Search

Sentiment analysis (SA) is the study of people's emotions and attitudes toward a particular topic. It is beneficial for monitoring and analyzing social media text in order to gather public opinion. Despite the fact that there are SA applications for monolingual text such as English and non-English languages like Hindi, Chinese and French, the Malay language has far fewer works, not to mention the mixed language such as Malay-English (also known as Manglish). Other than comments and posts from websites and social media, the emoji used by internet users can also help to provide better insights into how they truly feel about a particular topic. Our work focuses on Malay-English mixed language comments and posts on how Malaysians feel about daily new cases of Covid-19 in Malaysia. We proposed a neural network framework to perform SA on languages spoken by Malaysians, namely Malay, English, and Malay-English, by also taking into account the emoji used by internet users. The data was pre-processed to remove noises and then transformed into word vector representation using word embedding technique. Then we propose a framework that involves training and testing mixed language textual data along with emoji analysis by using bidirectional Long Short Term Memory (biLSTM) neural network. To compare with the proposed method, several machine learning models and Long Short Term Memory (LSTM) with word vectorization was used. Finally, compared to the machine learning model such as Naïve Bayes and Logistic Regression, neural networks such as LSTM, the proposed method; biLSTM with tuned hyper-parameter for Malay-English mixed language achieved the highest accuracy of 76.6%, and macro F1-score of 69.6%. [ABSTRACT FROM AUTHOR]

Plant disease classification is essential to the agriculture industry. In this work, a tomato disease classification using Extreme Learning Machine (ELM) with image-based features. Extreme Learning Machine (ELM), a classification algorithm with a single layer feed-forward neural network where it can be combined with few activation functions. The image features as the input where the image is pre-processed via HSV colour space and extracted using Haralick textures, colour moments and HSV histogram. The features are then loaded in the ELM classifier to perform the ELM training and testing. The accuracy result of ELM classification is then analysed after the validation. The dataset used for disease detection is tomato plant leaves which is a subset of the Plant-Village dataset. The results produced from the ELM demonstrate an accuracy of around 84.94% which is comparable to classifiers such as the Support Vector Machine and Decision Tree. [ABSTRACT FROM AUTHOR]

The objective of this study is to implement machine learning (ML) to identify and classify the level of contamination in leftover cooked foods based on its aroma. An evaluation on the smell profiles using as a model local Malaysian lunch or evening foods that have always been stored as leftover cooked food is done in this study. To capture the data, a simple e-nose application is built and affixed to the food containers, which will accommodate four types of sensors sensitive to different gases and is programmed using the Arduino platform. To determine the aroma categorization of leftover Malaysian cuisine, samples are examined using RStudio. The results in this study demonstrated satisfactory performances by k-Nearest Neighbours (k-NN), Support Vector Machines (SVM), and Random Forest (RF) with accuracies ranging from 87.5% to 100% using the oversampling and undersampling techniques. Unfortunately, Linear Discriminant Analysis (LDA) gave poor performances (19.64% – 58.93%) in classifying the contamination level of the samples. Hence, the results obtained gave an indication that the electronic nose presented in this research was a promising for classification of contamination level for leftover cooked foods, allowing food to be better anticipated as to whether it is still edible or not. [ABSTRACT FROM AUTHOR]