1 code implementation • 12 Apr 2024 • Emadeldeen Eldele, Mohamed Ragab, Zhenghua Chen, Min Wu, XiaoLi Li
Time series data, characterized by its intrinsic long and short-range dependencies, poses a unique challenge across analytical applications.
no code implementations • 17 Mar 2024 • Wenyu Zhang, Qingmu Liu, Felix Ong Wei Cong, Mohamed Ragab, Chuan-Sheng Foo
UniSSDA is at the intersection of Universal Domain Adaptation (UniDA) and Semi-Supervised Domain Adaptation (SSDA): the UniDA setting does not allow for fine-grained categorization of target private classes not represented in the source domain, while SSDA focuses on the restricted closed-set setting where source and target label spaces match exactly.
no code implementations • 12 Mar 2024 • Mohamed Ragab, Yury Savateev, Wenjie Wang, Reza Moosaei, Thanassis Tiropanis, Alexandra Poulovassilis, Adriane Chapman, Helen Oliver, George Roussos
The DESERE Workshop, our First Workshop on Decentralised Search and Recommendation, offers a platform for researchers to explore and share innovative ideas on decentralised web services, mainly focusing on three major topics: (i) societal impact of decentralised systems: their effect on privacy, policy, and regulation; (ii) decentralising applications: algorithmic and performance challenges that arise from decentralisation; and (iii) infrastructure to support decentralised systems and services: peer-to-peer networks, routing, and performance evaluation tools
1 code implementation • 14 Jul 2023 • Mohamed Ragab, Emadeldeen Eldele, Min Wu, Chuan-Sheng Foo, XiaoLi Li, Zhenghua Chen
The existing SFDA methods that are mainly designed for visual applications may fail to handle the temporal dynamics in time series, leading to impaired adaptation performance.
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.
no code implementations • 16 Jun 2022 • Wenyu Zhang, Mohamed Ragab, Chuan-Sheng Foo
Domain generalization methods aim to learn models robust to domain shift with data from a limited number of source domains and without access to target domain samples during training.
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.
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.
no code implementations • 29 Sep 2021 • Wenyu Zhang, Chuan-Sheng Foo, Mohamed Ragab
Domain generalization aims to learn models robust to domain shift, with limited source domains at training and without any access to target domain samples except at test time.
no code implementations • 29 Sep 2021 • Mohamed Ragab, Emadeldeen Eldele, Wee Ling Tan, Chuan-Sheng Foo, Zhenghua Chen, Min Wu, Chee Kwoh, XiaoLi Li
Our evaluation includes adaptations of state-of-the-art visual domain adaptation methods to time series data in addition to recent methods specifically developed for time series data.
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 • 26 Jun 2021 • Emadeldeen Eldele, Mohamed Ragab, Zhenghua Chen, Min Wu, Chee Keong Kwoh, XiaoLi Li, Cuntai Guan
In this paper, we propose an unsupervised Time-Series representation learning framework via Temporal and Contextual Contrasting (TS-TCC), to learn time-series representation from unlabeled data.
Ranked #1 on Recognizing And Localizing Human Actions on HAR
Automatic Sleep Stage Classification Contrastive Learning +9
no code implementations • 17 Feb 2021 • Wenyu Zhang, Mohamed Ragab, Ramon Sagarna
In this paper, we propose Domain-Free Domain Generalization (DFDG), a model-agnostic method to achieve better generalization performance on the unseen test domain without the need for source domain labels.
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.