Digital Beauty Standards: AI Approaches to Objectively Measure and Score Beauty Quotients
Automated Diabetic Retinopathy Screening in Resource-Limited Areas with Attention-Enhanced Deep Learning on Fundus Images
Detection and Classification of Player Formations in Sports using Neural Networks
Automated Detection of Tomato Leaf Diseases through Convolutional Neural Networks
Application of Computational and Geocomputation Techniques for Geospatial Analysis
Identification of Volcano Hotspots by using Resilient Back Propagation (RBP) Algorithm Via Satellite Images
Data Hiding in Encrypted Compressed Videos for Privacy Information Protection
Improved Video Watermarking using Discrete Cosine Transform
Contrast Enhancement based Brain Tumour MRI Image Segmentation and Detection with Low Power Consumption
Denoising of Images by Wavelets and Contourlets using Bi-Shrink Filter
Artificial intelligence (AI) has gained prominence in aesthetic dentistry, where precision and personalization are key to enhancing patient satisfaction. Facial aesthetics, influenced by symmetry, proportionality, and adherence to the golden ratio, play a significant role in perceived attractiveness. The Beauty Quotient (BQ), a novel metric based on mathematical ratios and geometric analysis, offers an objective framework for evaluating facial symmetry and balance. This study aims to validate the BQ as a reliable tool for correlating objective facial measurements with subjective beauty perceptions. Symmetry in the eye and mouth regions was calculated using a defined formula and compared with the golden ratio for proportionality. The BQ, computed through a composite formula incorporating symmetry, golden ratio adherence, and facial proportions, was normalized to a scale with customizable weights. The BQ was applied to a sample of participants to evaluate individual facial aesthetics. By quantifying facial attractiveness through AI-driven techniques, this study bridges subjective perceptions with objective mathematical principles, advancing AI's role in beauty assessment. Furthermore, AI is utilized to optimize smile design, symmetry, and facial harmony in dentistry, establishing objective standards that enhance treatment planning and patient outcomes.
Diabetic retinopathy (DR) is a leading contributor to vision impairment, particularly in areas with limited resources where access to specialized care is scarce. This study introduces an automated screening system for DR using attention- enhanced deep learning on retinal fundus images, specifically designed for these regions. The system leverages convolutional neural network (CNN) technology with integrated attention mechanisms to focus on critical features indicative of DR, such as microaneurysms and hemorrhages, improving detection accuracy and reliability. Varied retinal fundus images were used for training and validation, with data augmentation applied to enhance model robustness. The model was optimized for deployment on low-cost hardware, ensuring feasibility in resource-limited settings. Performance evaluation demonstrated high sensitivity and specificity, and attention maps provided interpretability for healthcare providers. This automated system has the potential to enhance early detection of diabetic retinopathy (DR) in underserved areas, facilitating timely intervention and reducing the risk of blindness. By making advanced diagnostic tools accessible, this approach promotes equitable healthcare and helps to prevent vision loss globally.
This study investigates the use of neural networks to identify and categorize player formations in sports, aiming to enhance tactical analysis and decision-making. High-resolution match footage is collected and meticulously labeled to identify player positions, forming the basis for training a convolutional neural network (CNN). The network is designed to recognize various player formations with high accuracy by applying sophisticated object detection algorithms. The model achieves promising results across common formations. Precision, recall, and F1 scores further demonstrate its effectiveness, indicating reliable classification even under varying conditions. These outcomes provide valuable insights for analysts and coaches, offering a robust tool to enhance strategic planning and improve team performance. Future work will focus on refining the model's accuracy, expanding the dataset, and incorporating real-time analysis capabilities to advance tactical decision-making in competitive sports.
The study aims to use Convolutional Neural Networks (CNNs) to develop an automated system for identifying and categorizing tomato leaf diseases, with the goal of increasing agricultural productivity and improving crop management. By addressing the inefficiencies of traditional manual inspection methods, this research aims to provide timely and accurate disease diagnoses, ultimately benefiting farmers. The methodology involves several key steps, including data collection from high-resolution images of tomato leaves, data preprocessing, and the implementation of CNNs for feature extraction and classification. The model demonstrated effectiveness in identifying various diseases, showcasing the potential of deep learning in agricultural applications. Moreover, the system is robust against variations in image quality and environmental conditions. This research contributes to ongoing efforts to improve disease management practices in agriculture. Future work will focus on expanding the model's capabilities to include other plant species and integrating real-time monitoring solutions for enhanced field applications.
Computational science has significantly advanced theory and experiment over many decades. Specifically, computational geography emerged in the 1980s in response to the reductionist limitations of early GIS software, which hindered deeper analyses of complex geographic data. The advent of relational databases further facilitated the use of computational methods in spatial data analysis. This study discusses the application of computational techniques and geocomputation in the spatial analysis of geographical phenomena. A literature search and data synthesis were conducted, followed by an exploration of computational methods, geocomputation, spatial data representation, storage and organization, spatial analytics, and GeoAI. Geocomputation is defined as the application of computer- intensive approaches, particularly those employing non-conventional data clustering and analysis methods, to discern knowledge. At present, these computational techniques enable the integration of diverse fields, supporting spatial analyses that require resources or ontological frameworks beyond the capabilities of traditional GIS software.
