Direct adaptive fuzzy control with membership function tuning

In this paper, a direct self‐structured adaptive fuzzy control is introduced for the class of nonlinear systems with unknown dynamic models. Control is accomplished by an adaptive fuzzy system with a fixed number of rules and adaptive membership functions. The reference signal and state errors are used to tune the membership functions and update them instantaneously. The Lyapunov synthesis method is also used to guarantee the stability of the closed loop system. The proposed control scheme is applied to an inverted pendulum and a magnetic levitation system, and its effectiveness is shown via simulation. Copyright © 2011 John Wiley and Sons Asia Pte Ltd and Chinese Automatic Control Society     

Calcium carbonate and ammonium polyphosphate flame retardant additives formulated to protect ethylene vinyl acetate copolymer against fire: Hydrated or carbonated calcium?

In this study, the effect of the chemical nature of different calcium (Ca)-based minerals as flame retardant additives in combination with ammonium polyphosphate (APP), in 1:1 proportions, on the flame retardancy behavior and performance of ethylene vinyl acetate copolymer was discussed. Combining APP with partly and completely hydrated calcium oxide led to superior flame-retardant function detected in mass loss calorimeter measurements with respect to the corresponding system containing carbonated calcium. This privileged character was attributed to the higher reactivity of hydrated Ca-based fillers toward APP in comparison with Ca carbonate, which induced the formation of an intumescent residue. The difference between reactivity potential of hydrated and dry Ca was demonstrated by the newly formed thermally stable species, and further evidenced by thermogravimetric analysis performed on APP/fillers blends. Moreover, the presence of more crystalline domains in the Ca/phosphorus-based compounds was evidenced by XRD analysis of the mass loss calorimeter test residues. The results of this work highlight the role of blend additive systems on the performance of flame retardancy of polymer materials.     

Laboratory Investigation of Stilling Basin Slope Effect on Bed Scour at Downstream of Stepped Spillway: Physical Modeling of Javeh RCC Dam

Stepped spillway and stilling basin are one of the most important energy dissipation structures. Eventhough, most of energy dissipated by these structures, but in skimming flow, the upstream flow motion is nonaerated and the residual energy capable to destroyed structures during floods. In this study, effect of stilling basin slope on bed scour, downstream of Javeh dam was investigating. Experiments performed in hydraulic structures laboratory of the University of Kerman with six different discharges (5, 7, 13, 17, 25 and 30 l/s.m) and five various stilling basin slope (0.02, 0.01, 0, ?0.01 and???0.02). The parameters such as maximum scour depth (d_s), flow velocity (in three point), water depth on upstream and downstream of stepped spillway and stilling basin, the distance of the maximum scour depth to sill (L_s) and the gheometery of scour hole measured. Result shown that when stilling basin slopes was 0.02, the average of maximum relative scour depth, 47% Increased and in ?0.02, 52.2% Decreased. In addition, the distance of maximum scour depth until stilling basin increased by increasing and decreased by decreasing the stilling basin slope.

     

Hybrid binary arithmetic optimization algorithm with simulated annealing for feature selection in high-dimensional biomedical data

Gene expression data play a significant role in the development of effective cancer diagnosis and prognosis techniques. However, many redundant, noisy, and irrelevant genes (features) are present in the data, which negatively affect the predictive accuracy of diagnosis and increase the computational burden. To overcome these challenges, a new hybrid filter/wrapper gene selection method, called mRMR-BAOAC-SA, is put forward in this article. The suggested method uses Minimum Redundancy Maximum Relevance (mRMR) as a first-stage filter to pick top-ranked genes. Then, Simulated Annealing (SA) and a crossover operator are introduced into Binary Arithmetic Optimization Algorithm (BAOA) to propose a novel hybrid wrapper feature selection method that aims to discover the smallest set of informative genes for classification purposes. BAOAC-SA is an enhanced version of the BAOA in which SA and crossover are used to help the algorithm in escaping local optima and enhancing its global search capabilities. The proposed method was evaluated on 10 well-known microarray datasets, and its results were compared to other current state-of-the-art gene selection methods. The experimental results show that the proposed approach has a better performance compared to the existing methods in terms of classification accuracy and the minimum number of selected genes.

     

An adaptive neuro‐fuzzy system for stock portfolio analysis

We propose an adaptive neuro‐fuzzy inference system (ANFIS) for stock portfolio return prediction. Previous work has shown that portfolio optimization can be improved by using predicted stock earnings rather than historical earnings. We show that predicted portfolio returns can be improved by using ANFIS and taking as input a variety of technical and fundamental attributes about various indices of the stock market. To generate membership functions, we use a robust noise rejection‐clustering algorithm. The neuro‐fuzzy model is tested on portfolios constituted from the Tehran Stock Exchange. In our experiments, the proposed method performs better in predicting the portfolio return than the classical Markowitz portfolio optimization method, a multiple regression, a neural network, and the Sugeno–Yasukawa method. © 2010 Wiley Periodicals, Inc.     

A fast and noise resilient cluster-based anomaly detection

Clustering, while systematically applied in anomaly detection, has a direct impact on the accuracy of the detection methods. Existing cluster-based anomaly detection methods are mainly based on spherical shape clustering. In this paper, we focus on arbitrary shape clustering methods to increase the accuracy of the anomaly detection. However, since the main drawback of arbitrary shape clustering is its high memory complexity, we propose to summarize clusters first. For this, we design an algorithm, called Summarization based on Gaussian Mixture Model (SGMM), to summarize clusters and represent them as Gaussian Mixture Models (GMMs). After GMMs are constructed, incoming new samples are presented to the GMMs, and their membership values are calculated, based on which the new samples are labeled as “normal” or “anomaly.” Additionally, to address the issue of noise in the data, instead of labeling samples individually, they are clustered first, and then each cluster is labeled collectively. For this, we present a new approach, called Collective Probabilistic Anomaly Detection (CPAD), in which, the distance of the incoming new samples and the existing SGMMs is calculated, and then the new cluster is labeled the same as of the closest cluster. To measure the distance of two GMM-based clusters, we propose a modified version of the Kullback–Libner measure. We run several experiments to evaluate the performances of the proposed SGMM and CPAD methods and compare them against some of the well-known algorithms including ABACUS, local outlier factor (LOF), and one-class support vector machine (SVM). The performance of SGMM is compared with ABACUS using Dunn and DB metrics, and the results indicate that the SGMM performs superior in terms of summarizing clusters. Moreover, the proposed CPAD method is compared with the LOF and one-class SVM considering the performance criteria of (a) false alarm rate, (b) detection rate, and (c) memory efficiency. The experimental results show that the CPAD method is noise resilient, memory efficient, and its accuracy is higher than the other methods.     

Supervised principal component analysis: Visualization, classification and regression on subspaces and submanifolds

We propose “supervised principal component analysis (supervised PCA)”, a generalization of PCA that is uniquely effective for regression and classification problems with high-dimensional input data. It works by estimating a sequence of principal components that have maximal dependence on the response variable. The proposed supervised PCA is solvable in closed-form, and has a dual formulation that significantly reduces the computational complexity of problems in which the number of predictors greatly exceeds the number of observations (such as DNA microarray experiments). Furthermore, we show how the algorithm can be kernelized, which makes it applicable to non-linear dimensionality reduction tasks. Experimental results on various visualization, classification and regression problems show significant improvement over other supervised approaches both in accuracy and computational efficiency.     

Sensing and identification of carbon monoxide using carbon films fabricated by methane arc discharge decomposition technique

Carbonaceous materials have recently received attention in electronic applications and measurement systems. In this work, we demonstrate the electrical behavior of carbon films fabricated by methane arc discharge decomposition technique. The current-voltage (I-V) characteristics of carbon films are investigated in the presence and absence of gas. The experiment reveals that the current passing through the carbon films increases when the concentration of CO₂ gas is increased from 200 to 800 ppm. This phenomenon which is a result of conductance changes can be employed in sensing applications such as gas sensors.     

Investigation of polyvinyl alcohol nanocomposite hydrogels containing chitosan nanoparticles as wound dressing

Polymeric hydrogels, water-swollen 3?D networks of the polymers, have found wide ranges of applications in the medical fields, such as wound care and wound dressing, in order to prevent infections. Prevention from microorganisms transfer in to the wounds is one of the ideal wound dressing duties of polyvinyl alcohol (PVA) hydrogels. In this study, at the start, under optimal conditions, nanoparticles of chitosan using ionotropic gelation method were synthesized and in the next step in order to achieve particles with a minimum size, they were evaluated by scanning electron microscope (SEM) and Fourier transform infrared spectroscopy (FTIR). Then after to obtain a wound dressing with preferable properties, nanocomposite hydrogels using a combination of PVA and 5, 10 and 15?wt% chitosan nanoparticles were prepared through freezing-thawing cycles. The necessary features of PVA nanocomposite hydrogels for wound dressing were investigated. The dispersion state of nanoparticles and structure of samples were evaluated by SEM microscopy. The nanoparticle size and the nanoparticle size distribution of chitosan was determined using the dynamic light scattering test at the nanometer scale. The physical behavior of hydrogels such as swelling and gel fraction was studied and their mechanical properties were investigated by compressive test. Finally the antimicrobial test and biocompatibility as cell viability were carried out. The results proved that the PVA nanocomposite hydrogels fulfill the requirements of a good wound dressing with desirable characteristics such as favorable swelling and acceptable strength, excellent barrier against microbial penetration.     

Injectable polyethylene glycol-laponite composite hydrogels as articular cartilage scaffolds with superior mechanical and rheological properties

In this study, injectable PEG-based hydrogels containing Laponite particles with mechanical and structural properties close to the natural articular cartilage are introduced. The nanocomposites are fabricated by imide ring opening reactions utilizing synthesized copolymers containing PEG blocks and nanoclay through a two-step thermal poly-(amic acid) process. Butane diamine is used as nucleophilic reagent and hydrogels with interconnected pores with sizes in the range of 100–250?µm are prepared. Improved viscoelastic properties compared with the conventional PEG hydrogels are shown. Evaluation of cell viability utilizing human mesenchymal stem cells determines cytocompatibility of the nanocomposite hydrogels.