Conference Papers

Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506

Browse

Author: search.filters.author.Gowhar, S.Subject: search.filters.subject.Machine Learning

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Binarization in DeepFake Audio Detection: A Comparative Study and Performance Analysis
    (Institute of Electrical and Electronics Engineers Inc., 2025) Gowhar, S.; Pandey, A.; Rudra, B.
    DeepFake audio, generated through advanced AI techniques, poses significant risks such as fraud, misinformation, and identity theft. As the quality of synthetic audio improves, detecting such fakes has become increasingly challenging. Traditional detection methods struggle to keep pace as AI-generated voices replicate speech patterns, tone, and pitch convincingly. While computationally intensive large-scale models can help detect DeepFakes generated by AI, their resource requirements make them impractical for deployment on mobile devices as well as on resource-constrained devices. This paper proposes a lightweight yet effective approach using binarized neural networks (BNNs) and further enhancements using additional dense layers and stacked modeling to overcome these challenges. We conduct a comprehensive performance analysis of the network and compare it with various machine learning and neural network methods to evaluate the tradeoff between detection accuracy and computational efficiency as an effect of binarization and precision loss in feature embeddings. © 2025 IEEE.
  • No Thumbnail Available
    Item
    Imbalanced Multi-Class Research Article Classification using Sentence Transformers and Machine Learning Algorithms
    (Association for Computing Machinery, Inc, 2025) Gowhar, S.; Kempaiah, P.; Kamath, S.S.; Sugumaran, V.
    Categorizing scientific articles into specific research fields is a challenging problem, considering the volume and variety of published literature. However, existing classification systems often suffer from limitations regarding taxonomy or the models used for classification. This article explores approaches built on Sentence Transformer embeddings combined with Machine Learning algorithms to classify articles into 123 predefined classes, with the dataset being heavily imbalanced in nature. The effectiveness of Large Language Models (LLMs) for generating synthetic data is also experimented with, along with synonym augmentation and SMOTE. The best-performing model, the One vs Rest classifier trained on MP-Net sentence embeddings with SMOTE, achieved an accuracy of 77%, and outperformed all the other models. © 2024 Copyright held by the owner/author(s).