arXiv subjects

Allison Clarke

Publications and source records attributed to Allison Clarke.

3 recordsLinked to original sources

arXiv2024

Analyzing Common Social and Physical Features of Flash-Flood Vulnerability Hotspots in Urban Areas

Flash flooding events, with their intense and sudden nature, present unique challenges for disaster researchers and emergency planners. To quantify the extent to which hotspots of flash flooding share similar social and physical features, the research uses community scale crowdsourced data and k means clustering. Crowdsourced data offers the potential to allocate limited resources, to improve spatial understanding, and to minimize the future effects of natural hazards. The research evaluates the impacts of Tropical Storm Imelda on Houston Metropolitan and Hurricane Ida on New York City. It develops a combined flash flood impact index based on FEMA claims, 311 calls, and Waze traffic reports which is able to capture a combination of crowdsourced data for the societal impact of flash flooding. In addition, k means clustering offers an essential tool for evaluating attributes associated with flash flooding events by grouping data into k number clusters of features. Thus, k means clustering evaluates the significance of a community's socio demographic, social capital, and physical features to the combined flood impact index. To ensure accessibility and replicability to different types of communities, our research uses publicly available datasets to understand how socio demographic data, social capital, and physical connectivity and development affect flash flood resilience. The findings reveal the intricate relationships associated with flash flooding impact as a combination of socio demographic and physical features. For instance, the cluster with the highest scores of the flash flood impact index from Tropical Storm Imelda had the highest percentage of minority population and lower income while the cluster with the second highest score flash flood impact index had the highest percentage of impervious surface and number of POIs.

physics.soc-ph↗

arXiv2021

Federated Learning for Privacy-Preserving Open Innovation Future on Digital Health

Privacy protection is an ethical issue with broad concern in Artificial Intelligence (AI). Federated learning is a new machine learning paradigm to learn a shared model across users or organisations without direct access to the data. It has great potential to be the next-general AI model training framework that offers privacy protection and therefore has broad implications for the future of digital health and healthcare informatics. Implementing an open innovation framework in the healthcare industry, namely open health, is to enhance innovation and creative capability of health-related organisations by building a next-generation collaborative framework with partner organisations and the research community. In particular, this game-changing collaborative framework offers knowledge sharing from diverse data with a privacy-preserving. This chapter will discuss how federated learning can enable the development of an open health ecosystem with the support of AI. Existing challenges and solutions for federated learning will be discussed.

cs.DC↗

arXiv2021

MIPO: Mutual Integration of Patient Journey and Medical Ontology for Healthcare Representation Learning

Representation learning on electronic health records (EHRs) plays a vital role in downstream medical prediction tasks. Although natural language processing techniques, such as recurrent neural networks, and self-attention, have been adapted for learning medical representations from hierarchical, time-stamped EHR data, they often struggle when either general or task-specific data are limited. Recent efforts have attempted to mitigate this challenge by incorporating medical ontologies (i.e., knowledge graphs) into self-supervised tasks like diagnosis prediction. However, two main issues remain: (1) small and uniform ontologies that lack diversity for robust learning, and (2) insufficient attention to the critical contexts or dependencies underlying patient journeys, which could further enhance ontology-based learning. To address these gaps, we propose MIPO (Mutual Integration of Patient Journey and Medical Ontology), a robust end-to-end framework that employs a Transformer-based architecture for representation learning. MIPO emphasizes task-specific representation learning through a sequential diagnosis prediction task, while also incorporating an ontology-based disease-typing task. A graph-embedding module is introduced to integrate information from patient visit records, thus alleviating data insufficiency. This setup creates a mutually reinforcing loop, where both patient-journey embedding and ontology embedding benefit from each other. We validate MIPO on two real-world benchmark datasets, showing that it consistently outperforms baseline methods under both sufficient and limited data conditions. Furthermore, the resulting diagnosis embeddings offer improved interpretability, underscoring the promise of MIPO for real-world healthcare applications.

cs.AI↗