Usman Ali · International Journal of Innovative Science and Research Technology (IJISRT) 2026 · 2026
DOI: 10.38124/ijisrt/26sep1189
Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).
Automatic waste classification is an important challenge for smart cities and intelligent recycling systems. Traditional manual sorting methods are time-consuming and inefficient, while existing computer vision approaches often require computationally expensive models. This research proposes an efficient convolutional neural network (CNN) framework for automatic waste classification from images. The proposed model learns visual features such as shape, texture, and color patterns to classify different waste categories. A customized dataset containing multiple waste classes is used for training and evaluation. The model performance is assessed using accuracy, precision, recall, and F1-score metrics. The proposed lightweight CNN architecture achieves reliable classification performance while reducing computational requirements, making it suitable for real-time deployment in smart recycling systems.
No comments yet — start the discussion below.