compressionkit-ppg-16x

A PPG signal compression codec using Residual Vector Quantization (RVQ), optimized for edge and wearable devices.

Model Details

• Modality: PPG
• Sample Rate: 64 Hz
• Compression Ratio: 16x
• Quantization: INT8
• RVQ Levels: 4
• Codebook Size: 256 entries × 16D
• Encoder Input: [None, 1, 320, 1]
• Encoder Output: [None, 1, 20, 16]

Quality Metrics

Time Domain

Metric	Mean	Median	P90
PRD (%)	12.4496	5.4119	25.0669
RMSE	0.0629	0.0476	0.0905
Cosine Similarity	0.9663	0.9986	0.9993

Spectral

• Band Total Relative Error (median): 0.0486

Bitrate

• Codec CR (uniform): 16.0x
• Codec CR (learned prior): 16.30x

Usage

Python (compressionkit runtime)

from compressionkit.runtime import RVQCodec

codec = RVQCodec.from_pretrained("Ambiq/compressionkit-ppg-16x")

# Encode: float32 signal → RVQ indices
indices = codec.encode(signal)

# Decode: RVQ indices → reconstructed signal
recon = codec.decode(indices)

Local deployment directory

codec = RVQCodec("path/to/deploy/")

Files

File	Description
encoder_int8.tflite	INT8 quantized encoder (on-device)
encoder.h	C header for encoder
decoder_float32.tflite	Float32 decoder (server-side evaluation)
decoder_int8.tflite	INT8 decoder (optional, on-device)
codebook.npz	RVQ codebook tables
codebook.h	C header for codebook
config.json	Deployment manifest
sample_stimulus.npz	Synthetic test data
quality_scorecard.json	Full evaluation metrics

Dataset & License

Training data: MESA (NSRR restricted). Sample data uses synthetic physiokit waveforms only — no patient data is redistributed.

Model weights are released under the Ambiq Model Weights License — deployment is restricted to Ambiq silicon devices. See LICENSE-MODEL-WEIGHTS.md for full terms.

Citation

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