登革熱是一種由蚊子傳播的急性傳染病，而預防登革熱最直接有效的方式是預測風險區域並加強該地區的防蚊策略。目前政府人員通常透過監測誘卵桶中的卵粒數來評估爆發登革熱的風險，然而未設置誘卵桶的區域就無法藉此進行監測，但這些區域仍需要管控其登革熱風險。因此，本研究著重於預測整個城市當中每個細粒度區域的登革熱風險，特別是無誘卵桶覆蓋的區域。然而，這些未設置誘卵桶區域缺乏卵粒數歷史數據的問題造成了建立準確模型的一大挑戰，此外，如何有效地融合城市中大量的時空間異質性特徵也是另一個重要的研究挑戰和實務性問題。在本研究中，我們提出一個創新的AI時空間預測模型MVFGRNN，其包含我們提出的可融合多視圖的模塊與近似模塊來解決以上兩個挑戰。MVFGRNN首先使用一個特徵提取器，去學習未設置誘卵桶區域中包含動態和靜態特徵的嵌入。然後透過圖構建器從不同的觀點建立多視圖，以更全面的方式描述誘卵桶之間的關係，並使用包含圖神經網路、注意力機制的多視圖融合模塊來學習這些涵蓋誘卵桶區域的區域嵌入。最後，我們使用包含循環神經網路、反距離加權注意力機制的近似模塊，來解決無誘卵桶區域缺乏過去歷史卵粒數資訊的問題並做出精準預測。本研究使用臺灣臺南市的真實數據集進行實驗，實驗結果顯示，我們提出的模型準確度優於目前最先進的方法和基線模型。此外，我們的消融研究也驗證出MVFGRNN的每個設計的模塊都能有效對於預測提升準確度。結合我們提出的MVFGRNN，政府官員將能夠更全面地監測整個城市的登革熱風險。 這將確保所有地區都處於監測網路之內，以便儘早實施預防措施並更有效地遏制登革熱傳播。此模型將用於與臺南市防疫登革熱預警之功能，促進數據市政治理。

Dengue fever is an emergency disease spread by mosquitoes. The most direct way to prevent the disease is to predict risky areas and bolster mosquito preventive strategies. Risk is usually evaluated by monitoring the number of eggs in the ovitraps set up by the government. However, areas without sensors still need to be checked and managed for dengue risk. In this study, we focus on forecasting each region's fine-grained dengue fever risk, especially in regions without sensor coverage. The paucity of historical data makes this endeavor challenging. Furthermore, determining how to effectively blend different features is another important research challenge and practical issue. We propose a Multi-View Graph Fusion Recurrent Neural Network (MVGFRNN) with an approximation module to address these two issues. For the regions that have no sensor coverage, MVGFRNN first uses a feature extractor to learn their representation based on their dynamic and static features. Then we use a graph constructor to formulate the relationship between sensors from different perspectives, and a multi-view graph fusion module to learn the embedding of sensors. Finally, we use an approximation module to deal with the lack of historical data. We conducted experiments using a real-world dataset from the urban area of Tainan, Taiwan. The results show that the proposed MVGFRNN outperforms the state-of-the-art methods and baselines. The ablation study also shows that every component in MVGFRNN has a significant impact on boosting the prediction effectiveness. By integrating our proposed prediction modules with the monitoring system of the city government, government officials will have the ability to monitor the dengue fever risk across the entire city in a more comprehensive manner. This will ensure that all areas are within the surveillance network, allowing for early implementation of preventive measures and more effective containment of dengue fever transmission.

[1] Leo Breiman. Random forests. Machine learning, 45(1):5–32, 2001.
[2] Thaddeus M Carvajal, Katherine M Viacrusis, Lara Fides T Hernandez, Howell T Ho, Divina M Amalin, and Kozo Watanabe. Machine learning methods reveal the temporal pattern of dengue incidence using meteorological factors in metropolitan manila, philippines. BMC infectious diseases, 18(1):1–15, 2018.
[3] Changlu Chen, Yanbin Liu, Ling Chen, and Chengqi Zhang. Bidirectional spatial- temporal adaptive transformer for urban traffic flow forecasting. IEEE Transactions on Neural Networks and Learning Systems, pages 1–13, 2022.
[4] Feng-Wen Chen and Chen-Wuing Liu. Estimation of the spatial rainfall distribution using inverse distance weighting (idw) in the middle of taiwan. Paddy and Water Environment, 10(3):209–222, 2012.
[5] Tianqi Chen and Carlos Guestrin. Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, pages 785–794, 2016.
[6] Weiyu Cheng, Yanyan Shen, Yanmin Zhu, and Linpeng Huang. A neural attention model for urban air quality inference: Learning the weights of monitoring stations. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 32, 2018.
[7] Megha Chovatiya, Anushka Dhameliya, Jayita Deokar, Jessica Gonsalves, and Amrita Mathur. Prediction of dengue using recurrent neural network. In 2019 3rd International Conference on Trends in Electronics and Informatics (ICOEI), pages 926–929. IEEE, 2019.
[8] Rahul Dey and Fathi M Salem. Gate-variants of gated recurrent unit (gru) neural networks. In 2017 IEEE 60th international midwest symposium on circuits and systems (MWSCAS), pages 1597–1600. IEEE, 2017.
[9] Jake Grigsby, Zhe Wang, and Yanjun Qi. Long-range transformers for dynamic spa- tiotemporal forecasting. arXiv preprint arXiv:2109.12218, 2021.
[10] Pi Guo, Tao Liu, Qin Zhang, Li Wang, Jianpeng Xiao, Qingying Zhang, Ganfeng Luo, Zhihao Li, Jianfeng He, Yonghui Zhang, et al. Developing a dengue forecast model using machine learning: A case study in china. PLoS neglected tropical diseases, 11(10):e0005973, 2017.
[11] Shengnan Guo, Youfang Lin, Ning Feng, Chao Song, and Huaiyu Wan. Attention based spatial-temporal graph convolutional networks for traffic flow forecasting. In Proceedings of the AAAI conference on artificial intelligence, volume 33, pages 922– 929, 2019.
[12] Sepp Hochreiter and Jürgen Schmidhuber. Long short-term memory. Neural computa- tion, 9(8):1735–1780, 1997.
[13] Hsun-Ping Hsieh, Shou-De Lin, and Yu Zheng. Inferring air quality for station location recommendation based on urban big data. In Proceedings of the 21th ACM SIGKDD international conference on knowledge discovery and data mining, pages 437–446, 2015.
[14] Hsun-Ping Hsieh, Su Wu, Ching-Chung Ko, Chris Shei, Zheng-Ting Yao, and Yu-Wen Chen. Forecasting fine-grained air quality for locations without monitoring stations based on a hybrid predictor with spatial-temporal attention based network. Applied Sciences, 12(9):4268, 2022.
[15] Naiyar Iqbal and Mohammad Islam. Machine learning for dengue outbreak prediction: A performance evaluation of different prominent classifiers. Informatica, 43(3), 2019.
[16] Guangyin Jin, Fuxian Li, Jinlei Zhang, Mudan Wang, and Jincai Huang. Automated dilated spatio-temporal synchronous graph modeling for traffic prediction. IEEE Trans- actions on Intelligent Transportation Systems, pages 1–11, 2022.
[17] Guangyin Jin, Yuxuan Liang, Yuchen Fang, Jincai Huang, Junbo Zhang, and Yu Zheng. Spatio-temporal graph neural networks for predictive learning in urban computing: A survey. arXiv preprint arXiv:2303.14483, 2023.
[18] Guolin Ke, Qi Meng, Thomas Finley, Taifeng Wang, Wei Chen, Weidong Ma, Qiwei Ye, and Tie-Yan Liu. Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems, 30, 2017.
[19] Van-Duc Le, Tien-Cuong Bui, and Sang-Kyun Cha. Spatiotemporal deep learning model for citywide air pollution interpolation and prediction. In 2020 IEEE international conference on big data and smart computing (BigComp), pages 55–62. IEEE, 2020.
[20] Lixin Li, Xingyou Zhang, James B Holt, Jie Tian, and Reinhard Piltner. Spatiotemporal interpolation methods for air pollution exposure. 2011.
[21] Mengzhang Li and Zhanxing Zhu. Spatial-temporal fusion graph neural networks for traffic flow forecasting. In Proceedings of the AAAI conference on artificial intelligence, volume 35, pages 4189–4196, 2021.
[22] Yaguang Li, Rose Yu, Cyrus Shahabi, and Yan Liu. Diffusion convolutional recurrent neural network: Data-driven traffic forecasting. arXiv preprint arXiv:1707.01926, 2017.
[23] Yuxuan Liang, Songyu Ke, Junbo Zhang, Xiuwen Yi, and Yu Zheng. Geoman: Multi- level attention networks for geo-sensory time series prediction. In IJCAI, volume 2018, pages 3428–3434, 2018.
[24] Yijun Lin, Yao-Yi Chiang, Fan Pan, Dimitrios Stripelis, José Luis Ambite, Sandrah P Eckel, and Rima Habre. Mining public datasets for modeling intra-city pm2. 5 con- centrations at a fine spatial resolution. In Proceedings of the 25th ACM SIGSPATIAL international conference on advances in geographic information systems, pages 1–10, 2017.
[25] Douglas C Montgomery, Elizabeth A Peck, and G Geoffrey Vining. Introduction to linear regression analysis. John Wiley & Sons, 2021.
[26] Meinard Müller. Dynamic time warping. Information retrieval for music and motion, pages 69–84, 2007.
[27] Elisa Mussumeci and Flavio Codeco Coelho. Machine-learning forecasting for dengue epidemics-comparing lstm, random forest and lasso regression. medRxiv, 2020.
[28] Leif E Peterson. K-nearest neighbor. Scholarpedia, 4(2):1883, 2009.
[29] Shanshan Qin, Feng Liu, Chen Wang, Yiliao Song, and Jiansheng Qu. Spatial-temporal analysis and projection of extreme particulate matter (pm10 and pm2. 5) levels using as- sociation rules: A case study of the jing-jin-ji region, china. Atmospheric Environment, 120:339–350, 2015.
[30] Nurul Azam Mohd Salim, Yap Bee Wah, Caitlynn Reeves, Madison Smith, Wan Fairos Wan Yaacob, Rose Nani Mudin, Rahmat Dapari, Nik Nur Fatin Fatihah Sapri, and Ubydul Haque. Prediction of dengue outbreak in selangor malaysia using machine learning techniques. Scientific reports, 11(1):1–9, 2021.
[31] Juan M Scavuzzo, Francisco Trucco, Manuel Espinosa, Carolina B Tauro, Marcelo Abril, Carlos M Scavuzzo, and Alejandro C Frery. Modeling dengue vector population using remotely sensed data and machine learning. Acta tropica, 185:167–175, 2018.
[32] Chao Song, Youfang Lin, Shengnan Guo, and Huaiyu Wan. Spatial-temporal syn- chronous graph convolutional networks: A new framework for spatial-temporal net- work data forecasting. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, pages 914–921, 2020.
[33] Hind Taud and JF Mas. Multilayer perceptron (mlp). In Geomatic approaches for modeling land change scenarios, pages 451–455. Springer, 2018.
[34] Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. Attention is all you need. Advances in neural information processing systems, 30, 2017.
[35] Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. Graph attention networks. stat, 1050:20, 2017.
[36] Xiaoyang Wang, Yao Ma, Yiqi Wang, Wei Jin, Xin Wang, Jiliang Tang, Caiyan Jia, and Jian Yu. Traffic flow prediction via spatial temporal graph neural network. In Proceedings of The Web Conference 2020, pages 1082–1092, 2020.
[37] David W Wong, Lester Yuan, and Susan A Perlin. Comparison of spatial interpola- tion methods for the estimation of air quality data. Journal of Exposure Science & Environmental Epidemiology, 14(5):404–415, 2004.
[38] Pei-Chih Wu, How-Ran Guo, Shih-Chun Lung, Chuan-Yao Lin, and Huey-Jen Su. Weather as an effective predictor for occurrence of dengue fever in taiwan. Acta tropica, 103(1):50–57, 2007.
[39] Zonghan Wu, Shirui Pan, Guodong Long, Jing Jiang, and Chengqi Zhang. Graph wavenet for deep spatial-temporal graph modeling. arXiv preprint arXiv:1906.00121, 2019.
[40] Jiucheng Xu, Keqiang Xu, Zhichao Li, Fengxia Meng, Taotian Tu, Lei Xu, and Qiyong Liu. Forecast of dengue cases in 20 chinese cities based on the deep learning method. International journal of environmental research and public health, 17(2):453, 2020.
[41] Bing Yu, Haoteng Yin, and Zhanxing Zhu. Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting. arXiv preprint arXiv:1709.04875, 2017.
[42] Mingyang Zhang, Tong Li, Yong Li, and Pan Hui. Multi-view joint graph representation learning for urban region embedding. In Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence, pages 4431– 4437, 2021.
[43] Weijia Zhang, Hao Liu, Yanchi Liu, Jingbo Zhou, and Hui Xiong. Semi-supervised hierarchical recurrent graph neural network for city-wide parking availability prediction. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, pages 1186–1193, 2020.
[44] Naizhuo Zhao, Katia Charland, Mabel Carabali, Elaine O Nsoesie, Mathieu Maheu- Giroux, Erin Rees, Mengru Yuan, Cesar Garcia Balaguera, Gloria Jaramillo Ramirez, and Kate Zinszer. 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):e0008056, 2020.
[45] Chuanpan Zheng, Xiaoliang Fan, Cheng Wang, and Jianzhong Qi. Gman: A graph multi-attention network for traffic prediction. In Proceedings of the AAAI conference on artificial intelligence, volume 34, pages 1234–1241, 2020.
[46] Yu Zheng, Xiuwen Yi, Ming Li, Ruiyuan Li, Zhangqing Shan, Eric Chang, and Tianrui Li. Forecasting fine-grained air quality based on big data. In Proceedings of the 21th ACM SIGKDD international conference on knowledge discovery and data mining, pages 2267–2276, 2015.