Search

School cafeterias face significant challenges in maintaining operational efficiency while minimizing food waste within the educational sector. Currently, the methods available for counting dishes are predominantly manual or semi-manual. Accurately counting served plates is crucial for evaluating meal portions and planning food preparation, yet these methods frequently result in inaccuracies and inefficiencies. To address these challenges, this project introduces an innovative automated system for counting washed dishes used in the school’s dining hall. The system employs embedded systems equipped with a proper machine learning model to detect dishes placed in trays and count them at the washing station in the kitchens of schools. By automating the dish counting process, the system improves operational efficiency, reduces food waste, and provides precise data for meal planning, inventory management, and budget planning. Initial results show promising accuracy and efficiency, with the best model achieving an average precision of 0.71, a precision of 95.2%, and a recall of 70.5% using Google Cloud’s AutoML platform. However, further optimization is needed for real-world deployment. This project is constrained by limited time for labeling images and a budget of 300$. This project represents a collaboration between Linnaeus University, Kalmar Municipality, and SensIot Company, reflecting a shared commitment to sustainability through reduced food waste in educational institutions.

Ammar Abdulrahman Jairoun,1,2 Sabaa Saleh Al-Hemyari,2,3 Moyad Shahwan,4,5 Hidayah Karuniawati,6,7 Samer H Zyoud,4,8– 10 Eman Abu-Gharbieh,11 Sa’ed H Zyoud,12,13 Mena Al-Ani,14 Mustafa Habeb,15 Maimona Jairoun5 1Health and Safety Department, Dubai Municipality, Dubai, United Arab Emirates; 2Discipline of Clinical Pharmacy, School of Pharmaceutical Sciences, Universiti Sains Malaysia (USM), Pulau Pinang, 11800, Malaysia; 3Pharmacy Department, Emirates Health Services, Dubai, United Arab Emirates; 4Centre of Medical and Bio-Allied Health Sciences Research, Ajman University, Ajman, 346, United Arab Emirates; 5Department of Clinical Sciences, College of Pharmacy and Health Sciences, Ajman University, Ajman, 346, United Arab Emirates; 6Discipline of Social and Administrative Pharmacy, School of Pharmaceutical Sciences, Universiti Sains Malaysia (USM), Pulau Pinang, 11800, Malaysia; 7Department of Pharmacology and Clinical Pharmacy, Faculty of Pharmacy, Universitas Muhammadiyah Surakarta, Surakarta, 57102, Indonesia; 8Department of Mathematics and Sciences, Ajman University, Ajman, United Arab Emirates; 9Nonlinear Dynamics Research Center (NDRC), Ajman University, Ajman, United Arab Emirates; 10School of Physics, Universiti Sains Malaysia (USM), Penang, 11800, Malaysia; 11Department of Clinical Sciences, College of Medicine, University of Sharjah, Sharjah, 27272, United Arab Emirates; 12Department of Clinical and Community Pharmacy, College of Medicine and Health Sciences, An-Najah National University, Nablus, 44839, Palestine; 13Clinical Research Centre, An-Najah National University Hospital, Nablus, 44839, Palestine; 14Developmental Biology & Cancer Department, University College London, UCL Great Ormond Street Institute of Child Health, London, UK; 15Edgware Community Hospital Barnet, Enfield and Haringey Mental Health NHS Trust, London, UKCorrespondence: Ammar Abdulrahman Jairoun; Moyad Shahwan, Tel +971558099957; 9716 705 6249, Email Dr_ammar_91_@hotmail.com