a voice-activated and gesture-recognizing smart trashcan utilizing the YOLO alogorithm for autonomous navigation Carique, Gerald M. creator author. Ruam, John Mark C. author. Sejera, Arnold Rie J. author. Benitez, Ian P. adviser. Fortuno, Kaela Marie N. chair, panelist. Oñate, Joseph Jessie S. panelist. Pandes, Tiffany Lyn O. panelist. text bibliography ph 2024 monographic eng

print

135 leaves. Effective waste management is a growing global concern, with an estimated 2.24 bil-lion tons of solid waste generated annually. For individuals with mobility impairments, disposing of waste independently remains a significant challenge. This study addresses this gap by developing "Dolly", a voice-activated, gesture-recognizing smart trashcan designed to enhance waste disposal efficiency and accessibility. Using the YOLO (You Only Look Once) algorithm, the system detects a thumbs-up gesture to trigger autonomous navigation, allowing the trashcan to move toward the user's location. This innovation is particularly useful for office workers and individuals with disabilities, promoting inclusivity and sus-tainability. The study's objectives include training and evaluating the YOLO algorithm for gesture recognition, integrating the model into a smart trashcan prototype, and testing the prototype's effectiveness in real-world scenarios. System integration used a Raspberry Pi 4 and Arduino Uno, and the system achieved a mean average precision (mAP@95) of 93%. Voice commands were incorporated through the PICO Voice Porcupine Wake Word engine. Results show that "Dolly" significantly improves accessibility for users with mobility im-pairments, promoting independence in waste disposal. Gerald M. Carique, John Mark C. Ruam, and Arnold Rie J. Sejera Undergraduate Thesis (BSCS) - Computer Science. Camarines Sur Polytechnic Colleges, 2024. Includes bibliographical references. CSPC 251202 20251202083136.0 eng