A Systematic Review of AI-Based Techniques for Automated Waste Classification DOI Creative Commons

Farnaz Fotovvatikhah,

Ismail Ahmedy, Rafidah Md Noor

и другие.

Sensors, Год журнала: 2025, Номер 25(10), С. 3181 - 3181

Опубликована: Май 18, 2025

Waste classification is a critical step in waste management that time-consuming and necessitates automation to replace traditional approaches. Recently, machine learning (ML) deep (DL) have gained attention from researchers seeking automate by providing alternative computational techniques address various waste-related challenges. Significant research on has emerged recent years, reflecting the growing focus this domain. This systematic literature review (SLR) explores role of artificial intelligence (AI), particularly (DL), automating classification. Using Kitchenham’s PRISMA guidelines, we analyze over 97 studies, categorizing AI-based into ML-based, DL-based, hybrid models. We further present an in-depth fifteen publicly available datasets, highlighting key limitations such as dataset imbalance, real-world variability, standardization issues. Our analysis reveals approaches dominate current landscape, with CNN-based architecture transfer showing promising results. To guide future advancements, study also proposes structured roadmap organizes challenges opportunities short-, mid-, long-term priorities. The integrates insights model accuracy, system efficiency, sustainability goals support practical deployment AI-powered systems. work provides comprehensive understanding state-of-the-art ML DL for offers areas remain unexplored.

Язык: Английский

A Systematic Review of AI-Based Techniques for Automated Waste Classification DOI Creative Commons

Farnaz Fotovvatikhah,

Ismail Ahmedy, Rafidah Md Noor

и другие.

Sensors, Год журнала: 2025, Номер 25(10), С. 3181 - 3181

Опубликована: Май 18, 2025

Waste classification is a critical step in waste management that time-consuming and necessitates automation to replace traditional approaches. Recently, machine learning (ML) deep (DL) have gained attention from researchers seeking automate by providing alternative computational techniques address various waste-related challenges. Significant research on has emerged recent years, reflecting the growing focus this domain. This systematic literature review (SLR) explores role of artificial intelligence (AI), particularly (DL), automating classification. Using Kitchenham’s PRISMA guidelines, we analyze over 97 studies, categorizing AI-based into ML-based, DL-based, hybrid models. We further present an in-depth fifteen publicly available datasets, highlighting key limitations such as dataset imbalance, real-world variability, standardization issues. Our analysis reveals approaches dominate current landscape, with CNN-based architecture transfer showing promising results. To guide future advancements, study also proposes structured roadmap organizes challenges opportunities short-, mid-, long-term priorities. The integrates insights model accuracy, system efficiency, sustainability goals support practical deployment AI-powered systems. work provides comprehensive understanding state-of-the-art ML DL for offers areas remain unexplored.

Язык: Английский

Процитировано

0