Inicio  /  Applied Sciences  /  Vol: 13 Par: 13 (2023)  /  Artículo
ARTÍCULO
TITULO

DABaCLT: A Data Augmentation Bias-Aware Contrastive Learning Framework for Time Series Representation

Yubo Zheng    
Yingying Luo    
Hengyi Shao    
Lin Zhang and Lei Li    

Resumen

Contrastive learning, as an unsupervised technique, has emerged as a prominent method in time series representation learning tasks, serving as a viable solution to the scarcity of annotated data. However, the application of data augmentation methods during training can distort the distribution of raw data. This discrepancy between the representations learned from augmented data in contrastive learning and those obtained from supervised learning results in an incomplete understanding of the information contained in the real data from the trained encoder. We refer to this as the data augmentation bias (DAB), representing the disparity between the two sets of learned representations. To mitigate the influence of DAB, we propose a DAB-aware contrastive learning framework for time series representation (DABaCLT). This framework leverages a raw features stream (RFS) to extract features from raw data, which are then combined with augmented data to create positive and negative pairs for DAB-aware contrastive learning. Additionally, we introduce a DAB-minimizing loss function (DABMinLoss) within the contrasting module to minimize the DAB of the extracted temporal and contextual features. Our proposed method is evaluated on three time series classification tasks, including sleep staging classification (SSC) and epilepsy seizure prediction (ESP) based on EEG and human activity recognition (HAR) based on sensors signals. The experimental results demonstrate that our DABaCLT achieves strong performance in self-supervised time series representation, 0.19% to 22.95% accuracy improvement for SSC, 2.96% to 5.05% for HAR, 1.00% to 2.46% for ESP, and achieves comparable performance to the supervised approach. The source code for our framework is open-source.

 Artículos similares

       
 
Fabi Prezja, Leevi Annala, Sampsa Kiiskinen and Timo Ojala    
Diagnosing knee joint osteoarthritis (KOA), a major cause of disability worldwide, is challenging due to subtle radiographic indicators and the varied progression of the disease. Using deep learning for KOA diagnosis requires broad, comprehensive dataset... ver más
Revista: Algorithms

 
Mohammad Alhumaid and Ayman G. Fayoumi    
Paranasal sinus pathologies, particularly those affecting the maxillary sinuses, pose significant challenges in diagnosis and treatment due to the complex anatomical structures and diverse disease manifestations. The aim of this study is to investigate t... ver más
Revista: Applied Sciences

 
Woonghee Lee, Mingeon Ju, Yura Sim, Young Kul Jung, Tae Hyung Kim and Younghoon Kim    
Deep learning-based segmentation models have made a profound impact on medical procedures, with U-Net based computed tomography (CT) segmentation models exhibiting remarkable performance. Yet, even with these advances, these models are found to be vulner... ver más
Revista: Applied Sciences

 
Lei Li, Xiaobao Zeng, Xinpeng Pan, Ling Peng, Yuyang Tan and Jianxin Liu    
Microseismic monitoring plays an essential role for reservoir characterization and earthquake disaster monitoring and early warning. The accuracy of the subsurface velocity model directly affects the precision of event localization and subsequent process... ver más
Revista: Applied Sciences

 
Daniel Rusche, Nils Englert, Marlen Runz, Svetlana Hetjens, Cord Langner, Timo Gaiser and Cleo-Aron Weis    
Background: In this study focusing on colorectal carcinoma (CRC), we address the imperative task of predicting post-surgery treatment needs by identifying crucial tumor features within whole slide images of solid tumors, analogous to locating a needle in... ver más
Revista: Applied Sciences