A new method for expert target recognition system: Genetic wavelet extreme learning machine (GAWELM)

In last year’s, the expert target recognition has been become very important topic in radar literature. In this study, a target recognition system is introduced for expert target recognition (ATR) using radar target echo signals of High Range Resolution (HRR) radars. This study includes a combination of an adaptive feature extraction and classification using optimum wavelet entropy parameter values. The features used in this study are extracted from radar target echo signals. Herein, a genetic wavelet extreme learning machine classifier model (GAWELM) is developed for expert target recognition. The GAWELM composes of three stages. These stages of GAWELM are genetic algorithm, wavelet analysis and extreme learning machine (ELM) classifier. In previous studies of radar target recognition have shown that the learning speed of feedforward networks is in general much slower than required and it has been a major disadvantage. There are two important causes. These are: (1) the slow gradient-based learning algorithms are commonly used to train neural networks, and (2) all the parameters of the networks are fixed iteratively by using such learning algorithms. In this paper, a new learning algorithm named extreme learning machine (ELM) for single-hidden layer feedforward networks (SLFNs) Ahern et al., 1989, Al-Otum and Al-Sowayan, 2011, Avci et al., 2005a, Avci et al., 2005b, Biswal et al., 2009, Frigui et al., in press, Cao et al., 2010, Guo et al., 2011, Famili et al., 1997, Han and Huang, 2006, Huang et al., 2011, Huang et al., 2006, Huang and Siew, 2005, Huang et al., 2009, Jiang et al., 2011, Kubrusly and Levan, 2009, Le et al., 2011, Lhermitte et al., in press, Martínez-Martínez et al., 2011, Matlab, 2011, Nelson et al., 2002, Nejad and Zakeri, 2011, Tabib et al., 2009, Tang et al., 2011, which randomly choose hidden nodes and analytically determines the output weights of SLFNs, to eliminate the these disadvantages of feedforward networks for expert target recognition area. Then, the genetic algorithm (GA) stage is used for obtaining the feature extraction method and finding the optimum wavelet entropy parameter values. Herein, the optimal one of four variant feature extraction methods is obtained by using a genetic algorithm (GA). The four feature extraction methods proposed GAWELM model are discrete wavelet transform (DWT), discrete wavelet transform–short-time Fourier transform (DWT–STFT), discrete wavelet transform–Born–Jordan time–frequency transform (DWT–BJTFT), and discrete wavelet transform–Choi–Williams time–frequency transform (DWT–CWTFT). The discrete wavelet transform stage is performed for optimum feature extraction in the time–frequency domain. The discrete wavelet transform stage includes discrete wavelet transform and calculating of discrete wavelet entropies. The extreme learning machine (ELM) classifier is performed for evaluating the fitness function of the genetic algorithm and classification of radar targets. The performance of the developed GAWELM expert radar target recognition system is examined by using noisy real radar target echo signals. The applications results of the developed GAWELM expert radar target recognition system show that this GAWELM system is effective in rating real radar target echo signals. The correct classification rate of this GAWELM system is about 90% for radar target types used in this study.     

Occurrence of ochratoxin A in cereal-derived food products commonly consumed in Turkey

Ochratoxin A (OTA) is a mycotoxin that can be found in several food commodities including cereals, wine, coffee, cacao, spices or dried fruits, resulting in chronic human exposure. The aim of our study was to investigate the presence of OTA in widely consumed cereal-derived products commercialized in Turkey. A total of 142 samples were collected from different supermarkets and traditional bazaars in Istanbul during 2008-2010 years. The analytical methods used in our study involved the liquid/liquid extraction of OTA, immunoaffinity clean-up and high performance liquid chromatography determination with fluorescence detection. The frequencies of OTA contamination were 21.62%, 19.05% and 55.95% and the mean concentrations of positive samples were 0.32 μg/kg, 0.14 μg/kg, 0.41 μg/kg for breakfast cereals, cereal-based baby foods and tarhana samples, respectively. Our findings show that contamination levels of OTA in all cereal-derived products were lower than the permitted level by European Commission Regulation.     

High‐performance filaments by melt spinning low viscosity nylon 6 using horizontal isothermal bath process

Several techniques and treatments have been developed for the production of high‐performance nylon‐6 fibers. The inherent problems of low productivity, high production cost, and high energy consumption, complexity of chemical reaction, mass transfer, and waste recovery systems make most of them inappropriate for industrial application. Horizontal isothermal bath (hIB) is an alternative ecofriendly simple treatment that can be used during melt spinning process for production of technical textile fibers. The efficacy of hIB in improving the mechanical properties of multifilament nylon‐6 yarn is studied in this research. The results showed that such treatment can increase the molecular orientation of the amorphous and crystalline functions up to 0.54 and 0.983, respectively, and raised both the amorphous isotropy and fiber birefringence by 67 and 45%, respectively. Hot drawing of the yarn at a very low draw ratio of 1.38, increased the tenacity and modulus up to 10 and 43.9 g/den, respectively, and decreased the elongation to 27%. POLYM. ENG. SCI., 55:2457–2464, 2015. © 2015 Society of Plastics Engineers     

Developing an ecologically friendly isothermal bath to obtain a new class high-tenacity and high-modulus polypropylene fibers

A number of production methods have been developed for high-performance fibers; however, most processes use toxic solvents or generate a lot of unwanted by-products. Our research resulted in the development of a new family of high-performance polypropylene (PP) fibers by utilizing a simple, ecologically friendly bath (ECOB). Various commodity polymers can be used with ECOB melt spinning system at high throughputs and performance benefits. Our treated as-spun PP fibers had a highly oriented, but not crystalline precursor morphology with f _a up to 0.6 generating superior mechanical properties. After drawing at draw ratios of 1.49 at 120 °C, highly oriented crystalline and amorphous phases were achieved for the drawn fibers with f _c and f _a values of 0.95 and 0.87, respectively. This fine structure for ECOB-treated fibers resulted in tenacity close to 12 g/d, initial modulus higher than 150 g/d, and ultimate elongation at break of 20 %. The polymer melting point of the new fibrillar PP fibers increased by 9 °C.     

Crystal Structures and Magnetic Properties of the Co2Mn1−x V x Sb (0 ≤ x ≤ 1) Heusler Compounds

Crystal structure and magnetic properties of the Co₂Mn_1?x V _x Sb (0 ≤ x ≤ 1) Heusler compounds have been studied by X-ray powder diffraction (XRD), magnetometric measurements, and full-potential linearized augmented plane wave (FP–LAPW) method. All compounds crystallize in a cubic Cu₂MnAl-type crystal structure with the space group Fm–3m. The samples for x<0.8 have the Curie temperatures above room temperature, while the Curie temperature is observed at 68 K for the sample with x = 0.8. The saturation magnetization at 5 K decreases linearly with increasing vanadium concentration x. The values of the saturation magnetization obtained by FP–LAPW–local density approximation (LDA) calculations are in better agreement with the experimental results compared with the results obtained by FP–LAPW–generalized gradient approximation (GGA) calculations.     

Eco-friendly approach on wool pretreatment and effect on the wool structure and dyeability

This research investigated the effect of various proteolytic enzymatic pretreatment on morphological and chemical features and the dyeability properties of wool fibres. Scoured merino wool fibres are treated with protease, papain, trypsin, and pepsin in specified conditions. Each enzyme activity measurement was provided by appropriate methods such as Bradford, BAPNA (N-benzoyl-1-arginine-p-nitroanilide), and BSA (Bovine Serum Albumin). Enzymatic processes were carried out for 24 h in the incubator set at 40°C, 100 rpm, and specified pH with 1 mg/ml enzyme concentration. Whiteness index (Stensby) and yellowness index (ASTM D 1925) were examined after enzymatic pretreatment. Pepsin and trypsin-treated wool fibres showed the highest whiteness index as 61.3 and 61.1, respectively whilst untreated wool fibres had 52.2. Fourier-transform infrared (FTIR) analysis revealed the increase in the intensity of amide-related bands and hydroxyl bands after enzymatic treatment. Scanning electron microscopy (SEM) photomicrographs manifested the cuticle layer is partially removed in enzyme-treated fibres. Elemental identification was provided by SEM–energy-dispersive X-ray spectroscopy (EDX). It appears that the sulphur bonds decreased after the treatment and the pepsin-treated fibres have fewer bonds of all. To examine the damage to the structure, photomicrographs were taken using fluorescence and light microscopes. The alkali solubility test (ASTM D1283) was also conducted to compare different enzyme types. Wool fibres were dyed in 2.0% concentration with reactive dyestuff. Dyeability and colorimetric features of fibres were measured by a spectrophotometer. The washing fastness test showed that all the samples have good results and the colour change after washing was better in enzyme-treated samples (grade 5) compared to untreated wool fibres (grade 4–5).     

Self-assembled fibrillar polyethylene crystals with tunable properties

Due to its simple linear chain structure, crystal morphology of linear low-density polyethylene (LLDPE) fibers can be controlled to fulfill the needs of diverse advanced applications. This study presents a simple two-step method to produce LLDPE fibers with self-assembled fibrillar crystals and highly oriented amorphous phase. Rather than conventional melt spinning, fibers were treated in a two-step eco-friendly bath without drawing after extruded fibers emerge from the spinneret. Treated fibers through the baths demonstrated lower crystallinity, but significantly higher degree of crystal orientation when compared to control fibers of traditional melt spinning. Morphological analysis revealed that a unique microstructure was formed after spinning through a two-step eco-friendly bath. As-spun fibers demonstrated spherulitic morphology which can be transformed into a fibrillar structure followed by post-drawing process. Cross sectional images of the treated LLDPE fibers produced at 400 m/min showed fibrillar PE crystals which can be more dominant upon post-drawing. After two-step bath treatment, produced fibers need low draw ratios to exhibit high performance. Our novel modification followed by hot drawing process can manipulate internal structure with performance of PE fibers to an outstanding level of 0.35 GPa strength and 3 GPa modulus at a production speed of 400 m/min.