人工智慧物聯網於大學教室室內空氣品質決策管理與應用之研究

A Study of Applying Artificial Intelligence in University-Classroom Indoor Air Quality and Decision Management

10.53106/101632122023090125004

劉俊伸(Chun-Shen Liu)；陳振誠(Chen-Cheng Chen)；陳韋謙(Wei-Chien Chen)；王崧任(Song-Jen Wang)

最佳化 ； 人工智慧 ； 人工智慧物聯網 ； 室內空氣品質 ； Optimum ； AI ； AIOT ； Indoor Air Quality

建築學報

125期（2023 / 09 / 30）

47 - 61

繁體中文;英文

本研究運用人工智慧物聯網技術並使用空氣盒子（AirBox）蒐集「環境特徵」變數因子，將該因子作為類神經網路之輸入變數，接著以物件導向程式語言（Python）與數據挖掘工具（IBM SPSS modeler 18.0）建立預測性模型，再採用XGBoost決策樹演算法作為實驗方法，進行模擬建築新風系統模型的準確度。研究結果發現，採用XGBoost決策樹演算法模型準確值平均可高達97.36%以上，證明透過導入智慧感測及人工智慧等感測分析技術結合空氣盒子及建築新風系統，可建構出優化的教學空間空氣品質決策管理運作模式，除可維持教學空間良好室內空氣品質外，同時亦可達到運用人工智慧物聯網技術落實建築室內空氣品質自主管理之目的。

This study utilizes Internet of Things technology with Air Box to gather environmental characteristics factors as input variables to a neural network, which applies the object-oriented programming language (Python) and data mining tools (IBM SPSS modeler 18.0) to establish a predictive model. The results found that the accuracy of the model by the XGBoost decision tree algorithm is up to 97.36%. It indicates that an optimized classroom with a "Quality Management Model", an intelligent fresh air system, could be constructed by smart sensing devices, artificial intelligence, and sensing data analysis technologies. In addition to maintaining good indoor air quality within the teaching spaces, it also achieves the purpose of independent indoor air quality management by placing artificial intelligence.

1. (2022).Ventilation regimes of school classrooms against airborne transmission of infectious respiratory droplets: A review.Building and Environment Part A,207(Part A),108484.
2. ANSI/ASHRAE Standard52.2-2017. https://www.ashrae.org/technical-resources/standards-and-guidelines.
3. Bakó-Biró, Zs,Clements-Croome, D .J.,Kochhar, N.,awbi, H. B.,Williams, M. J.(2012).Ventilation rates in schools and pupils’ performance.Building and Environment,48,215-223.
4. Carslaw, Nicola(2007).A new detailed chemical model for indoor air pollution.Atmospheric Environment,41(6),1164-1179.
5. Dionova, Brainvendra Widi,Mohammed, M. N.,Al-Zubaidi, S,Yusuf, Eddy(2020).Environment indoor air quality assessment using fuzzy inference system.ICT Express,6(3),185-194.
6. Ishak, Zurida,Fong, Sim Liew,Shin, See Cia(2019).SMART KPI Management System Framework.2019 IEEE 9th International Conference on System Engineering and Technology (ICSET)
7. Jarvi, Kati,Toomla, Sander,Ahmed, Kaiser(2018).Ventilation Positive Pressure Intervention Effect on Indoor Air Quality in a School Building with Moisture Problems.Environment Research and Public Health,15,23.
8. Lundberg, Scott,Lee, Su-In(2017).A Unified Approach to Interpreting Model Predictions.NIPS'17: Proceedings of the 31st International Conference on Neural Information Processing Systems
9. Maas, Andrew L.,Hannun, Awni Y.,Ng, Andrew Y.(2013).Rectifier nonlinearities improve neural network acoustic models.CML Workshop on Deep Learning for Audio. Speech and Language Processing
10. Rostami, Mehrdad,Oussalah, Mourad(2022).A novel explainable COVID-19 diagnosis method by integration of feature selection with random forest.Informatics in Medicine Unlocked,30,100941.
11. Rumelhart, D. E,Hinton, G. E.,Mcclelland, J.L.(1987).A General Framework for Parallel Distributed Processing.Publisher:MIT Press.
12. Swamy, G.S.N.V.K.S.N.(2021).Development of an indoor air purification system to improve ventilation and air quality.Science Direct,7(10),e0815.
13. Toftum, Jørn,Kjeldsen, Birthe U.,Wargocki, Pawel,Menå, Henriette R.,Hansen, Eva M.N.,Clausen, Geo(2015).Association between classroom ventilation mode and learning outcome in Danish schools.Building and Environment,92,494-503.
14. 古松國, S. K.(2004)。臺北市=Taipei, Taiwan，國立臺北科技大學電機工程學系=Department of Electrical Engineering, National Taipei University of Technology。
15. 陳建良, James.,王孔政, K. J.,吳政俊, C. J.,賴宜伶, Y. L.,陳佳雯, C. W.(2008)。類神經網路於農業產銷預測模式之應用。光進工程學刊，3(3)，241-249。
16. 陳韋謙, W. C.(2022)。臺北市=Taipei, Taiwan，國立臺北科技大學建築系建築與都市設計碩士班=Architecture and Urban Design, National Taipei University of Technology。