A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Machine learning-driven sustainable urban design: transforming Singapore's landscape with vertical greenery
Integrating state-of-the-art technology is now essential in pursuing environmentally sustainable urban development. This research focuses on Singapore's lush vertical landscape and explores the potential of machine learning. Specifically, Convolutional Neural Networks (CNN) to enhance sustainable urban design. The CNN-MOA model was created by incorporating the Mayfly Optimization Algorithm (MOA) to improve the performance of the CNN-based model further. Without the Mayfly Optimization Algorithm, the convolutional neural network (CNN) achieved impressive results. It had a total accuracy of 0.977725, a weighted average precision of 0.977679, a weighted average recall of 0.977725, a weighted average F1-Score of 0.977621, and a macro average precision of 0.953458. These measures unequivocally demonstrated CNN's ability to process and analyze data about urban design effectively. A significant advancement occurred when the fusion of the CNN model with the Mayfly Optimization Algorithm resulted in the creation of the CNN-MOA hybrid. The installation led to a substantial enhancement in the model's performance. The results revealed a weighted average accuracy of 99.98%, recall of 99.92%, macro average F1-Score of 99.95%, weighted average precision of 99.98%, weighted average recall of 99.98%, and weighted average F1-Score of 99.98%. Each of these indicators exhibited exceptional performance. The model's ability to comprehend and evaluate intricate urban design features has been significantly enhanced. These findings demonstrate significant prospects for the sustainable development of metropolitan areas, particularly in Singapore, as observed by urban planners. Combining machine learning with the Mayfly Optimization Algorithm offers a powerful method for enhancing the integration of vertical greenery and improving overall urban design. These developments align with Singapore's commitment to sustainable urban development, contributing to creating environmentally friendly and visually appealing cities. This research emphasizes the transformative potential of machine learning-powered solutions in shaping the future of sustainable and ecologically harmonious urban architecture.
Machine learning-driven sustainable urban design: transforming Singapore's landscape with vertical greenery
Integrating state-of-the-art technology is now essential in pursuing environmentally sustainable urban development. This research focuses on Singapore's lush vertical landscape and explores the potential of machine learning. Specifically, Convolutional Neural Networks (CNN) to enhance sustainable urban design. The CNN-MOA model was created by incorporating the Mayfly Optimization Algorithm (MOA) to improve the performance of the CNN-based model further. Without the Mayfly Optimization Algorithm, the convolutional neural network (CNN) achieved impressive results. It had a total accuracy of 0.977725, a weighted average precision of 0.977679, a weighted average recall of 0.977725, a weighted average F1-Score of 0.977621, and a macro average precision of 0.953458. These measures unequivocally demonstrated CNN's ability to process and analyze data about urban design effectively. A significant advancement occurred when the fusion of the CNN model with the Mayfly Optimization Algorithm resulted in the creation of the CNN-MOA hybrid. The installation led to a substantial enhancement in the model's performance. The results revealed a weighted average accuracy of 99.98%, recall of 99.92%, macro average F1-Score of 99.95%, weighted average precision of 99.98%, weighted average recall of 99.98%, and weighted average F1-Score of 99.98%. Each of these indicators exhibited exceptional performance. The model's ability to comprehend and evaluate intricate urban design features has been significantly enhanced. These findings demonstrate significant prospects for the sustainable development of metropolitan areas, particularly in Singapore, as observed by urban planners. Combining machine learning with the Mayfly Optimization Algorithm offers a powerful method for enhancing the integration of vertical greenery and improving overall urban design. These developments align with Singapore's commitment to sustainable urban development, contributing to creating environmentally friendly and visually appealing cities. This research emphasizes the transformative potential of machine learning-powered solutions in shaping the future of sustainable and ecologically harmonious urban architecture.
Machine learning-driven sustainable urban design: transforming Singapore's landscape with vertical greenery
Asian J Civ Eng
Hussein, Mohammed Yousef Abu (author) / AL-Karablieh, Mutasem (author) / Al-Kfouf, Safa’ (author) / Taani, Mahmoud (author)
Asian Journal of Civil Engineering ; 25 ; 3851-3863
2024-07-01
13 pages
Article (Journal)
Electronic Resource
English
Sustainable urban design , Machine learning , Convolutional neural networks (CNN) , Mayfly optimization algorithm (MOA) , Vertical greenery , Singapore's landscape , CNN-MOA hybrid model , Sustainable city development Engineering , Civil Engineering , Building Materials , Sustainable Architecture/Green Buildings