Browsing by Author "Pariserum Perumal, S.P."

Now showing 1 - 4 of 4

A Dual Phase Approach for Addressing Class Imbalance in Land-Use and Land-Cover Mapping From Remotely Sensed Images
(Institute of Electrical and Electronics Engineers Inc., 2024) Putty, A.; Annappa, B.; Prajwal, R.; Pariserum Perumal, S.P.
Semantic segmentation of remotely sensed images for land-use and land-cover classes plays a significant role in various ecosystem management applications. State-of-the-art results in assigning land-use and land-cover classes are primarily achieved using fully convolutional encoder-decoder architectures. However, the uneven distribution of the land-use and land-cover classes becomes a major hurdle leading to performance skewness towards majority classes over minority classes. This paper proposes a novel dual-phase training, with the first phase proposing a new undersampling technique using minority class focused class normalization and the second phase that uses this learnt knowledge for ensembling to prevent overfitting and compensate for the loss of information due to undersampling. The proposed method achieved an overall performance gain of up to 2% in MIoU, Kappa, and F1 Score metrics and up to 3% in class-wise F1-score when compared to the baseline models on Wuhan Dense Labeling, Vaihingen and Potsdam datasets. © 2013 IEEE.
An automated deep learning pipeline for detecting user errors in spirometry test
(Elsevier Ltd, 2024) Bonthada, S.; Pariserum Perumal, S.P.; Naik, P.P.; Mahesh, M.A.; Rajan, J.
Spirometer is used as a major diagnostic tool for obstructive airway diseases and a monitoring tool for therapy response and disease staging over time. It is a sophisticated medical device employed to quantify flow and volume of air exhaled by a subject during a specific testing period. The essential metrics obtained from the spirometry test, play a crucial role in enabling healthcare professionals to thoroughly evaluate the respiratory health and condition of the individual under examination. Several spirometer measurements including Forced Vital Capacity (FVC) and Forced Expiratory Volume (FEV) serve as guidelines for diagnosis and prognosis of Chronic Obstructive Pulmonary Diseases (COPD) and asthma. However, user errors caused by different reasons, including improper handling of the equipment and poor performance during the maneuvers of the expiratory airflow, end up in incorrect treatment directions. To ensure accurate results, spirometry tests traditionally require the presence of a skilled professional to identify and address these errors promptly. A novel machine learning approach is proposed in this paper to automatically identify four such user errors based on Volume-Time and Flow-Volume graphs. By detecting specific errors and providing immediate feedback to patients, reliability and accuracy of spirometry results will be improved and the need for trained professionals will be reduced. The implementation facilitates the widespread adoption of spirometry, particularly in low-resource telemedicine settings. This work implements a binary classification model distinguishing between normal and error test samples, achieving a prediction accuracy of 93%. Additionally, a 4-way classification model is presented for identifying individual error sub-types, demonstrating a prediction accuracy of 94%. © 2023 Elsevier Ltd
BENN: Balanced Ensemble Neural Network for Handling Class Imbalance in Big Data
(John Wiley and Sons Inc, 2025) Sneha, S.H.; Annappa, B.; Pariserum Perumal, S.P.
Class imbalance is a critical challenge in big data analytics, often leading to biased predictive models. This imbalance can lead to biased models that perform well on the majority class but poorly on the minority class. Many machine learning models tend to be biased towards the majority class because they aim to minimise overall error, often leading to poor performance on the minority class. This paper presents the balanced ensemble neural network, a novel solution to effectively address class imbalance in big data. Balanced ensemble neural network combines the robust capabilities of neural networks with the power of ensemble learning, incorporating class balancing strategies to ensure fair representation of minority classes. The methodology involves integrating multiple neural networks, each trained on balanced subsets of data using techniques like Synthetic Minority Over-sampling Technique and Random Undersampling. This integration aims to leverage the strengths of individual networks while reducing their inherent biases. Our extensive experiments across various datasets reveal that BENN achieves an AUC-ROC score of 0.94, surpassing other models such as random forest (0.88), support vector (0.84) and single neural net (0.80). It was also observed that BENN's performance is better compared to traditional neural network models and standard ensemble methods in key metrics like accuracy, precision, recall, F1-score and AUC-ROC. The results specifically highlight BENN's effectiveness in accurately classifying instances of minority classes, a notable challenge in many existing models. These findings underscore BENN's potential as a substantial advancement in handling class imbalance within big data environments, offering a promising direction for future research and application in machine learning. © 2024 John Wiley & Sons Ltd.
Semantic Segmentation of Remotely Sensed Images using Multisource Data: An Experimental Analysis
(Institute of Electrical and Electronics Engineers Inc., 2024) Putty, A.; Annappa, B.; Prajwal, R.; Pariserum Perumal, S.P.
Remotely sensed data obtained from diverse sensors provide rich information for a wide range of applications in remote sensing, such as land use and land cover mapping. Due to the availability of a large amount of data, advanced deep-learning techniques have been incorporated into this domain. However, these techniques require a significant amount of annotated data, which can be challenging to obtain for land-use and land-cover mapping. Multisource data fusion has become crucial in remotely sensed image analysis to overcome this challenge, providing significant benefits across various applications. This paper analyzes the fusion of multisource data tailored for land-use and land-cover mapping. The analysis showcases that incorporating the novel knowledge transfer approach from multisource data has helped to achieve a 1-6% improvement in mIoU for the Kaggle Aerial Image dataset. Â© 2024 IEEE.