Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
11 results
Search Results
Item Deep Neural Network Models for Question Classification in Community Question-Answering Forums(Institute of Electrical and Electronics Engineers Inc., 2019) Upadhya, B.A.; Udupa, S.; Kamath S․, S.S.Automatic generation of responses to questions is a challenging problem that has applications in fields like customer support, question-answering forums etc. Prerequisite to developing such systems is a requirement for a methodology that classifies questions as yes/no or opinion-based questions, so that quick and accurate responses can be provided. Performing this classification is advantageous, as yes/no questions can generally be answered using the data that is already available. In the case of an opinion-based or a yes/no question that wasn't previously answered, an external knowledge source is needed to generate the answer. We propose a LSTM based model that performs question classification into the two aforementioned categories. Given a question as an input, the objective is to classify it into opinion-based or yes/no question. The proposed model was tested on the Amazon community question-answer dataset as it is reflective of the problem statement we are trying to solve. The proposed methodology achieved promising results, with a high accuracy rate of 91% in question classification. © 2019 IEEE.Item Modulation and signal class labelling with active learning and classification using machine learning(Institute of Electrical and Electronics Engineers Inc., 2022) Bhargava, B.C.; Deshmukh, A.; Narasimhadhan, A.V.Supervised learning in machine learning (ML) requires labelled data set. Further real-time data classification requires an easily available methodology for labelling. Wireless modulation and signal classification find their application in plenty of areas such as military, commercial and electronic reconnaissance and cognitive radio. This paper mainly aims to solve the problem of real-time wireless modulation and signal class labelling with an active learning framework. Further modulation and signal classification is performed with machine learning algorithms such as KNN, SVM, Naive Bayes. Active learning helps in labelling the data points belonging to different classes with the least amount of data samples trained. An accuracy of 86 percent is obtained by the active learning algorithm for the signal with SNR 18 dB. Further, KNN based model for modulation and signal classification perform well over a range of SNR, and an accuracy of 99.8 percent is obtained for 18 dB signal. The novelty of this work exists in applying active learning for wireless modulation and signal class labelling. Both modulation and signal classes are labelled at a given time with help of couplet formation from the data samples. © 2022 IEEE.Item A novel sentiment analysis of social networks using supervised learning(Springer-Verlag Wien michaela.bolli@springer.at, 2014) Anjaria, M.; Guddeti, R.M.R.Online microblog-based social networks have been used for expressing public opinions through short messages. Among popular microblogs, Twitter has attracted the attention of several researchers in areas like predicting the consumer brands, democratic electoral events, movie box office, popularity of celebrities, the stock market, etc. Sentiment analysis over a Twitter-based social network offers a fast and efficient way of monitoring the public sentiment. This paper studies the sentiment prediction task over Twitter using machine-learning techniques, with the consideration of Twitter-specific social network structure such as retweet. We also concentrate on finding both direct and extended terms related to the event and thereby understanding its effect. We employed supervised machine-learning techniques such as support vector machines (SVM), Naive Bayes, maximum entropy and artificial neural networks to classify the Twitter data using unigram, bigram and unigram + bigram (hybrid) feature extraction model for the case study of US Presidential Elections 2012 and Karnataka State Assembly Elections (India) 2013. Further, we combined the results of sentiment analysis with the influence factor generated from the retweet count to improve the prediction accuracy of the task. Experimental results demonstrate that SVM outperforms all other classifiers with maximum accuracy of 88 % in predicting the outcome of US Elections 2012, and 68 % for Indian State Assembly Elections 2013. © 2014, Springer-Verlag Wien.Item Fog-Based Intelligent Machine Malfunction Monitoring System for Industry 4.0(IEEE Computer Society, 2021) Natesha, B.V.; Guddeti, R.M.R.There is an exponential increase in the use of Industrial Internet of Things (IIoT) devices for controlling and monitoring the machines in an automated manufacturing industry. Different temperature sensors, pressure sensors, audio sensors, and camera devices are used as IIoT devices for pipeline monitoring and machine operation control in the industrial environment. But, monitoring and identifying the machine malfunction in an industrial environment is a challenging task. In this article, we consider machines fault diagnosis based on their operating sound using the fog computing architecture in the industrial environment. The different computing units, such as industrial controller units or micro data center are used as the fog server in the industrial environment to analyze and classify the machine sounds as normal and abnormal. The linear prediction coefficients and Mel-frequency cepstral coefficients are extracted from the machine sound to develop and deploy supervised machine learning (ML) models on the fog server to monitor and identify the malfunctioning machines based on the operating sound. The experimental results show the performance of ML models for the machines sound recorded with different signal-to-noise ratio levels for normal and abnormal operations. © 2021 IEEE.Item Machine Learning for Vortex Flowmeter Design(Institute of Electrical and Electronics Engineers Inc., 2022) Thummar, D.; Reddy, Y.J.; Venugopal, V.Vortex flowmeters are one of the broadly used flow measurement devices in various industrial applications. The shape of the bluff body is the most critical parameter in the design of vortex flowmeter. The conventional approach of bluff body design relies on parametric shape optimization of a bluff body using experimentation and computational fluid dynamics simulations, which are expensive and time-consuming. In this study, we propose a novel machine learning (ML)-based approach to design bluff body shapes. Two ML models are developed using supervised ML using an artificial neural network (ANN). The first model predicts new optimum bluff body shapes for a given input flow characteristic. The second model predicts the deviation in Strouhal number for a given bluff body to determine its optimality. Data from the literature on the geometry of bluff bodies and fluid flow properties such as blockage ratio, Reynolds number, and Strouhal number are used for training ML models. The obtained ML results are in close agreement (±3.0%) compared with the computational fluid dynamics simulation results. This approach may find broad applicability for designing other fluid flowmeters. © 1963-2012 IEEE.Item Swarm optimisation-based bag of visual words model for content-based X-ray scan retrieval(Inderscience Publishers, 2022) Karthik, K.; Kamath S․, S.Classification and retrieval of medical images (MedIR) are emerging applications of computer vision for enabling intelligent medical diagnostics. Medical images are multi-dimensional and require specialised processing for the extraction of features from their manifold underlying content. Existing models often fail to consider the inherent characteristics of data and have thus often fallen short when applied to medical images. In this paper, we present a MedIR approach based on the bag of visual words (BoVW) model for content-based medical image retrieval. When it comes to any medical approach models, an imbalance in the dataset is one of the issues. Hence the perspective is also considering a balanced set of categories from an imbalanced dataset. The proposed work on BoVW model extracts features from each image are used to train supervised machine learning classifier for X-ray medical image classification and retrieval. During the experimental validation, the proposed model performed well with the classification accuracy of 89.73% and a good retrieval result using our filter-based approach. © © 2022 Inderscience Enterprises Ltd.Item Hydrological responses to land use/land cover change in Tikur Wuha Watershed in Southern Ethiopia(Springer Science and Business Media Deutschland GmbH, 2022) Ketema, A.; Dwarakish, G.S.; Makhdumi, W.Due to its diverse environmental impacts, change in land use/ land cover (LU/LC) has become a global concern. LU/LC change is a critical factor that directly impacts watershed hydrology. The study intends to assess the LU/LC dynamics and their impacts on the streamflow of the Tikur Wuha watershed (TWW) in Ethiopia. LU/LC change was assessed using Landsat images. Each image is classified using a maximum likelihood algorithm of the supervised classification method. The Soil and Water Assessment Tools (SWAT) model were used to examine the impact of LU/LC change on streamflow. The overall accuracy of the LU/LC maps ranged from 77.50 to 87.33%. The findings demonstrated an increase in built-up and cultivated areas and a decrease in shrubland, grassland, swampy areas, and water bodies. The calibration and validation results showed a reasonable performance rate of the SWAT model. The LU/LC changes, which occurred between 1978 and 2017, had increased the average annual streamflow by 8.12%, 9.78%, and 14.77% between 1978 and1988, 1978 and 1998, 1978 and 2017. The Kiremt season flow increased by 9.80% during the first half of the study period (1978–1998) and by 5.41% in the second half (1998–2017). It is risen by 15.74% in 2017 compared to in 1978. The observed changes in the streamflow have resulted from LU/LC changes in the TWW. The study suggests that quick action is required to manage the LU/LC shift and execute land use planning to ensure water availability in the watershed. © 2022, The Author(s), under exclusive licence to Springer Nature Switzerland AG.Item Spatio-temporal analysis of land use/land cover change detection in small regions using self-supervised lightweight deep learning(Springer Science and Business Media Deutschland GmbH, 2023) Naik, N.; Chandrasekaran, K.; Sundaram, V.; Prabhavathy, P.Change detection (CD) has sparked a lot of scientific interest in recent decades as one of the core concerns in Earth observation. The enhancement of the CD source data with the availability of multitemporal images with varying resolutions provides ample change indicators due to the rapid improvement of satellite sensors. However, precisely detecting real changed locations continues to be a complicated task. CD from remote sensing images (RSI) becomes challenging when the labeled data for supervised learning is unavailable. This article proposes a novel CD framework using a self-supervised learning (SSL) approach to overcome these limitations. First, the superpixel segmentation method of simple linear iterative clustering (SLIC) using a structural similarity index is incorporated to produce a difference image (DI). The change features are extracted to represent the difference information using spatial features between the corresponding superpixels. Second, a parallel clustering algorithm called fuzzy C-means (FCM) separates the DI into three clusters of changed, unchanged, and intermediate classes. The image patches of changed, unchanged and intermediate classes are constructed as training and testing samples. A lightweight deep convolutional neural network (LWDCNN) is trained with the training samples to detect the semantic difference and classify the testing samples into the changed or unchanged class. Finally, merging intermediate and change class labels generates a robust and high-contrast CD map. Numerical experiments were performed on two small regions like the Alappuzha, Kerala, India, and Paris building dataset to demonstrate the usefulness of the proposed approach, achieving an overall accuracy of 98.28% and 96.43% for determining changes effectively. © 2023, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.Item A Dual-Stage Semi-Supervised Pre-Training Approach for Medical Image Segmentation(Institute of Electrical and Electronics Engineers Inc., 2024) Aralikatti, R.C.; Pawan, S.J.; Rajan, J.Deep neural networks have played a vital role in developing automated methods for addressing medical image segmentation. However, their reliance on labeled data impedes the practicability. Semi-Supervised learning is gaining attention for its intrinsic ability to extract valuable information from labeled and unlabeled data with improved performance. Recently, consistency regularization methods have gained interest due to their efficient learning procedures. They are, however, confined to data or network-level perturbations, negating the benefit of having both forms in a single framework. In light of this, we ask an intriguing but unexplored question: Can we have both network-level and data-level perturbation in the semi-supervised framework? To this end, we present a holistic approach that integrates data-level perturbation in the model pre-training stage, followed by implicit network-level perturbation in the fine-tuning stage. Furthermore, we incorporate networks with manifold learning paradigms throughout the training to facilitate the formation of robust data representations by ensuring local and global semantic affinities adhering to the theory of consensus. Notably, this may be the first attempt in the semi-supervised medical image segmentation archetype to use data and network-level perturbation with a model pre-training strategy. We extensively validated the efficacy of the proposed framework on three benchmark datasets, namely the Automated Cardiac Diagnosis Challenge, ISIC-2018, and Left Atrial Segmentation Challenge datasets, subjected to severely low-sampled labeled data. Notably, in ACDC (4%), ISIC-2018 (5%), and LA (6%) labeled cases, the proposed method outperforms the second-best method by 2.95%, 1.31%, and 0.71% in the Dice Similarity Metric. © 2023 IEEE.Item WeakSegNet: Combining Unsupervised, Few-Shot, and Weakly Supervised Methods for the Semantic Segmentation of Low-Magnification Effusion Cytology Images(Institute of Electrical and Electronics Engineers Inc., 2025) Aboobacker, S.; Vijayasenan, D.; Sumam David, S.S.; Suresh, P.K.; Sreeram, S.Effusion cytology analysis can be time consuming for cytopathologists, but the burden can be reduced through automatic malignancy detection. The main challenge in the automation process is pixel-wise labeling. We proposed WeakSegNet, a new model that addresses the challenge of semantic segmentation in low-magnification images by utilizing only four images with pixel-wise labels. WeakSegNet combines unsupervised, few-shot, and weakly supervised learning methods. In the first stage, an unsupervised model, DeepClusterSeg, learns the homogeneous structures from different images. The few-shot method uses only four images with pixel-wise labels to map homogeneous structures to the required classes. The final stage utilized image-level labels to predict precise classes using weakly supervised learning. We conducted our experiments using a dataset from KMC Hospital, MAHE, which consisted of 345 images. We performed 5-fold cross-validation to evaluate the results. Our proposed model achieved promising results, with an F-score of 0.85 and an IoU of 0.81 for the malignant class, surpassing the performance of the standard k-means algorithm with weakly supervised learning (F-scores of 0.65 and an IoU of 0.61). The semantic segmentation of low-magnification images using our approach eliminated 47% of the sub-regions that need to be scanned at high magnification. This innovative approach reduces the workload of cytopathologists and maintains a high accuracy in effusion cytology malignancy detection. © 2013 IEEE.