Masturah Tunnur Mohamad Talib
Thumbnail Image
Preferred name
Masturah Tunnur Mohamad Talib
Official Name
Masturah Tunnur, Mohamad Talib
Alternative Name
Mohamad Talib, Masturah Tunnur
Main Affiliation
Scopus Author ID
57198358595

Research Output

Filters

2
2
Reset filters

Settings
Now showing 1 - 2 of 2
  • Publication
    Small metal objects classification based on the deep learning approach
    ( 2024)
    Nur Safariah Inani M. Tahir
    ;
    Masturah Tunnur Mohamad Talib
    ;
    Mohd Hafiz Fazalul Rahiman
    ;
    N. S. Khalid
    ;
    Siti Marhainis Othman
    Classification of small metal objects plays a crucial role in various engineering fields, including manufacturing, robotics, and security. With advancements in deep learning techniques, the use of Convolutional Neural Networks (CNNs) has emerged as a powerful tool for image classification tasks. The methodology begins by collecting diverse datasets consisting of images of small metal objects. The datasets are labelled with corresponding object classes to facilitate supervised learning. Preprocessing techniques like re-sizing, normalization, and augmentation are used to improve the quality and diversity of the datasets. The use of CNNs in classification can be a better option compared to commonly used machine learning approaches. The CNN architecture is designed and trained to learn the distinguishing features of small metal objects. The main objective of this study is to assess the accuracy of this classification and explain how CNNs can enhance classification accuracy. The results of this study also show the effect of the optimizer on the classification process, which changes when different types of optimizers such as RMSprop, Adam, and SGD are used. While some optimizers yield slightly lower accuracy results, the Adam optimizer with the CNN ResNet-50 module proves suitable for use with this dataset, achieving a high classification accuracy of 86%.
  • Publication
    Hand-held shelf life decay detector for non-destructive fruits quality assessment
    ( 2024)
    Nurul Syahirah Khalid
    ;
    Nordiana Shariffudiin
    ;
    Shazmin Aniza Abdul Shukor
    ;
    Humairah Mansor
    ;
    Masturah Tunnur Mohamad Talib
    ;
    Sukhairi Sudin
    ;
    Ismail I. Ibrahim
    ;
    Mohd Zamri Hasan
    ;
    Siti Marhainis Othman
    ;
    N.D.N Dalila
    ;
    M.Thaqif B.N Ashimi
    Perishable food such as fruits have a limited shelf life and can quickly degrade if not properly stored. One method for detecting decay in these foods is the use of ethylene gas. Ethylene is a naturally occurring hormone that is released by fruits as they ripen. By measuring the levels of ethylene in the storage area, it is possible to detect when fruits and vegetables are starting to degrade. This information can then be used to act, such as removing spoiled produce and adjusting storage conditions, to extend the shelf life of the remaining products. By utilizing ethylene gas for early detection of decay, it is possible to improve food safety and reduce food waste. The project aims to utilized ethylene gas from perishable food such as fruits before decay. This project proposed portable or hand-held detection ethylene gas by including temperature and humidity. The sensor will be measuring the level of ethylene gas, temperature and humidity. Next, machine learning method; K-Nearest Neighbour(KNN) were used to evaluate the accuracy of the proposed system. This project, a hand-held decay detector for perishable food products is believed can help to prevent food waste by detecting early signs of spoilage in fruits.