scholarly journals Chronic Disease Prediction Using Character-Recurrent Neural Network in The Presence of Missing Information

2019 ◽  
Vol 9 (10) ◽  
pp. 2170 ◽  
Author(s):  
Changgyun Kim ◽  
Youngdoo Son ◽  
Sekyoung Youm
Keyword(s):  
Neural Network ◽  
Chronic Diseases ◽  
Recurrent Neural Network ◽  
Multilayer Perceptron ◽  
Missing Values ◽  
Health And Nutrition ◽  
Partially Observed ◽  
Data Points ◽  
Multilayer Perceptron Network ◽  
The Relationship

The aim of this study was to predict chronic diseases in individual patients using a character-recurrent neural network (Char-RNN), which is a deep learning model that treats data in each class as a word when a large portion of its input values is missing. An advantage of Char-RNN is that it does not require any additional imputation method because it implicitly infers missing values considering the relationship with nearby data points. We applied Char-RNN to classify cases in the Korea National Health and Nutrition Examination Survey (KNHANES) VI as normal status and five chronic diseases: hypertension, stroke, angina pectoris, myocardial infarction, and diabetes mellitus. We also employed a multilayer perceptron network for the same task for comparison. The results show higher accuracy for Char-RNN than for the conventional multilayer perceptron model. Char-RNN showed remarkable performance in finding patients with hypertension and stroke. The present study utilized the KNHANES VI data to demonstrate a practical approach to predicting and managing chronic diseases with partially observed information.

scholarly journals Modeling Judges’ Scores in Artistic Gymnastics

2019 ◽  
Vol 12 (1) ◽  
pp. 1-9
Author(s):  
Melanie Mack ◽  
Maximilian Bryan ◽  
Gerhard Heyer ◽  
Thomas Heinen
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Evaluation Process ◽  
Model Calculations ◽  
Kinematic Data ◽  
Complete Dataset ◽  
Exploratory Approach ◽  
Movement Kinematic ◽  
Alternative Approaches ◽  
The Relationship

Background: In artistic gymnastics, performance is observed and evaluated by judges based on criteria defined in the code of points. However, there is a manifold of influences discussed in the literature that could potentially bias the judges’ evaluations in artistic gymnastics. In this context, several authors claim the necessity for alternative approaches to judging gymnastics utilizing biomechanical methods. Objective: The aim of this study was to develop and evaluate a model-based approach to judge gymnastics performance based on quantitative kinematic data of the performed skills. Methods: Four different model variants based on kinematic similarity calculated by a multivariate exploratory approach and the Recurrent Neural Network method were used to evaluate the relationship between the movement kinematics and the judges’ scores. The complete dataset consisted of movement kinematic data and judgment scores of a total of N = 173 trials of three different skills and routines from women’s artistic gymnastics. Results: The results exhibit a significant relationship between the predicted score and the actual score for six of the twelve model calculations. The different model variants yielded a different prediction performance in general across all skills and also in terms of the different skills. In particular, only the Recurrent Neural Network model exhibited significant correlation values between the actual and the predicted scores for all three investigated skills. Conclusion: The results were discussed in terms of the differences of the models as well as the various factors that might play a role in the evaluation process.

scholarly journals A Layered Recurrent Neural Network for Imputing Air Pollutants Missing Data and Prediction of NO 2, O 3, PM 10, and PM 2.5

2020 ◽  
Author(s):  
Hamza Turabieh ◽  
Alaa Sheta ◽  
Malik Braik ◽  
Elvira Kovač-Andrić
Keyword(s):  
Neural Network ◽  
Air Pollution ◽  
Air Quality ◽  
Recurrent Neural Network ◽  
Missing Values ◽  
Prediction Models ◽  
Air Pollutant ◽  
Forecasting Models ◽  
Monitoring Strategies ◽  
Artificial Neural Network Ann

To fulfill the national air quality standards, many countries have created emissions monitoring strategies on air quality. Nowadays, policymakers and air quality executives depend on scientific computation and prediction models to monitor that cause air pollution, especially in industrial cities. Air pollution is considered one of the primary problems that could cause many human health problems such as asthma, damage to lungs, and even death. In this study, we present investigated development forecasting models for air pollutant attributes including Particulate Matters (PM2.5, PM10), ground-level Ozone (O3), and Nitrogen Oxides (NO2). The dataset used was collected from Dubrovnik city, which is located in the east of Croatia. The collected data has missing values. Therefore, we suggested the use of a Layered Recurrent Neural Network (L-RNN) to impute the missing value(s) of air pollutant attributes then build forecasting models. We adopted four regression models to forecast air pollutant attributes, which are: Multiple Linear Regression (MLR), Decision Tree Regression (DTR), Artificial Neural Network (ANN) and L-RNN. The obtained results show that the proposed method enhances the overall performance of other forecasting models.

scholarly journals Prediction of PCR amplification from primer and template sequences using recurrent neural network

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Kotetsu Kayama ◽  
Miyuki Kanno ◽  
Naoto Chisaki ◽  
Misaki Tanaka ◽  
Reika Yao ◽  
...  
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Pcr Amplification ◽  
Nucleotide Sequences ◽  
Specific Primer ◽  
First Report ◽  
Novel Method ◽  
Primer Sequence ◽  
Dna Template ◽  
The Relationship

AbstractWe have developed a novel method to predict the success of PCR amplification for a specific primer set and DNA template based on the relationship between the primer sequence and the template. To perform the prediction using a recurrent neural network, the usual double-stranded formation between the primer and template nucleotide sequences was herein expressed as a five-lettered word. The set of words (pseudo-sentences) was placed to indicate the success or failure of PCR targeted to learn recurrent neural network (RNN). After learning pseudo-sentences, RNN predicted PCR results from pseudo-sentences which were created by primer and template sequences with 70% accuracy. These results suggest that PCR results could be predicted using learned RNN and the trained RNN could be used as a replacement for preliminary PCR experimentation. This is the first report which utilized the application of neural network for primer design and prediction of PCR results.

scholarly journals RnRTD: Intelligent Approach Based on the Relationship-Driven Neural Network and Restricted Tensor Decomposition for Multiple Accusation Judgment in Legal Cases

2019 ◽  
Vol 2019 ◽  
pp. 1-18 ◽  
Author(s):  
Xiaoding Guo ◽  
Hongli Zhang ◽  
Lin Ye ◽  
Shang Li
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Recurrent Neural Network ◽  
Feature Space ◽  
Tensor Decomposition ◽  
Target Feature ◽  
Legal Cases ◽  
Legal Case ◽  
The Relationship

The use of intelligent judgment technology to assist in judgment is an inevitable trend in the development of judgment in contemporary social legal cases. Using big data and artificial intelligence technology to accurately determine multiple accusations involved in legal cases is an urgent problem to be solved in legal judgment. The key to solving these problems lies in two points, namely, (1) characterization of legal cases and (2) classification and prediction of legal case data. Traditional methods of entity characterization rely on feature extraction, which is often based on vocabulary and syntax information. Thus, traditional entity characterization often requires extensive energy and has poor generality, thus introducing a large amount of computation and limitation to subsequent classification algorithms. This study proposes an intelligent judgment approach called RnRTD, which is based on the relationship-driven recurrent neural network (rdRNN) and restricted tensor decomposition (RTD). We represent legal cases as tensors and propose an innovative RTD method. RTD has low dependence on vocabulary and syntax and extracts the feature structure that is most favorable for improving the accuracy of the subsequent classification algorithm. RTD maps the tensors, which represent legal cases, into a specific feature space and transforms the original tensor into a core tensor and its corresponding factor matrices. This study uses rdRNN to continuously update and optimize the constraints in RTD so that rdRNN can have the best legal case classification effect in the target feature space generated by RTD. Simultaneously, rdRNN sets up a new gate and a similar case list to represent the interaction between legal cases. In comparison with traditional feature extraction methods, our proposed RTD method is less expensive and more universal in the characterization of legal cases. Moreover, rdRNN with an RTD layer has a better effect than the recurrent neural network (RNN) only on the classification and prediction of multiple accusations in legal cases. Experiments show that compared with previous approaches, our method achieves higher accuracy in the classification and prediction of multiple accusations in legal cases, and our algorithm is more interpretable.

scholarly journals Feedback Based Adaptive Recurrent Neural Network for Cancer Detection using Gene Data Pattern

2019 ◽  
Vol 9 (2) ◽  
pp. 2999-3006
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Missing Values ◽  
Data Augmentation ◽  
Research Work ◽  
Reduction Process ◽  
Computation Time ◽  
Activation Function ◽  
Vital Role ◽  
Medical Community

Cancer detecting technology plays a vital role in the medical community. Researches have shown that patients that are affected by cancer carry same type of genetic patterns in their DNA. With this in mind, this research work concentrates on analysing gene pattern for detecting cancer using deep learning algorithms. The Feedback based Adaptive Recurrent Neural Network (FA-RNN) approach is designed to classify and analyse the gene pattern recognition. The data augmentation is done to improve the quality of the input data from COSMIC dataset which includes the detection of missing values, removing the noise present in input using multiple imputations and reducing higher base value can be done using dimensionality reduction process. After obtaining the improved dataset, the training phase begins by estimating the exact weight value of feedback layer using feedback weight loop calculation technique to lessen number of repetition during training. Moreover, the error calculation is done to evaluate the exact weight values of feedback layer used for classification. Finally the classification is done by selecting the next appropriate hidden neuron using the neuron selection activation function. The performance of the Feedback based Adaptive Recurrent Neural Network technique can be analysed using the evaluation metrics accuracy, computation time and Root Mean Square Error (RMSE) and the attained results are compared with the Recursive Neural Network(RNN) and Convolutional Neural Network(CNN) algorithms. The obtained results such as higher accuracy, reduced RMSE and less computation time in Feedback based Adaptive Recurrent Neural Network indicates that it performs the enhanced operation than CNN and RNN.

scholarly journals Data Classification with an Improved Weightless Neural Network

2017 ◽  
Vol 1 (1) ◽  
pp. 17-34
Author(s):  
W.K. Lai ◽  
G. Coghill
Keyword(s):  
Neural Network ◽  
Multilayer Perceptron ◽  
Hardware Implementation ◽  
Network Models ◽  
Data Classification ◽  
Data Sets ◽  
Neural Network Models ◽  
Multilayer Perceptron Network ◽  
Pass Through

This paper examines the performance of an enhanced weightless neural network as a classifier. Like all earlier weightless neural network models, this network learns in one pass through the data This new weightless neural network has shown significant gains in the classifiction accuracy over the earlier Deterministic RAN Network (DARN), on a variety of problems. In addition, some comparisons between the DARN and the proposed network are presented. This will also include some evidence on how a standard Multilayer Perceptron network would behave on the same data sets. Finally, hardware implementation issues are discussed.

Axial Compressor Performance Map Prediction Using Artificial Neural Network

2007 ◽  
Author(s):  
Kaveh Ghorbanian ◽  
Mohammad Gholamrezaei
Keyword(s):  
Neural Network ◽  
Experimental Data ◽  
Artificial Neural Network ◽  
Multilayer Perceptron ◽  
General Regression Neural Network ◽  
Performance Map ◽  
Multilayer Perceptron Network ◽  
Compressor Performance ◽  
Artificial Neural ◽  
General Regression

The application of artificial neural network to compressor performance map prediction is investigated. Different types of artificial neural network such as multilayer perceptron network, radial basis function network, general regression neural network, and a rotated general regression neural network proposed by the authors are considered. Two different models are utilized in simulating the performance map. The results indicate that while the rotated general regression neural network has the least mean error and best agreement to the experimental data, it is however limited to curve fitting application. On the other hand, if one considers a tool for curve fitting as well as for interpolation and extrapolation applications, multilayer perceptron network technique is the most powerful candidate. Further, the compressor efficiency based on the multilayer perceptron network technique is determined. Excellent agreement between the predictions and the experimental data is obtained.

scholarly journals VS-GRU: A Variable Sensitive Gated Recurrent Neural Network for Multivariate Time Series with Massive Missing Values

2019 ◽  
Vol 9 (15) ◽  
pp. 3041 ◽  
Author(s):  
Qianting Li ◽  
Yong Xu
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Recurrent Neural Network ◽  
Real World ◽  
Missing Values ◽  
State Of The Art ◽  
Multivariate Time Series ◽  
Training Procedure ◽  
Model Training ◽  
Mimic Iii

Multivariate time series are often accompanied with missing values, especially in clinical time series, which usually contain more than 80% of missing data, and the missing rates between different variables vary widely. However, few studies address these missing rate differences and extract univariate missing patterns simultaneously before mixing them in the model training procedure. In this paper, we propose a novel recurrent neural network called variable sensitive GRU (VS-GRU), which utilizes the different missing rate of each variable as another input and learns the feature of different variables separately, reducing the harmful impact of variables with high missing rates. Experiments show that VS-GRU outperforms the state-of-the-art method in two real-world clinical datasets (MIMIC-III, PhysioNet).

A new car-following model considering recurrent neural network

2019 ◽  
Vol 33 (26) ◽  
pp. 1950304 ◽  
Author(s):  
Chen Hua
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Relative Velocity ◽  
Road Traffic ◽  
Safe Distance ◽  
Velocity Difference ◽  
Car Following ◽  
Depth Analysis ◽  
Car Following Model ◽  
The Relationship

A new car-following model is proposed based on recurrent neural network (RNN) to effectively describe the state change and road traffic congestion while the vehicle is moving. The model firstly gives a full velocity difference car-following model according to the driver’s reaction sensitivity and relative velocity, and then takes the vehicle position and velocity as the input parameters to optimize the safe distance between the front and rear vehicles in the car-following model based on RNN model. Finally, the effectiveness of the above model is validated by building a simulation experiment platform, and an in-depth analysis is conducted on the relationship among influencing factors, e.g., relative velocity, reaction sensitivity, headway, etc. The results reveal that, compared with traditional car-following models, the model can quickly analyze the relationship between initial position and velocity of the vehicle in a shorter time and thus obtain a smaller safe distance. In the case of small velocity difference between the front and rear vehicles, the running velocity of the front and rear vehicles is relatively stable, which is conducive to maintaining the headway.

scholarly journals Improving upon the efficiency of complete case analysis when covariates are MNAR

Biostatistics ◽  
2014 ◽  
Vol 15 (4) ◽  
pp. 719-730 ◽  
Author(s):  
Jonathan W. Bartlett ◽  
James R. Carpenter ◽  
Kate Tilling ◽  
Stijn Vansteelandt
Keyword(s):  
Missing Values ◽  
Case Analysis ◽  
Missing At Random ◽  
Complete Case Analysis ◽  
Complete Case ◽  
Independence Assumption ◽  
Health And Nutrition ◽  
Conditional Independence Assumption ◽  
Partially Observed ◽  
The Us

Abstract Missing values in covariates of regression models are a pervasive problem in empirical research. Popular approaches for analyzing partially observed datasets include complete case analysis (CCA), multiple imputation (MI), and inverse probability weighting (IPW). In the case of missing covariate values, these methods (as typically implemented) are valid under different missingness assumptions. In particular, CCA is valid under missing not at random (MNAR) mechanisms in which missingness in a covariate depends on the value of that covariate, but is conditionally independent of outcome. In this paper, we argue that in some settings such an assumption is more plausible than the missing at random assumption underpinning most implementations of MI and IPW. When the former assumption holds, although CCA gives consistent estimates, it does not make use of all observed information. We therefore propose an augmented CCA approach which makes the same conditional independence assumption for missingness as CCA, but which improves efficiency through specification of an additional model for the probability of missingness, given the fully observed variables. The new method is evaluated using simulations and illustrated through application to data on reported alcohol consumption and blood pressure from the US National Health and Nutrition Examination Survey, in which data are likely MNAR independent of outcome.

Sign in / Sign up

Export Citation Format

Share Document