Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Personalized and Safe Route Planning for Asthma Patients Using Real-Time Environmental Data

Nada Ayman, Shaimaa Alaa, Mohamed Hussein, Ali Hamdi

TL;DR

This paper addresses the problem of routing for asthma patients by integrating real-time environmental data with personalized health profiles. It introduces a health-aware routing framework that uses an enhanced A* heuristic, where the decision function is $\mathbf{R}(i,t) = f(\mathbf{A}_i, \mathbf{W}(t), \mathbf{T}(t))$ and the safety-aware objective is $r_{\text{safe}} = \arg\min_{\mathbf{r}} \left( \sum_i d(\mathbf{r}_i) + \alpha h_{\text{env}}(\mathbf{r}_i,t,\mathbf{A}_i) \right)$; $f(\mathbf{r}_i) = g(\mathbf{r}_i) + h_{\text{env}}(\mathbf{r}_i,t,\mathbf{A}_i)$. Using SUMO simulations and real-time data from the Microsoft Weather API, the approach demonstrates improved asthma-risk avoidance with only modest increases in computation time compared to traditional Dijkstra routing. The work's key contributions include a formal problem formulation, a data-acquisition and routing pipeline, and empirical evidence that health-aware heuristics can yield safer, more personalised routes in dynamic urban environments, with implications for public health and urban planning. Future extensions could incorporate forecasting via machine learning, long-term health considerations, and global deployment to broaden applicability.

Abstract

Asthmatic patients are very frequently affected by the quality of air, climatic conditions, and traffic density during outdoor activities. Most of the conventional routing algorithms, such as Dijkstra's algorithm, usually fail to consider these health dimensions, hence resulting in suboptimal or risky recommendations. Here, the health-aware heuristic framework is presented that shall utilize real-time data provided by the Microsoft Weather API. The advanced A* algorithm provides dynamic changes in routes depending on air quality indices, temperature, traffic density, and other patient-related health data. The power of the model is realized by running simulations in city environments and outperforming the state-of-the-art methodology in terms of recommendation accuracy at low computational overhead. It provides health-sensitive route recommendations, keeping in mind the avoidance of high-risk areas and ensuring safer and more suitable travel options for asthmatic patients.

Personalized and Safe Route Planning for Asthma Patients Using Real-Time Environmental Data

TL;DR

This paper addresses the problem of routing for asthma patients by integrating real-time environmental data with personalized health profiles. It introduces a health-aware routing framework that uses an enhanced A* heuristic, where the decision function is and the safety-aware objective is ; . Using SUMO simulations and real-time data from the Microsoft Weather API, the approach demonstrates improved asthma-risk avoidance with only modest increases in computation time compared to traditional Dijkstra routing. The work's key contributions include a formal problem formulation, a data-acquisition and routing pipeline, and empirical evidence that health-aware heuristics can yield safer, more personalised routes in dynamic urban environments, with implications for public health and urban planning. Future extensions could incorporate forecasting via machine learning, long-term health considerations, and global deployment to broaden applicability.

Abstract

Asthmatic patients are very frequently affected by the quality of air, climatic conditions, and traffic density during outdoor activities. Most of the conventional routing algorithms, such as Dijkstra's algorithm, usually fail to consider these health dimensions, hence resulting in suboptimal or risky recommendations. Here, the health-aware heuristic framework is presented that shall utilize real-time data provided by the Microsoft Weather API. The advanced A* algorithm provides dynamic changes in routes depending on air quality indices, temperature, traffic density, and other patient-related health data. The power of the model is realized by running simulations in city environments and outperforming the state-of-the-art methodology in terms of recommendation accuracy at low computational overhead. It provides health-sensitive route recommendations, keeping in mind the avoidance of high-risk areas and ensuring safer and more suitable travel options for asthmatic patients.
Paper Structure (16 sections, 4 equations, 2 figures, 2 tables)

This paper contains 16 sections, 4 equations, 2 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Problem Formulation
  4. Research Methodology
  5. Data Acquisition
  6. Route-Planning Request
  7. Search Optimization
  8. Simulation
  9. Simulation Testing
  10. Results and Discussion
  11. Experimental Setup
  12. Performance Metrics
  13. Limitations
  14. Future Work
  15. Conclusion
  16. ...and 1 more sections

Figures (2)

  • Figure 1: The proposed model optimizes route planning for asthma patients by considering their health sensitivity using multiple sources of data(a). It integrates data from asthma patient profiles and real-time weather and flow conditions into a comprehensive routing request. This request is executed within a transportation network, which is simulated for realism through SUMO(b). Advanced search optimisation processes are employed via heuristic-based searches on the A* and Dijkstra algorithms(c). The routes are analyzed dynamically concerning environmental and health-related factors(e), which would identify those with minimum exposure to high-risk areas(f). The final output is the best route that avoids polluted locations for asthma sufferers(g), guaranteeing safe and efficient transportation.
  • Figure 2: Route optimization in an urban environment, illustrating dynamic path adjustments based on real-time weather conditions and road disruptions. Green paths represent optimal routes, while the red path indicates a route affected by adverse conditions such as rain and dust.