Exploring the Geospatial Relationship Between COVID-19 Positivity and Income in Mixed Urban-Rural Population.

The COVID-19 pandemic has had a deep influence on American life in general and on the American economy in particular. However, the burden of the pandemic has not been distributed equally among members of a population based on their social-determinants-of-health. The purpose of this study was to investigate whether the median income was associated with COVID-19 total number of tests and positivity rate in Boone County, Missouri during the pandemic. We analyzed the geospatial data using three heat maps showing the Census tract-wise COVID-19 positivity rate, Census tract-wise median income, and Census tract-wise total number of COVID-19 tests to highlight our study findings. Our study results support the hypothesis that individuals with lower median income tend to have a lower total number of COVID-19 tests and higher COVID-19 positivity rates in Boone County, Missouri. The Pearson correlation coefficient between the positivity rate and median income is -0.324.

A semi-supervised approach to unobtrusively predict abnormality in breathing patterns using hydraulic bed sensor data in older adults aging in place.

Shortness of breath is often considered a repercussion of aging in older adults, as respiratory illnesses like COPD1 or respiratory illnesses due to heart-related issues are often misdiagnosed, under-diagnosed or ignored at early stages. Continuous health monitoring using ambient sensors has the potential to ameliorate this problem for older adults at aging-in-place facilities. In this paper, we leverage continuous respiratory health data collected by using ambient hydraulic bed sensors installed in the apartments of older adults in aging-in-place Americare facilities to find data-adaptive indicators related to shortness of breath. We used unlabeled data collected unobtrusively over the span of three years from a COPD-diagnosed individual and used data mining to label the data. These labeled data are then used to train a predictive model to make future predictions in older adults related to shortness of breath abnormality. To pick the continuous changes in respiratory health we make predictions for shorter time windows (60-s). Hence, to summarize each day's predictions we propose an abnormal breathing index (ABI) in this paper. To showcase the trajectory of the shortness of breath abnormality over time (in terms of days), we also propose trend analysis on the ABI quarterly and incrementally. We have evaluated six individual cases retrospectively to highlight the potential and use cases of our approach.

Anthropogenic Object Localization: Evaluation of Broad-Area High-Resolution Imagery Scans Using Deep Learning in Overhead Imagery.

Too often, the testing and evaluation of object detection, as well as the classification techniques for high-resolution remote sensing imagery, are confined to clean, discretely partitioned datasets, i.e., the closed-world model. In recent years, the performance on a number of benchmark datasets has exceeded 99% when evaluated using cross-validation techniques. However, real-world remote sensing data are truly big data, which often exceed billions of pixels. Therefore, one of the greatest challenges regarding the evaluation of machine learning models taken out of the clean laboratory setting and into the real world is the difficulty of measuring performance. It is necessary to evaluate these models on a grander scale, namely, tens of thousands of square kilometers, where it is intractable to the ground truth and the ever-changing anthropogenic surface of Earth. The ultimate goal of computer vision model development for automated analysis and broad area search and discovery is to augment and assist humans, specifically human-machine teaming for real-world tasks. In this research, various models have been trained using object classes from benchmark datasets such as UC Merced, PatternNet, RESISC-45, and MDSv2. We detail techniques to scan broad swaths of the Earth with deep convolutional neural networks. We present algorithms for localizing object detection results, as well as a methodology for the evaluation of the results of broad-area scans. Our research explores the challenges of transitioning these models out of the training-validation laboratory setting and into the real-world application domain. We show a scalable approach to leverage state-of-the-art deep convolutional neural networks for the search, detection, and annotation of objects within large swaths of imagery, with the ultimate goal of providing a methodology for evaluating object detection machine learning models in real-world scenarios.

Demographic and Time Trend Analysis of COVID-19 Test Results of Boone County, Missouri.

The COVID-19 pandemic has had deep influence on American life. However, the burden of the pandemic has not been distributed equally among members of a population based on their demographic features. The purpose of this study was to investigate whether sex, age, race, and religion were associated with COVID-19 positivity rates in Boone County, Missouri over a 22-month period (March 15, 2020 to December 2, 2021) of the pandemic. We analyzed the data using age distribution histograms, two-way delta tables, and trend analysis graphs to highlight our study findings. We evaluated those graphs with each demographic feature across a collection of defined epochs of key events, such as vaccine release, Delta variant, vaccine boosters, and initial Omicron variant. Our results supported the hypothesis that males and minority races such as Black or African Americans and All-Other are more likely to have a higher COVID-19 positivity rate across our defined epochs.

The Role of Remote Sensing and Geospatial Analysis for Understanding COVID-19 Population Severity: A Systematic Review.

Remote sensing (RS), satellite imaging (SI), and geospatial analysis have established themselves as extremely useful and very diverse domains for research associated with space, spatio-temporal components, and geography. We evaluated in this review the existing evidence on the application of those geospatial techniques, tools, and methods in the coronavirus pandemic. We reviewed and retrieved nine research studies that directly used geospatial techniques, remote sensing, or satellite imaging as part of their research analysis. Articles included studies from Europe, Somalia, the USA, Indonesia, Iran, Ecuador, China, and India. Two papers used only satellite imaging data, three papers used remote sensing, three papers used a combination of both satellite imaging and remote sensing. One paper mentioned the use of spatiotemporal data. Many studies used reports from healthcare facilities and geospatial agencies to collect the type of data. The aim of this review was to show the use of remote sensing, satellite imaging, and geospatial data in defining features and relationships that are related to the spread and mortality rate of COVID-19 around the world. This review should ensure that these innovations and technologies are instantly available to assist decision-making and robust scientific research that will improve the population health diseases outcomes around the globe.

Stepping Beyond Assessment: Fall Risk Prediction Models Among Older Adults from Cumulative Change in Gait Parameter Estimates.

Falls significantly affect the health of older adults. Injuries sustained through falls have long-term consequences on the ability to live independently and age in place, and are the leading cause of injury death in the United States for seniors. Early fall risk detection provides an important opportunity for prospective intervention by healthcare providers and home caregivers. In-home depth sensor technologies have been developed for real-time fall detection and gait parameter estimation including walking speed, the sixth vital sign, which has been shown to correlate with the risk of falling. This study evaluates the use of supervised classification for estimating fall risk from cumulative changes in gait parameter estimates as captured by 3D depth sensors placed within the homes of older adult participants. Using recall as the primary metric for model success rate due to the severity of fall injuries sustained by false negatives, we demonstrate an enhancement of assessing fall risk with univariate logistic regression using multivariate logistic regression, support vector, and hierarchical tree-based modeling techniques by an improvement of 18.80%, 31.78%, and 33.94%, respectively, in the 14 days preceding a fall event. Random forest and XGBoost models resulted in recall and precision scores of 0.805 compared to the best univariate regression model of Y-Entropy with a recall of 0.639 and precision of 0.527 for the 14-day window leading to a predicted fall event.

HTIDB: Hierarchical Time-Indexed Database for Efficient Storage and Access to Irregular Time-series Health Sensor Data.

With the enormous amount of data collected by unobtrusive sensors, the potential of utilizing these data and applying various multi-modal advanced analytics on them is numerous and promising. However, taking advantage of the ever-growing data requires high-performance data-handling systems to enable high data scalability and easy data accessibility. This paper demonstrates robust design, developments, and techniques of a hierarchical time-indexed database for decision support systems leveraging irregular and sporadic time series data from sensor systems, e.g., wearables or environmental. We propose a technique that leverages the flexibility of general purpose, high-scalability database systems, while integrating data analytics focused column stores that leverage hierarchical time indexing, compression, and dense raw numeric data storage. We have evaluated the performance characteristics and tradeoffs of each to understand the data access latencies and storage requirements, which are key elements for capacity planning for scalable systems.

Leveraging Unsupervised Machine Learning to Discover Patterns in Linguistic Health Summaries for Eldercare.

The Center for Eldercare and Rehabilitation Technology, at University of Missouri, has researched the use of smart, unobtrusive sensors for older adult residents' health monitoring and alerting in aging-in-place communities for many years. Sensors placed in the apartments of older adult residents generate a deluge of daily data that is automatically aggregated, analyzed, and summarized to aid in health awareness, clinical care, and research for healthy aging. When anomalies or concerning trends are detected within the data, the sensor information is converted into linguistic health messages using fuzzy computational techniques, so as to make it understandable to the clinicians. Sensor data are analyzed at the individual level, therefore, through this study we aim to discover various combinations of patterns of anomalies happening together and recurrently in the older adult's population using these text summaries. Leveraging various computational text data processing techniques, we are able to extract relevant analytical features from the health messages. These features are transformed into a transactional encoding, then processed with frequent pattern mining techniques for association rule discovery. At individual level analysis, resident ID 3027 was considered as an exemplar to describe the analysis. Seven combinations of anomalies/rules/associations were discovered in this resident, out of which rule group three showed an increased recurrence during the COVID lockdown of facility. At the population level, a total of 38 associations were discovered that highlight the health patterns, and we continue to explore the health conditions associated with them. Ultimately, our goal is to correlate the combinations of anomalies with certain health conditions, which can then be leveraged for predictive analytics and preventative care. This will improve the current clinical care systems for older adult residents in smart sensor, aging-in-place communities.

Extending the Morphological Hit-or-Miss Transform to Deep Neural Networks.

While most deep learning architectures are built on convolution, alternative foundations such as morphology are being explored for purposes such as interpretability and its connection to the analysis and processing of geometric structures. The morphological hit-or-miss operation has the advantage that it considers both foreground information and background information when evaluating the target shape in an image. In this article, we identify limitations in the existing hit-or-miss neural definitions and formulate an optimization problem to learn the transform relative to deeper architectures. To this end, we model the semantically important condition that the intersection of the hit and miss structuring elements (SEs) should be empty and present a way to express Don't Care (DNC), which is important for denoting regions of an SE that are not relevant to detecting a target pattern. Our analysis shows that convolution, in fact, acts like a hit-to-miss transform through semantic interpretation of its filter differences. On these premises, we introduce an extension that outperforms conventional convolution on benchmark data. Quantitative experiments are provided on synthetic and benchmark data, showing that the direct encoding hit-or-miss transform provides better interpretability on learned shapes consistent with objects, whereas our morphologically inspired generalized convolution yields higher classification accuracy. Finally, qualitative hit and miss filter visualizations are provided relative to single morphological layer.

GeoIRIS: Geospatial Information Retrieval and Indexing System-Content Mining, Semantics Modeling, and Complex Queries.

Searching for relevant knowledge across heterogeneous geospatial databases requires an extensive knowledge of the semantic meaning of images, a keen eye for visual patterns, and efficient strategies for collecting and analyzing data with minimal human intervention. In this paper, we present our recently developed content-based multimodal Geospatial Information Retrieval and Indexing System (GeoIRIS) which includes automatic feature extraction, visual content mining from large-scale image databases, and high-dimensional database indexing for fast retrieval. Using these underpinnings, we have developed techniques for complex queries that merge information from heterogeneous geospatial databases, retrievals of objects based on shape and visual characteristics, analysis of multiobject relationships for the retrieval of objects in specific spatial configurations, and semantic models to link low-level image features with high-level visual descriptors. GeoIRIS brings this diverse set of technologies together into a coherent system with an aim of allowing image analysts to more rapidly identify relevant imagery. GeoIRIS is able to answer analysts' questions in seconds, such as "given a query image, show me database satellite images that have similar objects and spatial relationship that are within a certain radius of a landmark."