SDAA429 June   2026 MSPM0G5187

 

  1.   1
  2.   Abstract
  3.   Trademarks
  4. 1Introduction
  5. 2MSPM0G5187 with TinyEngine NPU
  6. 3Edge AI Toolchains
    1. 3.1 TI Edge AI Studio
    2. 3.2 TI Tiny ML Tensorlab
    3. 3.3 TI Neural Network Compiler
  7. 4Edge AI Application: Digit Recognition
    1. 4.1 LeNet-5 Variant CNN Model
    2. 4.2 NPU/CPU Performance Comparison
  8. 5Edge AI Application: Waveform Classifier
    1. 5.1 Feature Extraction
    2. 5.2 Time-Series Classification Model
    3. 5.3 Model Memory Considerations
    4. 5.4 NPU/CPU Performance Comparison
  9. 6Summary
  10. 7References

5 Edge AI Application: Waveform Classifier

MSPM0 provides an experimental waveform classifier design capable of performing real-time, continuous detection and classification of input signals, identifying common waveform types such as sine, triangle, and sawtooth waves. The design is built upon a 13K-parameter time-series classification model, offering strong scalability and extensibility.

The waveform classifier system achieves 100% (R square) classification accuracy with an inference latency of only 5.84 ms, while consuming just 21.5KB of Flash and 3.3KB of RAM, as shown in Table 5-6.

Table 5-1 Waveform Classifier Edge AI Solution Performance
MetricValue
Accuracy100%
Flash Usage21.5KB
RAM Usage3.3KB
Inference Latency (NPU)5.84ms
Inference Power Consumption (AVG)412.90uJ

Table 5-5 shows the mode main information.

Table 5-2 Waveform Classifier AI Model Information
PropertyValue
Model ArchitectureCNN
Number of Parameters14,124
Input ShapeTensor [(1, 1, 128, 1)]
Output Classes3 (Sawtooth, Sine, Square)
QuantizationINT8