Aiding therapy using speech emotion recognition by Koh, En Rong

“…We will explore the use of a Convolutional Neural network, a type of Deep Learning method, to train and predict human emotions. …”
Get full text

Vehicle re-identification using machine learning by Tang, Lisha

Get full text

Aspect-based sentiment analysis using BERT by Kheriwala, Hussain Khozema

“…This project implements a method of using the pre-trained BERT model for this experiment. …”
Get full text

Makeup transfer using generative adversarial network by Feng, Qiyuan

“…Its main function is to transfer the makeup of the reference makeup portrait to the non-makeup portrait, so that users can try different makeup at will to find the makeup that suits them. Existing research uses model structures such as feedforward neural networks and generative adversarial networks to generate high-quality and high-fidelity portraits. …”
Get full text

Car cabin surveillance using computer vision by Soegeng, Andrew Ivan

Get full text

Facial spoofing indicator using deep learning by Lim, Eugen Wei Jie

“…Photo attack datasets were used to train the model and to test its accuracy by classifying 2 classes of images into fake and real. …”
Get full text

Image artefact removal using deep learning by Sanchari, Das

“…There are more traditional methods such as image adaptive filtering, bilateral filtering, methods using POCS and the SSRQC method. There are also newer approaches using deep learning such as AR CNN, DnCNN and GAN. …”
Get full text

Use of incineration bottom ash in geotechnical applications by G. Hayshagen

“…The outcome of this study indicates that IBA can be used as a partial replacement for Ordinary Portland Cement (OPC) but with an advised proportion of up to 20%. …”
Get full text

Removal of nitrogen using different carbon source by Chen, Yimin.

“…Denitrification is commonly used in activated sludge process for removal of nitrate, which combined with nitrification, converting ammonium to nitrate. …”
Get full text

Flow forecasting using artificial neural networks by Tan, Eugene.

“…This project will attempt to assess and evaluate the accuracy and suitability of using Artificial Neural Networks to forecast rain and flow runoff in a small watershed. …”
Get full text

Granger causality using Jacobian in neural networks by Suryadi, Chew, Lock Yue, Ong, Yew Soon

“…Granger causality is a commonly used method for uncovering information flow and dependencies in a time series. …”
Get full text

Using artificial intelligence to augment bug fuzzing by Tay, Zhixuan

“…Fuzz testing is a wide-use technique to test for bugs and vulnerabilities in software programs. …”
Get full text

Cloud movement prediction using GPS information by Xu, JingYi

“…To predict cloud movements in the sky, ground-based cameras are used progressively nowadays to capture the image of cloud movements. …”
Get full text

Protein engineering using asparaginyl peptide ligases by Wang, Zhen

“…Second, my study shows PALs can use non-canonical nucleophilic compounds – such as hydrazides – as acyl acceptor substrates. …”
Get full text

Facial expression transfer using StyleGAN by Zhao, Lan

“…StyleGAN generator is then used to generate the resulting image from the manipulated latent code. …”
Get full text

Attendance taking using QR code (III) by Sohn, Hyeonjun

“…The initial design of the system was inspired by the black and white pieces used in the game of Go. Although the main purpose of this code was created to manage and track automotive parts produced by a company, it became much popular in the market after adopting into mobile phones. …”
Get full text

Development of network communication system using ROS by Winata, Steven Edbert

Get full text

Housing price prediction using convolutional transformer by Ma, Weilun

“…To further improve this problem in housing price prediction, this project utilizes convolution embedding to enhance the correlation between adjacent data points. The data set used in this paper are the apartments sold-price in Toronto from 2005 to 2010, which holds nearly 81 features. …”
Get full text

Human action recognition using machine learning by Cao, QingTian

“…The accurate detection of human pose is useful in various areas such as surveillance, clothes parsing and game modelling. …”
Get full text

Stock price prediction using sentic API by Phoa, Justyn Zairen

“…We acknowledge limitations in using news headlines as sentiment proxies and suggest further research into the interplay between sentiment analysis and established financial factors to refine predictive models and understand stock price movements better.…”
Get full text