Scholarlink

<p>The large volumes of bio-waste pose significant health and sanitation hazards. Effective bio-waste management involves value addition and conversion processes to enable the utilization of municipal biological waste as low-carbon energy sources. This research suggests a new predictive analytics model using the YOLOv8-SPP algorithm for improved waste management. With precise structuring and data processing, YOLOv8-SPP enhances waste identification and segmentation of various wastes with the vision of facilitating proper anticipation of future trends in waste production. The enhanced framework is remarkably 92% accurate in predicting waste production compared to the 78% accuracy achieved with other data types. The deployment also had the effect of the recycling rate growing by 20% and reducing waste treatment expenses by 15%. The findings justify the success of executing state-of-the-art analytics to optimize waste management processes in intelligent cities.</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

Advanced predictive analytics for bio-waste management using YOLOv8-SPP to enhance waste prediction and sustainability in smart cities

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年7月2日

查看全文
  • Selvalakshmi Balasubramanium,
  • Bharathiraja Nagu,
  • Shonak Bansal,
  • Mohammad Rashed Iqbal Faruque,
  • Kholoud Saad Al-mugren

摘要

The large volumes of bio-waste pose significant health and sanitation hazards. Effective bio-waste management involves value addition and conversion processes to enable the utilization of municipal biological waste as low-carbon energy sources. This research suggests a new predictive analytics model using the YOLOv8-SPP algorithm for improved waste management. With precise structuring and data processing, YOLOv8-SPP enhances waste identification and segmentation of various wastes with the vision of facilitating proper anticipation of future trends in waste production. The enhanced framework is remarkably 92% accurate in predicting waste production compared to the 78% accuracy achieved with other data types. The deployment also had the effect of the recycling rate growing by 20% and reducing waste treatment expenses by 15%. The findings justify the success of executing state-of-the-art analytics to optimize waste management processes in intelligent cities.