Evaluation of a Clinical Acceptability of Deep Learning-Based Autocontouring: An Example of The Use of Artificial Intelligence in Prostate Radiotherapy

Analyzing public surveillance videos has become an important research area as it is linked to different real-world applications. Video Analytics for human action recognition is given significance due to its utility. However, it is very challenging to analyze live-streaming videos to identify human actions across the frames in the video. The literature showed that Convolutional Neural Networks (CNNs) are among computer vision applications' most popular deep learning algorithms. Another important observation is that Generative Adversarial Network(GAN) architecture with deep learning has the potential to leverage effectiveness in applications using computer vision. Inspired by this finding, we created a GAN-based framework (called HARGAN) in this research for human activity identification from surveillance films. The framework exploits a retrained deep learning model known as ResNet50 and convolutional LSTM for better performance in action recognition. Our framework has two critical functionalities: feature learning and human action recognition. The ResNet50 model achieves the former, while the GAN-based convolutional LSTM model achieves the latter. We proposed an algorithm called the Generative Adversarial Approach for Human Action Recognition (GAA-HAR) to realize the framework. We used a benchmark dataset known as UCF50, which is extensively used in studies on human action identification. Based on our experimental findings, the suggested framework performs better than the current baseline models like CNN, LSTM, and convolutional LSTM, with the highest accuracy of 97.73%. Our framework can be used in video analytics applications linked to large-scale public surveillance.

HARGAN: Generative Adversarial Network BasedDeep Learning Framework for Efficient Recognition of Human Actions from Surveillance Videos

Boddupally JANAIAH,

Suresh PABBOJU

2024

Comparative Assessment of Machine Learning Algorithms for Effective Diabetes Prediction and Care

Nuthakki,

Pavankumar T.

2024

The prevalence and impact of diabetes have increased significantly over time, posing a major concern for the healthcare sector globally, especially in India. This study aims to enhance diabetes prediction and management through the use of artificial intelligence (AI) and machine learning (ML) methodologies. We present a range of AI-driven approaches that leverage ML algorithms to classify and predict diabetes more effectively. While most studies utilize the PIMA dataset, a few notable cases have also incorporated custom datasets curated from select healthcare organizations. This research provides a comparative assessment of state-of-the-art diabetes prediction methods alongside carefully selected care strategies. The study is organized into three categories, each exploring distinct approaches, and analyzes methodologies, ML algorithms, accuracy results, and validation metrics. By examining key parameters and techniques, this paper considers diabetes prediction and care tailored to the Indian population, accounting for various influencing factors.

Enhancing Ophthalmological Diagnoses: An Adaptive Ensemble Learning Approach Using Fundus and OCT Imaging

LAVUDIYA,

C.V.P.R Prasad

2024

This study presents an innovative Ensemble Disease Learning Algorithm (EDL) for the detection and classification of retinal diseases using fundus images. We enhance our method by incorporating deep learning techniques and multi-modal imaging data, including optical coherence tomography (OCT) images alongside fundus photographs, to provide a more comprehensive understanding of retinal pathology. The advanced EDL integrates Convolutional Neural Networks (CNNs) and attention mechanisms with Capsule Networks (CapsNet) and Support Vector Machine (SVM) classifiers for more nuanced feature extraction and classification. We introduce a novel ensemble adaptive weighting approach that dynamically adjusts classifier weights based on performance across disease types and severity levels, significantly improving the algorithm's handling of complex and rare cases. To enhance model interpretability, we implement an explainable AI component that provides visual heatmaps of the most significant regions for each diagnosis to clinicians. We evaluate the enhanced EDL on a large, diverse dataset encompassing multiple retinal diseases, including diabetic retinopathy, age-related macular degeneration, and glaucoma, across various ethnicities and age groups. Our results demonstrate superior accuracy, sensitivity, and specificity compared to our previous model and other state-of-the-art approaches. A prospective clinical validation study assesses the algorithm's real-world performance. This research advances automated retinal disease diagnosis by making it more robust, accurate, and clinically relevant, potentially improving patient outcomes and global eye care through early disease detection and treatment planning.