http://oer.ums.edu.my/handle/oer_source_files/1401 Sun, 05 Apr 2026 01:39:02 GMT 2026-04-05T01:39:02Z http://oer.ums.edu.my/handle/oer_source_files/1876 CHILI GRADING USING ANN APPROACH Roujip, Rozaizie Shafiq; Fattah, Salmah The factor that farmers and traders that still have a quite difficult time grading are still using the traditional method, which is using manual grading method that consumes more time, laborers to do the grading and yet still having an error in grading the products. This problem can be solved if traders and farmers change the way of method to the modern view which is using new technology that has been introduced by Federal Agricultural Marketing Authority and Ministry of Algriculture and Food Industries. The objective of this research is to develop a prototype to classify and grade a chili even better and simply. The prototype provides the grading result which is examined from the taken photo of chili that taken from a smartphone camera that is connected to the pc or laptop. The grading is using a system of graphic user interface in MATLAB, then the result will be stored in the directional folder to be analyze. After the artificial neural network algorithm has been used then farmers and admin can grade their products after getting the grading result. And the preparation for categorizing the chili or product would be more quicker than the traditional method. Sat, 01 Jan 2022 00:00:00 GMT http://oer.ums.edu.my/handle/oer_source_files/1876 2022-01-01T00:00:00Z http://oer.ums.edu.my/handle/oer_source_files/1875 CABBAGE DISEASE DETECTION SYSTEM USING K-NN Sahimat, Mohamad Ainuddin; Fattah, Salmah Identification of plant diseases is key to avoiding losses in agricultural yields and product quantities. Plant disease study means the study of disease patterns that can be visually seen on plants. The main objective of this research is to develop a prototype system to detect cabbage diseases which are Alternaria Leaf Spot Disease, Mosaic Virus Disease and Downy Fungus Disease. It is very difficult to monitor plant diseases manually because it requires a large amount of work, deep expertise in plant diseases, and also requires excessive processing time. This project focuses on image processing techniques used to improve image quality and K-NN techniques to classify cabbage diseases. Disease detection involves image acquisition, image pre-processing, segmentation and classification of disease. This paper discusses the methods used for the detection of plant diseases using cabbage leaf images as well as some segmentation and feature extraction algorithms used in the detection of cabbage diseases. Sat, 01 Jan 2022 00:00:00 GMT http://oer.ums.edu.my/handle/oer_source_files/1875 2022-01-01T00:00:00Z http://oer.ums.edu.my/handle/oer_source_files/1830 A User – Centered Web Application to Address the Problem of Nutrition Intakes Among Older Adults Rasimi, Nur Syafiqah; Abdullah Sani, Zaidatol Haslinda The increasing population of older adults has raised concerns about their health as they are prone to diseases that are influenced by their dietary, especially malnutrition. The prevalence study of malnutrition among older adults by Nas, 2017 has shown that many participants have malnutrition during the study. Hence, this study aims to address the malnutrition problems among older adults. We want to investigate how information technology can help older adults practice healthy eating by analysing the suitable design for older adults. Besides that, we also want to examine the technology's effectiveness in changing their diet and spreading awareness of the importance of balanced nutrition. Therefore, in this study, we developed a web-based application called HealthyElderEat (HEE) to allow older adults to self-monitor their nutrition intake that focused explicitly on the liquid intakes and the fruit and vegetable intakes. In addition to ensuring older adults consume enough nutrition for their body. In developing practical usability and interface design for older adults, the HEE prototype is designed and evaluated by a usability expert. We have considered the expert evaluation results; the improvement of the HEE app is brought straight into the development process. After completing the HEE app development, a user pilot is conducted through beta testing with the real user for three days. Upon completing the testing, users have filled the ten questions of the System Usability Scale (SUS) to evaluate the HEE app usability and more additional questions to assess the HEE app design and usability. The results show that the HEE app usability, design, and functionality are averagely good. The user finds the HEE app useful, beneficial, and attractive. They also stated that the app's traffic light element boosts their motivation to improve their nutritional intakes. However, there still some flaws in the app design and the information presentation in the app. The app lacks certain functionality that could provide more freedom and choices to the user to customize their intake form. Despite that, we conclude the HEE app can help older adults self-monitor their nutrition intake and increase their motivation to complete their recommended or target intake. However, we also hoped for more participants to be involved during the user testing phase for more data to analyse. Mon, 28 Feb 2022 00:00:00 GMT http://oer.ums.edu.my/handle/oer_source_files/1830 2022-02-28T00:00:00Z http://oer.ums.edu.my/handle/oer_source_files/1829 MULTI-CLASS STUDENT EMOTION CLASSIFICATION IN ONLINE LEARNING USING DEEP LEARNING VIA WEBCAM Teo, Jason Tze Wi; Lek, Jeniffer Xin Ying The traditional classroom learning approach has been replaced with an online learning system in the educational field due to the COVID-19 pandemic. During this pandemic, a lot of students suffered from depression, academic stress, or anxiety in e-learning because they could not adapt to the new norm. Thus, a system that can recognize the students' emotions is beneficial to evaluate the students' emotions during e-learning. Most of the current student emotion recognition systems do not focus on classifying academic emotions. Hence, this project proposed a system that can classify multi-class student emotions based on facial expressions such as "bored", "confused", "engaged", and "frustrated using a deep learning approach. The dataset used in this project is Dataset for Affective States in E-Environments (DAiSEE). Based on the results obtained in the research experiment, it was reported that the CNN model had the highest accuracy (88.92%) compared to LSTM (79.17%) and ConvLSTM (85.33%). This project is expected to develop a real-time system where the student emotions can be evaluated during online learning, and the result of student emotion classification will be shown. Mon, 28 Feb 2022 00:00:00 GMT http://oer.ums.edu.my/handle/oer_source_files/1829 2022-02-28T00:00:00Z