Deep Learning-Based Swot Analysis in Construction and Demolition Waste Management

Researchers worldwide have employed a varied array of sources to calculate the successful management of Construction and Demolition (C&DW). Limited research has been undertaken in the domain of Construction and Demolition Waste Management (C&DWM) and consequently leaving a large gap in the availability of effective management techniques. Due to the limited time available for building removal and materials collection, preparing for building materials reuse at the end of life is frequently a challenging task. In this research work Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) is proposed to predict the number of waste materials that are obtained from a building at the end of its useful life. As a result, an effective Waste Management (WM) plan has been established through SWOT analysis. The results of the study reveal that, given fundamental building characteristics, it is possible to predict the number of materials that would be collected with high precision from a building after demolition. The proposed deep learning models achieved an average R-squared value of 0.98 and a Mean Absolute Error of 18.1 and 20.14 better than existing methods such as random forest, CNN, and DBN (Data Bus Network).

Automated summary

Researchers have used various sources to calculate the successful management of Construction and Demolition Waste (C&DW). However, there is limited research in the field of Construction and Demolition Waste Management (C&DWM), leading to a lack of effective management techniques. This study proposes using a Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) model to predict the amount of waste materials obtained from a building at the end of its useful life. The results show that the proposed deep learning models outperform existing methods with an average R-squared value of 0.98 and a Mean Absolute Error of 18.1 and 20.14.