SKANN-SSL V5 Demo

Underwater Acoustic Vessel Classification System

Self-supervised learning approach for classifying vessel types from hydrophone audio signatures.

© 2026 Oravont Systems LLP. All rights reserved.

---

Features

• 5-Class Vessel Classification: Cargo Ship, Tanker, Fishing Vessel, Small Craft, No Vessel (Ambient)
• Real-time Audio Playback: Listen to acoustic signatures while classifying
• Radar Plot Visualization: Interactive probability display with animated transitions
• Physics-Aware Architecture: Selective Kernel convolutions tuned for underwater acoustics (15–500+ Hz)

---

Installation

# 1. Install dependencies
pip install -r requirements.txt

# 2. Run the demo
python skann_ssl_v5_demo.py

Requirements

• Python 3.10+
• Windows / macOS / Linux
• ~700 MB disk space (model + sample data)

---

Folder Structure

SKANN-SSL-V5-Demo/
├── skann_ssl_v5_demo.py                        # Main demo application
├── requirements.txt                            # Python dependencies
├── README.md                                   # This file
├── model/
│   ├── SKANN_SSL_V3_Production_Bundle.joblib   # Trained encoder + embeddings
│   └── vessel_territories_v3.joblib            # Classification centroids
└── data/
    ├── manifest.csv                            # Clip metadata
    └── tensors/                                # Audio tensors (16 kHz, 5 seconds)
        ├── tensor_000000.npy
        ├── tensor_000001.npy
        └── ...

---

Usage

1. Launch: Run python skann_ssl_v5_demo.py
2. Select Clip: Use dropdown or click "🎲 Random"
3. Classify: Click "🎯 Classify"
4. Listen: Audio plays in loop (click "🔊" to mute)
5. Review: Radar plot shows class probabilities with build-up animation

---

Model Performance

Metric	Value
Silhouette Score	0.9697
kNN Accuracy	100%
Embedding Dimension (h)	512
Embedding Dimension (z)	256
Vessel Classes	5
Sample Rate	16 kHz
Clip Duration	5 seconds
Training Clips	12,000

Vessel Classes

Class	Description
Cargo Ship	Large commercial cargo vessels
Tanker	Oil/chemical tankers
Fishing Vessel	Commercial fishing boats
Small Craft	Recreational boats, yachts
No Vessel	Ambient ocean noise (no vessel present)

Frequency Coverage (SK Kernels)

Kernel Size	Frequency	Acoustic Phenomenon
1023	15+ Hz	Shaft rate
511	31+ Hz	Generator (25 Hz)
255	62+ Hz	Generator (50 Hz)
127	125+ Hz	Blade pass
63	250+ Hz	Hull resonance
31	500+ Hz	Cavitation

---

Troubleshooting

"sounddevice not installed"

pip install sounddevice

No audio output

• Check system audio settings
• Demo works without audio (visual classification still functional)

CUDA errors on CPU machine

• The demo automatically handles CPU-only environments

GUI becomes unresponsive

• Avoid rapid clicking; the demo includes debounce protection
• Restart the application if needed

---

Contact

For licensing, integration, or technical support:

Oravont Systems LLP

---

SKANN-SSL: Selective Kernel Audio Neural Networks with Self-Supervised Learning