Human lower extremity joint moment prediction: A wavelet neural network approach

Joint moment is one of the most important factors in human gait analysis. It can be calculated using multi body dynamics but might not be straight forward. This study had two main purposes; firstly, to develop a generic multi-dimensional wavelet neural network (WNN) as a real-time surrogate model to calculate lower extremity joint moments and compare with those determined by multi body dynamics approach, secondly, to compare the calculation accuracy of WNN with feed forward artificial neural network (FFANN) as a traditional intelligent predictive structure in biomechanics.To aim these purposes, data of four patients walked with three different conditions were obtained from the literature. A total of 10 inputs including eight electromyography (EMG) signals and two ground reaction force (GRF) components were determined as the most informative inputs for the WNN based on the mutual information technique. Prediction ability of the network was tested at two different levels of inter-subject generalization. The WNN predictions were validated against outputs from multi body dynamics method in terms of normalized root mean square error (NRMSE (%)) and cross correlation coefficient (ρ).Results showed that WNN can predict joint moments to a high level of accuracy (NRMSE < 10%, ρ > 0.94) compared to FFANN (NRMSE < 16%, ρ > 0.89). A generic WNN could also calculate joint moments much faster and easier than multi body dynamics approach based on GRFs and EMG signals which released the necessity of motion capture. It is therefore indicated that the WNN can be a surrogate model for real-time gait biomechanics evaluation.     

An automated signalized junction controller that learns strategies by temporal difference reinforcement learning

This paper shows how temporal difference learning can be used to build a signalized junction controller that will learn its own strategies through experience. Simulation tests detailed here show that the learned strategies can have high performance. This work builds upon previous work where a neural network based junction controller that can learn strategies from a human expert was developed (Box and Waterson, 2012). In the simulations presented, vehicles are assumed to be broadcasting their position over WiFi giving the junction controller rich information. The vehicle's position data are pre-processed to describe a simplified state. The state-space is classified into regions associated with junction control decisions using a neural network. This classification is the strategy and is parametrized by the weights of the neural network. The weights can be learned either through supervised learning with a human trainer or reinforcement learning by temporal difference (TD). Tests on a model of an isolated T junction show an average delay of 14.12 s and 14.36 s respectively for the human trained and TD trained networks. Tests on a model of a pair of closely spaced junctions show 17.44 s and 20.82 s respectively. Both methods of training produced strategies that were approximately equivalent in their equitable treatment of vehicles, defined here as the variance over the journey time distributions.     

A 24-h forecast of ozone peaks and exceedance levels using neural classifiers and weather predictions

A neural network combined to a neural classifier is used in a real time forecasting of hourly maximum ozone in the centre of France, in an urban atmosphere. This neural model is based on the MultiLayer Perceptron (MLP) structure. The inputs of the statistical network are model output statistics of the weather predictions from the French National Weather Service. These predicted meteorological parameters are very easily available through an air quality network. The lead time used in this forecasting is (t + 24) h. Efforts are related to a regularisation method which is based on a Bayesian Information Criterion-like and to the determination of a confidence interval of forecasting. We offer a statistical validation between various statistical models and a deterministic chemistry-transport model. In this experiment, with the final neural network, the ozone peaks are fairly well predicted (in terms of global fit), with an Agreement Index = 92%, the Mean Absolute Error = the Root Mean Square Error = 15 μg m⁻³ and the Mean Bias Error = 5 μg m⁻³, where the European threshold of the hourly ozone is 180 μg m⁻³.To improve the performance of this exceedance forecasting, instead of the previous model, we use a neural classifier with a sigmoid function in the output layer. The output of the network ranges from [0,1] and can be interpreted as the probability of exceedance of the threshold. This model is compared to a classical logistic regression. With this neural classifier, the Success Index of forecasting is 78% whereas it is from 65% to 72% with the classical MLPs. During the validation phase, in the Summer of 2003, six ozone peaks above the threshold were detected. They actually were seven.Finally, the model called NEUROZONE is now used in real time. New data will be introduced in the training data each year, at the end of September. The network will be re-trained and new regression parameters estimated. So, one of the main difficulties in the training phase – namely the low frequency of ozone peaks above the threshold in this region – will be solved.     

Precipitation forecasting by using wavelet-support vector machine conjunction model

A new wavelet-support vector machine conjunction model for daily precipitation forecast is proposed in this study. The conjunction method combining two methods, discrete wavelet transform and support vector machine, is compared with the single support vector machine for one-day-ahead precipitation forecasting. Daily precipitation data from Izmir and Afyon stations in Turkey are used in the study. The root mean square errors (RMSE), mean absolute errors (MAE), and correlation coefficient (R) statistics are used for the comparing criteria. The comparison results indicate that the conjunction method could increase the forecast accuracy and perform better than the single support vector machine. For the Izmir and Afyon stations, it is found that the conjunction models with RMSE=46.5 mm, MAE=13.6 mm, R=0.782 and RMSE=21.4 mm, MAE=9.0 mm, R=0.815 in test period is superior in forecasting daily precipitations than the best accurate support vector regression models with RMSE=71.6 mm, MAE=19.6 mm, R=0.276 and RMSE=38.7 mm, MAE=14.2 mm, R=0.103, respectively. The ANN method was also employed for the same data set and found that there is a slight difference between ANN and SVR methods.     

Artificial neural network-based model for predicting VO2max from a submaximal exercise test

The goal of this study is to develop an accurate artificial neural network (ANN)-based model to predict maximal oxygen uptake (VO₂max) of fit adults from a single stage submaximal treadmill jogging test. Participants (81 males and 45 females), aged from 17 to 40 years, successfully completed a maximal graded exercise test (GXT) to determine VO₂max. The variables; gender, age, body mass, steady-state heart rate and jogging speed are used to build the ANN prediction model. Using 10-fold cross validation on the dataset, the average values of standard error of estimate (SEE), Pearson’s correlation coefficient (r) and multiple correlation coefficient (R) of the model are calculated as 1.80 ml kg^?1 min^?1, 0.95 and 0.93, respectively. Compared with the results of the other prediction models in literature that were developed using Multiple Linear Regression Analysis, the reported values of SEE, r and R in this study are considerably more accurate.     

ANN based simulation and experimental verification of analytical four- and five-parameters models of PV modules

In this article, artificial neural network (ANN) is adopted to predict photovoltaic (PV) panel behaviors under realistic weather conditions. ANN results are compared with analytical four and five parameter models of PV module. The inputs of the models are the daily total irradiation, air temperature and module voltage, while the outputs are the current and power generated by the panel. Analytical models of PV modules, based on the manufacturer datasheet values, are simulated through Matlab/Simulink environment. Multilayer perceptron is used to predict the operating current and power of the PV module. The best network configuration to predict panel current had a 3–7–4–1 topology. So, this two hidden layer topology was selected as the best model for predicting panel current with similar conditions. Results obtained from the PV module simulation and the optimal ANN model has been validated experimentally. Results showed that ANN model provide a better prediction of the current and power of the PV module than the analytical models. The coefficient of determination (R²), mean square error (MSE) and the mean absolute percentage error (MAPE) values for the optimal ANN model were 0.971, 0.002 and 0.107, respectively. A comparative study among ANN and analytical models was also carried out. Among the analytical models, the five-parameter model, with MAPE = 0.112, MSE = 0.0026 and R² = 0.919, gave better prediction than the four-parameter model (with MAPE = 0.152, MSE = 0.0052 and R² = 0.905). Overall, the 3–7–4–1 ANN model outperformed four-parameter model, and was marginally better than the five-parameter model.     

Using artificial neural networks to invert 2D DC resistivity imaging data for high resistivity contrast regions: A MATLAB application

MATLAB is a high-level matrix/array language with control flow statements and functions. MATLAB has several useful toolboxes to solve complex problems in various fields of science, such as geophysics. In geophysics, the inversion of 2D DC resistivity imaging data is complex due to its non-linearity, especially for high resistivity contrast regions. In this paper, we investigate the applicability of MATLAB to design, train and test a newly developed artificial neural network in inverting 2D DC resistivity imaging data. We used resilient propagation to train the network. The model used to produce synthetic data is a homogeneous medium of 100 Ω m resistivity with an embedded anomalous body of 1000 Ω m. The location of the anomalous body was moved to different positions within the homogeneous model mesh elements. The synthetic data were generated using a finite element forward modeling code by means of the RES2DMOD. The network was trained using 21 datasets and tested on another 16 synthetic datasets, as well as on real field data. In field data acquisition, the cable covers 120 m between the first and the last take-out, with a 3 m x-spacing. Three different electrode spacings were measured, which gave a dataset of 330 data points. The interpreted result shows that the trained network was able to invert 2D electrical resistivity imaging data obtained by a Wenner–Schlumberger configuration rapidly and accurately.     

Investigating data preprocessing methods for circuit complexity models

Preprocessing the data is an important step while creating neural network (NN) applications because this step usually has a significant effect on the prediction performance of the model. This paper compares different data processing strategies for NNs for prediction of Boolean function complexity (BFC). We compare NNs’ predictive capabilities with (1) no preprocessing (2) scaling the values in different curves based on every curve’s own peak and then normalizing to [0, 1] range (3) applying z-score to values in all curves and then normalizing to [0, 1] range, and (4) logarithmically scaling all curves and then normalizing to [0, 1] range. The efficiency of these methods was measured by comparing RMS errors in NN-made BFC predictions for numerous ISCAS benchmark circuits. Logarithmic preprocessing method resulted in the best prediction statistics as compared to other techniques.     

Modelling of residual stresses in the shot peened material C-1020 by artificial neural network

This study consists of two cases: (i) The experimental analysis: Shot peening is a method to improve the resistance of metal pieces to fatigue by creating regions of residual stress. In this study, the residual stresses induced in steel specimen type C-1020 by applying various strengths of shot peening, are investigated using the electrochemical layer removal method. The best result is obtained using 0.26 mm A peening strength and the stress encountered in the shot peened material is ?276 MPa, while the maximum residual stress obtained is ?363 MPa at a peening strength of 0.43 mm A. (ii) The mathematical modelling analysis: The use of ANN has been proposed to determine the residual stresses based on various strengths of shot peening using results of experimental analysis. The back-propagation learning algorithm with two different variants and logistic sigmoid transfer function were used in the network. In order to train the neural network, limited experimental measurements were used as training and test data. The best fitting training data set was obtained with four neurons in the hidden layer, which made it possible to predict residual stress with accuracy at least as good as that of the experimental error, over the whole experimental range. After training, it was found the R² values are 0.996112 and 0.99896 for annealed before peening and shot peened only, respectively. Similarly, these values for testing data are 0.995858 and 0.999143, respectively. As seen from the results of mathematical modelling, the calculated residual stresses are obviously within acceptable uncertainties.     

Prediction of cutting temperature in orthogonal machining of AISI 316L using artificial neural network

In this study, an approach based on artificial neural network (ANN) was proposed to predict the experimental cutting temperatures generated in orthogonal turning of AISI 316L stainless steel. Experimental and numerical analyses of the cutting forces were carried out to numerically obtain the cutting temperature. For this purpose, cutting tests were conducted using coated (TiCN + Al₂O₃ + TiN and Al₂O₃) and uncoated cemented carbide inserts. The Deform-2D programme was used for numerical modelling and the Johnson–Cook (J–C) material model was used. The numerical cutting forces for the coated and uncoated tools were compared with the experimental results. On the other hand, the cutting temperature value for each cutting tool was numerically obtained. The artificial neural network model was used to predict numerical cutting temperatures by means of the numerical cutting forces. The best results in predicting the cutting temperature were obtained using the network architecture with a hidden layer which has seven neurons and LM learning algorithm. Finally, the experimental cutting temperatures were predicted by entering the experimental cutting forces into a formula obtained from the artificial neural networks. Statistical results (R², RMSE, MEP) were quite satisfactory. This demonstrates that the established ANN model is a powerful one for predicting the experimental cutting temperatures.     

Integration of growing self-organizing map and continuous genetic algorithm for grading lithium-ion battery cells

This study attempts to employ growing self-organizing map (GSOM) algorithm and continuous genetic algorithm (CGA)-based SOM (CGASOM) to improve the performance of SOM neural network (SOMnn). The proposed GSOM + CGASOM approach for SOMnn is consisted of two stages. The first stage determines the SOMnn topology using GSOM algorithm while the weights are fine-tuned by using CGASOM algorithm in the second stage. The proposed CGASOM algorithm is compared with other two clustering algorithms using four benchmark data sets, Iris, Wine, Vowel, and Glass. The simulation results indicate that CGASOM algorithm is able to find the better solution. Additionally, the proposed approach has been also employed to grade Lithium-ion cells and characterize the quality inspection rules. The results can assist the battery manufacturers to improve the quality and decrease the costs of battery design and manufacturing.     

Artificial neural network and fuzzy expert system comparison for prediction of performance and emission parameters on a gasoline engine

This study is deals with artificial neural network (ANN) and fuzzy expert system (FES) modelling of a gasoline engine to predict engine power, torque, specific fuel consumption and hydrocarbon emission. In this study, experimental data, which were obtained from experimental studies in a laboratory environment, have been used. Using some of the experimental data for training and testing an ANN for the engine was developed. Also the FES has been developed and realized. In this systems output parameters power, torque, specific fuel consumption and hydrocarbon emission have been determined using input parameters intake valve opening advance and engine speed. When experimental data and results obtained from ANN and FES were compared by t-test in SPSS and regression analysis in Matlab, it was determined that both groups of data are consistent with each other for p > 0.05 confidence interval and differences were statistically not significant. As a result, it has been shown that developed ANN and FES can be used reliably in automotive industry and engineering instead of experimental work.     

Application of feedforward neural network in the study of dissociated gas flow along the porous wall

This paper concerns the use of feedforward neural networks (FNN) for predicting the nondimensional velocity of the gas that flows along a porous wall. The numerical solution of partial differential equations that govern the fluid flow is applied for training and testing the FNN. The equations were solved using finite differences method by writing a FORTRAN code. The Levenberg–Marquardt algorithm is used to train the neural network. The optimal FNN architecture was determined. The FNN predicted values are in accordance with the values obtained by the finite difference method (FDM). The performance of the neural network model was assessed through the correlation coefficient (r), mean absolute error (MAE) and mean square error (MSE). The respective values of r, MAE and MSE for the testing data are 0.9999, 0.0025 and 1.9998 · 10^?5.     

Artificial neural networks for earthquake prediction using time series magnitude data or Seismic Electric Signals

The aim of this study is to evaluate the performance of artificial neural networks in predicting earthquakes occurring in the region of Greece with the use of different types of input data. More specifically, two different case studies are considered: the first concerns the prediction of the earthquake magnitude (M) of the following day and the second the prediction of the magnitude of the impending seismic event following the occurrence of pre-seismic signals, the so-called Seismic Electric Signals (SES), which are believed to occur prior to an earthquake, as well as the time lag between the SES and the seismic event itself. The neural network developed for the first case study used only time series magnitude data as input with the output being the magnitude of the following day. The resulting accuracy rate was 80.55% for all seismic events, but only 58.02% for the major seismic events (M ? 5.2 on the Richter scale). Our second case study for earthquake prediction uses SES as input data to the neural networks developed. This case study is separated in two parts with the differentiating element being the way of constructing the missing SES. In the first part, where the missing SES were constructed randomly for all the seismic events, the resulting accuracy rates for the magnitude of upcoming seismic events were just over 60%. In the second part, where the missing SES were constructed for the major seismic events (M ? 5.0 on the Richter scale) only by the use of neural networks reversely, the resulting accuracy rate by predicting only the magnitude was 84.01%, and by predicting both the magnitude and time lag was 83.56% for the magnitude and 92.96% for the time lag. Based on the results we conclude that, when the neural networks are trained by using the appropriate data they are able to generalise and predict unknown seismic events relatively accurately.     

Performance of radial basis and LM-feed forward artificial neural networks for predicting daily watershed runoff

This study investigated the effects of upstream stations’ flow records on the performance of artificial neural network (ANN) models for predicting daily watershed runoff. As a comparison, a multiple linear regression (MLR) analysis was also examined using various statistical indices. Five streamflow measuring stations on the Cahaba River, Alabama, were selected as case studies. Two different ANN models, multi layer feed forward neural network using Levenberg–Marquardt learning algorithm (LMFF) and radial basis function (RBF), were introduced in this paper. These models were then used to forecast one day ahead streamflows. The correlation analysis was applied for determining the architecture of each ANN model in terms of input variables. Several statistical criteria (RMSE, MAE and coefficient of correlation) were used to check the model accuracy in comparison with the observed data by means of K-fold cross validation method. Additionally, residual analysis was applied for the model results. The comparison results revealed that using upstream records could significantly increase the accuracy of ANN and MLR models in predicting daily stream flows (by around 30%). The comparison of the prediction accuracy of both ANN models (LMFF and RBF) and linear regression method indicated that the ANN approaches were more accurate than the MLR in predicting streamflow dynamics. The LMFF model was able to improve the average of root mean square error (RMSE_ave) and average of mean absolute percentage error (MAPE_ave) values of the multiple linear regression forecasts by about 18% and 21%, respectively. In spite of the fact that the RBF model acted better for predicting the highest range of flow rate (flood events, RMSE_ave/RBF = 26.8 m³/s vs. RMSE_ave/LMFF = 40.2 m³/s), in general, the results suggested that the LMFF method was somehow superior to the RBF method in predicting watershed runoff (RMSE/LMFF = 18.8 m³/s vs. RMSE/RBF = 19.2 m³/s). Eventually, statistical differences between measured and predicted medians were evaluated using Mann-Whitney test, and differences in variances were evaluated using the Levene's test.     

Analysis of flow patterns in a patient-specific thoracic aortic aneurysm model

In this study, a newly developed two-equation transitional model was employed for the prediction of blood flow patterns in a thoracic aortic aneurysm (TAA) where the growth and progression are closely linked to low and oscillating wall shear stresses. Laminar–turbulent transition in the dilated vessel can alter the flow structure, shear stress and pressure distribution within the aneurysm. A patient-specific TAA model was reconstructed from magnetic-resonance (MR) images and measured velocity waveform was used as the inflow condition. Laminar flow and a correlation-based transitional version of Menter’s hybrid k ? ?/k ? ω Shear Stress Transport (SST Tran) model were implemented in pulsatile simulations from which WSS distribution was obtained throughout a cardiac cycle and velocity profiles were compared with MR measurements. The correlation-based transitional model was found to produce results in closer agreement with the MR data than the laminar flow simulation.     

Extension of a hybrid thermal LBE scheme for large-eddy simulations of turbulent convective flows

Following the work of Lallemand and Luo [Lallemand P, Luo L-S. Theory of the lattice Boltzmann method: acoustic and thermal properties in two and three dimensions. Phys Rev E 2003;68:036706] we validate, apply and extend the hybrid thermal lattice Boltzmann scheme (HTLBE) by a large-eddy approach to simulate turbulent convective flows. For the mass and momentum equations, a multiple-relaxation-time LBE scheme is used while the heat equation is solved numerically by a finite difference scheme. We extend the hybrid model by a Smagorinsky subgrid scale model for both the fluid flow and the heat flux. Validation studies are presented for laminar and turbulent natural convection in a cavity at various Rayleigh numbers up to 5 × 10¹⁰ for Pr = 0.71 using a serial code in 2D and a parallel code in 3D, respectively. Correlations of the Nusselt number are discussed and compared to benchmark data. As an application we simulated forced convection in a building with inner courtyard at Re = 50 000.     

Artificial neural network approaches for prediction of backwater through arched bridge constrictions

This paper presents the findings of laboratory model testing of arched bridge constrictions in a rectangular open channel flume whose bed slope was fixed at zero. Four different types of arched bridge models, namely single opening semi-circular arch (SOSC), multiple opening semi-circular arch (MOSC), single opening elliptic arch (SOE), and multiple opening elliptic arch (MOE), were used in the testing program. The normal crossing (ϕ = 0), and five different skew angles (ϕ = 10°, 20°, 30°, 40°, and 50°) were tested for each type of arched bridge model. The main aim of this study is to develop a suitable model for estimating backwater through arched bridge constrictions with normal and skewed crossings. Therefore, different artificial neural network approaches, namely multi-layer perceptron (MLP), radial basis neural network (RBNN), generalized regression neural network (GRNN), and multi-linear and multi-nonlinear regression models, MLR and MNLR, respectively were used. Results of these experimental studies were compared with those obtained by the MLP, RBNN, GRNN, MLR, and MNLR approaches. The MLP produced more accurate predictions than those of the others.     

Brain processing of vocal sounds in advertising: A functional magnetic resonance imaging (fMRI) study

Using functional magnetic resonance imaging (fMRI), this study aimed at investigating the neural mechanisms associated with human and non-human sounds’ perception in advertising. The study employed a block design paradigm in which participants heard human versus non-human sounds in different sets of advertisements. The results showed that, compared to nonhuman sounds, human sounds elicited greater activation in several areas in or around the primary auditory cortex (t > 5.16, p < 0.001). This result suggests that different types of sounds are processed in different functional brain pathways. The existence of voice-selective areas in the brain lends strong support to the face perception neurocognitive model which proposes that visual, affective and linguistic information are processed in different cortical regions in the brain.     

Evaluation of a non-point source pollution model,AnnAGNPS, in a tropical watershed

Impaired water quality caused by human activity and the spread of invasive plant and animal species has been identified as a major factor of degradation of coastal ecosystems in the tropics. The main goal of this study was to evaluate the performance of AnnAGNPS (Annualized Non-Point Source Pollution Model), in simulating runoff and soil erosion in a 48 km² watershed located on the Island of Kauai, Hawaii. The model was calibrated and validated using 2 years of observed stream flow and sediment load data. Alternative scenarios of spatial rainfall distribution and canopy interception were evaluated. Monthly runoff volumes predicted by AnnAGNPS compared well with the measured data (R² = 0.90, P < 0.05); however, up to 60% difference between the actual and simulated runoff were observed during the driest months (May and July). Prediction of daily runoff was less accurate (R² = 0.55, P < 0.05). Predicted and observed sediment yield on a daily basis was poorly correlated (R² = 0.5, P < 0.05). For the events of small magnitude, the model generally overestimated sediment yield, while the opposite was true for larger events. Total monthly sediment yield varied within 50% of the observed values, except for May 2004. Among the input parameters the model was most sensitive to the values of ground residue cover and canopy cover. It was found that approximately one third of the watershed area had low sediment yield (0–1 t ha⁻¹ y⁻¹), and presented limited erosion threat. However, 5% of the area had sediment yields in excess of 5 t ha⁻¹ y⁻¹. Overall, the model performed reasonably well, and it can be used as a management tool on tropical watersheds to estimate and compare sediment loads, and identify “hot spots” on the landscape.