You can deploy this model and start earning money today!

Ambiq/
compressionkit-ppg-hybrid-16x-v1.0

Views

No views yet

compressionkit-ppg-hybrid-16x

A PPG signal compression codec: a learned wavelet-gain denoiser (trained weights) followed by wavelet + SPIHT + arithmetic coding. The deployable artifact is the denoiser weights, the bitstream contract, and a portable C99 reference implementation for the SPIHT stage.

Operating point

Field	Value
Modality	PPG
Sample rate	64 Hz
Frame size	320 samples
Target CR	16x
Wavelet	`bior4.4`
DWT levels	6
Bit budget	320 bits/frame
Entropy coder	arithmetic coding

Quality metrics

Fidelity & Robustness

Both fidelity yardsticks are reported so the codec is judged fairly: faithfulness is PRD vs the recorded (still-noisy) input, while truth fidelity is PRD vs clean ground truth. Lower is better.

Metric	Value
Truth PRD vs clean (%)	10.45
Truth PRD at native noise (%)	30.02
Faithful PRD vs input (%)	8.14
PRD degradation slope (PRD%/dB)	4.30
PRD at 0 dB SNR (%)	70.59
PRD at -6 dB SNR (%)	100.40
Pure-noise imprint autocorr	0.2664

Time Domain

PRD here is faithfulness (vs the recorded input); see Fidelity & Robustness above for the clean-truth and noise-regime view.

Metric	Mean	Median	P90
PRD vs input — faithfulness (%)	8.1445	7.4074	10.4517
RMSE	0.0814	0.0741	0.1045
Cosine Similarity	0.9953	0.9973	0.9987

Spectral

Band Total Relative Error (median): 0.0350

Bitrate

Python quickstart

python

from compressionkit.runtime import load_codec

codec = load_codec("Ambiq/compressionkit-ppg-hybrid-16x")
enc = codec.compress(frame)   # frame: (frame_size,) float32
recon = codec.decompress(enc)

C quickstart

The SPIHT stage ships a portable C99 reference; the denoiser (denoiser_gain_model.keras) currently only has a Python/TFLite runtime path. Run the denoiser stage first (Python, or a converted TFLite Micro model) and feed its output into the C SPIHT encoder below.

#include "spiht_app_config.h"

float frame[APP_SPIHT_FRAME_SIZE];
uint8_t bitstream[APP_SPIHT_MAX_BYTES];
/* ... fill frame from sensor (post-denoise, if hybrid) ... */
size_t nbits = spiht_encode_frame(&enc, bitstream, APP_SPIHT_MAX_BITS);

Files

File	Description
`config.json`	Deploy manifest (`family: "hybrid"`)
`spiht_config.json`	Codec parameters (language-neutral)
`sample_stimulus.npz`	Synthetic test frames
`reference_vectors.npz`	Reference encode/decode vectors
`c_sources/spiht.[ch]`	Portable C99 reference
`c_sources/spiht_app_config.h`	Codec-specific defines
`model_card.json`	Provenance metadata
`scorecard.json`	Frozen evaluation summary
`denoiser_gain_model.keras`	Learned wavelet-gain denoiser (trained weights)
`hybrid_manifest.json`	Pipeline stage order (denoise → SPIHT)

Dataset & license

Evaluation data provenance is not recorded in this package; sample data uses synthetic physiokit waveforms only — no patient data is redistributed.

Codec source released under the OTHER license.

Citation

bibtex

@software{compressionkit,
  author = {Ambiq AI},
  title = {compressionKIT: Signal Compression for Edge AI},
  url = {https://github.com/AmbiqAI/compressionkit}
}

Ambiq/compressionkit-ppg-hybrid-16x-v1.0