Related papers: Sensor-Aware Classifiers for Energy-Efficient Time Series Applications on IoT Devices

Sensor-Aware Classifiers for Energy-Efficient Time Series Applications on IoT Devices

URL: http://arxiv.org/abs/2407.08715v1
Date: Thu, 11 Jul 2024 17:50:31 GMT
Title: Sensor-Aware Classifiers for Energy-Efficient Time Series Applications on IoT Devices
Authors: Dina Hussein, Lubah Nelson, Ganapati Bhat,
Abstract summary: Time-series data processing is an important component of many real-world applications, such as health monitoring, environmental monitoring, and digital agriculture. Machine learning (ML) models are being employed in time-series applications due to their generalization abilities for classification. We propose to employ early exit classifiers with partial sensor windows to minimize energy consumption while maintaining accuracy.
Score: 2.7446241148152257
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Time-series data processing is an important component of many real-world applications, such as health monitoring, environmental monitoring, and digital agriculture. These applications collect distinct windows of sensor data (e.g., few seconds) and process them to assess the environment. Machine learning (ML) models are being employed in time-series applications due to their generalization abilities for classification. State-of-the-art time-series applications wait for entire sensor data window to become available before processing the data using ML algorithms, resulting in high sensor energy consumption. However, not all situations require processing full sensor window to make accurate inference. For instance, in activity recognition, sitting and standing activities can be inferred with partial windows. Using this insight, we propose to employ early exit classifiers with partial sensor windows to minimize energy consumption while maintaining accuracy. Specifically, we first utilize multiple early exits with successively increasing amount of data as they become available in a window. If early exits provide inference with high confidence, we return the label and enter low power mode for sensors. The proposed approach has potential to enable significant energy savings in time series applications. We utilize neural networks and random forest classifiers to evaluate our approach. Our evaluations with six datasets show that the proposed approach enables up to 50-60% energy savings on average without any impact on accuracy. The energy savings can enable time-series applications in remote locations with limited energy availability.

Related papers

Scaling Wearable Foundation Models [54.93979158708164]
We investigate the scaling properties of sensor foundation models across compute, data, and model size. Using a dataset of up to 40 million hours of in-situ heart rate, heart rate variability, electrodermal activity, accelerometer, skin temperature, and altimeter per-minute data from over 165,000 people, we create LSM. Our results establish the scaling laws of LSM for tasks such as imputation, extrapolation, both across time and sensor modalities.
arXiv Detail & Related papers (2024-10-17T15:08:21Z)
Quanv4EO: Empowering Earth Observation by means of Quanvolutional Neural Networks [62.12107686529827]
This article highlights a significant shift towards leveraging quantum computing techniques in processing large volumes of remote sensing data. The proposed Quanv4EO model introduces a quanvolution method for preprocessing multi-dimensional EO data. Key findings suggest that the proposed model not only maintains high precision in image classification but also shows improvements of around 5% in EO use cases.
arXiv Detail & Related papers (2024-07-24T09:11:34Z)
Event-based vision on FPGAs -- a survey [0.0]
Field programmable gate Arrays (FPGAs) have enabled fast data processing (even in real-time) and energy efficiency. This paper gives an overview of the most important works, where FPGAs have been used in different contexts to process event data. It covers applications in the following areas: filtering, stereovision, optical flow, acceleration of AI-based algorithms for object classification, detection and tracking, and applications in robotics and inspection systems.
arXiv Detail & Related papers (2024-07-11T10:07:44Z)
Environmental Sensor Placement with Convolutional Gaussian Neural Processes [65.13973319334625]
It is challenging to place sensors in a way that maximises the informativeness of their measurements, particularly in remote regions like Antarctica. Probabilistic machine learning models can suggest informative sensor placements by finding sites that maximally reduce prediction uncertainty. This paper proposes using a convolutional Gaussian neural process (ConvGNP) to address these issues.
arXiv Detail & Related papers (2022-11-18T17:25:14Z)
To Compute or not to Compute? Adaptive Smart Sensing in Resource-Constrained Edge Computing [1.7361161778148904]
We consider a network of smart sensors for an edge computing application that sample a time-varying signal and send updates to a base station for remote global monitoring. Sensors are equipped with sensing and compute, and can either send raw data or process them on-board before transmission. We propose an estimation-theoretic optimization framework that embeds both computation and communication latency.
arXiv Detail & Related papers (2022-09-05T23:46:42Z)
Evaluating Short-Term Forecasting of Multiple Time Series in IoT Environments [67.24598072875744]
Internet of Things (IoT) environments are monitored via a large number of IoT enabled sensing devices. To alleviate this issue, sensors are often configured to operate at relatively low sampling frequencies. This can hamper dramatically subsequent decision-making, such as forecasting.
arXiv Detail & Related papers (2022-06-15T19:46:59Z)
Braille Letter Reading: A Benchmark for Spatio-Temporal Pattern Recognition on Neuromorphic Hardware [50.380319968947035]
Recent deep learning approaches have reached accuracy in such tasks, but their implementation on conventional embedded solutions is still computationally very and energy expensive. We propose a new benchmark for computing tactile pattern recognition at the edge through letters reading. We trained and compared feed-forward and recurrent spiking neural networks (SNNs) offline using back-propagation through time with surrogate gradients, then we deployed them on the Intel Loihimorphic chip for efficient inference. Our results show that the LSTM outperforms the recurrent SNN in terms of accuracy by 14%. However, the recurrent SNN on Loihi is 237 times more energy
arXiv Detail & Related papers (2022-05-30T14:30:45Z)
Motion Detection using CSI from Raspberry Pi 4 [5.826796031213696]
Channel State Information (CSI) is a low cost, unintrusive form of radio sensing. We have developed a novel, self-calibrating motion detection system which uses CSI data collected and processed on a stock Raspberry Pi 4.
arXiv Detail & Related papers (2021-11-17T13:17:02Z)
Energy Aware Deep Reinforcement Learning Scheduling for Sensors Correlated in Time and Space [62.39318039798564]
We propose a scheduling mechanism capable of taking advantage of correlated information. The proposed mechanism is capable of determining the frequency with which sensors should transmit their updates. We show that our solution can significantly extend the sensors' lifetime.
arXiv Detail & Related papers (2020-11-19T09:53:27Z)
Deep ConvLSTM with self-attention for human activity decoding using wearables [0.0]
We propose a deep neural network architecture that captures features of multiple sensor time-series data but also selects important time points. We show the validity of the proposed approach across different data sampling strategies and demonstrate that the self-attention mechanism gave a significant improvement. The proposed methods open avenues for better decoding of human activity from multiple body sensors over extended periods time.
arXiv Detail & Related papers (2020-05-02T04:30:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.