降低采样率可大幅减少微控制器上时间序列分类的能耗与计算开销。
Optimizing TinyML: The Impact of Reduced Data Acquisition Rates for Time Series Classification on Microcontrollers
- 通过降低数据采样频率，减少计算和内存占用。
- 采样率降75%时能耗降70%，内存降60%，运算量减75%。
- 适合电池供电的物联网设备部署，兼顾能效与精度。
TinyML使机器学习推理可在连接传感器的微控制器单元（MCU）上高效、低成本且保护隐私地运行。优化模型以适应此类资源受限环境至关重要。本文研究了降低数据采集频率对时间序列分类中TinyML模型的影响，重点关注资源受限、电池供电的物联网设备。通过降低采样频率，我们旨在将计算需求、内存使用、能量消耗、延迟和乘加操作（MAC）约降低四倍，同时保持相近的分类准确率。在六个基准数据集（UCIHAR、WISDM、PAMAP2、MHEALTH、MITBIH 和 PTB）上的实验表明，降低数据采集频率显著减少了能量消耗和计算负载，且精度损失极小。例如，针对MITBIH和PTB数据集，采样率降低75%时，内存使用减少60%，MAC操作减少75%，延迟下降74%，能量消耗降低70%，准确率未受影响。这些结果为在受限环境中部署高效TinyML模型提供了重要参考。
原文摘要 · Abstract (English)
Tiny Machine Learning (TinyML) enables efficient, lowcost, and privacy preserving machine learning inference directly on microcontroller units (MCUs) connected to sensors. Optimizing models for these constrained environments is crucial. This paper investigates how reducing data acquisition rates affects TinyML models for time series classification, focusing on resource-constrained, battery operated IoT devices. By lowering data sampling frequency, we aim to reduce computational demands RAM usage, energy consumption, latency, and MAC operations by approximately fourfold while maintaining similar classification accuracies. Our experiments with six benchmark datasets (UCIHAR, WISDM, PAMAP2, MHEALTH, MITBIH, and PTB) showed that reducing data acquisition rates significantly cut energy consumption and computational load, with minimal accuracy loss. For example, a 75\% reduction in acquisition rate for MITBIH and PTB datasets led to a 60\% decrease in RAM usage, 75\% reduction in MAC operations, 74\% decrease in latency, and 70\% reduction in energy consumption, without accuracy loss. These results offer valuable insights for deploying efficient TinyML models in constrained environments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。