no code implementations • 18 Apr 2023 • Gabriel Tjio, Ping Liu, Chee-Keong Kwoh, Joey Tianyi Zhou
To tackle this challenge, we introduce a dual-stage Feature Transform (dFT) layer within the Adversarial Semantic Hallucination+ (ASH+) framework.
no code implementations • 13 Feb 2023 • Emadeldeen Eldele, Mohamed Ragab, Zhenghua Chen, Min Wu, Chee-Keong Kwoh, XiaoLi Li
The scarcity of labeled data is one of the main challenges of applying deep learning models on time series data in the real world.
1 code implementation • 3 Dec 2022 • Emadeldeen Eldele, Mohamed Ragab, Zhenghua Chen, Min Wu, Chee-Keong Kwoh, XiaoLi Li
Specifically, we propose a novel temporal mixup strategy to generate two intermediate augmented views for the source and target domains.
1 code implementation • 10 Oct 2022 • Emadeldeen Eldele, Mohamed Ragab, Zhenghua Chen, Min Wu, Chee-Keong Kwoh, XiaoLi Li
The past few years have witnessed a remarkable advance in deep learning for EEG-based sleep stage classification (SSC).
2 code implementations • 13 Aug 2022 • Emadeldeen Eldele, Mohamed Ragab, Zhenghua Chen, Min Wu, Chee-Keong Kwoh, XiaoLi Li, Cuntai Guan
Specifically, we propose time-series specific weak and strong augmentations and use their views to learn robust temporal relations in the proposed temporal contrasting module, besides learning discriminative representations by our proposed contextual contrasting module.
1 code implementation • 15 Mar 2022 • Mohamed Ragab, Emadeldeen Eldele, Wee Ling Tan, Chuan-Sheng Foo, Zhenghua Chen, Min Wu, Chee-Keong Kwoh, XiaoLi Li
Our evaluation includes adapting state-of-the-art visual domain adaptation methods to time series data as well as the recent methods specifically developed for time series data.
no code implementations • 14 Jan 2022 • Zhuoyi Lin, Sheng Zang, Rundong Wang, Zhu Sun, J. Senthilnath, Chi Xu, Chee-Keong Kwoh
We then introduce a dynamic transformer encoder (DTE) to capture user-specific inter-item relationships among item candidates by seamlessly accommodating the learned latent user intentions via IDM.
1 code implementation • 29 Nov 2021 • Mohamed Ragab, Emadeldeen Eldele, Zhenghua Chen, Min Wu, Chee-Keong Kwoh, XiaoLi Li
Second, we propose a novel autoregressive domain adaptation technique that incorporates temporal dependency of both source and target features during domain alignment.
1 code implementation • 9 Jul 2021 • Emadeldeen Eldele, Mohamed Ragab, Zhenghua Chen, Min Wu, Chee-Keong Kwoh, XiaoLi Li, Cuntai Guan
Second, we design an iterative self-training strategy to improve the classification performance on the target domain via target domain pseudo labels.
1 code implementation • 28 Apr 2021 • Emadeldeen Eldele, Zhenghua Chen, Chengyu Liu, Min Wu, Chee-Keong Kwoh, XiaoLi Li, Cuntai Guan
The MRCNN can extract low and high frequency features and the AFR is able to improve the quality of the extracted features by modeling the inter-dependencies between the features.
Ranked #1 on Automatic Sleep Stage Classification on Sleep-EDF
no code implementations • 28 Jul 2020 • Zhuoyi Lin, Lei Feng, Rui Yin, Chi Xu, Chee-Keong Kwoh
We argue that recommendation on global and local graphs outperforms that on a single global graph or multiple local graphs.
no code implementations • 20 Jul 2020 • Mohamed Ragab, Zhenghua Chen, Min Wu, Chee-Keong Kwoh, Ruqiang Yan, Xiao-Li Li
Accurate estimation of remaining useful life (RUL) of industrial equipment can enable advanced maintenance schedules, increase equipment availability and reduce operational costs.
no code implementations • 4 Mar 2019 • Dong Huang, Chang-Dong Wang, Jian-Sheng Wu, Jian-Huang Lai, Chee-Keong Kwoh
Experiments on various large-scale datasets have demonstrated the scalability and robustness of our algorithms.
Ranked #3 on Image/Document Clustering on pendigits
no code implementations • 30 Oct 2018 • Dong Huang, Chang-Dong Wang, Hongxing Peng, Jian-Huang Lai, Chee-Keong Kwoh
Upon the constructed graph, a transition probability matrix is defined, based on which the random walk process is conducted to propagate the graph structural information.
1 code implementation • 9 Oct 2017 • Dong Huang, Chang-Dong Wang, Jian-Huang Lai, Chee-Keong Kwoh
The rapid emergence of high-dimensional data in various areas has brought new challenges to current ensemble clustering research.
no code implementations • 16 Feb 2015 • Jian-Ping Mei, Chee-Keong Kwoh, Peng Yang, Xiao-Li Li
Classification is one of the most popular and widely used supervised learning tasks, which categorizes objects into predefined classes based on known knowledge.