Sun Jingjing, Guan Xin, Yuan Siqi, Guo Yalin, Tan Yepei, Gao Yajuan
School of Public Administration, Guangzhou University, Guangzhou, China.
Guangzhou Xinhua University, Dongguan, China.
Front Public Health. 2024 Dec 16;12:1440049. doi: 10.3389/fpubh.2024.1440049. eCollection 2024.
Smart cities, artificial intelligence (AI) in healthcare, and low-carbon building materials are pivotal to public health, environmental sustainability, and green efficiency. Despite their critical importance, understanding public perceptions and attitudes toward these domains remains underexplored. Additionally, the effective use of advanced technologies like convolutional neural networks (CNN) in predicting and promoting low-carbon solutions in construction is gaining attention.
This study employs a dual approach: (1) A survey of 200 respondents was conducted to gauge public perceptions and attitudes toward smart cities, AI in medicine, and low-carbon building materials. (2) A CNN model was developed and implemented to predict the performance of low-carbon building materials. The model utilized convolutional and pooling layers to capture local features and spatial information from image datasets, with tasks including image classification and segmentation.
The survey results indicate high awareness of smart cities (80%), with 60% associating them with environmental protection and green living. For AI in medicine, 70% of respondents are aware of its applications, but only 45% perceive it as environmentally beneficial. Regarding low-carbon building materials, 60% expressed willingness to pay premium prices, and 65% recognized their positive environmental impact. The CNN model demonstrated high prediction accuracy on both training and validation datasets, effectively aiding in the identification of low-carbon materials and reducing building energy consumption and carbon emissions.
The findings highlight significant public awareness and diverse attitudes toward these critical domains, suggesting the need for improved communication and advocacy for AI's environmental benefits. The application of CNN models in the construction industry showcases a promising pathway to enhance material selection efficiency and foster sustainable practices. These insights are essential for aligning public understanding with technological advancements to achieve environmental and public health goals.
智慧城市、医疗保健领域的人工智能（AI）以及低碳建筑材料对公众健康、环境可持续性和绿色效率至关重要。尽管它们至关重要，但对公众对这些领域的认知和态度的了解仍未得到充分探索。此外，卷积神经网络（CNN）等先进技术在预测和推广建筑领域的低碳解决方案方面的有效应用正受到关注。
本研究采用了双重方法：（1）对200名受访者进行了调查，以评估公众对智慧城市、医学人工智能和低碳建筑材料的认知和态度。（2）开发并实施了一个CNN模型来预测低碳建筑材料的性能。该模型利用卷积层和池化层从图像数据集中捕获局部特征和空间信息，任务包括图像分类和分割。
调查结果表明，公众对智慧城市的认知度很高（80%），其中60%将其与环境保护和绿色生活联系起来。对于医学人工智能，70%的受访者了解其应用，但只有45%的人认为它对环境有益。关于低碳建筑材料，60%的人表示愿意支付更高的价格，65%的人认识到它们对环境有积极影响。CNN模型在训练数据集和验证数据集上均显示出较高的预测准确率，有效地帮助识别低碳材料并减少建筑能耗和碳排放。
研究结果凸显了公众对这些关键领域的高度认知和多样态度，表明需要加强关于人工智能环境效益的沟通和宣传。CNN模型在建筑行业的应用展示了一条提高材料选择效率和促进可持续实践的有前景的途径。这些见解对于使公众理解与技术进步保持一致以实现环境和公众健康目标至关重要。
