空氣污染是世界各地日益嚴重的問題，根據世界衛生組織研究指出，2019年全球約99%的人口居住地的空氣污染高於世界衛生組織空氣品質指南，而其中都市區域更是長期處於空氣品質不佳的環境之下，面對持續存在的空氣污染問題，也使我們開始思考如何減輕空氣污染暴露對人們所帶來的負面影響。在所有受影響的人類群體之中我們尤為關注學童，主要是因為他們相較於成人並沒有那麼完整的免疫機制，為空氣污染暴露下之脆弱族群。過去的研究中指出，通勤時間的PM2.5、NO2、SO2濃度高於非通勤時段，且對於就學的學童，通勤也是主要接觸室外空氣污染的時段，由此可知，儘管通勤時間在一天之中的佔比並不高，卻是室外空氣污染暴露的潛在高峰，也使得通勤時間的暴露減量是值得仔細探討的。另外，傳統最短路徑規劃多半著重於使用最短時間或是距離抵達目的地，卻忽略了空氣污染所帶來的不良影響，隨著大眾健康與環保意識抬頭，將空氣污染因子納入路徑規劃被視為是一項解決方法，也提供了學童在通勤過程中的另一個選擇。在污染物推估的部分，過往研究並未針對多項對人體有害之污染物進行綜合規劃，導致無法良好地解釋空氣污染對人們影響的情形，因此本研究納入了PM2.5、NO2、SO2和O3等4項標準污染物，綜合污染指標的部分考量了主成分分數指標、空氣品質指標的成果進行規劃，以期更加全面地了解學童在通勤的暴露情形，提供多個替代路徑上的選擇。後續建立模型的部分，本研究之研究對象選擇了2019年至2020年，參與國家衛生研究院研究之高雄市899名學童，所使用之4項單一污染物、空氣品質指標(AQI Value)皆為機器學習所訓練之成果，模型解釋力達到了70~96%，驗證的部分皆有超過80%以上的解釋力，代表模型在時間、空間上也具有良好的適應能力。在路徑規劃的部份，我們使用了距離、空氣污染暴露等5項指標進行評估，以觀察各個替代路線的暴露改善情況。針對899學童之整體結果，相較於最短路徑，最低空氣污染暴露路線可以使學童的空氣污染暴露減少0.8至1.5%，同時稍微增加1.3至2.3%的距離，最低AQI value情境則是可以同時考量4項單一污染物，同時降低其暴露量；從暴露改善效率(DP/ED)來看，最低NO2暴露情境、最低AQI value情境的暴露改善效率值為0.91、0.96，為建議的最佳路徑。至於個案分析當中的3位學童，學童A、B、C皆能找到其相對應最佳的路徑，其中學童A、B、C最佳路徑之暴露改善效率為14.30、2.41、0.22，而透過最佳路徑，學童可以更有效地降低通勤過程中之空氣污染暴露，進而降低氣喘等其他呼吸道疾病發生之風險。

In face of the persistent issue of air pollution, considering how to mitigate adverse effects from air pollutant exposure is worthy of attention. Among the affected groups, we are particularly concerned about school children due to their weak protection mechanism compared to adults. Some studies indicate that commuting is when peak PM2.5, NO2, and SO2 exposures to outdoor air pollution occur. Therefore, finding ways to reduce exposure during commuting time requires careful consideration. Compared with traditional shortest route planning, the least air pollution exposure route in recent years provides another option for school children during commute. We utilized machine learning to estimate four. criterion pollutant such as PM2.5, NO2, SO2, and O3. For our subjects, we choose 899 school children in Kaohsiung City of Taiwan. They participated in the research conducted by the National Health research institute from 2019 to 2020. The results were evaluated by distance, air pollution exposure and other indicators. Then, we can assess the improvement of these alternative routes. Overall, the lowest air pollutants exposure routes can have 0.8~1.5% air pollution exposure reduction to school children's by slightly increasing 1.3~2.3% of distance comparing with the shortest routes. We provide school children with more efficient exposure reduction routes from the efficiency rate of exposure improvement(DP/ED). Through the optimal route, school children can reduce their exposure, thereby reducing the risk of asthma or another respiratory disease.

Ahmed, S., Adnan, M., Janssens, D., & Wets, G. (2020). A route to school informational intervention for air pollution exposure reduction. Sustainable Cities and Society, 53, 101965. https://doi.org/https://doi.org/10.1016/j.scs.2019.101965
Alvarez-Pedrerol, M., Rivas, I., López-Vicente, M., Suades-González, E., Donaire-Gonzalez, D., Cirach, M., de Castro, M., Esnaola, M., Basagaña, X., Dadvand, P., Nieuwenhuijsen, M., & Sunyer, J. (2017). Impact of commuting exposure to traffic-related air pollution on cognitive development in children walking to school. Environmental pollution, 231, 837-844. https://doi.org/https://doi.org/10.1016/j.envpol.2017.08.075
Ambient outdoor air pollution. (2023). Retrieved 6/26 from https://www.who.int/news-room/fact-sheets/detail/ambient-(outdoor)-air-quality-and-health
Anenberg, S. C., Mohegh, A., Goldberg, D. L., Kerr, G. H., Brauer, M., Burkart, K., Hystad, P., Larkin, A., Wozniak, S., & Lamsal, L. (2022). Long-term trends in urban NO2 concentrations and associated paediatric asthma incidence: estimates from global datasets. The Lancet Planetary Health, 6(1), e49-e58.
Babaan, J., Hsu, F.-T., Wong, P.-Y., Chen, P.-C., Guo, Y.-L., Lung, S.-C. C., Chen, Y.-C., & Wu, C.-D. (2023). A Geo-AI-based Ensemble Mixed Spatial Prediction Model with Fine Spatial-Temporal Resolution for Estimating Daytime/Nighttime/Daily Average Ozone Concentrations Variations in Taiwan. Journal of Hazardous Materials, 130749.
Bigazzi, A. Y., Broach, J., & Dill, J. (2016). Bicycle route preference and pollution inhalation dose: Comparing exposure and distance trade-offs. Journal of Transport & Health, 3(1), 107-113.
Boniardi, L., Dons, E., Campo, L., Van Poppel, M., Int Panis, L., & Fustinoni, S. (2019). Is a land use regression model capable of predicting the cleanest route to school? Environments, 6(8), 90.
Briggs, D. J., Collins, S., Elliott, P., Fischer, P., Kingham, S., Lebret, E., Pryl, K., Van Reeuwijk, H., Smallbone, K., & Van Der Veen, A. (1997). Mapping urban air pollution using GIS: a regression-based approach. International Journal of Geographical Information Science, 11(7), 699-718.
Castell, N., Dauge, F. R., Schneider, P., Vogt, M., Lerner, U., Fishbain, B., Broday, D., & Bartonova, A. (2017). Can commercial low-cost sensor platforms contribute to air quality monitoring and exposure estimates? Environment International, 99, 293-302.
Chakraborty, T., Khan, T. A., Naznin, M., Hyder, C. S., & Islam, A. A. A. (2016). What we breathe as we commute: From the perspective of a developing country. Proceedings of the 7th Annual Symposium on Computing for Development,
Chen, B. Y., Chen, C. H., Chuang, Y. C., Wu, Y. H., Pan, S. C., & Guo, Y. L. (2019). Changes in the relationship between childhood asthma and ambient air pollution in Taiwan: Results from a nationwide survey repeated 5 years apart. Pediatric Allergy and Immunology, 30(2), 188-194.
Cimorelli, A. J., Perry, S. G., Venkatram, A., Weil, J. C., Paine, R. J., Wilson, R. B., Lee, R. F., Peters, W. D., & Brode, R. W. (2005). AERMOD: A dispersion model for industrial source applications. Part I: General model formulation and boundary layer characterization [Article]. Journal of Applied Meteorology, 44(5), 682-693. https://doi.org/10.1175/JAM2227.1
CSDN中國開發者網絡. (2020). 解决最短路径的Dijkstra算法详解，附加Java代码. Retrieved 7 from https://blog.csdn.net/yldmkx/article/details/109962795
Dantzig, G. B., & Ramser, J. H. (1959). The truck dispatching problem. Management science, 6(1), 80-91.
De, D., & Das, C. S. (2021). Measuring livelihood sustainability by PCA in Indian Sundarban. Environment, Development and Sustainability, 23, 18424-18442.
Elford, S., & Adams, M. D. (2019). Exposure to ultrafine particulate air pollution in the school commute: Examining low-dose route optimization with terrain-enforced dosage modelling. Environmental research, 178, 108674.
ESRI. (2021). Algorithms used by the ArcGIS Network Analyst extension. Retrieved 8/17 from https://desktop.arcgis.com/en/arcmap/latest/extensions/network-analyst/algorithms-used-by-network-analyst.htm
Gao, L.-N., Tao, F., Ma, P.-L., Wang, C.-Y., Kong, W., Chen, W.-K., & Zhou, T. (2022). A short-distance healthy route planning approach. Journal of Transport & Health, 24, 101314.
Gilliland, J., Maltby, M., Xu, X., Luginaah, I., Loebach, J., & Shah, T. (2019). Is active travel a breath of fresh air? Examining children's exposure to air pollution during the school commute. Spatial and Spatio-temporal Epidemiology, 29, 51-57. https://doi.org/https://doi.org/10.1016/j.sste.2019.02.004
Huang, T. (2018). 機器/統計學習:主成分分析(Principal Component Analysis, PCA). Retrieved 7/10 from https://reurl.cc/nDp4Zl
Landrigan, P. J., Fuller, R., Fisher, S., Suk, W. A., Sly, P., Chiles, T. C., & Bose-O'Reilly, S. (2019). Pollution and children's health. Science of the Total Environment, 650, 2389-2394. https://www.sciencedirect.com/science/article/pii/S0048969718338543
Luo, J., Boriboonsomsin, K., & Barth, M. (2018). Reducing pedestrians' inhalation of traffic-related air pollution through route choices: Case study in California suburb. Journal of Transport & Health, 10, 111-123.
Luo, J., Boriboonsomsin, K., & Barth, M. (2020). Consideration of exposure to traffic-related air pollution in bicycle route planning. Journal of Transport & Health, 16, 100792.
Mölter, A., & Lindley, S. (2015). Influence of walking route choice on primary school children's exposure to air pollution—A proof of concept study using simulation. Science of the Total Environment, 530, 257-262.
Ma, X., Longley, I., Gao, J., & Salmond, J. (2020). Assessing schoolchildren's exposure to air pollution during the daily commute-A systematic review. Science of the Total Environment, 737, 140389.
Maugeri, A., Barchitta, M., Favara, G., La Mastra, C., La Rosa, M. C., Magnano San Lio, R., & Agodi, A. (2023). The Application of Clustering on Principal Components for Nutritional Epidemiology: A Workflow to Derive Dietary Patterns. Nutrients, 15(1), 195.
Mazaheri, M., Lin, W., Clifford, S., Yue, D., Zhai, Y., Xu, M., Rizza, V., & Morawska, L. (2019). Characteristics of school children's personal exposure to ultrafine particles in Heshan, Pearl River Delta, China – A pilot study. Environment International, 132, 105134. https://doi.org/https://doi.org/10.1016/j.envint.2019.105134
McKercher, G. R., Salmond, J. A., & Vanos, J. K. (2017). Characteristics and applications of small, portable gaseous air pollution monitors. Environmental pollution, 223, 102-110.
Mejía, J. F., Choy, S. L., Mengersen, K., & Morawska, L. (2011). Methodology for assessing exposure and impacts of air pollutants in school children: data collection, analysis and health effects–a literature review. Atmospheric environment, 45(4), 813-823.
Nyarku, M., Buonanno, G., Ofosu, F., Jayaratne, R., Mazaheri, M., & Morawska, L. (2019). Schoolchildren’s personal exposure to ultrafine particles in and near Accra, Ghana. Environment International, 133, 105223. https://doi.org/https://doi.org/10.1016/j.envint.2019.105223
Perera, F. P. (2017). Multiple threats to child health from fossil fuel combustion: impacts of air pollution and climate change. Environmental health perspectives, 125(2), 141-148.
Perry, S. G., Cimorelli, A. J., Paine, R. J., Brode, R. W., Weil, J. C., Venkatram, A., Wilson, R. B., Lee, R. F., & Peters, W. D. (2005). AERMOD: A dispersion model for industrial source applications. Part II: Model performance against 17 field study databases. Journal of Applied Meteorology and Climatology, 44(5), 694-708.
Salvi, S. (2007). Health effects of ambient air pollution in children. Paediatric Respiratory Reviews, 8(4), 275-280. https://doi.org/https://doi.org/10.1016/j.prrv.2007.08.008
Shihab, A. S. (2022). Identification of Air Pollution Sources and Temporal Assessment of Air Quality at a Sector in Mosul City Using Principal Component Analysis. Polish Journal of Environmental Studies, 31(3).
Shukla, K., Kumar, P., Mann, G. S., & Khare, M. (2020). Mapping spatial distribution of particulate matter using Kriging and Inverse Distance Weighting at supersites of megacity Delhi. Sustainable Cities and Society, 54, 101997. https://doi.org/https://doi.org/10.1016/j.scs.2019.101997
slundberg, & 2023 GitHub, I. (2023). Retrieved 7/10 from https://github.com/slundberg/shap
Wang, Y., Wu, Y., Li, Z., Liao, K., Li, C., & Song, G. (2022). Route planning for active travel considering air pollution exposure. Transportation Research Part D: Transport and Environment, 103, 103176.
Willberg, E., Poom, A., Helle, J., & Toivonen, T. (2023). Cyclists’ exposure to air pollution, noise, and greenery: a population-level spatial analysis approach. International Journal of Health Geographics, 22(1), 5.
Wong, P.-Y., Lee, H.-Y., Chen, Y.-C., Zeng, Y.-T., Chern, Y.-R., Chen, N.-T., Lung, S.-C. C., Su, H.-J., & Wu, C.-D. (2021). Using a land use regression model with machine learning to estimate ground level PM2. 5. Environmental pollution, 277, 116846.
Wong, P.-Y., Su, H.-J., Lee, H.-Y., Chen, Y.-C., Hsiao, Y.-P., Huang, J.-W., Teo, T.-A., Wu, C.-D., & Spengler, J. D. (2021). Using land-use machine learning models to estimate daily NO2 concentration variations in Taiwan. Journal of Cleaner Production, 317, 128411.
Wu, C.-D., Chen, Y.-C., Pan, W.-C., Zeng, Y.-T., Chen, M.-J., Guo, Y. L., & Lung, S.-C. C. (2017). Land-use regression with long-term satellite-based greenness index and culture-specific sources to model PM2. 5 spatial-temporal variability. Environmental pollution, 224, 148-157.
Zhang, L., Tian, X., Zhao, Y., Liu, L., Li, Z., Tao, L., Wang, X., Guo, X., & Luo, Y. (2021). Application of nonlinear land use regression models for ambient air pollutants and air quality index. Atmospheric Pollution Research, 12(10), 101186.
Zou, B., Li, S., Zheng, Z., Zhan, B. F., Yang, Z., & Wan, N. (2020). Healthier routes planning: A new method and online implementation for minimizing air pollution exposure risk. Computers, Environment and Urban Systems, 80, 101456.
行政院環境保護署. (2023). 空氣品質指標. Retrieved 7/10 from https://airtw.epa.gov.tw/cht/Information/Standard/AirQualityIndicator.aspx
張先生. (2023). 111年民眾日常使用運具狀況調查統計表 交通部統計處民眾日常使用運具狀況調查 Retrieved from https://www.motc.gov.tw/ch/app/data/view?module=survey&id=56&serno=202304280010
張家銘. (2021). 可解釋 AI (XAI) 系列 — SHAP. Retrieved 7/10 from https://medium.com/ai-academy-taiwan/%E5%8F%AF%E8%A7%A3%E9%87%8B-ai-xai-%E7%B3%BB%E5%88%97-shap-2c600b4bdc9e
淺談主成分分析(PCA)與因素分析(FA). (2021). Retrieved 8/18 from https://www.wensread.com/principal-component-analysis-and-factor-analysis/