scholarly journals Bootstrapping a Neural Morphological Generator from Morphological Analyzer Output for Inuktitut

2019 ◽  
Vol 2 (1) ◽  
Author(s):  
Jeffrey Micher
Keyword(s):  
Neural Network ◽  
Training Data ◽  
Data Set ◽  
Set Size ◽  
The Neural Network ◽  
Surface Character ◽  
Finite State ◽  
Character Sequences ◽  
Finite State Transducer

We present a method for building a morphological generator from the output of an existing analyzer for Inuktitut, in the absence of a two-way finite state transducer which would normally provide this functionality. We make use of a sequence to sequence neural network which “translates” underlying Inuktitut morpheme sequences into surface character sequences. The neural network uses only the previous and the following morphemes as context. We report a morpheme accuracy of approximately 86%. We are able to increase this accuracy slightly by passing deep morphemes directly to output for unknown morphemes. We do not see significant improvement when increasing training data set size, and postulate possible causes for this.

Aerodynamic Prediction on the Off-Design Performance of a S-CO2 Turbine Based on Deep Learning

2021 ◽  
Author(s):  
Yuqi Wang ◽  
Tianyuan Liu ◽  
Di Zhang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Performance Prediction ◽  
Aerodynamic Performance ◽  
Operating Conditions ◽  
Training Data ◽  
Brayton Cycle ◽  
Data Set ◽  
Set Size ◽  
The Mean

Abstract The research on the supercritical carbon dioxide (S-CO2) Brayton cycle has gradually become a hot spot in recent years. The off-design performance of turbine is an important reference for analyzing the variable operating conditions of the cycle. With the development of deep learning technology, the research of surrogate models based on neural network has received extensive attention. In order to improve the inefficiency in traditional off-design analyses, this research establishes a data-driven deep learning off-design aerodynamic prediction model for a S-CO2 centrifugal turbine, which is based on a deep convolutional neural network. The network can rapidly and adaptively provide dynamic aerodynamic performance prediction results for varying blade profiles and operating conditions. Meanwhile, it can illustrate the mechanism based on the field reconstruction results for the generated aerodynamic performance. The training results show that the off-design aerodynamic prediction convolutional neural network (OAP-CNN) has reduced the mean and maximum error of efficiency prediction compared with the traditional Gaussian Process Regression (GPR) and Artificial Neural Network (ANN). Aiming at the off-design conditions, the pressure and temperature distributions with acceptable error can be obtained without a CFD calculation. Besides, the influence of off-design parameters on the efficiency and power can be conveniently acquired, thus providing the reference for an optimized operation strategy. Analyzing the sensitivity of AOP-CNN to training data set size, the prediction accuracy is acceptable when the percentage of training samples exceeds 50%. The minimum error appears when the training data set size is 0.8. The mean and maximum errors are respectively 1.46% and 6.42%. In summary, this research provides a precise and fast aerodynamic performance prediction model in the analyses of off-design conditions for S-CO2 turbomachinery and Brayton cycle.

System Identification of UAV Alap-Alap Using Back Propagation Neural Network

2013 ◽  
Vol 373-375 ◽  
pp. 1212-1219
Author(s):  
Afrias Sarotama ◽  
Benyamin Kusumoputro
Keyword(s):  
Neural Network ◽  
Back Propagation ◽  
Back Propagation Neural Network ◽  
Training Data ◽  
Data Sets ◽  
Input Output ◽  
Data Set ◽  
Flight Data ◽  
The Neural Network ◽  
Aerial Vehicle

A good model is necessary in order to design a controller of a system off-line. It is especially beneficial in the implementation of new advanced control schemes in Unmanned Aerial Vehicle (UAV). Considering the safety and benefit of an off-line tuning of the UAV controllers, this paper identifies a dynamic MIMO UAV nonlinear system which is derived based on the collection of input-output data taken from a test flights (36250 samples data). These input-output sample flight data are grouped into two flight data sets. The first flight data set, a chirp signal, is used for training the neural network in order to determine parameters (weights) for the network. Validation of the network is performed using the second data set, which is not used for training, and is a representation of UAV circular flight movement. An artificial neural network is trained using the training data set and thereafter the network is excited by the second set input data set. The predicted outputs based on our proposed Neural Network model is similar to the desired outputs (roll, pitch and yaw) which has been produced by real UAV system.

scholarly journals USING OF PROJECTIVE TRANSFORMATION IN CREATING NEURAL NETWORK DATA SET

2018 ◽  
pp. 73-78
Author(s):  
V. V. Kuzmina ◽  
A. V. Khamukhin ◽  
A. I. Kononova
Keyword(s):  
Neural Network ◽  
Projective Transformation ◽  
Training Data ◽  
Network Data ◽  
License Plate ◽  
Data Set ◽  
Network Training ◽  
The Neural Network ◽  
Recognition Quality ◽  
Long Time

An experience of the neural network data set creation automation, which is used for license plate recognition, has been presented. The main problem of neural network training with data, obtained by nature filming is that collecting require amount of data takes a long time, beside this neural network does not effectively recognizer rare license plate formats after training. The main objective of the work is to improve recognition quality and training speed of the neural network. To achieve this objective, training data set is formed from automatically generated license plate images. Projective transformation are used for filming distortion imitation. The data set, generated in this way, includes all license plate standards, and the rare kinds percentage is enough to effectively recognize them. Using of the presented generator allows not only to significantly accelerate training data set creation, but also to improve rarely used standards of license plates recognition quality.

scholarly journals Does the Zero Carry Essential Information for Artificial Neural Network learning to simulate the contaminant transport in Urban Areas?

2021 ◽  
Vol 2090 (1) ◽  
pp. 012027
Author(s):  
M. Berendt-Marchel ◽  
A. Wawrzynczak
Keyword(s):  
Neural Network ◽  
Urban Areas ◽  
Training Data ◽  
Industrial Complex ◽  
Dispersion Models ◽  
Contamination Source ◽  
Data Set ◽  
Essential Information ◽  
The Neural Network ◽  
Artificial Neural

Abstract The release of hazardous materials in urbanized areas is a considerable threat to human health and the environment. Therefore, it is vital to detect the contamination source quickly to limit the damage. In systems localizing the contamination source based on the measured concentrations, the dispersion models are used to compare the simulated and registered point concentrations. These models are run tens of thousands of times to find their parameters, giving the model output’s best fit to the registration. Artificial Neural Networks (ANN) can replace in localization systems the dispersion models, but first, they need to be trained on a large, diverse set of data. However, providing an ANN with a fully informative training data set leads to some computational challenges. For example, a single simulation of airborne toxin dispersion in an urban area might contain over 90% of zero concentration in the positions of the sensors. This leads to the situation when the ANN target includes a few percent positive values and many zeros. As a result, the neural network focuses on the more significant part of the set - zeros, leading to the non-adaptation of the neural network to the studied problem. Furthermore, considering the zero value of concentration in the training data set, we have to face many questions: how to include zero, scale a given interval to hide the zero in the set, and include zero values at all; or limit their number? This paper will try to answer the above questions and investigate to what extend zero carries essential information for the ANN in the contamination dispersion simulation in urban areas. For this purpose, as a testing domain, the center of London is used as in the DAPPLE experiment. Training data is generated by the Quick Urban & Industrial Complex (QUIC) Dispersion Modeling System.

scholarly journals Mimicking spectropolarimetric inversions using convolutional neural networks

2020 ◽  
Vol 644 ◽  
pp. A129 ◽  
Author(s):  
I. Milić ◽  
R. Gafeira
Keyword(s):  
Neural Network ◽  
Excellent Agreement ◽  
Model Fitting ◽  
Training Data ◽  
Machine Learning Techniques ◽  
Physical Parameters ◽  
Data Set ◽  
The Neural Network ◽  
Unseen Data ◽  
Physical Quantities

Context. Interpreting spectropolarimetric observations of the solar atmosphere takes much longer than the acquiring the data. The most important reason for this is that the model fitting, or “inversion”, used to infer physical quantities from the observations is extremely slow, because the underlying models are numerically demanding. Aims. We aim to improve the speed of the inference by using a neural network that relates input polarized spectra to the output physical parameters. Methods. We first select a subset of the data to be interpreted and infer physical quantities from corresponding spectra using a standard minimization-based inversion code. Taking these results as reliable and representative of the whole data set, we train a convolutional neural network to connect the input polarized spectra to the output physical parameters (nodes, in context of spectropolarimetric inversion). We then apply the neural network to the various other data, previously unseen to the network. As a check, we apply the referent inversion code to the unseen data and compare the fit quality and the maps of the inferred parameters between the two inversions. Results. The physical parameters inferred by the neural network show excellent agreement with the results from the inversion, and are obtained in a factor of 105 less time. Additionally, substituting the results of the neural network back in the forward model, shows excellent agreement between inferred and original spectra. Conclusions. The method we present here is very simple for implementation and extremely fast. It only requires a training data set, which can be obtained by inverting a representative subset of the observed data. Applying these (and similar) machine learning techniques will yield orders of magnitude acceleration in the routine interpretation of spectropolarimetric data.

Influence of neural network structure and data-set size on its performance in the prediction of height of growth hormone-treated patients

2016 ◽  
Vol 12 (2) ◽  
Author(s):  
Urszula Smyczyńska ◽  
Joanna Smyczyńska ◽  
Ryszard Tadeusiewicz
Keyword(s):  
Neural Network ◽  
Growth Hormone ◽  
Final Height ◽  
Training Data ◽  
Data Set ◽  
Set Size ◽  
Wide Range ◽  
Complex Models ◽  
Neural Network Structure ◽  
Hidden Neurons

AbstractIt is well known that the structure of neural network and the amount of available training data influence the accuracy of developed models; however, the exact character of this relation depends on the chosen problem. Thus, it was decided to analyze what impact these parameters have on the solution of the problem on which we work – the prediction of final height of children treated with growth hormone. It was observed that multilayer perceptron with a wide range of numbers of hidden neurons (from 1 to 100) could solve the problem almost equally well. Thus, this task seems to be rather simple, not requiring complex models. Larger networks tended to produce less accurate results and did not generalize well while working with the data not used in training. Repeating the experiment with the training data set reduced to 50% of its original content, as expected, caused a decrease in accuracy.

Abstract 268: A Convolutional Neural Network for Real-Time Discrimination of Shock-Indicated Rhythms During CPR

Circulation ◽  
2018 ◽  
Vol 138 (Suppl_2) ◽  
Author(s):  
Tetsuo Hatanaka ◽  
Hiroshi Kaneko ◽  
Aki Nagase ◽  
Seishiro Marukawa
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Sensitivity And Specificity ◽  
Binary Classification ◽  
Total Duration ◽  
Training Data ◽  
Validation Data ◽  
Data Set ◽  
The Neural Network ◽  
Fully Connected

Introduction: An interruption of chest compressions during CPR adversely affects patient outcome. Currently, however, periodical interruptions are unavoidable to assess the ECG rhythms and to give shocks for defibrillation if indicated. Evidence suggests a 5-second interruption immediately before shocks may translate into ~15% reduction of the chance of survival. The objective of this study was to build, train and validate a convolutional neural network (artificial intelligence) for detecting shock-indicated rhythms out of ECG signals corrupted with chest compression artifacts during CPR. Methods: Our convolutional neural network consisted of 7 convolutional layers, 3 pooling layers and 3 fully-connected layers for binary classification (shock-indicated vs non-shock-indicated). The input data set was a spectrogram consisting of 56 frequency-bins by 80 time-segments transformed from a 12.16-seconds ECG signal. From AEDs used for 236 patients with out-of-hospital cardiac arrest, 1,223 annotated ECG strips were extracted. Ventricular fibrillation and wide-QRS ventricular tachycardia with HR>180 beats/min were annotated as shock-indicated, and the others as non-shock-indicated. The total length of the strips was 8:49:57 (hr:min:sec) and 8:02:07 respectively for shock-indicated and non-shock-indicated rhythms. Those strips were converted into 465,102 spectrograms allowing partial overlaps and were fed into the neural network for training. The validation data set was obtained from a separate group of 225 patients, from which annotated ECG strips (total duration of 62:11:28) were extracted, yielding 43,800 spectrograms. Results: After the training, both the sensitivity and specificity of detecting shock-indicated rhythms over the training data set were 99.7% - 100% (varying with training instances). The sensitivity and specificity over the validation data set were 99.3% - 99.7% and 99.3% - 99.5%, respectively. Conclusions: The convolutional neural network has accurately and continuously evaluated the ECG rhythms during CPR, potentially obviating the need for rhythm checks for defibrillation during CPR.

Development of an Optimized Neural Network for the Detection of Pipe Defects Using a Microwave Signal

2018 ◽  
Vol 140 (4) ◽  
Author(s):  
Wissam M. Alobaidi ◽  
Entidhar A. Alkuam ◽  
Eric Sandgren
Keyword(s):  
Neural Network ◽  
Network Models ◽  
Microwave Signal ◽  
Training Data ◽  
Optimal Topology ◽  
Data Set ◽  
Optimal Weights ◽  
Future Performance ◽  
The Neural Network ◽  
Data Files

Neural network technology is applied to the detection of a pipe wall thinning (PWT) in a pipe using a microwave signal reflection as an input. The location, depth, length, and profile geometry of the PWT are predicted by the neural network from input parameters taken from the resonance frequency plots for training data generated through computer simulation. The network is optimized using an evolutionary optimization routine, using the 108 training data samples to minimize the errors produced by the neural network model. The optimizer specified not only the optimal weights for the network links but also the optimal topology for the network itself. The results demonstrate the potential of the approach in that when data files were input that were not part of the training data set, fairly accurate predictions were made by the network. The results from the initial network models can be utilized to improve the future performance of the network.

Sign in / Sign up

Export Citation Format

Share Document