Dual-Stream Contrastive Learning for Channel State Information Based Human Activity Recognition

Xu, Ke; Wang, Jiangtao; Zhang, Le; Zhu, Hongyuan; Zheng, Dingchang

doi:10.1109/jbhi.2022.3219640

Cited by 8 publications

(2 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They used Normalized Temperature-scaled cross-entropy (NT-Xent) [19] contrastive loss. Xu et al [20], instead of views, took spectrograms augmented by, among other augmentation methods, time direction flipping and Sobel operator processing. Pre-training considered two data flows per input sample, one for time-and one for channel-wise augmentations.…”

Section: Related Work 21 Unsupervised Representation Learning At Diff...mentioning

confidence: 99%

Use of Domain Labels during Pre-Training for Domain-Independent WiFi-CSI Gesture Recognition

Berlo,

Verhoeven,

Meratnia

2023

Sensors

View full text Add to dashboard Cite

To minimize dependency on the availability of data labels, some WiFi-CSI based-gesture recognition solutions utilize an unsupervised representation learning phase prior to fine-tuning downstream task classifiers. In this case, however, the overall performance of the solution is negatively affected by domain factors present in the WiFi-CSI data used by the pre-training models. To reduce this negative effect, we propose an integration of the adversarial domain classifier in the pre-training phase. We consider this as an effective step towards automatic domain discovery during pre-training. We also experiment with multi-class and label versions of domain classification to improve situations, in which integrating a multi-class and single label-based domain classifier during pre-training fails to reduce the negative impact domain factors have on overall solution performance. For our extensive random and leave-out domain factor cross-validation experiments, we utilise (i) an end-to-end and unsupervised representation learning baseline, (ii) integration of both single- and multi-label domain classification, and (iii) so-called domain-aware versions of the aformentioned unsupervised representation learning baseline in (i) with two different datasets, i.e., Widar3 and SignFi. We also consider an input sample type that generalizes, in terms of overall solution performance, to both aforementioned datasets. Experiment results with the Widar3 dataset indicate that multi-label domain classification reduces domain shift in position (1.2% mean metric improvement and 0.5% variance increase) and orientation (0.4% mean metric improvement and 1.0% variance decrease) in domain factor leave-out cross-validation experiments. The results also indicate that domain shift reduction, when considering single- or multi-label domain classification during pre-training, is negatively impacted when a large proportion of negative view combinations contain views that originate from different domains within a substantial amount of mini-batches considered during pre-training. This is caused by the view contrastive loss repelling the aforementioned negative view combinations, eventually causing more domain shift in the intermediate feature space of the overall solution.

show abstract

Section: Related Work 21 Unsupervised Representation Learning At Diff...mentioning

confidence: 99%

Use of Domain Labels during Pre-Training for Domain-Independent WiFi-CSI Gesture Recognition

Berlo,

Verhoeven,

Meratnia

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Contrastive learning (CL) has gained significant prominence as a leading approach in the field of unsupervised learning, with a particular focus on self-supervised learning [12] . CL methods have demonstrated notable performance in many applications such as diagnosis of Alzheimer’s disease using brain positron emission tomography (PET) [17] , human activity recognition [18] , [19] , tissue segmentation in histopathological images [20] , [21] , whole slide image classification [22] , ultrasound images analysis [23] , underwater image enhancement [24] , medical image segmentation [25] , and optical coherence tomography (OCT) fluid segmentation [26] . For various applications, CL in self-supervised learning has outperformed supervised learning [12] , [27] , [28] .…”

Section: Introductionmentioning

confidence: 99%

Contrastive Transfer Learning for Prediction of Adverse Events in Hospitalized Patients

Salehinejad,

Meehan,

Caraballo

et al. 2024

IEEE J. Transl. Eng. Health Med.

View full text Add to dashboard Cite

Objective: Deterioration index (DI) is a computer-generated score at a specific frequency that represents the overall condition of hospitalized patients using a variety of clinical, laboratory and physiologic data. In this paper, a contrastive transfer learning method is proposed and validated for early prediction of adverse events in hospitalized patients using DI scores. Methods and procedures: An unsupervised contrastive learning (CL) model with a classifier is proposed to predict adverse outcome using a single temporal variable (DI scores). The model is pretrained on an unsupervised fashion with large-scale time series data and fine-tuned with retrospective DI score data. Results: The performance of this model is compared with supervised deep learning models for time series classification. Results show that unsupervised contrastive transfer learning with a classifier outperforms supervised deep learning solutions. Pretraining of the proposed CL model with large-scale time series data and fine-tuning that with DI scores can enhance prediction accuracy. Conclusion: A relationship exists between longitudinal DI scores of a patient and the corresponding outcome. DI scores and contrastive transfer learning can be used to predict and prevent adverse outcomes in hospitalized patients. Clinical impact: This paper successfully developed an unsupervised contrastive transfer learning algorithm for prediction of adverse events in hospitalized patients. The proposed model can be deployed in hospitals as an early warning system for preemptive intervention in hospitalized patients, which can mitigate the likelihood of adverse outcomes.

show abstract

A prospective approach for human-to-human interaction recognition from Wi-Fi channel data using attention bidirectional gated recurrent neural network with GUI application implementation

Khan,

Shams,

Raihan

2024

Multimed Tools Appl

View full text Add to dashboard Cite

Dual-Stream Contrastive Learning for Channel State Information Based Human Activity Recognition

Cited by 8 publications

References 39 publications

Use of Domain Labels during Pre-Training for Domain-Independent WiFi-CSI Gesture Recognition

Use of Domain Labels during Pre-Training for Domain-Independent WiFi-CSI Gesture Recognition

Contrastive Transfer Learning for Prediction of Adverse Events in Hospitalized Patients

A prospective approach for human-to-human interaction recognition from Wi-Fi channel data using attention bidirectional gated recurrent neural network with GUI application implementation

Contact Info

Product

Resources

About