scholarly journals Predicting continuous ground reaction forces from accelerometers during uphill and downhill running: A recurrent neural network solution

2021 ◽  
Author(s):  
Ryan S. Alcantara ◽  
W. Brent Edwards ◽  
Guillaume Y. Millet ◽  
Alena M. Grabowski
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Stance Phase ◽  
Accelerometer Data ◽  
Step Frequency ◽  
Laboratory Environment ◽  
Downhill Running ◽  
The Neural Network ◽  
Reaction Forces ◽  
Active Peak

AbstractBackgroundGround reaction forces (GRFs) are important for understanding the biomechanics of human movement but the measurement of GRFs is generally limited to a laboratory environment. Wearable devices like accelerometers have been used to measure biomechanical variables outside the laboratory environment, but they cannot directly measure GRFs. Previous studies have used neural networks to predict the entire GRF waveform during the stance phase from wearable device data, but these networks require normalization of GRFs to the duration of a step or stance phase, resulting in a loss of the GRF waveform’s temporal component. Additionally, previous studies have predicted GRF waveforms during level-ground, but not uphill or downhill running. A method of predicting the normal (perpendicular to running surface) GRF waveform using wearable devices across a range of running speeds and slopes, while maintaining the GRF waveform’s temporal component, could allow researchers and clinicians to predict kinetic and kinematic variables outside the laboratory environment.PurposeWe sought to develop a recurrent neural network capable of predicting normal GRF waveforms across a range of running speeds and slopes using data from accelerometers located on the sacrum and shoe.Methods19 subjects completed 30-s running trials on a force-measuring treadmill at five slopes (0°, ±5°, ±10°) and three speeds (2.5, 3.33, and 4.17 m/s) per slope. One biaxial accelerometer was adhered to the sacrum and two uniaxial accelerometers were adhered to the right shoe during all trials. Accelerometers on the shoe were used to classify foot strike patterns as rearfoot, midfoot, or forefoot, and sacral acceleration data were divided into overlapping 12-ms windows, allowing the neural network to iteratively predict the experimentally-measured normal GRF waveform frame-by-frame. The mean, SD, and range of accelerometer data for each 12-ms window were included as neural network input features, along with the subject’s body mass, height, running speed, slope, and percentage of a trial’s steps classified as a rearfoot, midfoot, or forefoot strike. We assessed the accuracy and generalizability of the neural network using leave-one-subject-out cross validation, which provided an ensemble of Root Mean Square Error (RMSE) and relative RMSE (rRMSE) values comparing the normal GRF waveform predicted by the neural network to the normal GRF waveform measured by the force-measuring treadmill. Additionally, we calculated the mean absolute percent error (MAPE) of step frequency, contact time, normal impulse, normal GRF active peak, and loading rate between the predicted and measured GRF waveforms.ResultsThe average ± SD RMSE was 0.16 ± 0.04 BW and rRMSE was 6.4 ± 1.5% for neural network predictions of each subject’s normal GRF waveform compared to measured GRF waveforms across all conditions. RMSE values were lower during slow uphill running (2.5 m/s, +10°; 0.13 ± 0.07 BW) compared to fast downhill running (4.17 m/s, −10°; 0.20 ± 0.05 BW). The MAPE ± SD for step frequency was 0.1 ± 0.1%, contact time was 4.9 ± 4.0%, normal impulse was 6.4 ± 6.9%, normal GRF active peak was 8.5 ± 8.2%, and loading rate was 27.6 ± 36.1%.ConclusionsWe developed a recurrent neural network that uses accelerometer data to predict the continuous normal GRF waveform across a range of running speeds and slopes. The neural network does not require preliminary identification of the stance phase, maintains the temporal component of the GRF waveform, can be applied to up- and downhill running, and facilitates the prediction of kinetic and kinematic variables outside the laboratory environment. This represents a substantial step towards accurately quantifying and monitoring the external loads experienced by the body when running outdoors.

scholarly journals Predicting continuous ground reaction forces from accelerometers during uphill and downhill running: a recurrent neural network solution

PeerJ ◽  
2022 ◽  
Vol 10 ◽  
pp. e12752
Author(s):  
Ryan S. Alcantara ◽  
W. Brent Edwards ◽  
Guillaume Y. Millet ◽  
Alena M. Grabowski
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Recurrent Neural Network ◽  
Human Movement ◽  
The Body ◽  
Ground Reaction Forces ◽  
Accelerometer Data ◽  
Laboratory Environment ◽  
Reaction Forces ◽  
External Forces

Background Ground reaction forces (GRFs) are important for understanding human movement, but their measurement is generally limited to a laboratory environment. Previous studies have used neural networks to predict GRF waveforms during running from wearable device data, but these predictions are limited to the stance phase of level-ground running. A method of predicting the normal (perpendicular to running surface) GRF waveform using wearable devices across a range of running speeds and slopes could allow researchers and clinicians to predict kinetic and kinematic variables outside the laboratory environment. Purpose We sought to develop a recurrent neural network capable of predicting continuous normal (perpendicular to surface) GRFs across a range of running speeds and slopes from accelerometer data. Methods Nineteen subjects ran on a force-measuring treadmill at five slopes (0°, ±5°, ±10°) and three speeds (2.5, 3.33, 4.17 m/s) per slope with sacral- and shoe-mounted accelerometers. We then trained a recurrent neural network to predict normal GRF waveforms frame-by-frame. The predicted versus measured GRF waveforms had an average ± SD RMSE of 0.16 ± 0.04 BW and relative RMSE of 6.4 ± 1.5% across all conditions and subjects. Results The recurrent neural network predicted continuous normal GRF waveforms across a range of running speeds and slopes with greater accuracy than neural networks implemented in previous studies. This approach may facilitate predictions of biomechanical variables outside the laboratory in near real-time and improves the accuracy of quantifying and monitoring external forces experienced by the body when running.

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

Electronics ◽  
2021 ◽  
Vol 10 (14) ◽  
pp. 1715
Author(s):  
Michele Alessandrini ◽  
Giorgio Biagetti ◽  
Paolo Crippa ◽  
Laura Falaschetti ◽  
Claudio Turchetti
Keyword(s):  
Neural Network ◽  
Embedded System ◽  
Activity Recognition ◽  
Human Activity ◽  
Recurrent Neural Network ◽  
Low Cost ◽  
Low Complexity ◽  
Human Activity Recognition ◽  
Motion Artifacts ◽  
Accelerometer Data

Photoplethysmography (PPG) is a common and practical technique to detect human activity and other physiological parameters and is commonly implemented in wearable devices. However, the PPG signal is often severely corrupted by motion artifacts. The aim of this paper is to address the human activity recognition (HAR) task directly on the device, implementing a recurrent neural network (RNN) in a low cost, low power microcontroller, ensuring the required performance in terms of accuracy and low complexity. To reach this goal, (i) we first develop an RNN, which integrates PPG and tri-axial accelerometer data, where these data can be used to compensate motion artifacts in PPG in order to accurately detect human activity; (ii) then, we port the RNN to an embedded device, Cloud-JAM L4, based on an STM32 microcontroller, optimizing it to maintain an accuracy of over 95% while requiring modest computational power and memory resources. The experimental results show that such a system can be effectively implemented on a constrained-resource system, allowing the design of a fully autonomous wearable embedded system for human activity recognition and logging.

scholarly journals Where to put the image in an image caption generator

2018 ◽  
Vol 24 (3) ◽  
pp. 467-489 ◽  
Author(s):  
MARC TANTI ◽  
ALBERT GATT ◽  
KENNETH P. CAMILLERI
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
State Vector ◽  
Language Model ◽  
Image Features ◽  
Subsequent Stage ◽  
Multimodal Integration ◽  
The Neural Network ◽  
Large Memory ◽  
Image Caption

AbstractWhen a recurrent neural network (RNN) language model is used for caption generation, the image information can be fed to the neural network either by directly incorporating it in the RNN – conditioning the language model by ‘injecting’ image features – or in a layer following the RNN – conditioning the language model by ‘merging’ image features. While both options are attested in the literature, there is as yet no systematic comparison between the two. In this paper, we empirically show that it is not especially detrimental to performance whether one architecture is used or another. The merge architecture does have practical advantages, as conditioning by merging allows the RNN’s hidden state vector to shrink in size by up to four times. Our results suggest that the visual and linguistic modalities for caption generation need not be jointly encoded by the RNN as that yields large, memory-intensive models with few tangible advantages in performance; rather, the multimodal integration should be delayed to a subsequent stage.

scholarly journals Solving the problem of classification of material properties using a neural network

2021 ◽  
Vol 2131 (3) ◽  
pp. 032084
Author(s):  
N E Babushkina ◽  
A A Lyapin
Keyword(s):  
Neural Network ◽  
Experimental Data ◽  
Recurrent Neural Network ◽  
Material Properties ◽  
Practical Significance ◽  
Experimental Measurements ◽  
Statistical Parameters ◽  
The Neural Network ◽  
Main Components

Abstract The article sets the task of classifying various materials and determining their belonging to a specified group using a recurrent neural network. The practical significance of the article is to obtain the results of the neural network, confirming the possibility of classifying materials by the hardness parameter using a neural network. As part of the study, a number of experimental measurements were carried out. The structure of the neural network and its main components are described. The statistical parameters of the experimental data are estimated.

scholarly journals Hybrid deep learning model using recurrent neural network and gated recurrent unit for heart disease prediction

2021 ◽  
Vol 11 (6) ◽  
pp. 5467
Author(s):  
Surenthiran Krishnan ◽  
Pritheega Magalingam ◽  
Roslina Ibrahim
Keyword(s):  
Neural Network ◽  
Heart Disease ◽  
Deep Learning ◽  
Recurrent Neural Network ◽  
Short Term Memory ◽  
Learning Model ◽  
Disease Prediction ◽  
The Neural Network ◽  
Proposed Model ◽  
Deep Learning Model

<span>This paper proposes a new hybrid deep learning model for heart disease prediction using recurrent neural network (RNN) with the combination of multiple gated recurrent units (GRU), long short-term memory (LSTM) and Adam optimizer. This proposed model resulted in an outstanding accuracy of 98.6876% which is the highest in the existing model of RNN. The model was developed in Python 3.7 by integrating RNN in multiple GRU that operates in Keras and Tensorflow as the backend for deep learning process, supported by various Python libraries. The recent existing models using RNN have reached an accuracy of 98.23% and deep neural network (DNN) has reached 98.5%. The common drawbacks of the existing models are low accuracy due to the complex build-up of the neural network, high number of neurons with redundancy in the neural network model and imbalance datasets of Cleveland. Experiments were conducted with various customized model, where results showed that the proposed model using RNN and multiple GRU with synthetic minority oversampling technique (SMOTe) has reached the best performance level. This is the highest accuracy result for RNN using Cleveland datasets and much promising for making an early heart disease prediction for the patients.</span>

scholarly journals Performance Analysis and Recognition of Speech using Recurrent Neural Network

2019 ◽  
Vol 1 (1) ◽  
pp. 87-95
Author(s):  
Bishon Lamichanne ◽  
Hari K.C.
Keyword(s):  
Neural Network ◽  
Speech Recognition ◽  
Performance Analysis ◽  
Recurrent Neural Network ◽  
Error Rate ◽  
English Language ◽  
Daily Lives ◽  
Crucial Step ◽  
The Neural Network ◽  
Positive Results

Speech is one of the most natural ways to communicate between people. It plays an important role in our daily lives. To make machines able to talk with people is a challenging but very useful task. A crucial step is to enable machines to recognize and understand what people are saying. Hence, speech recognition becomes a key technique providing an interface for communication between machines and humans. There has been a long research history on speech recognition. Neural network is known as a technique that has ability to classify nonlinear problem. Today, lots of research are going in the field of speech recognition with the help of the Neural Network. Even though positive results have been obtained from continuous study, research on minimizing the error rate is still gaining lots attention. The English language offers a number of challenges for speech recognition. This paper implements the RNN to analyze and recognize speech from the set of spoken words.

Self-Organized Maps on Continuous Bump Attractors

2013 ◽  
Vol 8 (1) ◽  
pp. 234-247 ◽  
Author(s):  
К.П. Соловьева ◽  
K.P. Solovyeva
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Recurrent Network ◽  
External Signal ◽  
Stable States ◽  
Factors Affecting ◽  
One Dimensional ◽  
Self Organized ◽  
The Neural Network ◽  
Winner Takes All

In this article, we describe a simple binary neuron system, which implements a self-organized map. The system consists of R input neurons (R receptors), and N output neurons of a recurrent neural network. The neural network has a quasi-continuous set of attractor states (one-dimensional “bump attractor”). Due to the dynamics of the network, each external signal (i.e. activity state of receptors) imposes transition of the recurrent network into one of its stable states (points of its attractor). That makes our system different from the “winner takes all” construction of T.Kohonen. In case, when there is a one-dimensional cyclical manifold of external signals in R-dimensional input space, and the recurrent neural network presents a complete ring of neurons with local excitatory connections, there exists a process of learning of connections between the receptors and the neurons of the recurrent network, which enables a topologically correct mapping of input signals into the stable states of the neural network. The convergence rate of learning and the role of noises and other factors affecting the described phenomenon has been evaluated in computational simulations.

A One-Layer Recurrent Neural Network with a Discontinuous Activation Function for Linear Programming

2008 ◽  
Vol 20 (5) ◽  
pp. 1366-1383 ◽  
Author(s):  
Qingshan Liu ◽  
Jun Wang
Keyword(s):  
Neural Network ◽  
Linear Programming ◽  
Recurrent Neural Network ◽  
Optimal Solution ◽  
Activation Function ◽  
High Gain ◽  
Discontinuous Activation ◽  
The Neural Network ◽  
Decision Variables ◽  
Discontinuous Activation Function

A one-layer recurrent neural network with a discontinuous activation function is proposed for linear programming. The number of neurons in the neural network is equal to that of decision variables in the linear programming problem. It is proven that the neural network with a sufficiently high gain is globally convergent to the optimal solution. Its application to linear assignment is discussed to demonstrate the utility of the neural network. Several simulation examples are given to show the effectiveness and characteristics of the neural network.

scholarly journals Individuality decoded by running patterns: Movement characteristics that determine the uniqueness of human running

PLoS ONE ◽  
2021 ◽  
Vol 16 (4) ◽  
pp. e0249657
Author(s):  
Fabian Hoitz ◽  
Vinzenz von Tscharner ◽  
Jennifer Baltich ◽  
Benno M. Nigg
Keyword(s):  
Neural Network ◽  
Sagittal Plane ◽  
Gait Recognition ◽  
Transverse Plane ◽  
Human Gait ◽  
Ground Reaction Forces ◽  
Movement Trajectories ◽  
Gait Characteristics ◽  
The Neural Network ◽  
Reaction Forces

Human gait is as unique to an individual as is their fingerprint. It remains unknown, however, what gait characteristics differentiate well between individuals that could define the uniqueness of human gait. The purpose of this work was to determine the gait characteristics that were most relevant for a neural network to identify individuals based on their running patterns. An artificial neural network was trained to recognize kinetic and kinematic movement trajectories of overground running from 50 healthy novice runners (males and females). Using layer-wise relevance propagation, the contribution of each variable to the classification result of the neural network was determined. It was found that gait characteristics of the coronal and transverse plane as well as medio-lateral ground reaction forces provided more information for subject identification than gait characteristics of the sagittal plane and ground reaction forces in vertical or anterior-posterior direction. Additionally, gait characteristics during the early stance were more relevant for gait recognition than those of the mid and late stance phase. It was concluded that the uniqueness of human gait is predominantly encoded in movements of the coronal and transverse plane during early stance.

Maritime Anomaly Detection using Density-based Clustering and Recurrent Neural Network

2019 ◽  
Vol 72 (04) ◽  
pp. 894-916 ◽  
Author(s):  
Liangbin Zhao ◽  
Guoyou Shi
Keyword(s):  
Neural Network ◽  
Anomaly Detection ◽  
Real Time ◽  
Recurrent Neural Network ◽  
Situational Awareness ◽  
Short Term Memory ◽  
Spatial Clustering ◽  
Dbscan Algorithm ◽  
The Neural Network ◽  
Density Based Clustering

Maritime anomaly detection can improve the situational awareness of vessel traffic supervisors and reduce maritime accidents. In order to better detect anomalous behaviour of a vessel in real time, a method that consists of a Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm and a recurrent neural network is presented. In the method presented, the parameters of the DBSCAN algorithm were determined through statistical analysis, and the results of clustering were taken as the traffic patterns to train a recurrent neural network composed of Long Short-Term Memory (LSTM) units. The neural network was applied as a vessel trajectory predictor to conduct real-time maritime anomaly detection. Based on data from the Chinese Zhoushan Islands, experiments verified the applicability of the proposed method. The results show that the proposed method can detect anomalous behaviours of a vessel regarding speed, course and route quickly.

Sign in / Sign up

Export Citation Format

Share Document