Optimizing TinyML: The Impact of Reduced Data Acquisition Rates for Time Series Classification on Microcontrollers
- URL: http://arxiv.org/abs/2409.10942v1
- Date: Tue, 17 Sep 2024 07:21:49 GMT
- Title: Optimizing TinyML: The Impact of Reduced Data Acquisition Rates for Time Series Classification on Microcontrollers
- Authors: Riya Samanta, Bidyut Saha, Soumya K. Ghosh, Ram Babu Roy,
- Abstract summary: This paper investigates how reducing data acquisition rates affects TinyML models for time series classification.
By lowering data sampling frequency, we aim to reduce computational demands RAM usage, energy consumption, latency, and MAC operations by approximately fourfold.
- Score: 6.9604565273682955
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: 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.
Related papers
- Enhancing Field-Oriented Control of Electric Drives with Tiny Neural Network Optimized for Micro-controllers [0.8328638943795448]
This paper introduces a tiny feed-forward neural network, TinyFC, integrated into the Field-Oriented Control (FOC) of Permanent Magnet Synchronous Motors (PMSMs)
A lightweight 1,400 parameters TinyFC was devised to enhance the FOC performance while fitting into the computational and memory constraints of a micro-controller.
arXiv Detail & Related papers (2025-02-01T19:16:51Z) - Optimising TinyML with Quantization and Distillation of Transformer and Mamba Models for Indoor Localisation on Edge Devices [7.229732269884237]
This paper proposes small and efficient machine learning models (TinyML) for resource-constrained edge devices.
The work focuses on model compression techniques, including quantization and knowledge distillation, to significantly reduce the model size.
The application of these TinyML models in healthcare has the potential to revolutionize patient monitoring.
arXiv Detail & Related papers (2024-12-12T13:59:21Z) - Enhancing Lightweight Neural Networks for Small Object Detection in IoT
Applications [1.6932009464531739]
The paper proposes a novel adaptive tiling method that can be used on top of any existing object detector.
Our experimental results show that the proposed tiling method can boost the F1-score by up to 225% while reducing the average object count error by up to 76%.
arXiv Detail & Related papers (2023-11-13T08:58:34Z) - NeuralFuse: Learning to Recover the Accuracy of Access-Limited Neural Network Inference in Low-Voltage Regimes [50.00272243518593]
Deep neural networks (DNNs) have become ubiquitous in machine learning, but their energy consumption remains problematically high.
We have developed NeuralFuse, a novel add-on module that handles the energy-accuracy tradeoff in low-voltage regimes.
At a 1% bit-error rate, NeuralFuse can reduce access energy by up to 24% while recovering accuracy by up to 57%.
arXiv Detail & Related papers (2023-06-29T11:38:22Z) - The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in
Transformers [59.87030906486969]
This paper studies the curious phenomenon for machine learning models with Transformer architectures that their activation maps are sparse.
We show that sparsity is a prevalent phenomenon that occurs for both natural language processing and vision tasks.
We discuss how sparsity immediately implies a way to significantly reduce the FLOP count and improve efficiency for Transformers.
arXiv Detail & Related papers (2022-10-12T15:25:19Z) - BottleFit: Learning Compressed Representations in Deep Neural Networks
for Effective and Efficient Split Computing [48.11023234245863]
We propose a new framework called BottleFit, which includes a novel training strategy to achieve high accuracy even with strong compression rates.
BottleFit achieves 77.1% data compression with up to 0.6% accuracy loss on ImageNet dataset.
We show that BottleFit decreases power consumption and latency respectively by up to 49% and 89% with respect to (w.r.t.) local computing and by 37% and 55% w.r.t. edge offloading.
arXiv Detail & Related papers (2022-01-07T22:08:07Z) - AnalogNets: ML-HW Co-Design of Noise-robust TinyML Models and Always-On
Analog Compute-in-Memory Accelerator [50.31646817567764]
This work describes TinyML models for the popular always-on applications of keyword spotting (KWS) and visual wake words (VWW)
We detail a comprehensive training methodology, to retain accuracy in the face of analog non-idealities.
We also describe AON-CiM, a programmable, minimal-area phase-change memory (PCM) analog CiM accelerator.
arXiv Detail & Related papers (2021-11-10T10:24:46Z) - A TinyML Platform for On-Device Continual Learning with Quantized Latent
Replays [66.62377866022221]
Latent Replay-based Continual Learning (CL) techniques enable online, serverless adaptation in principle.
We introduce a HW/SW platform for end-to-end CL based on a 10-core FP32-enabled parallel ultra-low-power processor.
Our results show that by combining these techniques, continual learning can be achieved in practice using less than 64MB of memory.
arXiv Detail & Related papers (2021-10-20T11:01:23Z) - Unit-Modulus Wireless Federated Learning Via Penalty Alternating
Minimization [64.76619508293966]
Wireless federated learning (FL) is an emerging machine learning paradigm that trains a global parametric model from distributed datasets via wireless communications.
This paper proposes a wireless FL framework, which uploads local model parameters and computes global model parameters via wireless communications.
arXiv Detail & Related papers (2021-08-31T08:19:54Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.