Scholarlink

<p>Substantial efforts have been made to modernize and decarbonize the waste collection industry. Smart sensor-based waste collection (SWC) systems have been developed to optimize collection routes based on the actual waste levels in bins, thereby reducing service frequency, fuel consumption, and air pollution. To date, there has not been a fully functional commercial SWC system due to the complexity and limited practicality of such a hardware-intensive design. Alternatively, this study presents an innovative cloud-based approach in which historical waste generation data from onboard-truck sensors replaces bin sensor data. The proposed knowledge-based waste collection (KWC) system incorporates machine learning for waste forecasting, expert bin selection, route optimization, and autonomous navigation. The system was simulated in an actual residential district to collect recyclables over three scenarios: conventional, SWC, and KWC. Historical data were used to train various machine learning algorithms, including generalized linear models, support vector machines, deep neural networks, gradient-boosted trees (XGBoost), and random forests to predict daily waste generation per bin. The heuristic bin-selection algorithm selected the bins to be served based on the actual and forecasted waste quantities in SWC and KWC, respectively. XGBoost achieved the highest prediction accuracy, with a 4.2% relative error and a root mean square error of 0.47, owing to its enhanced ability to handle nonlinear interactions among variables and produce unbiased predictions. KWC significantly reduced the travel distance by 60.9%, the number of collected bins by 89%, and the number of collection days by 10%. The implementation of connected and autonomous vehicles significantly improved the system, reducing the total delay by 90%. Moreover, a life cycle costing analysis revealed that, compared with conventional collection, the 5% reduction in travel expenses in SWC was insufficient to offset the cost of bin sensors, whereas KWC achieved a 63% cost reduction by replacing hardware-intensive components with a cloud-based system. Overall, this study demonstrated that KWC systems can potentially outperform hardware-intensive SWC systems, given the substantial economic and operational benefits of a cloud-based approach.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Development and simulation of an innovative autonomous knowledge-based smart waste collection system

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月26日

查看全文
  • Mohamed Abdallah,
  • Mariam Hosny

摘要

Substantial efforts have been made to modernize and decarbonize the waste collection industry. Smart sensor-based waste collection (SWC) systems have been developed to optimize collection routes based on the actual waste levels in bins, thereby reducing service frequency, fuel consumption, and air pollution. To date, there has not been a fully functional commercial SWC system due to the complexity and limited practicality of such a hardware-intensive design. Alternatively, this study presents an innovative cloud-based approach in which historical waste generation data from onboard-truck sensors replaces bin sensor data. The proposed knowledge-based waste collection (KWC) system incorporates machine learning for waste forecasting, expert bin selection, route optimization, and autonomous navigation. The system was simulated in an actual residential district to collect recyclables over three scenarios: conventional, SWC, and KWC. Historical data were used to train various machine learning algorithms, including generalized linear models, support vector machines, deep neural networks, gradient-boosted trees (XGBoost), and random forests to predict daily waste generation per bin. The heuristic bin-selection algorithm selected the bins to be served based on the actual and forecasted waste quantities in SWC and KWC, respectively. XGBoost achieved the highest prediction accuracy, with a 4.2% relative error and a root mean square error of 0.47, owing to its enhanced ability to handle nonlinear interactions among variables and produce unbiased predictions. KWC significantly reduced the travel distance by 60.9%, the number of collected bins by 89%, and the number of collection days by 10%. The implementation of connected and autonomous vehicles significantly improved the system, reducing the total delay by 90%. Moreover, a life cycle costing analysis revealed that, compared with conventional collection, the 5% reduction in travel expenses in SWC was insufficient to offset the cost of bin sensors, whereas KWC achieved a 63% cost reduction by replacing hardware-intensive components with a cloud-based system. Overall, this study demonstrated that KWC systems can potentially outperform hardware-intensive SWC systems, given the substantial economic and operational benefits of a cloud-based approach.