scholarly journals Online Epileptic Seizure Prediction Using Phase Synchronization and Two Time Characteristics: SOP and SPH

2019 ◽  
Vol 7 (1) ◽  
pp. 16-25
Author(s):  
Hesam Shokouh Alaei ◽  
Mohammad Ali Khalilzadeh ◽  
Ali Gorji
Keyword(s):  
Epileptic Seizure ◽  
False Positive ◽  
Evaluation Method ◽  
Fuzzy Model ◽  
Seizure Prediction ◽  
Inference System ◽  
Neuro Fuzzy ◽  
Prediction Time ◽  
On Line ◽  
Labeling Method

Background: The successful prediction of epileptic seizures will significantly improve the living conditions of patients with refractory epilepsy. A proper warning impending seizure system should be resulted not only in high accuracy and low false-positive alarms but also in suitable prediction time. Methods: In this research, the mean phase coherence index used as a reliable indicator for identifying the preictal period of the 14-patient Freiburg EEG dataset. In order to predict the seizures on-line, an adaptive Neuro-fuzzy model named ENFM (evolving neuro-fuzzy model) was used to classify the extracted features. The ENFM trained by a new class labeling method based on the temporal properties of a prediction characterized by two time intervals, seizure prediction horizon (SPH), and seizure occurrence period (SOP), which subsequently applied in the evaluation method. It is evident that an increase in the duration of the SPH can be more useful for the subject in preventing the irreparable consequences of the seizure, and provides adequate time to deal with the seizure. Also, a reduction in duration of the SOP can reduce the patient’s stress in the SOP interval. In this study, the optimal SOP and SPH obtained for each patient using Mamdani fuzzy inference system considering sensitivity, false-positive rate (FPR), and the two mentioned points, which generally ignored in most studies. Results: The results showed that last seizure, as well as 14-hour interictal period of each patient, were predicted on-line without false negative alarms: the average yielding of sensitivity by 100%, the average FPR by 0.13 per hour and the average prediction time by 30 minutes. Conclusion: Based on the obtained results, such a data-labeling method for ENFM showed promising seizure prediction for online machine learning using epileptic seizure data. Apart from that, the proposed fuzzy system can consider as an evaluation method for comparing the results of studies.

Mapping arsenic vulnerability at different spatial scales using statistical and machine learning models 

2021 ◽  
Author(s):  
Sonal Bindal
Keyword(s):  
Spatial Resolution ◽  
Spatial Data ◽  
Fuzzy Inference ◽  
Spatial Scales ◽  
Fuzzy Model ◽  
Fuzzy Regression ◽  
Percentage Error ◽  
Inference System ◽  
Neuro Fuzzy ◽  
Predictive Algorithms

<p>In the recent years, prediction modelling techniques have been widely used for modelling groundwater arsenic contamination. Determining the accuracy, performance and suitability of these different algorithms such as univariate regression (UR), fuzzy model, adaptive fuzzy regression (AFR), logistic regression (LR), adaptive neuro-fuzzy inference system (ANFIS), and hybrid random forest (HRF) models still remains a challenging task. The spatial data which are available at different scales with different cell sizes. In the current study we have tried to optimize the spatial resolution for best performance of the model selecting the best spatial resolution by testing various predictive algorithms. The model’s performance was evaluated based of the values of determination coefficient (R<sup>2</sup>), mean absolute percentage error (MAPE) and root mean square error (RMSE). The outcomes of the study indicate that using 100m × 100m spatial resolution gives best performance in most of the models. The results also state HRF model performs the best than the commonly used ANFIS and LR models.</p>

Fuzzy and neuro-fuzzy approaches to control a flexible single-link manipulator

2003 ◽  
Vol 217 (5) ◽  
pp. 387-399 ◽  
Author(s):  
B Subudhi ◽  
A S Morris
Keyword(s):  
Fuzzy Logic Controller ◽  
Fuzzy Controller ◽  
Fuzzy Model ◽  
Scale Parameters ◽  
Neuro Fuzzy ◽  
On Line ◽  
Position Regulation ◽  
Tip Position ◽  
Typical Model ◽  
Better Than

In this paper, new fuzzy and neuro-fuzzy approaches to tip position regulation of a flexible-link manipulator are presented. Firstly, a non-collocated, proportional-dervative (PD) type, fuzzy logic controller (FLC) is developed. This is shown to perform better than typical model-based controllers (LQR and PD). Following this, an adaptive neuro-fuzzy controller (NFC) is described that has been developed for situations where there is payload variability. The proposed NFC tunes the input and output scale parameters of the fuzzy controller on-line. The efficacy of the NFC has been evaluated by comparing it with a fuzzy model reference adptive controller (FMRC).

Research of Faulty Sensors Data Reconstructed for Liquid-Propellant Rocket Engines

2012 ◽  
Vol 229-231 ◽  
pp. 1449-1453 ◽  
Author(s):  
Yan Jun Li ◽  
Xiao Hui Peng ◽  
Yu Qiang Cheng ◽  
Jian Jun Wu
Keyword(s):  
Fuzzy Inference System ◽  
Fuzzy Inference ◽  
Rocket Engine ◽  
Fuzzy Model ◽  
Rocket Engines ◽  
Liquid Propellant ◽  
Inference System ◽  
Neuro Fuzzy ◽  
Faulty Sensors ◽  
Propellant Rocket

In this paper, the data of faulty sensors reconstruct algorithm of liquid-propellant rocket engine is developed based on adaptive neuro-fuzzy inference system. First, the input parameters selected for method is according to regularity criterion and the relationships between each parameter; second, adaptive neuro-fuzzy inference system is train by normal test, finally, the fuzzy mode is validated by normal data and the data of faulty sensor is reconstructed. The results indicate that this algorithm can reconstruct the data of faulty sensors accurately and show that the fuzzy model approach has good performance in faulty sensors data reconstruct for LRE.

scholarly journals A NEURO FUZZY MODEL FOR THE INVESTIGATION OF DETERIORATION OF METALLIC PIPE CONVEYING FLUID UNDER DIFFERENT PIPE BURIAL DEPTH, SOIL TYPES AND PROPERTIES

2016 ◽  
Vol 36 (1) ◽  
pp. 72-79
Author(s):  
TT Akano ◽  
OA Fakindele ◽  
HE Mgbemere ◽  
JC Amechi
Keyword(s):  
Soil Properties ◽  
Membership Function ◽  
Fuzzy Model ◽  
Soil Types ◽  
Burial Depth ◽  
Pipe Conveying Fluid ◽  
Inference System ◽  
Neuro Fuzzy ◽  
Proposed Model ◽  
Conveying Fluid

Several factors may contribute directly or indirectly to the structural failure of metallic pipes. The most important of which is corrosion. Corrosivity of pipes is not a directly measurable parameter as pipe corrosion is a very random phenomenon. The main aim of the present study is to develop a neuro-fuzzy model capable of establishing corrosion rate criterion as a function of pipe burial depth, soil types, and properties for the prediction of deterioration of metallic pipe conveying fluid. The proposed model includes a fuzzy model and the artificial neural network (ANN) to determine soil corrosivity potential (CoP) based on soil properties. The combination contains the data of linguistic variables characterising various soil properties, and learning capability of the system that constructs relationships among those soil properties and CoP. Subsequently, the artificial neuro-fuzzy inference system (ANFIS) maps each element of its input membership function to an output membership function between 0 and 1 to determine the deterioration rate (CoP) of metallic fluid-conveying-pipe. Field data from buried fluid pipes were examined to illustrate the application of the proposed model. The ultimate goal is the ability to access the current and future life of oil pipe, given a set of circumstances, and also appropriate adoptable methodology in view of a preventive maintenance measure for the pipes in a given operating environment. Results reveal that with more than 40% clay content quickens corrosion of buried fluid pipes more than any other considered factor. http://dx.doi.org/10.4314/njt.v36i1.10

scholarly journals Modeling of the Safety Climate and the Cultural Attitudes to Predict Unsafe Behaviors Using the Neuro-Fuzzy Inference System (ANFIS)

2020 ◽  
Author(s):  
Reza Pourbabaki ◽  
Zahra Beigzadeh ◽  
Behnam Haghshenas ◽  
Ali Karimi ◽  
Zahra Alaei ◽  
...  
Keyword(s):  
Fuzzy Inference System ◽  
Safety Climate ◽  
Fuzzy Inference ◽  
Fuzzy Model ◽  
Cross Sectional ◽  
Inference System ◽  
Cultural Attitudes ◽  
Neuro Fuzzy ◽  
Unsafe Behavior ◽  
Unsafe Behaviors

Background: Unsafe behavior in industries can be due to different factors. The aim of this study was to predict and model unsafe behavior using a safety atmosphere and cultural attitudes questionnaires. Methods: This study was a descriptive-analytic and cross-sectional examination that analyzed the data and predicted the unsafe behaviors of 90 construction workers using Neuro-Fuzzy Inference System (ANFIS) in MATLAB R2016a software. Results: In this study, the model of the safety atmosphere - unsafe behavior and the model of the cultural attitudes - unsafe behavior had the regression coefficients of 0.93373 and 0.9234, respectively. It showed that each of the parameters has a close relationship to the rate of the unsafe behavior. In this regard, a combination of the safety atmosphere and safety attitude parameters for the estimation of the unsafe behaviors achieved the better results with a regression coefficient of 0.9453 which indicates the direct effect of both parameters simultaneously on unsafe behavior. Conclusion: Based on the findings, it can be concluded that the neuro-fuzzy model can be used as an appropriate tool for predicting unsafe behavior in the industries.

Sign in / Sign up

Export Citation Format

Share Document