本論文旨在建置一個適合教室場域使用的AIoT智慧照明系統，此系統整合物聯網技術、軟硬體應用與人工智慧演算法進行燈光調控。系統中使用物聯網裝置感測教室環境照明，並透過本論文所提出之「動態控制區域劃分調光最佳化演算法」計算最佳的調光數值後進行遠端燈光控制，使得教室中的燈光能夠隨著日照採光的改變而即時調整至最適當的調光狀態，希望能為學生提供一個照度充足、色溫適當且分佈均勻的照明環境，進而提升學生們的學習成效，也能有效預防學生們的視力惡化。
本論文以模擬實驗與實際場域實驗進行結果討論，其中為了討論光感測器放置於天花板的可行性，在實際場域實驗前，我們分別進行天花板及工作水平兩種不同光感測器位置的實驗設置。調光結果的均勻度討論以照度最小值與最大值的比值作為評估依據。誤差計算方面以平均百分誤差(Mean percent error, MPE) 以及平均絕對百分誤差(Mean absolute percent error, MAPE)。在模擬實驗中，無日照條件下最佳調光結果有MPE = 0.15%、MAPE = 5.61%的誤差表現；直接日照條件下最佳調光結果有MPE = 5.69%、MAPE = 6.15%的誤差表現。在實際場域實驗中，無日照條件下最佳調光結果有MPE = -5.52、MAPE = 14.79%的誤差表現；直接日照條件下最佳調光結果有MPE = -1.6%、MAPE = 7.49的誤差表現。
除了自動化系統建置以及動態控制區域劃分調光最佳化演算法開發之外，本論文中也另外開發了一個「智慧光照」App應用程式，可供使用者在基於系統演算法調光的基礎上，隨著主觀感受或是特定任務需求進行空間中的燈光調整或系統開關的操作，使得整體系統更加貼近使用者需求。

This thesis aims to develop an AIoT-based smart lighting system suitable for classroom use, allowing classroom lighting to be adjusted dynamically according to changes in natural light throughout the day due to factors such as time and weather. The system uses IoT devices to sense the classroom lighting environment and calculates the optimal dimming values through the "Dynamic Control Zone Partition and Dimming Optimization Algorithm" proposed in this thesis, enabling remote control of lighting to ensure that the illuminance and correlated color temperature meet the required values while maintaining uniform distribution of light.
This thesis conducts results discussion through simulation experiments and actual field experiments. To explore the feasibility of placing light sensors on the ceiling, field experiments were conducted with light sensors positioned at both the ceiling and work levels. The uniformity of the dimming results is discussed based on the ratio of the minimum to maximum illuminance values. For error calculation, the Mean Percent Error (MPE) and Mean Absolute Percent Error (MAPE) are used. In the simulation experiments, the optimal dimming results showed MPE = 0.15% and MAPE = 6.15% error under no sunlight conditions, and MPE = 5.69% and MAPE = 6.15% error under direct sunlight conditions. In the actual field experiments, the optimal dimming results showed MPE = -5.52% and MAPE = 14.79% error under no sunlight conditions, and MPE = -1.6% and MAPE = 7.49% error under direct sunlight conditions.
In addition to the development of the automated system and the dynamic control zone partition and dimming optimization algorithm, this thesis also developed a "Smart Lighting" app. This application allows users to adjust the lighting or control the system based on their subjective preferences or specific task requirements, building on the system algorithm's adjustments. This makes the overall system more user-friendly and tailored to individual needs.

[1] 教育部，《國民小學及國民中學設施設備基準》，教育部，國民及學前教育署，2019。
[2] 朱英雄，《高雄市國小教室照明環境之調查研究》，碩士論文，國立高雄師範大學，2001。
[3] 教育部，《學校照明節能改善參考手冊》，2012。
[4] 黃國倉，《研析公部門特定業務類型照明最佳化配置》，經濟部能源科技研究發展計劃(財團法人台灣產業服務基金會委託)，2021。
[5] 黃國倉，《公部門特定業務類型LED燈具最佳化配置研析》，經濟部能源科技研究發展計畫(財團法人台灣產業服務基金會委託)，2022。
[6] S. A. Samani, “The influence of light on student’s learning performance in learning environments: A knowledge internalization perspective.” World Academy of Science, Engineering and Technology, 81: 540-547, 2011.
[7] S. Samardzic, A. Mihailovic, S. Adamovic, D. Adamovic, B. Banjanin, V. Rajs, and R. Lakatos, “Noise and lighting as physical stressors in a printing laboratory-a case study,” Environmental Engineering and Management Journal, vol. 22, no. 3, pp. 595-606, 2023.
[8] W. Schakel, C. Bode, EBM. Elsman, HPA. van der Aa, R. de Vries, GHMB. van Rens, and RMA. van Nispen, “The association between visual impairment and fatigue: a systematic review and meta-analysis of observational studies,” Ophthalmic Physiological Optics., vol. 39, pp. 399-413, 2019.
[9] 衛生福利部，《兒童青少年視力監測調查計畫》，衛生福利部，國民健康署，2015。
[10] T. H. Tsai, Y. L. Liu, I. H. Ma, C.C. Su, C.W. Line, L. K. Lin, C.H. Hsiao, and I. J. Wang, “Evolution of the prevalence of myopia among Taiwanese schoolchildren: a review of survey data from 1983 through 2017,” Ophthalmology, vol. 128, no. 2, pp. 290-301, 2021.
[11] S. Mariotti, I. Kocur, S. Resnikoff, M. Jong, K. Naidoo, and M. He, “The impact of myopia and high myopia,” Joint World Health Organization-Brien Holden Vision Institute Global Scientific Meeting on Myopia, Sidney, Australia, 2015.
[12] L. Lan, S. Hadji, L. Xia, and Z. Lian, “The effects of light illuminance and correlated color temperature on mood and creativity,” Building Simulation, vol. 14, pp. 463-475, 2021.
[13] M. He, T. Ru, S. Li, Y. Li, and G. Zhou, “Shine light on sleep: Morning bright light improves nocturnal sleep and next morning alertness among college students,” Journal of Sleep Research, vol. 32, no. 2, 2023.
[14] A. U. Viola, L. M. James, L. J. Schlangen, and D. J. Dijk, “Blue-enriched white light in the workplace improves self-reported alertness, performance and sleep quality,” Scandinavian Journal of Work, Environment & Health, vol. 34, no. 4, pp.297-306, 2008.
[15] M. Boubekri, I. N. Cheung, K. J. Reid, C. H. Wang, and P. C. Zee, “Impact of windows and daylight exposure on overall health and sleep quality of office workers: A case-control pilot study,” Journal of clinical sleep medicine, vol. 10, no. 6, pp. 603-611, 2014.
[16] M. G. Figueiro, B. Steverson, J. Heerwagen, K. Kampschroer, C. M. Hunter, K. Gonzales, B. Plitnick, and Mark S. Rea, “The impact of daytime light exposures on sleep and mood in office workers,” Sleep Health, vol. 3, pp.204-215, 2017.
[17] M. S. Mott, D. H. Robinson, A. Walden, J. Burnette, and A. S. Rutherford, “Illuminating the effects of dynamic lighting on student learning,” Sage Open, vol. 2, no. 2, 2012.
[18] K. Schledermann, H. Pihlajaniemi, S. Sen, and E. K. Hansen, “Dynamic lighting in classrooms: A new interactive tool for teaching,” Interactivity, Game Creation, Design, Learning, and Innovation: 7th EAI International Conf., ArtsIT 2018, and 3rd EAI International Conf., Braga, Portugal, Oct. 24-26, 2018, pp. 374-384.
[19] P. J. Sleegers, N. M. Moolenaar, M. Gaketzka, A. Pruyn, B. E. Sarroukh, B. van der Zande, “Lighting affects students’ concentration positively: Findings from three Dutch studies,” Lighting Research & Technology, vol. 45, no. 2, pp. 159-175, 2013.
[20] B. Von Neida, D. Maniccia, and A. Tweed, “An analysis of the energy and cost savings potential of occupancy sensors for commercial lighting systems,” Journal of the Illuminating Engineering Society, vol. 30, pp. 111-125, 2001.
[21] J. Byun, I. Hong, B. Lee, and S. Park, “Intelligent household LED lighting system considering energy efficiency and user satisfaction,” IEEE Transactions on Consumer Electronics, vol. 59, no. 1, pp. 70-76, 2013.
[22] M. Rossi, “LEDs and new technologies for circadian lighting,” Circadian Lighting Design in the LED Era, pp.157-207, 2019.
[23] C. T. Lee, L. B. Chen, H. M. Chu, and C. J. Hsieh, “Design and implementation of a leader-follower smart office lighting control system based on IoT technology,” IEEE Access, vol. 10, pp. 28066-28079, 2022.
[24] I. P. E. W. Pratama, T. Soehartanto, D. D. D. Wibowo, N. A. Tjandra, and M. Nizar, “Automated lighting design in the classroom,” Bulletin of Electrical Engineering and Informatics, vol. 13, pp. 160-166, 2024.
[25] J. Zhang, Z. Chen, A. Wang, Z. Li and W. Wan, “Intelligent personalized lighting control system for residents,” Sustainability, vol. 15, no. 21, 2023.
[26] R. Kumar, “New algorithms for daylight harvesting in a private office,” 2015 18th International Conference on Information Fusion (Fusion), Washington, DC, USA, 2015, pp. 383-392.
[27] L. Parise, F. Lamonaca, and D. L. Cami, “Interior lighting control system: A practical case using daylight harvesting control strategy,” 2015 IEEE 15th International Conference on Environment and Electrical and Electrical Engineering (EEEIC), Rome, Italy, 2015, pp. 719-724.
[28] Y. Gao, Y. Lin, and Y. Sun, “A wireless sensor network based on the novel concept of an I-matrix to achieve high-precision lighting control,” Building and Environment, vol. 70, pp. 223-231, 2013.
[29] D. Caicedo, S. Li, and A. Pandharipande, “Smart lighting control with workspace and ceiling sensors,” Lighting Research & Technology search & Technology, vol. 49, no. 4, pp. 446-460, 2017.
[30] M. Beccali, M. Bonomolo, G. Ciulla, and V. L. Brano, “Assessment of indoor illuminance and study on best photosensors’ position for design and commissioning of daylight linked control system. A new method based on artificial neural networks,” Energy, vol. 154, pp. 466-476, 2018.
[31] 陳彥溥，《智慧人因照明調控系統開發及其教室成效評估》，碩士論文，國立成功大學，2022。
[32] H. Zhang, C. Guo, X. Su, and C. Zhu, “Measurement data fitting based on moving least squares method,” Mathematical Problems in Engineering, vol. 2015.
[33] Y. Sun, C. Zhang, H. Ji, and J. Qiu, “A temperature field reconstruction method for spacecraft leading edge structure with optimized sensor array,” Journal of Intelligent Material Systems and Structures, vol. 32, no. 17, pp. 2024-2038, 2021.
[34] A. Antal, P. M. Guerrero, and S. Cheval, “Comparison of spatial interpolation methods for estimating the precipitation distribution in Portugal,” Theoretical and Applied Climatology, vol. 145, no. 3, pp. 1193-1206, 2021.
[35] J. Ma, Y. Ding, J. C. Cheng, F. Jiang, and Z. Wan, “A temporal-spatial interpolation and extrapolation method based on geographic Long Short-Term Memory neural network for PM2.5,” Journal of Cleaner Production, vol. 237, 2019.
[36] H. Lee, C. H. Choi, and M. Sung, “Development of a dimming lighting control system using general illumination and location-awareness technology,” Energies, vol. 11, no. 11, 2018.
[37] A. Seyedolhosseini, N. Masoumi, M. Modarressi, and N. Karimian, “Zone based control methodology of smart indoor lighting systems using feedforward neural networks,” 2018 9th International Symposium on Telecommunications (IST), Tehran, Iran, 2018, pp. 201-206.
[38] Y. Cheng, C. Fang, J. Yuan, and L. Zhu, “Design and application of a smart lighting system based on distributed wireless sensor networks,” Applied Sciences, vol. 10, 2020.
[39] V. M. Albornoz, L. J. Ñanco, and J. L. Sáez, “Delineating robust rectangular management zones based on column generation algorithm,” Computers and Electronics in Agriculture, vol. 161, pp. 194-201, 2019.
[40] M. Neardey, E. Aminudin, L. P. Chung, R. M. Zin, R. Zakaria, C. C. Wahid, and Z. Z. N. Noor, “Simulation on lighting energy consumption based on building information modelling for energy efficiency at highway rest and service areas Malaysia,” IOP Conference Series: Materials Science and Engineering, vol. 943, no. 1, 2020.
[41] J. Liu, W. Zhang, and X. Chu, and Y. Liu, “Fuzzy logic controller for energy savings in a smart LED lighting system considering lighting comfort and daylight,” Energy and Buildings, vol. 127, pp. 95-104, 2016.
[42] L. Wang, “Home intelligent lighting control system based on wireless sensor,” Journal of Engineering, Design and Technology, vol. 18, no. 5, pp. 1231-1240, 2020.
[43] I. Park and G. Choi, “Designing of high power LED lighting system using Bluetooth based fuzzy lighting control,” International Information Institute (Tokyo), vol. 19, no. 9, pp. 3809-3818, 2016.
[44] N. Vikram, K. S. Harish, M. S. Nihaal, R. Umesh, and S. A. A. Kumar, “A low cost home automation system using Wi-Fi based wireless sensor network incorporating Internet of Things (IoT),” 2017 IEEE 7th International Advance Computing Conference (IACC), Hyderabad, India, 2017, pp. 174-178.
[45] P. K. Soori and M. Vishwas, “Lighting control strategy for energy efficient office lighting system design,” Energy and Buildings, vol. 66, pp. 329-337, 2013.
[46] G. Chiesa, D. Di Vita, A. Ghadirzadeh, A. H. M. Herrera and J. C. L. Rodriguez, “A fuzzy-logic IoT lighting and shading control system for smart buildings,” Automation in Construction, vol. 120, 2020.
[47] A. Seyedolhosseini, N. Masoumi, M. Modarressi, and N. Karimian, “Daylight adaptive smart indoor lighting control method using artificial neural networks,” Journal of Building Engineering, vol. 29, 2020.
[48] E. N. D. Madias, P. A. Kontaxis, and F. V. Topalis, “Application of multi-objective genetic algorithms to interior lighting optimization,” Energy and Buildings, vol. 125, pp. 66-74, 2016.
[49] “MQTT – The Standard for IoT Messaging.” [Online] Available: https://mqtt.org/ (accessed May. 18, 2024)
[50] W. Gao, and T. H. Morris, “On cyber attacks and signature based intrusion detection for modbus based industrial control systems,” Journal of Digital Forensics, Security and Law, vol. 9, 2014.
[51] “Bluetooth Mesh Networking: Friendship.” [Online] Available: https://www.bluetooth.com/blog/bluetooth-mesh-networking-series-friendship/ (accessed May. 22, 2024)
[52] R. Tibshirani, “Regression shrinkage and selection via the lasso,” Journal of the Roual Statistical Society Series B: Statistical Methodology, vol. 58, no. 1, pp. 267-288, 1996.
[53] A. E. Hoerl, and R. W. Kennard, “Ridge regression: Biased estimation for nonorthogonal problems,” Technometrics, vol. 12, no. 1, pp. 55-67, 1970.
[54] H. Zou, and T. Hastie, “Regularization and variable selection via the elastic net,” Journal of the Royal Statistical Society: Series B (Statistical Methodology), vol. 67, pp. 301-320, 2005.
[55] M. Wei, K. W. Houser, B. Orland, D. H. Lang, N. Ram, M. J. Sliwinski, and M. Bose, “Field study of office worker responses to fluorescent lighting of different CCT and lumen output,” Journal of Environmental Psychology, vol. 39, pp. 62-76, 2014.