91341 research outputs found
Sort by
Multi-Semantic-Stage Neural Networks for Robust and Interpretable Deep Learning
Get PDFDeep neural networks have great representational power. However, most deep neural nets today optimize directly for performance on a single task defined only by labeled training data. This excludes potential sources of knowledge and ways of learning which could improve their performance, and address challenges, such as explainability, which are pressing to the field. We propose a framework for neural network architecture which generalizes it to a graph of many semantically-meaningful variables. We call it the Multi-Semantic-Stage Neural Network (MSSNN). An MSSNN models its domain as a web of conditional probabilities, i.e. a collection of inter-related tasks which can learn from each other. This way of conceptualizing a deep learning model manifests in several immediately useful capabilities. Such a model can easily exploit more and different kinds of labels in its training data. It can supplement its training data by incorporating expert knowledge, both in the structure of its graph and in the form of hard-coded relationships between variables. Graph structures such as multiple incident edges on a single variable automatically lead to semi-supervised learning ability. And finally, the MSSNN’s ability to sample from learned joint distributions allows us to construct novel explanations, directly tied to actual causes of the model’s behavior. We perform an initial demonstration of these capabilities by constructing and evaluating Multi-Semantic-Stage Neural Networks of several sizes for a collection of computer vision tasks
Application of Multiple Data Augmentation Techniques to Improve Training with Synthetic SAR Data in Common CNN
Get PDFTo address the issues of limited target data in the Synthetic Aperture Radar Automatic Target Recognition (SAR ATR) problem set, synthetic data is often used to aid in filling the gap. This paper covers an in depth look at the use of colorization, dynamic range adjustment, and target extraction as data augmentation techniques to improve the accuracy of deep learning networks trained on synthetic SAR data. The use of multiple different data augmentations combine to dramatically improve the accuracy of a common Convolutional Neural Network (CNN) over the use of standard synthetic data. A comparison of increasing fraction of measured data were used to show that the less measured data there is available the more critical these data augmentation techniques are to improve target recognition
Pneumonia Detection With Limited and Imbalanced Data Using Energy-Based Out-of-Distribution Technique
Get PDFThe automated detection of pneumonia through chest X-ray presents a critical challenge in medical diagnostics, particularly due to the restrictions of limited and imbalanced chest X-ray data for training AI models. Traditional methods that depend on softmax confidence scores can be overconfident even when generating erroneous outputs especially when they are processing completely new inputs, leading to unreliable diagnostic results. This research addresses challenges in AI models which aim to develop a robust pneumonia detection system using an Energy-Based Out-of-Distribution (OOD) technique that can work effectively even with limited and imbalanced data. The study focused on creating a more reliable diagnostic framework that could maintain high accuracy and F1 scores even with limited training datasets. The proposed method uses energy scores derived from neural networks to distinguish between pneumonia (Out-of-Distribution) chest X-rays and non-pneumonia (In-Distribution) chest X-rays. Experiment is performed on chest X-ray datasets, comparing the performance against conventional softmax-based methods and other baseline approaches such as CNN, ResNet, DenseNet, and Outlier Exposure. The pneumonia detection using Energy-Based Out-of-Distribution approach showed superior performance even though it is trained only on 50 images, achieving a significant reduction in false negative rates while maintaining high accuracy and F1 score in pneumonia (Out-of-Distribution) cases. This research addresses the challenges of implementing deep learning neural networks in medical contexts with limited and imbalanced datasets
An Enhanced Real-Time Object Detection of Helmets and License Plates Using a Lightweight YOLOv8 Deep Learning Model
Get PDFTraffic surveillance and enforcement heavily depend on the real-time detection of helmets and license plates, particularly in high-density urban environments. This study presents a dynamic and optimized lightweight model, the proposed G-YOLOv8n, designed for resource constrained edge devices like the Raspberry Pi. By integrating the GhostNet module into the YOLOv8n architecture, this research achieves a nearly 50% reduction in model size and computational load, while maintaining comparable detection accuracy to the original YOLOv8n. These enhancements enable real-time processing capabilities crucial for traffic monitoring operations. The growing demand for real-time, low-power solutions in intelligent transportation systems necessitates lightweight, efficient detection models. The proposed G-YOLOv8n model developed in this research leverages advancements in deep learning model compression and efficient feature extraction techniques to meet the constraints of edge computing platforms. Through methodologies of pruning and quantization, the model’s deployment on Raspberry Pi devices is optimized to balance detection accuracy with processing speed, addressing the challenges of limited memory and computational power typical of edge environments. In addition to object detection, this study also integrates Optical Character Recognition (OCR) for license plate recognition, enabling an integrated solution for helmet detection and automatic license plate recognition (ALPR) in traffic enforcement scenarios. Extensive experimental validation on real-world traffic datasets demonstrates the proposed G-YOLOv8n model’s ability to perform reliably under varied lighting and weather conditions. To ensure robustness, the model was subjected to adversarial patch attacks to evaluate its robustness under challenging conditions. While a strong indicator of performance in detecting license plates and riders is demonstrated by the model, it exhibited a degree of vulnerability to occlusions, particularly in the helmet and no-helmet classes. This research advances the field of real-time traffic surveillance by showcasing a scalable and energy-efficient approach for deploying advanced object detection on low-power devices. The findings offer valuable insights into model optimization strategies for edge deployment and adversarial attack resilience, paving the way for enhanced safety and compliance in intelligent transportation system
Investigation of NDV in Southern African Waterfowl Reveal Insightful Geographic and Biodiversity Trends to Help Contain the Virus
Get PDFThis study assesses the infection rates and trends of Newcastle disease in southern African waterfowl, a project carried out by Emily Murphy in Dr. Jeffrey Peters’ laborator
Can Periodical Cicadas Contribute To Urban Greening?
No full textThe potential fertilization effect of the decomposition of periodical cicadas on plant growth has been often discussed, but little quantified. I demonstrated this effect in an urban context by examining the effect of decomposing cicada carcasses and commercial lawn fertilizer on the growth of lawn grass in an 80-day greenhouse experiment. Deposition of cicada carcasses benefited aboveground growth of several lawn grasses in a dose-dependent manner, as did lawn fertilizer addition. The effect of cicadas at high levels of deposition was similar to that of the application of lawn fertilizer at half recommended rates. Notable increases in plant height and greenness were also observed in grasses given either treatment indicating the decomposition of cicadas can benefit growth in ways similar to lawn fertilizer, at least during the season following emergence
Physicians and The Holocaust: Book of Responses, Quotes, Reflections
Get PDFA book of responses, quotes, and reflections written for Physicians and the Holocaust course.https://corescholar.libraries.wright.edu/medicine_holocaust_books/1003/thumbnail.jp
Characterizing the Polyamorous Experience Through Research
Get PDFScientific study of polyamory and the individuals who practice it has seen a sharp increase in the last decade, revealing data and subjective experiences that support their capacity to be closely intimate and fulfilling, to bolster personal development, to provide a positive and stable family environment, and to mutually strengthen the bonds of each relationship involved. Understanding the unique experiences and challenges faced by polyamorous lovers is essential for cultural competence in relational research, clinical practice, institutional regulations, and moving toward greater social acceptance. Examined here are the associated stigmas and their impacts on polyamorous individuals, the motivations people have for becoming and remaining poly, the underlying values of the concept, the benefits these relationships can carry, prosocial behaviors that facilitate successful polyamory, the different ways multiple consensual relationships are arranged and interpreted, need fulfillment, the dynamics of poly families, and how jealousy and compersion interact within polyamorous contexts
Exploring the Systems-Related Factors Influencing Depression and Anxiety in the Private Healthcare System: A Nursing Student’s Perspective
Get PDFThis paper presents a student’s critical synthesis of the literature and excellent grasp of the application of the World Health Organization Health Systems Building Blocks Framework to identify strengths, and improvement opportunities for nursing interventions in mental health care. The student’s writing demonstrates an awareness of factors that impact complex health systems in nursing practice which is an important competency in system-based practice
Festival of Research Abstracts, Spring 2024
Get PDFThe collection of abstracts accepted for the Spring 2024 Festival of Research hosted by the Wright State University College of Science and Mathematics