Optimizing neuro-fuzzy modules for data fusion of vehicular navigation systems using temporal cross-validation

Noureldin, Aboelmagd; El-Shafie, Ahmed; Taha, Mahmoud Reda

doi:10.1016/j.engappai.2006.03.002

Cited by 65 publications

(40 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several methods for implementing the cross-validation theory were proposed in the literature; however, the essence of all these methods is similar [15]. Cross-validation method, basically, classifies the whole data set into 2 groups as training and test data.…”

Section: Explanation Of the Cross-validation Proceduresmentioning

confidence: 99%

Adaptive Neuro-Fuzzy Inference System in Predicting the Success of Student’s in a Particular Course

Kaynak¹,

Evirgen²,

Kaynak³

2014

IJCTE

View full text Add to dashboard Cite

Abstract-Students are required to choose a certain number of elective courses for next semester. One of the factors influencing the course selection of the students is their grade in the course. The grades that students will get from the course at the end of the semester depend on many factors and includes uncertainties. The student's gpa, gender and grades of related courses are the parameters that can be obtained to eliminate this uncertainty. However, the parameters such as student's psychological state, etc. are difficult to obtain, and will eventually have a large impact on his/her grade at the end of the semester. Estimate implementation depends on many factors and the degree that these factors affect the estimation is uncertain. In this study, using adaptive neuro-fuzzy model, the estimation of the score range that the student will complete the courses s/he requests is analysed and an average result of ±0.36 points is found.

show abstract

Section: Explanation Of the Cross-validation Proceduresmentioning

confidence: 99%

Adaptive Neuro-Fuzzy Inference System in Predicting the Success of Student’s in a Particular Course

Kaynak¹,

Evirgen²,

Kaynak³

2014

IJCTE

View full text Add to dashboard Cite

show abstract

“…Firstly, conventional methods (CMs) such as Auto Regression (AG), Moving Average (MA) and Auto Regression Moving Average (ARMA) have been examined for several case studies and show potential for accurate forecasting for medium stream-flow classes (Billings, 2013;Chen and Dyke, 2007;Clark et al, 2008;Husain, 1985;Kalman and others, 1960;Moradkhani et al, 2005;Noureldin et al, 2007;Schreider et al, 2001;Valipour et al, 2012;Veiga et al, 2014). However, it has been reported that 15 there are several drawbacks in developing these models (Clark et al, 2008;El-Shafie et al, 2012;Husain, 1985;Ju et al, 2009;Maier et al, 2004;Noureldin et al, 2007Noureldin et al, , 2011Schreider et al, 2001). The main meagreness that associated to the application of CMs methods for developing the forecasting model for stream-flow is the stipulation to integrate it with a pre-formulation of the trustful stochastic model to ascertain the source of uncertainty for the model input and output.…”

Section: Problem Statementmentioning

confidence: 99%

Acclimatizing Fast Orthogonal Search (FOS) Model for River Stream-flow Forecasting

Osman

Allawi

Afan

et al. 2016

Preprint

Self Cite

View full text Add to dashboard Cite

Abstract. River stream-flow is well-thought-out as an essential element in the hydrology studies, especially for reservoir management. Forecasting river stream-flow is the key for the hydrologists in 10 proposing certain short or long-term planning and management for water resources system. In fact, developing stream-flow forecasting models are generally categorized into two main classes; process and data-driven model. Different model techniques based on empirical methods, such as stochastic model or regression model, more recently, Artificial Intelligent (AI) models have been examined and could provide accurate stream-15 flow forecasting. However, AI models experienced crucial difficulty is the necessity to utilize appropriate pre-processing methods for the raw data. In addition, the AI model should be augmented with proper optimization model to adjust the model parameters to achieve the optimal accuracy.In this paper, a novel model namely; Fast Orthogonal Search (FOS) model is proposed to develop river stream-flow forecasting. FOS is basically structured for recognizing the difference equation and its 20 functional expression model for the mapping between the model input and output. The major advantage of using FOS is the waiver of the requirement of data pre-processing and optimization model for model parameters adjustment as these procedures are performed implicitly inside FOS. In addition, pole-zero cancellation procedure within FOS process can detect the over-fitted models and avoid them.Hydrol. Earth Syst. Sci. Discuss., doi:10.5194/hess-2016Discuss., doi:10.5194/hess- -347, 2016 Manuscript under review for journal Hydrol. Earth Syst. Sci. 2The proposed FOS method was adopted in this research to perform stream-flow forecasting model at Aswan High Dam using monthly basis for130 years. Results showed outstanding performance for streamflow forecasting accuracy compared to other AI models developed during the last 10 years.

show abstract

“…Neuro-fuzzy system has been proved to have significant results in modeling nonlinear functions. Neuro-fuzzy system has been used frequently in the literature as fishing predictions [23], vehicular navigation [24], identifying the turbine speed dynamics [25], radio frequency power amplifier linearization [26], microwave application [27], image denoising [28,29], prediction in cleaning with high pressure water [30], sensor calibration [31], fetal electrocardiogram extraction from ECG signal captured from mother [32], and identification of normal and glaucomatous eyes [33].…”

Section: Neuro-fuzzy-based Combinermentioning

confidence: 99%

Gait Recognition Based on Invariant Leg Classification Using a Neuro-Fuzzy Algorithm as the Fusion Method

Yazdi

Fariman

Roohi

2012

ISRN Artificial Intelligence

View full text Add to dashboard Cite

This paper presents a human gait recognition algorithm based on a leg gesture separation. Main innovation in this paper is gait recognition using leg gesture classification which is invariant to covariate conditions during walking sequence and just focuses on underbody motions and a neuro-fuzzy combiner classifier (NFCC) which derives a high precision recognition system. At the end, performance of the proposed algorithm has been validated by using the HumanID Gait Challenge data set (HGCD), the largest gait benchmarking data set with 122 objects with different realistic parameters including viewpoint, shoe, surface, carrying condition, and time. And it has been compared to recent algorithm of gait recognition.

show abstract

Optimizing neuro-fuzzy modules for data fusion of vehicular navigation systems using temporal cross-validation

Cited by 65 publications

References 29 publications

Adaptive Neuro-Fuzzy Inference System in Predicting the Success of Student’s in a Particular Course

Adaptive Neuro-Fuzzy Inference System in Predicting the Success of Student’s in a Particular Course

Acclimatizing Fast Orthogonal Search (FOS) Model for River Stream-flow Forecasting

Gait Recognition Based on Invariant Leg Classification Using a Neuro-Fuzzy Algorithm as the Fusion Method

Contact Info

Product

Resources

About