An intelligent material detection using deep learning and reverse vending machine with cat food reward system/ Lanz Angelo M. Acuña, Eadric Gabriel C. Belen, Jhuvic S. Esteves, Jarl Leander L. Madamba, and Arlon Jr. T. Ylasco.--

Bachelor's thesis

College of Industrial Technology.--
Bachelor of engineering technology major in computer engineering technology: Technological University of the Philippines,
2025.

Includes bibliographic references and index.

This study was aligned with intelligent waste management systems and leverages deep
learning technology to address persistent environmental issues, particularly the improper
disposal of polyethylene terephthalate (PET) bottles. Rooted in gaps involving limited
material classification, lack of incentivization, and insufficient recycling infrastructure, this

research developed a Reverse Vending Machine (RVM) equipped with a deep learning-
based material detection system and an automated cat food reward mechanism. The system

aimed to detect and classify plastic waste, identify liquid contamination, and encourage
user participation through tangible incentives. The methodology followed a prototyping
approach, encompassing system design, hardware integration (camera modules, load cells,
servo motors, GSM), software development (deep learning model), functional testing, and
ISO 25010 compliant evaluation. The anticipated outcome was a cost-effective, scalable,
and community-friendly recycling machine that promotes responsible consumption and
production behaviors. Primary beneficiaries include local communities, LGUs, and pet
welfare organizations. This study aligned with the Technological University of the
Philippines (TUP) innovation agenda Department of Science and Technology (DOST)
priorities and directly supports the United Nations Sustainable Development Goal #12:
Responsible Consumption and Production. It demonstrated how intelligent systems can
enhance environmental sustainability while fostering community engagement.