Compressed Sensing for Low-Power PPG: Theory, Algorithms & Hardware Implementation

Hardware Architectures for CS-PPG

Analog Compressed Sensing

The most power-efficient CS implementation operates at the analog level, before the ADC. An analog CS front-end modulates the photodetector output with a pseudo-random sequence and integrates the result over measurement windows, producing M analog values that are then digitized by a slower ADC. This architecture can replace the high-speed ADC with a lower-rate converter, reducing both ADC power and digital data throughput.

Digital Random Sampling

The simplest implementation strategy is digital random sampling: the ADC operates at a fixed rate, but a digital controller randomly selects which samples to retain and discards the rest. This approach does not reduce ADC power but reduces LED power by only activating the LED for retained samples and reduces data storage/transmission bandwidth. Since LED power dominates the system budget, this achieves substantial savings even without analog modifications.

Hybrid Architectures

Modern CS-PPG systems often combine compressed acquisition with adaptive sampling rate control. The system monitors signal quality metrics (perfusion index, SNR estimates) in real time and adjusts the compression ratio dynamically. During rest when the signal is clean and highly sparse, compression ratios of 8:1 or higher are used. During motion when sparsity decreases, the system gracefully reduces compression to 2:1 or even reverts to full Nyquist sampling.

This adaptive approach requires a lightweight quality assessment running alongside the CS acquisition, typically consuming less than 5% additional power. The overall system achieves average compression ratios of 5:1 to 6:1 across mixed activity scenarios while maintaining reconstruction quality above 20 dB SNR.

Sparsity-Aware Reconstruction for PPG

Dictionary Learning for PPG

Generic sparsifying bases (Fourier, wavelet) do not fully capture PPG signal structure. Dictionary learning algorithms such as K-SVD (Aharon et al., 2006, doi:10.1109/TSP.2006.881199) can learn overcomplete dictionaries directly from training data, achieving sparser representations. Mamaghanian et al. (2011, doi:10.1109/TBME.2011.2156795) applied compressed sensing to ECG signals using wavelet sparsity, demonstrating that similar principles apply to other biosignals. Learned dictionaries can capture morphological features that are not efficiently represented in standard bases.

The tradeoff is that dictionary learning requires offline training on representative data, and the learned dictionary may not generalize well to PPG signals with significantly different morphology (e.g., different measurement sites, pathological conditions). For clinical applications where waveform morphology is diagnostically relevant, site-specific and condition-specific dictionaries may be necessary.

Deep Learning Reconstruction

Neural network-based reconstruction has emerged as a promising alternative to iterative optimization algorithms. Learned ISTA (LISTA) networks unroll a fixed number of ISTA iterations into a feedforward network with learnable parameters, achieving reconstruction quality comparable to hundreds of ISTA iterations in a single forward pass.

For PPG applications, learned iterative shrinkage-thresholding (LISTA) networks achieve reconstruction quality comparable to traditional optimization while running substantially faster, making real-time on-device reconstruction feasible on microcontrollers.

For more on deploying neural networks for PPG processing on embedded hardware, see our guides on PPG signal processing algorithms and related deep learning approaches.

Performance Benchmarks and Tradeoffs

Compression Ratio vs. Reconstruction Quality

Published CS-PPG studies differ in datasets, sparsifying bases, reconstruction algorithms, and quality metrics, so no single benchmark table transfers cleanly between systems. The general pattern follows from CS theory. As the compression ratio rises, reconstruction quality falls, and fine morphological features such as the dicrotic notch degrade before the fundamental (heart rate) frequency does. Modest ratios are the safer choice when full waveform fidelity is needed, while heart-rate-only applications can tolerate more aggressive compression. Because the required number of measurements scales with sparsity (M = $O(K \log(N/K))$), the usable ratio for a given system should be determined empirically on representative data, including noisy segments.

Effect of Motion Artifacts

Motion artifacts fundamentally challenge CS-PPG by reducing signal sparsity. A clean resting PPG is highly sparse in the Fourier domain: a fundamental plus a few significant harmonics. Motion adds components at the movement frequency and its harmonics, which raises K and therefore the number of measurements needed. During vigorous activity the signal may no longer be sparse enough for useful compression.

Joint sparsity models address this by decomposing the signal into cardiac and motion subspaces with separate sparsity constraints. Accelerometer data can inform the motion subspace, allowing the reconstruction to allocate measurement resources appropriately. For more on motion artifact handling, see our PPG motion artifact removal guide.

Power Consumption Results

Research systems have demonstrated significant power reduction using digital CS with wavelet sparsity, substantially reducing total system power during continuous monitoring. Custom ASIC implementations of CS-PPG front-ends have achieved even lower power consumption with on-chip reconstruction, targeting implantable or patch-type long-term monitoring applications.

Commercial implementations in recent wearable platforms report battery life extension using adaptive CS with variable compression ratios, though detailed power breakdowns are typically proprietary.

Implementation Guidelines for Wearable Systems

For engineers designing CS-PPG wearable systems, the following practical recommendations emerge from the literature and our analysis:

Start with digital random sampling. It requires minimal hardware modification (LFSR-based sample selector, LED gate control), cuts LED on-time roughly in proportion to the compression ratio, and can be implemented as a firmware update on existing PPG platforms.

Use OMP for on-device reconstruction. Its greedy nature avoids iterative convergence issues, its computational cost is predictable (bounded by K iterations), and its memory footprint is small (storing the measurement matrix and intermediate vectors). Benchmark reconstruction time on your target processor, since it scales with segment length, sparsity level and dictionary size.

Implement adaptive compression. Monitor the residual energy after initial OMP iterations as a sparsity proxy. When residual energy exceeds a threshold (indicating reduced sparsity from motion or poor signal quality), reduce the compression ratio by retaining more samples in the next acquisition window.

Validate against clinical metrics. Reconstruction SNR alone does not capture clinical relevance. Validate that heart rate, HRV features (RMSSD, SDNN, frequency-domain measures), and any morphological features of interest are preserved within acceptable tolerances at the target compression ratio. For HRV features, even small waveform distortions can introduce timing jitter in peak detection that corrupts interval-based metrics.

For broader context on PPG signal processing pipelines and how compressed sensing integrates with downstream algorithms, our algorithm guides provide comprehensive implementation references.

Future Directions

Several emerging trends promise to further advance CS-PPG technology. Hardware-software co-design approaches are developing custom ADC architectures that natively produce compressed measurements, eliminating the overhead of a conventional ADC followed by digital compression. Federated dictionary learning enables wearable devices to collaboratively learn optimal sparsifying dictionaries without sharing raw physiological data, addressing both personalization and privacy. Neuromorphic sensing using event-driven photodetectors that only produce outputs when the PPG signal changes could achieve even more efficient acquisition than CS by exploiting temporal sparsity at the sensor level.

The convergence of compressed sensing with edge AI processing for on-device inference creates opportunities for ultra-low-power PPG systems that perform both acquisition and analysis at microwatt-level power budgets, enabling truly continuous long-term physiological monitoring.

References

• Donoho, D. L. (2006). Compressed sensing. IEEE Transactions on Information Theory, 52(4), 1289-1306. https://doi.org/10.1109/TIT.2006.871582
• Baraniuk, R. G. (2007). Compressive sensing. IEEE Signal Processing Magazine, 24(4), 118-121. https://doi.org/10.1109/MSP.2007.4286571
• Tropp, J. A., & Gilbert, A. C. (2007). Signal recovery from random measurements via orthogonal matching pursuit. IEEE Transactions on Information Theory, 53(12), 4655-4666. https://doi.org/10.1109/TIT.2007.909108
• Chen, S. S., Donoho, D. L., & Saunders, M. A. (2001). Atomic decomposition by basis pursuit. SIAM Review, 43(1), 129-159. https://doi.org/10.1137/S003614450037906X
• Aharon, M., Elad, M., & Bruckstein, A. (2006). K-SVD: An algorithm for designing overcomplete dictionaries for sparse representation. IEEE Transactions on Signal Processing, 54(11), 4311-4322. https://doi.org/10.1109/TSP.2006.881199
• Mamaghanian, H., et al. (2011). Compressed sensing for real-time energy-efficient ECG compression on wireless body sensor nodes. IEEE Transactions on Biomedical Engineering, 58(9), 2456-2466. https://doi.org/10.1109/TBME.2011.2156795