Design, Development, and Evaluation of Automatic Waste Segregation with Machine Learning of Aparri Public Market
DOI:
https://doi.org/10.55687/aah.v2i1.190Keywords:
Keywords: Automatic Waste Segregator, Waste Management, Machine Learning, Environmental Sustainability, Technology Acceptance ModelAbstract
ABSTRACT
Waste management is an issue in public markets and needs creative segregation and disposal measures. In this study, the design, implementation, and acceptability of a machine learning and sensor technology-powered Automatic Waste Segregator (AWS) system were explored. A descriptive-evaluative design was utilized through questionnaires adapted from ISO 25010:2011 Software Quality Standards and an extended Technology Acceptance Model (TAM). Participants were 30 vendors, 100 consumers and 10 IT experts chosen through purposive sampling.
Results reflected very high to high ratings for all ISO 25010 quality attributes, with especially good scores in functional suitability, reliability, performance efficiency, and usability. IT professionals confirmed system performance while suggesting improvements in environmental adaptability and maintenance. TAM measures also reflected strong acceptance, particularly in Performance Expectancy, Perceived Ease of Use, and Behavioral Intention.
