Joint Feature Learning for Face Recognition by Lu, Jiwen, Liong, Venice Erin, Wang, Gang, Moulin, Pierre

“…Unlike many existing face recognition systems, where conventional feature descriptors, such as local binary patterns and Gabor features, are used for face representation, we propose an unsupervised feature learning method to learn hierarchical feature representation. …”
Get full text
Get full text

Deep learning based action recognition by Ong, Zong You

“…One of the more successful ways of recognizing human action is through the use of skeleton data. This method provides an excellent representation for describing human activities. …”
Get full text

Software development for E-learning tool by Foong, Alexander Kwok Leong

“…Therefore, these apps are expensive for students to learn with. Furthermore, existing knowledge of FEM is required for these apps, making it hard for students to apprehend. …”
Get full text

Predictive maintenance using machine learning by Amal Roy Lerroy Ashwin

“…An ensemble of AEs was implemented with ensemble learning to further improve the performance of anomaly detection. …”
Get full text

Comparison of character recognition performance - bayes classifier and neural network methods by Low, Siew Eng.

“…In this project, two learning schemes had been tested and verified, in the recognition unit within the image processing environment of the Machine Vision Tool, namely the Bayes classifier method and the neural network-error back propagation gradient descent learning method. …”
Get full text

Elucidating the mechanism of mRNA transport using novel imaging technologies by Stoychev, D

“…I begin to fill this technological gap by assessing and applying state-of-the-art methods from the fields of microscopy and image processing. …”

Numerical and Analytical Methods in Low-Dimensional Strongly Correlated Quantum Systems by Peng, Changnan

“…The study of low-dimensional strongly correlated quantum systems lies at the intersection of intricate theoretical models and practical numerical methods, offering deep insights into condensed matter physics. …”
Get full text

4.661 Theory and Method in the Study of Architecture and Art, Fall 2002 by Jones, Caroline

Get full text

A Mixed-Methods Research Design to Advance Inclusive and Equitable Teaching by Soicher, Raechel N., Baker, Amanda R., Thomas, Ruthann C.

“…We developed an innovative framework and mixed methods research design to systematically assess inclusive and equitable teaching at the student, course, department, and institution levels. …”
Get full text

Determination of soil-water characteristics curves of sands using the evaporation method by On, Roger Zhi Wei

“…Commercial equipment such as the HYPROP 2 by Meter Group AG has been developed to expedite the experimental process of obtaining the SWCC of soils from 0 to 200 kPa suction using the evaporation method but is very costly. Moreover, such commercial equipment requires a steep learning curve and proper training to use them effectively. …”
Get full text

Image artefact removal using deep learning by Sanchari, Das

“…The results are then compared to non-deep learning approaches, SSRQC method and Bilateral filtering, in order to see the differences in performance…”
Get full text

Machine learning for mathematical question difficulty classification by Pang, Jarald Qi Kai

“…Four machine learning methods, Support Vector Machines, Naïve Bayes, Random Forest and Extreme Gradient Boosting, were then used to classify the data to their respective topic. …”
Get full text

Deep reinforcement learning for optimal resource allocation by Ng, Steffi Si Yu

“…Hence, there is a need to use methods that do not increase production cost to improve productivity such as optimizing scheduling of activities and resources in a production. …”
Get full text

Query cost estimation in DBMS with deep learning by Acharya, Atul

“…With the recent rise of ML for DB, the database community explored the use of learned methods in cost and cardinality estimation. …”
Get full text

Natural robustness of machine learning in the open world by Wei, Hongxin

“…Secondly, classic machine learning methods are built on the i.i.d. assumption that training and testing data are independent and identically distributed. …”
Get full text

Machine learning enabled multivariate analysis of neuroimages by Chen, Dawen

“…This project also aimed to implement and conduct various multi-variant and machine learning methodologies on fMRI scans in order to investigate analysis methods of neuroimages. …”
Get full text

Personalized question recommendation for English grammar learning by Fang, Lanting, Tuan, Luu Anh, Hui, Siu Cheung, Wu, Lenan

“…Additionally, we incorporated the proposed recommendation method into a Web‐based English grammar learning system and presented its performance evaluation in this paper. …”
Get full text
Get full text

Active learning with applications in biomedical document annotation by Han, Xu

“…We also apply our active learning method for the task of named entity recognition. …”
Get full text

Residual learning diagnosis detection: an advanced residual learning diagnosis detection system for COVID-19 in industrial internet of things by Zhang, Mingdong, Chu, Ronghe, Dong, Chaoyu, Wei, Jianguo, Lu, Wenhuan, Xiong, Naixue

“…Early diagnosis and isolation are effective and imperative strategies for epidemic prevention and control. Most diagnostic methods for the COVID-19 is based on nucleic acid testing (NAT), which is expensive and time-consuming. …”
Get full text

Enhanced extreme learning machines for image classification by Cui, Dongshun

“…Among numerous machine learning methods, we choose the Extreme Learning Machine (ELM) for our image classification applications. …”
Get full text
Get full text