scholarly journals A fuzzy recurrent neural network for driver fatigue detection based on steering-wheel angle sensor data

2019 ◽  
Vol 15 (9) ◽  
pp. 155014771987245 ◽  
Author(s):  
Zuojin Li ◽  
Qing Yang ◽  
Shengfu Chen ◽  
Wei Zhou ◽  
Liukui Chen ◽  
...  
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Recurrent Neural Network ◽  
Recognition Rate ◽  
Feature Learning ◽  
Sensor Data ◽  
Steering Wheel ◽  
Input Layer ◽  
Driving Conditions ◽  
Hidden Layer

The study of the robust fatigue feature learning method for the driver’s operational behavior is of great significance for improving the performance of the real-time detection system for driver’s fatigue state. Aiming at how to extract more abstract and deep features in the driver’s direction operation data in the robust feature learning, this article constructs a fuzzy recurrent neural network model, which includes input layer, fuzzy layer, hidden layer, and output layer. The steering-wheel direction sensing time series sends the time series to the input layer through a fixed time window. After the fuzzification process, it is sent to the hidden layer to share the weight of the hidden layer, realize the memorization of the fatigue feature, and improve the feature depth capability of the steering wheel angle time sequence. The experimental results show that the proposed model achieves an average recognition rate of 87.30% in the fatigue sample database of real vehicle conditions, which indicates that the model has strong robustness to different subjects under real driving conditions. The model proposed in this article has important theoretical and engineering significance for studying the prediction of fatigue driving under real driving conditions.

scholarly journals Kp forecasting with a recurrent neural network

2019 ◽  
Vol 9 ◽  
pp. A19 ◽  
Author(s):  
Ernest Scott Sexton ◽  
Katariina Nykyri ◽  
Xuanye Ma
Keyword(s):  
Neural Network ◽  
Solar Wind ◽  
Recurrent Neural Network ◽  
Historical Data ◽  
Time Step ◽  
Prediction Horizon ◽  
Sigma B ◽  
Input Layer ◽  
Solar Wind Parameters ◽  
Hidden Layer

In an effort to forecast the planetary Kp-index beyond the current 1-hour and 4-hour predictions, a recurrent neural network is trained on three decades of historical data from NASA’s Omni virtual observatory and forecasts Kp with a prediction horizon of up to 24 h. Using Matlab’s neural network toolbox, the multilayer perceptron model is trained on inputs comprised of Kp for a given time step as well as from different sets of the following six solar wind parameters, Bz, n, V, |B|, σB and $ {\sigma }_{{B}_z}$. The purpose of this study was to test which combination of the solar wind and Interplanetary Magnetic Field (IMF) parameters used for training gives the best performance as defined by correlation coefficient, C, between the predicted and actually measured Kp values and Root Mean Square Error (RMSE). The model consists of an input layer, a single nonlinear hidden layer with 28 neurons, and a linear output layer that predicts Kp up to 24 h in advance. For 24 h prediction, the network trained on Bz, n, V, |B|, σB performs the best giving C in the range from 0.8189 (for 31 predictions) to 0.8211 (for 9 months of predictions), with the smallest RMSE.

Design and formulation of microbially induced self-healing concrete for building structure strength enhancement

2021 ◽  
Vol 11 (11) ◽  
pp. 1753-1765
Author(s):  
K. Vijaya Sundravel ◽  
S. Ramesh ◽  
D. Jegatheeswaran
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Material Strength ◽  
Self Healing ◽  
Building Structure ◽  
Chi Square ◽  
Deep Recurrent Neural Network ◽  
Input Layer ◽  
Structure Strength ◽  
Hidden Layer

Self-healing concrete is described as the capability of material to repair their cracks independently. Cracks in concrete are well-known circumstance because of their short tensile strength. Many researchers carried out their research on self-healing concrete using different classification and clustering methods. But the temperature variation and pH variation were not minimized. In order to address these problems, a Multivariate Logistic Regressed Chi-Square Deep Recurrent Neural Network based Self-Healing (MLRCSDRNN-SH) Method is introduced. The main aim of MLRCSDRNN-SH method is to improve building structures strength through inducing the micro-bacteria in concrete. Multiple Logistic Regressed Chi-Square Deep Recurrent Neural Network (MLRCSDRNN) is used to revise bacteria’s stress-strain behaviour towards enhanced material strength in the MLRCSDRNN-SH approach. Initially, the bacteria selection is carried out in alkaline environment like Bacillus subtilis, E. coli and Pseudomonas sps. The data sample is given to the input layer. The input layer transmits sample to the hidden layer 1. The regression analysis is carried out between the multiple independent variables (i.e., parameters) using multivariate logistic function for improving the building structure strength. The regressed value is transmitted to the hidden layer 2. The pearson chi-squared independence hypothesis is performed to identify the probability of crack self-healing property for increasing the building structure strength. When probability value is higher, then the building structure strength is high. Otherwise, the output of second hidden layer is feedback to the input of hidden layer 1. The mixture with higher strength of building structure is sent to the output layer. Several specimens have different sizes used by various researchers for bacterial material study in comparison with the concrete. Depending on experimental results, compressive strength restoration proved higher self-healing ability of the concrete.

scholarly journals Remaining Useful Life Prediction Using Temporal Convolution with Attention

AI ◽  
2021 ◽  
Vol 2 (1) ◽  
pp. 48-70
Author(s):  
Wei Ming Tan ◽  
T. Hui Teo
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Time Series Data ◽  
Remaining Useful Life ◽  
Sensor Data ◽  
Series Data ◽  
Multiple Time ◽  
Data Set ◽  
Form Complex ◽  
Useful Life

Prognostic techniques attempt to predict the Remaining Useful Life (RUL) of a subsystem or a component. Such techniques often use sensor data which are periodically measured and recorded into a time series data set. Such multivariate data sets form complex and non-linear inter-dependencies through recorded time steps and between sensors. Many current existing algorithms for prognostic purposes starts to explore Deep Neural Network (DNN) and its effectiveness in the field. Although Deep Learning (DL) techniques outperform the traditional prognostic algorithms, the networks are generally complex to deploy or train. This paper proposes a Multi-variable Time Series (MTS) focused approach to prognostics that implements a lightweight Convolutional Neural Network (CNN) with attention mechanism. The convolution filters work to extract the abstract temporal patterns from the multiple time series, while the attention mechanisms review the information across the time axis and select the relevant information. The results suggest that the proposed method not only produces a superior accuracy of RUL estimation but it also trains many folds faster than the reported works. The superiority of deploying the network is also demonstrated on a lightweight hardware platform by not just being much compact, but also more efficient for the resource restricted environment.

scholarly journals Ensemble Empirical Mode Decomposition with Adaptive Noise with Convolution Based Gated Recurrent Neural Network: A New Deep Learning Model for South Asian High Intensity Forecasting

Symmetry ◽  
2021 ◽  
Vol 13 (6) ◽  
pp. 931
Author(s):  
Kecheng Peng ◽  
Xiaoqun Cao ◽  
Bainian Liu ◽  
Yanan Guo ◽  
Wenlong Tian
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Deep Learning ◽  
South Asian ◽  
Recurrent Neural Network ◽  
Ensemble Empirical Mode Decomposition ◽  
South Asian High ◽  
Mode Decomposition ◽  
Adaptive Noise ◽  
Deep Learning Model

The intensity variation of the South Asian high (SAH) plays an important role in the formation and extinction of many kinds of mesoscale systems, including tropical cyclones, southwest vortices in the Asian summer monsoon (ASM) region, and the precipitation in the whole Asia Europe region, and the SAH has a vortex symmetrical structure; its dynamic field also has the symmetry form. Not enough previous studies focus on the variation of SAH daily intensity. The purpose of this study is to establish a day-to-day prediction model of the SAH intensity, which can accurately predict not only the interannual variation but also the day-to-day variation of the SAH. Focusing on the summer period when the SAH is the strongest, this paper selects the geopotential height data between 1948 and 2020 from NCEP to construct the SAH intensity datasets. Compared with the classical deep learning methods of various kinds of efficient time series prediction model, we ultimately combine the Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) method, which has the ability to deal with the nonlinear and unstable single system, with the Permutation Entropy (PE) method, which can extract the SAH intensity feature of IMF decomposed by CEEMDAN, and the Convolution-based Gated Recurrent Neural Network (ConvGRU) model is used to train, test, and predict the intensity of the SAH. The prediction results show that the combination of CEEMDAN and ConvGRU can have a higher accuracy and more stable prediction ability than the traditional deep learning model. After removing the redundant features in the time series, the prediction accuracy of the SAH intensity is higher than that of the classical model, which proves that the method has good applicability for the prediction of nonlinear systems in the atmosphere.

Sign in / Sign up

Export Citation Format

Share Document