detecting stress using deep learning. A set of pre-trained models are employed for stress detection. The proposed technique is evaluated with publicly available datasets. Experimented results showed that the proposed stress detection method achieves accuracy in the range of 85.71-97.50% and the loss ranging from 0.4061 to 1.8144. © 2023 IEEE.Item Feature Selection for Peer-to-Peer Lending Default Risk Using Boruta and mRMR Approach(Institute of Electrical and Electronics Engineers Inc., 2023) Anusha Hegde, H.; Bhowmik, B.Peer-to-peer (P2P) lending in the Financial Technology (FinTech) sector is increasingly gaining attention from people where the online platform enables lenders to offer loans to borrowers. The platform as a much needed mechanism targets to reduce the risk of default and increase profitability for lenders and the platform. Each loan record maintains a variety of attributes, including details about the loan, the borrower, their credit history, their finances, and public data. If all the features are considered, the performance of the lending platform may decline. Finding the necessary characteristics more helpful in forecasting loan default is a concern. This paper investigates essential features of the P2P lending mechanism with adequate performance in lending money to individuals or businesses. We employ two algorithms to find the pertinent features: Boruta and Max-Relevance and Min-Redundancy (mRMR). Further, we use two classifiers-decision tree and XGBoost that exercise the selected elements to predict the loan defaults. © 2023 IEEE.Item Accuracy Comparison of Logistic Regression and Decision Tree Prediction Models Using Machine Learning Technique(Springer Science and Business Media Deutschland GmbH, 2025) Tantri, B.R.; Bhat, S.With the advancements in data science and machine learning, it has become beneficial for scientists, technologists, social scientists, and businessmen to adopt the latest developments in machine learning into their domains to make important decisions about their problems of interest. The biggest advantage of machine learning algorithms in such fields is their prediction capability. Statistical tools in powerful machine-learning languages like R have led to simpler solutions to more complex problems. Various models are in use in the process of making decisions and predictions. The most commonly used model in many situations is the regression model. Herein, it is intended to use the logistic regression model and the decision tree model in the prediction of binary categorical variables. R programming is used in the development of these prediction models. It is intended to compare the accuracy of the two models by using the confusion matrices. Two different datasets have been used for the prediction using these models and their comparisons. It has been observed that prediction using a decision tree model has a better accuracy as compared to that of a logistic regression model. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.Item An exhaustive review of computational prediction techniques for PPI sites, protein locations, and protein functions(Springer, 2023) Bhat, P.; Patil, N.The field of proteomics encompasses a comprehensive examination of proteins, encompassing their structural properties, interactions with other biomolecules, subcellular localization, functional roles, interaction sites, regions of disorder, and exploring novel protein designs. Each of these domains interlinks, contributing valuable information to the study of each other part. Extensive research in most of these areas has given rise to many more challenges that require further exploration. This review mainly concentrates on prediction approaches for protein–protein interaction sites, protein subcellular locations, and protein functions. We provide an exhaustive collection of several latest works in the above three domains, along with a digest of their descriptions in the most recent times. We conclude the review by highlighting the existing challenges and emphasizing the need for a deeper exploration of the research gaps in these studies. © 2023, The Author(s), under exclusive licence to Springer-Verlag GmbH Austria, part of Springer Nature.Item Accurate detection of congestive heart failure using electrocardiomatrix technique(Springer, 2022) Sharma, K.; Mohan Rao, B.M.; Marwaha, P.; Kumar, A.Congestive Heart Failures (CHFs) are prevalent, expensive, and deadly, causing damage or overload to the pumping power of the heart muscles. These leads to severe medical issues amongst humans and contribute to a greater death risk of numerous diseases at a later stage. We need accurate and less difficult techniques to detect these problems in our world with a growing population which will prevent many diseases and reduce deaths. In this work, we have developed a technique to diagnose CHF using the Electrocardiomatrix (ECM) technique. The 1-D ECG signals are transformed to a colourful 3D matrix to diagnose CHF. The detection of CHF using ECM are then compared with annotated CHF Electrocardiogram (ECG) signals manually. It has been found that ECM is able to detect the affected CHF duration from the ECG signals. Also, the ECM provides the reduction in both false positive and false negative which in turn improves the detection accuracy. The performance of the proposed approach has been tested on BIDMC CHF database. The proposed method achieved an accuracy of 97.6%, sensitivity of 98.0%, specificity of 97.0%, precision of 99.4%, and F1-Score of 98.3%. From this study, it has been revealed that the ECM technique allows the accurate, intuitive, and efficient detection of CHF and using ECM practitioners can diagnose the CHF without sacrificing the accuracy. © 2022, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.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.