臺灣的氣候溫暖潮濕，加上有梅雨季與颱風的關係，容易短時間累積大雨產生積水，是登革熱病毒孕育的溫床。109年全國登革熱本土病例73例，境外移入病例4例，臺南市僅有境外移入7例，無論本土或境外案例數，均較前年低。因應國際嚴重特殊傳染性肺炎（COVID-19）大流行實施邊境管制及相關防疫措施，除了民眾防疫觀念與健康識能提升外，或許間接影響臺灣本土登革熱風險。臺南市因地理位置及氣候，每年飽受登革熱疫病防治所苦，而校園較一般的公共場合封閉，每逢高度傳染性流行病高峰期，相當容易爆發群聚傳染。為降低臺南市各校園登革熱流行風險，在本論文中，不同於一般收集登革熱病例相關資料，我們的研究以誘卵桶當作監測環境指標，設計了一套登革熱預警系統。利用每週誘卵桶的監測資料，以深度學習方式預測結果，並結合氣象觀測資訊計算出各學校的暴險程度。接著透過地理資訊系統（GIS）的圖資運用，將學校、誘卵桶、天氣和暴險度等資訊即時呈現在地圖上，以便承辦人員操作使用。本系統有助於臺南市政府教育局強化早期向學校進行登革熱通報等防治作為，以執行校園動員維護環境整潔及衛教宣導，並落實人力部署在社區推動孳生源清除及容器減量，確保校園乾淨安全，免除蚊蟲孳生疑慮，才能避免登革熱疫情發生。

Due to its geographical location and climate, Tainan City suffers from the prevention and control of dengue fever every year, and the campus is closed to ordinary public places. During the peak period of highly contagious epidemics, it is quite prone to cluster infections. In order to reduce the risk of dengue fever in the campuses of Tainan City, in this paper, different from the general collection of dengue fever case-related data, our study designed a dengue fever early warning system with ovitraps as monitoring environmental indicators. Using the monitoring data of the ovitraps every week, the results are predicted by in-depth learning, and the risk exposure score in each school is calculated based on the meteorological observation information. Then, through the use of geographic information system (GIS) map data, information such as schools, ovitraps, weather, and danger levels are displayed on the map in real time for monitoring personnel to operate and use. This system helps the Bureau of Education, Tainan City Government to strengthen early notification of dengue fever to schools and other prevention and control actions, to implement campus mobilization to maintain a clean environment and health education promotion, and to implement manpower deployment in the community to promote the removal of breeding sources and container reduction to ensure a clean campus. Avoiding the worry of mosquito breeding can prevent the occurrence of dengue fever.

[1] Stewart Ibarra, Anna M., et al. "Dengue vector dynamics (Aedes aegypti) influenced by climate and social factors in Ecuador: implications for targeted control." PloS one 8.11 (2013): e78263.
[2] Pessanha, José Eduardo Marques, et al. "Ovitrap surveillance as dengue epidemic predictor." Journal of Health & Biological Sciences 2.2 (2014): 51-56.
[3] Guo, Pi, et al. "Developing a dengue forecast model using machine learning: A case study in China." PLoS neglected tropical diseases 11.10 (2017): e0005973.
[4] Ahmad, Rohani, et al. "Factors determining dengue outbreak in Malaysia." PLoS One 13.2 (2018): e0193326.
[5] Carvajal, Thaddeus M., et al. "Machine learning methods reveal the temporal pattern of dengue incidence using meteorological factors in metropolitan Manila, Philippines." BMC infectious diseases 18.1 (2018): 1-15.
[6] Scavuzzo, Juan M., et al. "Modeling Dengue vector population using remotely sensed data and machine learning." Acta tropica 185 (2018): 167-175.
[7] Anno, Sumiko, et al. "Spatiotemporal dengue fever hotspots associated with climatic factors in taiwan including outbreak predictions based on machine-learning." Geospatial health 14.2 (2019).
[8] Chovatiya, Megha, et al. "Prediction of dengue using recurrent neural network." 2019 3rd International Conference on Trends in Electronics and Informatics (ICOEI). IEEE, 2019.
[9] Iqbal, Naiyar, and Mohammad Islam. "Machine learning for dengue outbreak prediction: A performance evaluation of different prominent classifiers." Informatica 43.3 (2019).
[10] Stolerman, Lucas M., Pedro D. Maia, and J. Nathan Kutz. "Forecasting dengue fever in Brazil: An assessment of climate conditions." PloS one 14.8 (2019): e0220106.
[11] Mussumeci, Elisa, and Flavio Codeco Coelho. "Machine-learning forecasting for Dengue epidemics-Comparing LSTM, Random Forest and Lasso regression." medRxiv (2020).
[12] Xu, Jiucheng, et al. "Forecast of dengue cases in 20 Chinese cities based on the deep learning method." International journal of environmental research and public health 17.2 (2020): 453.
[13] Zhao, Naizhuo, et al. "Machine learning and dengue forecasting: Comparing random forests and artificial neural networks for predicting dengue burden at national and sub-national scales in Colombia." PLoS neglected tropical diseases 14.9 (2020): e0008056.
[14] Salim, Nurul Azam Mohd, et al. "Prediction of dengue outbreak in Selangor Malaysia using machine learning techniques." Scientific reports 11.1 (2021): 1-9.