Multimodal deception detection in videos by Syazwan Bin Jainal

“…There have been many approaches to the problem of deception detection, which include psychological, physiological and even machine learning methods. Deception detection has been successful in high-stakes situations, like courtrooms, where subjects are put under a stressful situation and experiments have yielded an accuracy of over 90%. …”
Get full text

E-learning for mobile learning platform by MacInnes, Catriona

“…By studying the way people learn, methods can be created to increase learning potential and efficiency. …”
Get full text

Individual Mobility Prediction in Mass Transit Systems Using Smart Card Data: An Interpretable Activity-Based Hidden Markov Approach by Mo, Baichuan, Zhao, Zhan, Koutsopoulos, Haris N, Zhao, Jinhua

“…Therefore, the activity-based prediction framework offers a way to preserve the predictive power of advanced machine learning methods while enhancing our ability to generate insightful behavioral explanations, which is useful for user-centric policy design and intelligent transportation applications such as personalized traveler information.…”
Get full text

Machine health monitoring using local feature-based gated recurrent unit networks by Zhao, Rui, Wang, Dongzhe, Yan, Ruqiang, Mao, Kezhi, Shen, Fei, Wang, Jinjiang

“…Inspired by the success of deep learning methods that redefine representation learning from raw data, we propose local feature-based gated recurrent unit (LFGRU) networks. …”
Get full text

Invited perspectives : how machine learning will change flood risk and impact assessment by Wagenaar, Dennis, Curran, Alex, Balbi, Mariano, Bhardwaj, Alok, Soden, Robert, Hartato, Emir, Mestav Sarica, Gizem, Ruangpan, Laddaporn, Molinario, Giuseppe, Lallemant, David

“…Flood risk and impact assessments are also being influenced by this trend, particularly in areas such as the development of mitigation measures, emergency response preparation and flood recovery planning. Machine learning methods have the potential to improve accuracy as well as reduce calculating time and model development cost. …”
Get full text

ELM embedded discriminative dictionary learning for image classification by Zeng, Yijie, Li, Yue, Chen, Jichao, Jia, Xiaofan, Huang, Guang-Bin

“…Results show that our approach achieves state-of-the-art performance compared to other dictionary learning methods.…”
Get full text

Multi-agent deep reinforcement learning based distributed control architecture for interconnected multi-energy microgrid energy management and optimization by Zhang, Bin, Hu, Weihao, Ghias, Amer M. Y. M., Xu, Xiao, Chen, Zhe

“…Unlike existing single-agent deep reinforcement learning methods that rely on homogeneous MG settings, the proposed MADRL adopts a form of decentralized execution, in which agents operate independently to meet local customized energy demands while preserving privacy. …”
Get full text

AI assisted indoor localization by Lee, Yih Jie

“…In this report, the obstacles that Wi-Fi fingerprinting and traditional machine learning methods face will be overcome by relying on deep learning approaches. …”
Get full text

Social media sentiment enhanced stock market prediction analysis by Tan, Adrian Yong Chang

“…The result implies that for classification, ensemble learning methods tend to perform better in terms of accuracy, while SVM tend to perform better in terms of F-Measure. …”
Get full text

Looking deep at people: towards understanding and generating humans in images with deep learning by de Bem, RA

“…</p> <p>This thesis pursues further advances towards understanding and generating people in visual data by the development of new discriminative and generative deep learning methods. The main contributions are: </p> <p>i) A deep learning framework for 2D human pose estimation, which allows for mean-field inference over part-based models; </p> <p>ii) A conditional deep generative model that achieves state-of-the-art results on generating images of humans conditioned on body posture; and </p> <p>iii) A structured semi-supervised deep generative model that jointly performs pose estimation and image generation, <em>understanding</em> and <em>generating</em> people in images in a single framework.…”

Using AI for music source separation by Lee, Jasline Jie Yu

“…In recent years, supervised deep learning methods are known to be state-of-the-art source separation technology and can be categorised as Spectrogram-based and Waveform-based methods. …”
Get full text

Feature selection for demand forecasting incorporating external covariates by Mantri, Raghav

“…We utilise machine learning methods for this purpose and perform feature selection to use only relevant features. …”
Get full text

Crowd-based people detection using deep learning by Chen, Lei

“…This project first reviewed an extensive list of literature related to object detection based on handcraft and deep learning methods. Then, two state of art neural networks were introduced (EfficientDet and YOLOv5), and through further analysis, I analyzed the components and the thesis and the subsequent source codes, deduced the complete network structure, and explained the specific implementation process of the critical parts. …”
Get full text

Deep learning for communication signal classification – part A by Wang, Chien Wei

“…Deep Learning methods have seen significant success in a variety of applications in recent years. …”
Get full text

Sensor fusion for object detection under adverse weather by Soh, Brandon Jian Zheng

“…In recent years, there has been a rise in the use of deep learning methods relying on LiDARs and Radars, given their long history of achieving state of art performance in different types of applications. …”
Get full text

Investigation on effective solutions against insider attacks by Ang, Jun Hao

“…This report investigates the effectiveness of dimensionality reduction techniques in reducing this high demand needed by the machine learning methods used for insider threat detection. The dimensionality reduction techniques discussed in this report are feature selection methods i.e. …”
Get full text

Machine Learning Prediction of Treatment Response to Inhaled Corticosteroids in Asthma by Ong, Mei-Sing, Sordillo, Joanne E., Dahlin, Amber, McGeachie, Michael, Tantisira, Kelan, Wang, Alberta L., Lasky-Su, Jessica, Brilliant, Murray, Kitchner, Terrie, Roden, Dan M., Weiss, Scott T., Wu, Ann Chen

“…Conclusions: An accurate risk prediction of ICS response can be obtained using machine learning methods, with the potential to inform personalized treatment decisions. …”
Get full text

Accelerating Urban Building Energy Modeling by Le Hong, Zoe, Wolk, Samuel

“…Identifying machine learning methods as a viable approach, we implement convolutional neural networks (CNNs) which embed timeseries from hourly weather data and building schedules; the embeddings are then combined with static building characteristics and projected to monthly heating and cooling loads. …”
Get full text
Get full text

Camera domain transfer for video-based person re-identification by Ding, Bangjie

“…Besides, feature learning based on deep learning methods is prone to overfitting on the relatively small scale video dataset. …”
Get full text

Optimising public transit using big data and machine learning by Lee, Kelvin

“…Despite decades of research on optimisation of public transit, recent advances in big data collection and machine learning methods have created new possibilities for further optimisation. …”
Get full text