Conference Papers
Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506
Browse
4 results
Search Results
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 Detecting COVID-19 Infection Using Customized Convolutional Neural Network(Institute of Electrical and Electronics Engineers Inc., 2024) Kumar, S.; Kisku, B.; Vardhan K, S.H.; Kumar, S.; Bhowmik, B.The COVID-19 pandemic has affected 775 million people globally, with an estimated death toll of 7 million. Detection methods like reverse transcription polymer chain reaction (RT-PCR) face multiple challenges, including false positive cases, time-consuming, and high cost. A rapid, precise, affordable screening alternative is essential to expedite COVID-19 detection. Various efforts have focused on expediting COVID-19 detection due to the high costs and logistical challenges associated with traditional methods. This paper proposes a customized deep-learning framework architecture for automatically identifying COVID-19 infection in chest X-ray (CXR) images. Multiple neural networks extract deep features from the CXR images, including popular models such as VGG19, DenseNet201, EfficientNet, MobileNetV2, and InceptionV3. The proposed model undergoes training and testing using the QaTa-COVID-19 dataset. The proposed model achieves classification accuracy of 97.06%, with precision, recall, and F1 score rates for COVID-19 cases recorded at 97.34%, 96.36%, and 97.01%, respectively, for the 4-class cases (COVID vs. Normal vs. Pediatric Bacterial Pneumonia vs. Pediatric Viral Pneumonia). © 2024 IEEE.Item Automated Segmentation of COVID-19 Infected Lungs via Modified U-Net Model(Institute of Electrical and Electronics Engineers Inc., 2024) Kumar, S.; Bhowmik, B.The COVID-19 pandemic has led to significant outbreaks in more than 220 countries worldwide, profoundly impacting the public health and lives. As of February 2024, over 774 million cases have been reported, with more than 7,035,337 deaths recorded. Therefore, there is a significant need for automated image segmentation to serve as clinical decision support. This paper presents a novel automated segmentation framework that dynamically generates distinct and randomized image patches for training using preprocessing techniques and extensive data augmentation. The proposed architecture employs a semantic segmentation approach, ensuring accuracy despite limited data availability. Experimental assessment comprises a visual inspection of the predicted segmentation outcomes. Quantitative evaluation of segmentation includes standards performance metrics such as precision, recall, Dice score, and Intersection over Union (IoU). The results exhibit a remarkable Dice coefficient score of 98.3% and an IoU rate surpassing 96.8%, demonstrating the model's robustness in identifying COVID-19-infected lung regions. © 2024 IEEE.Item Money Laundering Detection in Banking Transactions using RNNs and Hybrid Ensemble(Institute of Electrical and Electronics Engineers Inc., 2024) Girish, K.K.; Bhowmik, B.The financial sector has witnessed significant transformations due to the emergence of financial technology (FinTech), transitioning from traditional paperbased processes to a dynamic digital ecosystem. Despite the industry's advancements driven by FinTech innovations, concerns persist, particularly regarding financial fraud, notably money laundering. Perpetrators exploit modern technologies to launder illicitly obtained funds, posing a global threat to economies. Effective detection mechanisms for money laundering are crucial. This paper introduces a novel approach utilizing a recurrent neural network (RNN) for detecting money laundering in banking transactions. The proposed framework exercises standalone RNN models such as LSTM, GRU, BiLSTM, and stacked RNN models for the detection. Additionally, the effectiveness of hybrid ensemble models combining RNNs with XGBoosts is investigated. The evaluation achieves standard performance metrics, with the stacked RNN model achieving 92% accuracy. Surpassing it, the ensemble model achieves an impressive 95%. These results underscore the superiority of hybrid ensemble models over standalone RNNs, particularly in accurately detecting money laundering activities. © 2024 IEEE.