Structural Analysis with Fuzzy Data and Neural Network Based Material Description

Abstract

In the article, a new approach is presented utilizing artificial neural networks for uncertain time‐dependent structural behavior. Recurrent neural networks (RNNs) for fuzzy data can be trained by uncertain experimental data to describe arbitrary stress–strain–time dependencies. The benefit is a generalized formulation, which can be applied to describe the behavior of several materials without definition of a specific material model. Model‐free material descriptions can be used as numerical efficient material formulations within the finite element method. To perform fuzzy or fuzzy stochastic finite element analyses, a new approach is introduced. An ‐level optimization is utilized for signal computation and training of RNNs for fuzzy data. The applicability is demonstrated by means of examples.

Computer-aided diagnosis of alcoholism-related EEG signals

“…In recent years, Adeli and associates have advanced the idea that judicious combination of signal processing techniques such as wavelet transforms [37,[69][70][71][72][73], nonlinear dynamics, and chaos theory [74][75][76][77][78], and pattern recognition and classification techniques such as neural networks [79][80][81][82][83][84][85], principal component analysis (PCA) [86,87], support vector machine (SVM) [88,89], and recently developed enhanced probabilistic networks (EPNN) [90], is the most effective approach to model the subtle variation in EEG signals for computer-aided diagnosis of various neurological and psychiatric disorders. This also applies to alcoholism and its impact on the human brain [39,91,92].…”

On the use of fuzzy partitions to protect data

“…Regarding the study of the t-closeness, given Q = {13, 16,40,45,50,60,80} the set of values that the sensitive attribute take, the distributions in the whole table (W ) and in each q * -block (P 1 , . .…”

“…Other situations where these techniques are employed to act as a bridge between advances being made in computer technology and civil and infrastructure engineering can be seen [9,16,18,23,44,47].…”

An Approach to Dynamic Classification of Traffic Flow Patterns

“…There exists a great number of studies employing neural network methods as estimators and predictors to various problems of civil engineering (Flood and Kartam, 1994; Hung and Jan, 1999; Adeli, 2001; Panakkat and Adeli, 2009; Graf et al, 2010; Graf et al, 2012; Osornio‐Rios et al, 2012; Ghodrati Amiri et al, 2012) and particularly transportation engineering, including work‐zone capacity and delay estimation (Jiang and Adeli, 2003, 2004a; Karim and Adeli, 2003; Hooshdar and Adeli, 2004; Ghosh‐Dastidar and Adeli, 2006); short‐term traffic flow forecasting (Jiang and Adeli, 2005; Vlahogianni et al, 2008; Stathopoulos et al, 2008; Boto‐Giralda et al, 2010); incident detection (Adeli and Karim, 2000; Adeli and Samant, 2000; Samant and Adeli, 2001; Karim and Adeli, 2002a; Ghosh‐Dastidar and Adeli, 2003); pave performance (Mei et al, 2004; Bianchini and Bandini, 2010); zonal trip distribution modeling (Tillema et al, 2006); and road safety (Pande and Abdel‐Aty, 2008). Specifically, in a series of works on traffic pattern estimation (Treiber et al, 2010; Treiber et al, 2011) and classification, the time‐series characteristics of input flow measures are deeply analyzed employing various methods for time‐frequency representation.…”