Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
6 results
Search Results
Item Smartphone based emotion recognition and classification(Institute of Electrical and Electronics Engineers Inc., 2017) Sneha, H.R.; Rafi, M.; Manoj Kumar, M.V.; Thomas, L.; Annappa, B.This paper proposes a method that classifies the emotion status of a human being based on one's interactions with the smart phone. Due to one or the other practical limitations, the existing set of emotion recognition methods are difficult to use on daily basis (most of the known methods cause inconvenience to user since they require devices like wearable sensors, camera, or answering a questionnaire). The essence of this paper is to analyze the textual content of the message and user typing behavior to build a classifier that efficiently classifies the future instances. Each observation in the data set consists of 14 features. A machine learning technique called Naive Bayes classifier is applied to construct the classifier. Method proposed is capable of classifying emotions in one of the seven classes (anger, disgust, happy, sad, neutral, surprised, and fear). Experimental result has shown 72% accuracy in classification. © 2017 IEEE.Item TORA: Text Summarization Using Optical Character Recognition and Attention Neural Networks(Springer Science and Business Media Deutschland GmbH, 2022) Sneha, H.R.; Annappa, B.Text Summarization is the process of creating a short and coherent version of a longer document that holds the same meaning as that of the original data. This article illustrates the technique to read the text in a printed document (such as newspaper, brochure, web document, etc.) and generate a summary of text. The method proposed is named Text Summarization using Optical Character Recognition and Attention Neural Networks (TORA). TORA can perform extractive summarization of a news article with the aid of Recurrent Neural Networks, Bidirectional Long Short-Term Memory, and Bahadanu Attention Network. The experimental results of the proposed method are promising. The experimental results have shown 80% accuracy in producing the summary from the large text document. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.Item Process Logo: An Approach for Control-Flow Visualization of Information System Process in Process Mining(Springer Science and Business Media Deutschland GmbH, 2022) Manoj Kumar, M.V.; Bs, B.S.; Sneha, H.R.; Thomas, L.; Annappa, B.; Vishnu Srinivasa Murthy, Y.V.S.This paper proposes a new technique named “Process Logo†for visualizing the causal relationship between the activities of a process (Control flow). Traditional process mining algorithms rely on representing the activity as a sequence of operations modeled using nodes and edges, as the number of activities increases, the representation of the entire control flow becomes quite tedious. Process logo is a compact yet highly informative method for visually representing the process model. It visually summarizes the number of activities, sequence of execution, relative significance, and dependency between activities. It uses a dynamic programming method—sequence alignment and clustering approach with Levenshtein measure as a distance measure. The proposed method is evaluated on the synthetic event log, the experimental result is promising. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.Item YARS-IDS: A Novel IDS for Multi-Class Classification(Institute of Electrical and Electronics Engineers Inc., 2023) Madwanna, Y.; Annappa, B.; Rashmi Adyapady, R.; Sneha, H.R.An Intrusion Detection System (IDS) is a defence system that provides safety and security against different threats and attacks, acting as a wall of defence against attackers. As internet usage increases, IDSs are becoming an essential part of day-to-day life. Various Machine Learning (ML) and Deep Learning (DL) based IDS are available, and the domain of IDS is still evolving and growing. Here this paper proposes two DL-based IDSs, first is a combination of LuNet and Bidirectional LSTM (Bi-LSTM) and other is a combination of Temporal Convolutional Network (TCN), CNN and Bi-LSTM. Such IDS must be fed with an efficient number of samples to keep them updated and accurate. The first model has been trained and tested against two benchmark datasets, NSL-KDD and UNSW-NB15. The second model has been trained and tested against the NSL-KDD dataset. To overcome the insufficient number of samples, the models have used a technique called Synthetic Minority Oversampling Technique (SMOTE). These models provided better experimental outcomes than traditional ML-based approaches and many DL approaches. They have better results in classification accuracy and, detection rate. The classification accuracy of the first model for UNSW-NB15 and NSL-KDD is 82.19% and 98.87% respectively. The classification accuracy of the second model for NSL-KDD is 98.8%. © 2023 IEEE.Item Exploratory Analysis of Methods, Techniques, and Metrics to Handle Class Imbalance Problem(Elsevier B.V., 2024) Sneha, H.R.; Annappa, B.Class imbalance a common challenge in machine learning, often results in skewed predictions and misrepresentative model assessments, highlighting the need for effective countermeasures. Our detailed survey dives into three primary techniques for addressing this issue: data-level interventions, algorithmic modifications, and integrated hybrid solutions. We thoroughly dissect each approach, delineating its merits, drawbacks, and ideal use cases. Data-level methods aim to restructure the dataset for class balance, while algorithmic techniques recalibrate the learning process to better detect the minority class. The hybrid strategies merge the benefits of both for a holistic remedy. The study further emphasizes the importance of precise evaluation metrics, elaborating on both conventional metrics and those tailored for imbalanced scenarios. Our objective is to arm professionals with a deep insight into tackling class imbalance, especially within the big data framework. The insights shared aspire to inspire the creation of resilient, equitable machine learning models adapt at navigating imbalanced data, ensuring enhanced prediction fidelity and consistency. © 2024 Elsevier B.V.. All rights reserved.Item Hybrid Approach for Handling Class Imbalance on Medical Data(Institute of Electrical and Electronics Engineers Inc., 2024) Sujay, J.K.; Surakshith, D.T.; Uday, T.Y.; Sneha, H.R.; Annappa, B.; Sushma, V.Class imbalance in medical X-ray image datasets poses a significant challenge for developing accurate machine-learning models. This paper presents a novel 'Integrated Strategy for Addressing Class Imbalance in Medical Image Datasets' aiming to tackle this issue systematically. The proposed approach combines weighted loss functions and an ensemble model comprising a pre-trained DenseNet architecture and a customized model. The methodology is applied to a representative medical image dataset, demonstrating its effectiveness in mitigating class imbalance issues. The findings reveal notable improvements in model performance, particularly in underrepresented classes. This research advances robust machine learning models in medical image analysis, with potential applications in medical imaging and illness diagnostics. The results underscore the necessity for hybrid approaches and highlight the efficacy of ensemble models and weighted loss in addressing class imbalance in medical imaging datasets. © 2024 IEEE.