Short Term Project

IoT-BASED PUBLIC RESTROOM CLEANING MANAGEMENT SYSTEM

This project presents the design and implementation of a low-cost and effective prototype for IoT Based Public Restroom Cleaning Management System.. The supervisors and cleaners can monitor the restroom condition through an Android application and the data is stored in a cloud that allows for further analysis.

Researchers: Dr. Amiza Amir, Muhammad Zulhusni Saad & Dr Norsaidatul Norlyana Azemi

Keywords: IoT

Steel Defect Detection by Using Deep Learning

Steel defects could reduce the features of the products, which are steel corrosion resistance, abrasion resistance, and endurance limit, which will cause significant economic losses. This work aims at developing deep learning models that can perform steel defect detection. In our preliminary result, the model developed by using MobileNet enables the classification of defects in steel with identifying rate up to for 80% SEVERSTAL database and 96% for NEU database. In the current research, we aim to improve the performance of the steel defect detection by devising a new architecture of deep learning network by incorporating MobileNet.

Researchers: Dr. Amiza Amir, Masyitah Abu & Dr Nik Adilah Hanin Zahri

Keywords : Deep Learning