Recurrent Neural Network for Human Activity Recognition in Embedded Systems Using PPG and Accelerometer Data

Self Cite

The use of electroencephalography (EEG) has recently grown as a means to diagnose neurodegenerative pathologies such as Alzheimer’s disease (AD). AD recognition can benefit from machine learning methods that, compared with traditional manual diagnosis methods, have higher reliability and improved recognition accuracy, being able to manage large amounts of data. Nevertheless, machine learning methods may exhibit lower accuracies when faced with incomplete, corrupted, or otherwise missing data, so it is important do develop robust pre-processing techniques do deal with incomplete data. The aim of this paper is to develop an automatic classification method that can still work well with EEG data affected by artifacts, as can arise during the collection with, e.g., a wireless system that can lose packets. We show that a recurrent neural network (RNN) can operate successfully even in the case of significantly corrupted data, when it is pre-filtered by the robust principal component analysis (RPCA) algorithm. RPCA was selected because of its stated ability to remove outliers from the signal. To demonstrate this idea, we first develop an RNN which operates on EEG data, properly processed through traditional PCA; then, we use corrupted data as input and process them with RPCA to filter outlier components, showing that even with data corruption causing up to 20% erasures, the RPCA was able to increase the detection accuracy by about 5% with respect to the baseline PCA.

Section: Brief Of Rnnsmentioning

confidence: 99%

“…The RNN used in this paper is depicted in Figure 6 , for the case of PCA applied and 50 principal components retained. It is based on architectures commonly used with time-based sensor data [ 36 , 40 , 41 , 46 ] and consisting of a mix of LSTM cells and fully connected layers.…”

Section: Rnn Architecturementioning

confidence: 99%

EEG-Based Alzheimer’s Disease Recognition Using Robust-PCA and LSTM Recurrent Neural Network

Alessandrini

Biagetti

Crippa

et al. 2022

Self Cite

“…Initially, the idea of using temporal information was proposed in 1991 [178] to recognize a finger alphabet consisting of 42 symbols and in 1995 [179] to classify 66 different hand shapes with about 98% accuracy. Since then, the recurrent neural network (RNN) with time series as input has been widely applied to classify human activities or estimate hand gestures [180][181][182][183][184][185][186][187].…”

Section: Recurrent Neural Network (Rnn)mentioning

confidence: 99%

Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances

Zhang

et al. 2022

244

Mobile and wearable devices have enabled numerous applications, including activity tracking, wellness monitoring, and human–computer interaction, that measure and improve our daily lives. Many of these applications are made possible by leveraging the rich collection of low-power sensors found in many mobile and wearable devices to perform human activity recognition (HAR). Recently, deep learning has greatly pushed the boundaries of HAR on mobile and wearable devices. This paper systematically categorizes and summarizes existing work that introduces deep learning methods for wearables-based HAR and provides a comprehensive analysis of the current advancements, developing trends, and major challenges. We also present cutting-edge frontiers and future directions for deep learning-based HAR.

“…In this work, authors focus only on the inference time without considering time and energy spent to real-time collecting data from IMU sensors or to preprocess signals [ 29 ]. Recently, Alessandrini et al, presented a recurrent neural network (RNN), deployed on an embedded device, which takes in input data from Photoplethysmography (PPG) and tri-axial accelerometer sensors to infer the current human activity [ 30 ]. Similarly, Coelho et al [ 17 ] and Mayer et al [ 31 ] showed the adequacy of different deep learning models to be run on low-power platforms.…”

Section: Related Workmentioning

confidence: 99%

Exploring Artificial Neural Networks Efficiency in Tiny Wearable Devices for Human Activity Recognition

Lattanzi

Donati

Freschi

2022

The increasing diffusion of tiny wearable devices and, at the same time, the advent of machine learning techniques that can perform sophisticated inference, represent a valuable opportunity for the development of pervasive computing applications. Moreover, pushing inference on edge devices can in principle improve application responsiveness, reduce energy consumption and mitigate privacy and security issues. However, devices with small size and low-power consumption and factor form, like those dedicated to wearable platforms, pose strict computational, memory, and energy requirements which result in challenging issues to be addressed by designers. The main purpose of this study is to empirically explore this trade-off through the characterization of memory usage, energy consumption, and execution time needed by different types of neural networks (namely multilayer and convolutional neural networks) trained for human activity recognition on board of a typical low-power wearable device.Through extensive experimental results, obtained on a public human activity recognition dataset, we derive Pareto curves that demonstrate the possibility of achieving a 4× reduction in memory usage and a 36× reduction in energy consumption, at fixed accuracy levels, for a multilayer Perceptron network with respect to more sophisticated convolution network models.