A General Framework for Generative Self-supervised Learning in Non-invasive Estimation of Physiological Parameters Using Photoplethysmography

Zexing Zhang; Huimin Lu; Songzhe Ma; Jianzhong Peng; Chenglin Lin; Niya Li; Bingwang Dong

eess.SPApr 3, 2026

A General Framework for Generative Self-supervised Learning in Non-invasive Estimation of Physiological Parameters Using Photoplethysmography

Authors: Zexing Zhang, Huimin Lu, Songzhe Ma, Jianzhong Peng, Chenglin Lin, Niya Li, Bingwang Dong

Organizations: School of Computer Science and Engineering, Changchun University of Technology, Jilin, Changchun, 130102, China · Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Jilin, Changchun, 130012, China · Smart Health Joint Innovation Laboratory for the New Generation of AI, Jilin, Changchun, 130102, China

Abstract

Aligning physiological parameter labels with large-scale photoplethysmographic (PPG) data for deep learning is challenging and resource-intensive. While self-supervised representation learning (SSRL) can handle limited annotated data, the challenge lies in learning robust shared representations from vast unlabeled data and integrating contextual cues to learn distinctive representations. To alleviate these challenges, a generative SSRL framework TS2TC is proposed to utilize the temporal, spectrogram, and temporal-spectrogram mixed domains to explore and incorporate the unique features of PPG for universal and noninvasive physiological parameter estimation. A pretext task named Cross-Temporal Fusion Generative Anchor (CTFGA) is designed, modeling temporal dependencies and reconstructing independent segments at a coarse level to provide robust global feature extraction and local contextual representation. The framework includes sub-signals from PPG with diverse frequency scales and order derivatives reflecting hemodynamics to facilitate learning shared representations at varying semantic levels. Secondly, a cognitive-inspired dual-process transfer (DPT) strategy is formulated, consisting of prior-dependent autonomous processes and posterior observation reasoning processes, to leverage the independent and integrated advantages of shared and specific representations. TS2TC introduces a bilinear temporal-spectrogram fusion method in the mixed domain, aligning latent representations from different domains and establishing fine-grained contextual interactions across multiple sources of information. Extensive experiments on physiological parameter estimation tasks showed that the joint performance of CTFGA and DPT outperforms standard generative learning significantly. TS2TC achieved an average 2.49% improvement in RMSE over state-of-the-art estimation methods with only 10% training data.

Figures & tables

Figure 1: Overview of photoplethysmography technology.

Figure 2: Overview of the TS2TC framework. In the figure, $x(t)$ represents the input PPG signal, $x_{s}$ denotes the corresponding spectrogram, and $y$ signifies the labeled physiological parameters. $\hat{x}_{B}^{\prime}(t)$ and $\hat{y}_{1}$ represent the signals and physiological parameters estimated in the temporal domain. Similarly, $\hat{x}_{s}$ and $\hat{y}_{2}$ are the spectrogram and physiological parameters estimated in the spectrogram domain, while $\hat{y}_{3}$ represents the physiological parameters estimated in the mixed domain.

Figure 3: Contrasting supervised, unsupervised, and self-supervised learning paradigms. Unsupervised learning involves learning from unlabeled data by constructing generative models or density estimators. Here, we illustrate this with the classical method known as the autoencoder.

Figure 4: Workflow of self-supervised representation learning. The term ’(Update)’ signifies that parameter updates are optional. When not updated, the method follows a linear probing paradigm; when updated, it adheres to a fine-tuning paradigm. (SBP is systolic blood pressure, DBP is diastolic blood pressure, HR is heart rate, $\text{SpO}_{2}$ is blood oxygen saturation)

Panel of Figure 5 — Figure 5: Generative-based SSRL for time series data. (Repainted from ( Zhang et al., 2024 ) )

\hat{u}_{i}(t)=\mathcal{F}^{-1}(\hat{u}_{i}(\omega))

Algorithm 2 Variational mode decomposition (VMD)

\mathcal{L}_{SR}=\|\hat{x}_{B}^{\prime}(t)-x_{B}^{\prime}(t)\|_{1}

Algorithm 3 Cross-Temporal Fusion Generated Anchor (CTFGA)

	$\displaystyle\nabla_{\theta_{new},W,b}\mathcal{L}_{MAE}$	$\displaystyle=\frac{\partial\mathcal{L}_{MAE}}{\partial y^{\prime}}\cdot\frac{\partial y^{\prime}}{\partial(f_{\theta_{new}},g_{new})}$
		$\displaystyle=\frac{\partial\mathcal{L}_{MAE}}{\partial y^{\prime}}\cdot\frac{\partial(Wf_{\theta_{new}}(x^{\prime}(t))+b)}{\partial(f_{\theta_{new}},g_{new})}$

Algorithm 4 CTFGA with Dual-process Transfer (DPT)

\nabla_{\theta_{unlock},\theta_{1},g_{new}}\mathcal{L}_{IR}=\frac{\partial\mathcal{L}_{IR}}{\partial\hat{x}_{s}}\cdot\frac{\partial\hat{x}_{s}}{\partial(Encoder,Decoder,g_{new})}

Algorithm 5 Spectrogram Domain Strategy

Figure 6: Novel Bilinear Temporal-Spectrogram Fusion (NBTSF)

Database	Pretraining			Validation
VitalDB	222360			24720
BCG	24768			2752
Class	Database	Training	Validation	Test	Length	Sampling Rate (Hz)
$\text{SpO}_{2}$	BIDMC	178057	25436	50875	4000	125
	UniGreifswald	29976	3138	9566	1316000	512
	UniSydney	27854	3649	8479	245000	500

Table 1: Statistical distribution of the PPG databases.

Figure 7: Transfer results under different pre-training methods and data amounts. (Standardized)

Figure 8: Pre-training results under different transfer methods and data amounts ( $P$ : proportion of training data, SBP: systolic blood pressure, DBP: diastolic blood pressure).

	Component	Temporal		Spectrogram		Mixed
	Database	MAE	MAPE	MAE	MAPE	MAE	MAPE
$\text{SpO}_{2}$ (%)	BIDMC	1.007±0.0485	0.010	2.297±0.218	0.024	0.996±0.085	0.010
	UniGreifswald	0.947±0.0215	0.010	0.463±0.041	0.010	0.514±0.042	0.011
	UniSydney	0.467±0.0175	0.005	0.273±0.011	0.004	0.427±0.024	0.006
HR (bpm)	BIDMC	1.879±0.074	0.022	10.41±1.105	0.104	8.001±0.687	0.080
	IEEEPPG	15.293±0.2405	0.149	22.525±0.669	0.239	16.439±1.482	0.174

Table 2: Performance of components in each composition of TS2TC. (bold represents the best results in different domains)

		$\text{SpO}_{2}$ (%)			HR (bpm)			RR (bpm)			DBP (mmHg)			SBP (mmHg)			Average
Models	Metric	BIDMC	UniGreifswald	UniSydney	BIDMC	IEEEPPG	UniSydney	BIDMC	PWDB	CapnoBase	UniSydney	PPGBP	NBPE	UniSydney	PPGBP	NBPE	Average
TFTC	MAE	1.217±0.103	0.608±0.051	0.428±0.035	4.094±0.172	16.305±0.613	3.950±0.236	1.445±0.095	4.832±0.171	4.707±0.141	8.571±0.367	9.576±0.303	3.426±0.149	5.504±0.550	12.836±1.347	9.352±0.827	5.790
TFTC	MAPE	0.022	0.006	0.006	0.041	0.173	0.053	0.136	0.338	0.292	0.035	0.088	0.033	0.027	0.178	0.072	0.100
PatchTST	MAE	2.537±0.101	4.749±0.390	11.261±0.472	3.097±0.300	27.797±2.348	8.180±0.550	2.029±0.057	14.016±0.598	6.033±0.365	57.325±5.869	19.729±0.956	6.230±0.551	9.300±0.871	17.437±1.014	14.582±0.884	13.620
PatchTST	MAPE	0.027	0.049	0.115	0.035	0.262	0.108	0.159	0.909	0.364	0.757	0.281	0.089	0.080	0.143	0.106	0.232
TSSequencer	MAE	2.456±0.229	0.907±0.046	0.532±0.023	1.834±0.147	24.746±1.230	7.839±0.398	1.817±0.187	14.018±0.898	6.107±0.444	56.396±5.521	9.473±0.980	5.985±0.534	9.222±0.941	17.526±1.138	12.829±0.625	11.446

Table 3: Comparison of results of TS2TC framework under sample scarcity situation (MAE and MAPE

\pm

Std), where bold and underline represent the best performance among the comparison methods, and underline only represents the second best performance.

Panel of Figure 9 — Figure 9: The results of the TS2TC method on IEEEPPG (P=10%).

Models			CTFG-DPT		PatchTST		TSSequencer		TSPerceiver		XCM		MultiRocket		TSiTransformer		TST		OmniScale		InceptionTime
Metric			RMSE	MAPE	RMSE	MAPE	RMSE	MAPE	RMSE	MAPE	RMSE	MAPE	RMSE	MAPE	RMSE	MAPE	RMSE	MAPE	RMSE	MAPE	RMSE	MAPE
$\text{SpO}_{2}$ (%)	BIDMC	10%	1.444±0.156	0.010	3.384±0.142	0.027	3.276±0.156	0.026	3.245±0.251	0.026	2.814±0.243	0.022	2.445±0.149	0.019	3.277±0.115	0.026	5.506±0.268	0.050	2.615±0.277	0.019	2.963±0.188	0.022
		50%	0.800±0.065	0.005	3.253±0.263	0.025	3.277±0.126	0.026	3.233±0.155	0.025	2.053±0.122	0.015	1.236±0.078	0.009	3.276±0.328	0.026	3.839±0.164	0.027	1.225±0.119	0.009	1.506±0.115	0.011
		100%	0.603±0.061	0.004	3.275±0.246	0.026	3.276±0.285	0.026	3.202±0.239	0.025	1.514±0.077	0.011	1.138±0.120	0.008	3.276±0.217	0.026	3.265±0.512	0.026	1.006±0.099	0.007	1.100±0.092	0.008
	UniGreifswald	10%	1.422±0.102	0.010	19.515±2.024	0.049	1.328±0.098	0.009	1.590±0.092	0.011	2.058±0.062	0.014	5.373±0.307	0.038	1.306±0.092	0.009	10.367±0.794	0.101	1.647±0.165	0.014	8.572±0.449	0.024
		50%	1.333±0.110	0.009	19.497±0.866	0.046	1.328±0.035	0.009	1.330±0.100	0.009	1.306±0.091	0.009	1.679±0.047	0.013	1.309±0.992	0.009	1.597±0.098	0.010	1.323±0.110	0.010	1.392±0.068	0.009

Table 4: Comparison of results based on CTFGA and DPT (RMSE±Std and MAPE), where bold indicates the best performance of the method, and underline indicates the second-best performance method.

Figure 10: Pretraining Validation Loss Results at Different $\gamma$ and $T$ .

Figure 11: Performance of different $\gamma$ and $T$ values in downstream tasks, with asterisks indicating the best performance.

	Model	OCTFG		OCTFG+VMD		OCTFG+VMD+MSDI		OCTFG+VMD+MSDI+ZDL
	Database	MAE	MAPE	MAE	MAPE	MAE	MAPE	MAE	MAPE
$\text{SpO}_{2}$	BIDMC	1.698±0.252	0.018	1.695±0.111	0.018	1.614±0.047	0.016	1.007±0.049	0.010
	UniGreifswald	1.170±0.030	0.012	1.144±0.099	0.012	1.085±0.069	0.012	0.947±0.022	0.010
	UniSydney	8.201±1.602	0.084	5.929±0.407	0.061	4.931±0.348	0.056	0.467±0.018	0.005
HR	BIDMC	2.345±0.040	0.028	2.205±0.039	0.026	2.109±0.189	0.026	1.879±0.074	0.022
	IEEEPPG	16.491±0.484	0.145	16.280±0.111	0.146	16.245±1.404	0.146	15.293±0.241	0.149

Table 5: Ablation of VMD, MSDI, and ZDL.

	Database	R-squared	$\phi_{1}$	$\phi_{2}$	$\phi_{3}$
$\text{SpO}_{2}$	BIDMC	0.916±0.034	0.755±0.014	-0.106±0.012	0.755±0.099
	UniGreifswald	0.906±0.027	0.853±0.012	-0.190±0.016	0.853±0.063
	UniSydney	0.918±0.038	0.848±0.026	0.170±0.028	0.848±0.081
HR	BIDMC	0.953±0.036	0.997±0.031	0.129±0.066	0.997±0.072
	IEEEPPG	0.969±0.022	0.943±0.033	-0.115±0.062	0.943±0.126
	UniSydney	0.934±0.029	0.932±0.014	-0.296±0.036	0.932±0.090

Table 6: Parameters of the TS2TC framework based on OLS fusion across different tasks.

Figure 12: Analysis of the contributions of components in the TS2TC framework on IEEEPPG.

Figure 13: Clarke error grid analysis of the proposed TS2TC.

Method	MAE (mmol/L)	MAPE (%)	Zone A (%)	Zone B (%)
PatchTST	2.522±0.122	35.93	42.55	53.19
TSSequencer	1.312±0.072	19.08	63.82	34.04
TSPerceiver	2.261±0.257	31.76	27.65	70.21
XCM	1.509±0.086	22.31	55.31	42.55
MultiRocket	1.699±0.102	25.24	40.42	57.44
TSiTransformer	1.387±0.019	20.91	44.68	53.19

Table 7: Comparison results of different methods on the BGDB dataset.

Self-Supervised Time Series Representation Learning

Self-supervised time series representation learning uses unlabeled sequences to learn features that transfer to forecasting, classification, and anomaly detection.

See all 143 papers

Intervention-Based Self-Supervised Learning: A Causal Probe Paradigm for Remote Photoplethysmography
Apr 26, 2026Zhiyi Niu, Xiaoguang Tu, Bo Zhao +3Remote Photoplethysmography Causal Representation Learning
School of Computer Science and Information Engineering, Hefei University of Technology, Hefei 230601, PR China. · College of Aviation Electronic and Electrical Engineering, Civil Aviation Flight University of China, Guanghan 618307, PR China. · School of Computing and Information Technology, Great Bay University, Dongguan 523000, PR China.
Interaction-Gated Time-Frequency Learning for Parameter-Efficient PPG-Based Heart Rate Estimation
Oct 20, 2026Anh Khoi Pham, Phat Lam, Thien Truong Nguyen Ly +1Heart Rate Estimation Photoplethysmography
International University, Vietnam National University HCMC, Ho Chi Minh City, Vietnam · University of New Brunswick, Fredericton, Canada · Ho Chi Minh City University of Technology, Ho Chi Minh City, Vietnam +1
FCUS-rPPG: A Fast-Converging Unsupervised Framework for Remote Photoplethysmography via Gradient Oscillation Suppression
Jun 2, 2026Jiajie Li, Yu Liu, Rencheng Song +2Remote Photoplethysmography Unsupervised Representation Learning
Department of Biomedical Engineering, and also with Anhui Province Key Laboratory of Measuring Theory and Precision Instrument, Hefei University of Technology, Hefei 230009, China · Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei 230026, China

Apr 26, 2026J/K move · Enter open · S save

Intervention-Based Self-Supervised Learning: A Causal Probe Paradigm for Remote Photoplethysmography

Zhiyi Niu, Xiaoguang Tu, Bo Zhao, Junzhe Cao+2

School of Computer Science and Information Engineering, Hefei University of Technology, Hefei 230601, PR China. · College of Aviation Electronic and Electrical Engineering, Civil Aviation Flight University of China, Guanghan 618307, PR China. · School of Computing and Information Technology, Great Bay University, Dongguan 523000, PR China.

Remote Photoplethysmography Causal Representation Learning Self-Supervised Learning Photoplethysmography

Open paper AskPDF arXiv

Remote Photoplethysmography (rPPG) enables convenient non-contact physiological measurement. Existing Self-Supervised Learning (SSL) methods commonly fall into a correlation trap: they tend to learn the most dominant periodic signals in the data, such as high-energy motion or illumination noise, rather than the faint, true rPPG signal, leading to poor model generalization. To address this, we propose a new SSL paradigm, Physiological Causal Probing (PCP), which treats the latent rPPG signal as the underlying physical source and the resulting pixel chrominance variations as its visual manifestation. Its core idea is to shift from passive correlation learning to active, precise intervention: it intervenes on the video based on a proposed rPPG hypothesis, and verifies whether the post-intervention changes match physical expectations. We propose the Interv-rPPG framework to implement PCP: an rPPG extractor named PhysMambaFormer hypothesizes the rPPG signal, while a Controllable Physiological Signal Editor conducts precise chrominance-domain interventions on videos based on this hypothesis. Interv-rPPG validates the physical realism of the hypothesis through Falsifiability via Nulling' and Axiomatic Equivariance'. Our editor achieves precise editing of the rPPG signal by intervening in the low-frequency chrominance components of the video. Our method improves both in-domain and cross-domain performance on challenging datasets such as VIPL-HR and MMPD. Furthermore, it surpasses the supervised baseline in complex cross-dataset settings, while remaining competitive on clean datasets where the intervention mechanism may introduce slight residual chrominance noise. Extensive experiments, including diagnostic analysis of nuisance sensitivity, demonstrate that the PCP paradigm effectively resists motion and illumination artifacts.

Abstract

Self-Supervised Time Series Representation Learning

Explore similar work

Intervention-Based Self-Supervised Learning: A Causal Probe Paradigm for Remote Photoplethysmography

Interaction-Gated Time-Frequency Learning for Parameter-Efficient PPG-Based Heart Rate Estimation

FCUS-rPPG: A Fast-Converging Unsupervised Framework for Remote Photoplethysmography via Gradient Oscillation Suppression