人們長時間待在室內環境中，室內空氣品質對人體的影響更直接，已經有相當多的研究證實空氣品質與呼吸道疾病之間存在著關聯性，尤其是學校教室這類長時間人群聚集且互動頻繁的密閉空間，對於學生的健康以及學習力都會受到影響。在高度工業化發展的環境下，容易有空氣品質不佳的問題產生，而大多數的學校屬於較老舊的建築，很難有適當的通風設備讓教室維持在標準通風率下，使得校園群聚感染的風險上升。
本研究提出了使用神經網路以室內空氣品質預測教室呼吸道疾病的發生(CROP-IAQ)的方法。
本研究使用MAPS V6.0空氣盒子佈建於國立臺灣師範大學林口校區教室內，蒐集室內的溫濕度、PM10、PM2.5、PM1.0、二氧化碳、TVOC和光度等數據，以各班級學生防疫假的日期標記可能有疾病影響的空氣品質資料，透過神經網路模型建構的分類器，預測疾病發生的可能性，並提供示警。CROP-IAQ的示警可以讓校園及早針對高風險教室做通風或隔離等措施，以減少校園群聚感染發生的風險。
研究中所使用的數據加入了以SMOTE生成的相似資料，做為模型訓練時的輸入資料，模型共有四種包含Basic CNN model、Inception model、ResNet model及ResNeXt model，四種模型也再加入Squeeze-and-Excitation module提高模型預測能力。根據實驗結果，最終是Inception-SE model有最好的正確率，F1score為0.72、靈敏度為0.76。

People staying indoors for long periods are more directly affected by indoor air quality. Numerous studies have already confirmed the correlation between air quality and respiratory diseases. Particularly in the case of spaces like school classrooms, where people gather for long durations and interact frequently, students' health is significantly impacted. Especially in most modernized environments, the issue of poor air quality is prone to arise. In addition, most schools are in relatively old buildings; it is challenging to implement adequate ventilation systems to maintain classrooms at the standard ventilation rate, thereby increasing the risk of cluster infections in classrooms.
In this paper, we proposed a Classroom Respiratory disease Occurrence Prediction method with Indoor Air Quality data (CROP-IAQ) using Neural Networks.
This study used MAPS V6.0 Airbox deployed in classrooms to collect data on indoor temperature, relative humidity, PM1.0, PM2.5, PM10, CO2, TVOC, and luminosity. The data, combined with the records of student epidemic prevention leave in each class, were used to mark the air quality data potentially affected by diseases. A classifier is constructed using a neural network model to predict the possibility of disease occurrence and to provide alerts for classrooms with a risk of clustered infection. CROP-IAQ can reduce the risk of clustered infections on campus with early warnings for authorities to implement measures such as ventilation and isolation.
In addition to the data collected, the Synthetic Minority Over-sampling TEchnique (SMOTE) method was employed to generate similar data for input into the models during training. The models included the Basic Convolutional Neural Networks (CNN) model, the Inception model, the Residual Network (ResNet) model, and the ResNeXt model. These four models were enhanced with a Squeeze-and-Excitation (SE) module to improve the predictive capabilities. Based on the experimental results, the Inception model with the SE module achieved the highest accuracy, with an F1-score of 0.72 and a Sensitivity of 0.76.

[1] World Health Organization. WHO global air quality guidelines: particulate matter (PM2.5 and PM10), ozone, nitrogen dioxide, sulfur dioxide and carbon monoxide. (World Health Organization, 2021).
[2] Babatola, S. S. Global burden of diseases attributable to air pollution. J Public Health Afr 9, 813 (2018).
[3] Regulatory Sharing System of the Environmental Protection Administration of the Executive Yuan - Contents of Regulations - Indoor Air Quality Standards https://oaout.epa.gov.tw/law/LawContent.aspx?id=FL068252#lawmenu (2023).
[4] Simoni, M. et al. School air quality related to dry cough, rhinitis and nasal patency in children. European Respiratory Journal 35, 742–749 (2010).
[5] Sowa, J. Air Quality And Ventilation Rates In Schools In Poland - Requirements, Reality And Possible Improvements. (2002).
[6] Park, S., Choi, Y., Song, D. & Kim, E. K. Natural ventilation strategy and related issues to prevent coronavirus disease 2019 (COVID-19) airborne transmission in a school building. Sci Total Environ 789, 147764 (2021).
[7] Calatayud, L. et al. Pandemic (H1N1) 2009 virus outbreak in a school in London, April–May 2009: an observational study. Epidemiology & Infection 138, 183–191 (2010).
[8] Stein-Zamir, C. et al. A large COVID-19 outbreak in a high school 10 days after schools’ reopening, Israel, May 2020. Eurosurveillance 25, 2001352 (2020).
[9] Statistics on causes of death in Taiwan in 2022. Ministry of Health and Welfare
[10] Wu, I.-P., Liao, S.-L., Lai, S.-H. & Wong, K.-S. The respiratory impacts of air pollution in children: Global and domestic (Taiwan) situation. Biomedical Journal 45, 88–94 (2022).
[11] Air pollution and child health: prescribing clean air. https://www.who.int/publications-detail-redirect/WHO-CED-PHE-18-01 (2023).
[12] Requia, W. J., Saenger, C. C., Cicerelli, R. E., Monteiro de Abreu, L. & Cruvinel, V. R. N. Air quality around schools and school-level academic performance in Brazil. Atmospheric Environment 279, 119125 (2022).
[13] Heissel, J. A., Persico, C. & Simon, D. Does Pollution Drive Achievement? The Effect of Traffic Pollution on Academic Performance. Journal of Human Resources (2020) doi:10.3368/jhr.57.3.1218-9903R2.
[14] Palumbo, J. R. et al. Assessing associations between indoor environment and health symptoms in Romanian school children: an analysis of data from the SINPHONIE project. Environ Sci Pollut Res 25, 9186–9193 (2018).
[15] Alsmo, T. & Alsmo, C. Ventilation and Relative Humidity in Swedish Buildings. Journal of Environmental Protection 5, 1022–1036 (2014).
[16] Wargocki, P., Porras-Salazar, J. A., Contreras-Espinoza, S. & Bahnfleth, W. The relationships between classroom air quality and children’s performance in school. Building and Environment 173, 106749 (2020).
[17] Shendell, D. G. et al. Associations between classroom CO2 concentrations and student attendance in Washington and Idaho. Indoor Air 14, 333–341 (2004).
[18] Mendell, M. J. et al. Association of classroom ventilation with reduced illness absence: a prospective study in California elementary schools. Indoor Air 23, 515–528 (2013).
[19] Communicable Disease Control Act – Laws & Regulations Database of The Republic of China (Taiwan) https://law.moj.gov.tw/LawClass/LawAll.aspx?pcode=L0050001 (2023).
[20] Lessler, J. et al. Incubation periods of acute respiratory viral infections: a systematic review. Lancet Infect Dis 9, 291–300 (2009).
[21] Leung, D. Y. C. Outdoor-indoor air pollution in urban environment: challenges and opportunity. Frontiers in Environmental Science 2, (2015).
[22] Yang, D. & Mak, C. M. Relationships between indoor environmental quality and environmental factors in university classrooms. Building and Environment 186, 107331 (2020).
[23] Sharma, P. K. et al. IndoAirSense: A framework for indoor air quality estimation and forecasting. Atmospheric Pollution Research 12, 10–22 (2021).
[24] Elbayoumi, M., Ramli, N. A. & Fitri Md Yusof, N. F. Development and comparison of regression models and feedforward backpropagation neural network models to predict seasonal indoor PM2.5–10 and PM2.5 concentrations in naturally ventilated schools. Atmospheric Pollution Research 6, 1013–1023 (2015).
[25] Wong, P.-Y. et al. An alternative approach for estimating large-area indoor PM2.5 concentration – A case study of schools. Building and Environment 219, 109249 (2022).
[26] Tagliabue, L. C., Re Cecconi, F., Rinaldi, S. & Ciribini, A. L. C. Data driven indoor air quality prediction in educational facilities based on IoT network. Energy and Buildings 236, 110782 (2021).
[27] Du, C. et al. Effect of Ventilation Improvement during a Tuberculosis Outbreak in Underventilated University Buildings. Indoor Air 30, (2019).
[28] Yu-Ru Chen. Unsupervised anomaly detection using indoor air quality with autoencoder for respiratory disease prevention. (2022)
[29] Kirisci, M. & cagcag yolcu, O. A New CNN-Based Model for Financial Time Series: TAIEX and FTSE Stocks Forecasting. Neural Processing Letters 54, (2022).
[30] Hema, C. & Garcia Marquez, F. P. Emotional speech Recognition using CNN and Deep learning techniques. Applied Acoustics 211, 109492 (2023).
[31] Fergus, P. et al. Modeling Segmented Cardiotocography Time-Series Signals Using One-Dimensional Convolutional Neural Networks for the Early Detection of Abnormal Birth Outcomes. IEEE Transactions on Emerging Topics in Computational Intelligence 5, 882–892 (2021).
[32] Shi, W., Fang, X., Yang, G. & Huang, J. Human Activity Recognition Based on Multichannel Convolutional Neural Network With Data Augmentation. IEEE Access 10, 76596–76606 (2022).
[33] Chakraborty, S., Aich, S., Joo, M., Sain, M. & Kim, H.-C. A Multichannel Convolutional Neural Network Architecture for the Detection of the State of Mind Using Physiological Signals from Wearable Devices. Journal of Healthcare Engineering 2019, e5397814 (2019).
[34] Szegedy, C. et al. Going deeper with convolutions. in 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 1–9 (2015). doi:10.1109/CVPR.2015.7298594.
[35] Kim, J.-H., Seo, S.-Y., Song, C.-G. & Kim, K.-S. Assessment of Electrocardiogram Rhythms by GoogLeNet Deep Neural Network Architecture. Journal of Healthcare Engineering 2019, e2826901 (2019).
[36] He, K., Zhang, X., Ren, S. & Sun, J. Deep Residual Learning for Image Recognition. in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 770–778 (2016). doi:10.1109/CVPR.2016.90.
[37] Xie, S., Girshick, R., Dollár, P., Tu, Z. & He, K. Aggregated Residual Transformations for Deep Neural Networks. in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 5987–5995 (2017). doi:10.1109/CVPR.2017.634.
[38] Ramanathan, A. & McDermott, J. Fall detection with accelerometer data using Residual Networks adapted to multi-variate time series classification. in 2021 International Joint Conference on Neural Networks (IJCNN) 1–8 (2021). doi:10.1109/IJCNN52387.2021.9533670.
[39] Hu, J., Shen, L. & Sun, G. Squeeze-and-Excitation Networks. in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition 7132–7141 (2018). doi:10.1109/CVPR.2018.00745.
[40] Chen, L.-J. et al. An Open Framework for Participatory PM2.5 Monitoring in Smart Cities. IEEE Access 5, 14441–14454 (2017).
[41] Chawla, N. V., Bowyer, K. W., Hall, L. O. & Kegelmeyer, W. P. SMOTE: synthetic minority over-sampling technique. J. Artif. Int. Res. 16, 321–357 (2002).
[42] Hajian-Tilaki, K. Receiver Operating Characteristic (ROC) Curve Analysis for Medical Diagnostic Test Evaluation. Caspian J Intern Med 4, 627–635 (2013).
[43] Habibzadeh, F., Habibzadeh, P. & Yadollahie, M. On determining the most appropriate test cut-off value: the case of tests with continuous results. Biochem Med (Zagreb) 26, 297–307 (2016).