AIoT影像感測器在建築物安全應用與效益研究

因應近年來人工智慧深度學習技術在電腦視覺、影像辨識上快速發展，使得原本必須透過雲端平台進行決策判斷之任務，已經可以由AIoT感測器端的邊緣運算來提供即時影像辨識結果，不但加速決策之即時性，亦有助於改善資訊之安全性。本研究探討如何應用AIoT影像感測器（AIoT-IS）提升智慧建築之效能，及其在未來智慧生活空間之應用潛力。本文透過次級資料分析、專家訪談與效益分析模型設計，共歸納AIoT-IS於建築生命週期四個階段18種可能應用情境類型；並提出｢建築智慧科技應用成本效益分析模式CAMITA）｣以做為AIoT-IS之應用效益分析方法。經兩個模擬案例效益評估試算發現：在｢建築施工中工地安全監控｣案例中，淨現值指標（NPVI）為20.21%，而益本比（BCR）則為5.10；另外，在｢建築使用營運階段之智慧社區安全管理｣案例中，其NPVI為12.63%，而BCR則為2.10；可見AIoT-IS在建築物安全應用確實具有明顯效益。另外，透過專家訪談亦發現，AIoT-IS之應用也存在著潛在之社會風險；不同利害關係人對於AIoT-IS於建築物安全應用之期待效益、成本接受度、未來發展潛力，以及社會風險之感受度亦皆有不同。本文最後針對建築安全之利害關係人對於AIoT-IS於建築物安全應用之相關議題，歸納出具體建議，以提供建築工程不同參與單位之參考。

關鍵字

人工智慧物聯網；智慧建築；智慧安全監測；效益分析

並列摘要

Thanks to the fast development of Deep Learning and Computer Visualization, the traditional cloud-based decision-making can be carried out with the edge-computing of AIoT Image Sensors (AIoT-IS), and thus improve the timeliness and security of image recognition. This study aims to investigate the potential scenarios and the associated benefits of AIoT-IS applications. Through literature review, expert interviews, and benefit analysis model development, this study summarizes 18 AIoT-IS application scenarios categorizedinto four different phases of building lifecycle and a "Cost/benefit Analysis Model for Intelligent building Technology Adoption, CAMITA)" is proposed for benefit evaluation of AIoT-IS for building safety monitoring. According to the results of two simulated case studies, AIoT-IS achieves significant benefits, with Net Present Value Index (NPVI) of 20.21% and Benefit/Cost Ratio (BCR) of 5.10 in "Case (I)-AIoT image sensing for construction site safety monitoring", and also achievesNPVI of 12.63% and BCR of 2.10 in "Case (II)-AIoT images sensing adoption in the security control of smart community." The interviews with the domain experts also point out potential threats and risks while adopting AIoT image sensing in building safety monitoring. Different interviewees (stakeholders of buildings) have different perspectives on the benefits and risks of such an innovative technology from the angles of their priority issues, expected benefits, application limitations and implementation obstacles. Finally, suggestions are summarized for stakeholders of buildings regarding the safety monitoring the application of AIoT-IS to provide references for different interested parties of building projects.

並列關鍵字

AIoT ； Smart Building ； Intelligent Safety Monitoring ； Benefit Evaluation

參考文獻

周國村，袁建中 (2014)。應用決策實驗室分析法(DEMATEL)與網路層級分析法(ANP)在研發專案計畫評選。中山管理評論，22(3)，543-572。DOI: 10.6160/2014.09.04。Chou, G.T., & Yuan, B.J.C. (2014). Application of DEMATEL and ANP to the R&D Project Selection.” Sun Yat Sen Management Review, 22(3), 543-572. DOI: 10.6160/2014.09.04.

Arfi, W. B., Nasr, I. B., Khvatova, T., & Zaied, Y. B. (2021). Understanding acceptance of eHealthcare by IoT natives and IoT immigrants: An integrated model of UTAUT, perceived risk, and financial cost. Technological Forecasting and Social Change, 163, 120437, https://doi.org/10.1016/j.techfore.2020.120437.

Boominathan, L., Kruthiventi, S. S. S., & Babu, R. V. (2016). CrowdNet: A deep convolutional network for dense crowd counting. Proceedings of the 24th ACM international conference on Multimedia, Amsterdam, The Netherlands. [Online]. Available: https://doi.org/10.1145/2964284.2967300.

Burnett, J. D., & Wing, M. G. (2018). A low-cost near-infrared digital camera for fire detection and monitoring. International Journal of Remote Sensing, 39(3), 741-753. 2018/02/01. doi: 10.1080/01431161.2017.1385109.

Chor, K. H. B., Wisdom, J. P., Olin, S. C. S., Hoagwood, K. E., & Horwitz, S. M. (2015). Measures for predictors of innovation adoption. Administration and Policy in Mental Health and Mental Health Services Research, 42(5), 545-73. http://doi: 10.1007/s10488-014-0551-7.

主題瀏覽