A new automatic target recognition system based on wavelet extreme learning machine

In this paper, an automatic system is presented for target recognition using target echo signals of High Resolution Range (HRR) radars. This paper especially deals with combination of the feature extraction and classification from measured real target echo signal waveforms by using X-band pulse radar. The past studies in the field of radar target recognition have shown that the learning speed of feedforward neural networks is in general much slower than required and it has been a major disadvantage. There are two key reasons forth is status of feedforward neural networks: (1) the slow gradient-based learning algorithms are extensively used to train neural networks, and (2) all the parameters of the networks are tuned iteratively by using such learning algorithms (Feng et al., 2009, Huang and Siew, 2004, Huang and Chen, 2007, Huang and Chen, 2008, Huang et al., 2006, Huang et al., 2010, Huang et al., 2004, Huang et al., 2005, Huang et al., 2012, Huang et al., 2008, Huang and Siew, 2005, Huang et al., 2011, Huang et al., 2006, Huang et al., 2006a, Huang et al., 2006b, Lan et al., 2009, Li et al., 2005, Liang et al., 2006, Liang et al., 2006, Rong et al., 2009, Wang and Huang, 2005, Wang et al., 2011, Yeu et al., 2006, Zhang et al., 2007, Zhu et al., 2005). To resolve these disadvantages of feedforward neural networks for automatic target recognition area in this paper suggested a new learning algorithm called extreme learning machine (ELM) for single-hidden layer feedforward neural networks (SLFNs) (Feng et al., 2009, Huang and Siew, 2004, Huang and Chen, 2007, Huang and Chen, 2008, Huang et al., 2006, Huang et al., 2010, Huang et al., 2004, Huang et al., 2005, Huang et al., 2012, Huang et al., 2008, Huang and Siew, 2005, Huang et al., 2011, Huang et al., 2006, Huang et al., 2006a, Huang et al., 2006b, Lan et al., 2009, Li et al., 2005, Liang et al., 2006, Liang et al., 2006, Rong et al., 2009, Wang and Huang, 2005, Wang et al., 2011, Yeu et al., 2006, Zhang et al., 2007, Zhu et al., 2005) which randomly choose hidden nodes and analytically determines the output weights of SLFNs. In theory, this algorithm tends to provide good generalization performance at extremely fast learning speed. Moreover, the Discrete Wavelet Transform (DWT) and wavelet entropy is used for adaptive feature extraction in the time-frequency domain in feature extraction stage to strengthen the premium features of the ELM in this study. The correct recognition performance of this new system is compared with feedforward neural networks. The experimental results show that the new algorithm can produce good generalization performance in most cases and can learn thousands of times faster than conventional popular learning algorithms for feedforward neural networks.     

A novel quantum steganography algorithm based on LSBq for multi-wavelength quantum images

In this study, a novel quantum steganography algorithm based on LSBq for multi-wavelength quantum images is proposed. In this study, both the text and the binary image messages are embedded into the cover image. The results of simulations and analysis show that our algorithm satisfies the requirements of steganography algorithms. Also, we used modulo method and Hilbert scrambling method for the security of the hidden message. It is seen that an unauthorized person obtains meaningless information when attempting to extract a embedded information through known methods. The results show that the algorithm is robust against attack when several attacks are applied on the stego-image. Finally, we compare our proposed algorithm with the related works. The results of simulation show that the our proposed algorithm has many advantages according to the related algorithms.     

Investigation on thermal performance calculation of two type solar air collectors using artificial neural network

In this study, two types of solar air collectors are constructed and examined experimentally. The types are called as zigzagged absorber surface type and flat absorber surface type called Model I and Model II respectively. Experiments are carried out between 10.00 and 17.00 h in August and September under the prevailing weather conditions of Karabuk (city of the Turkey) for 5 days. Then, thermal performances belongs to experimental systems are calculated by using data obtained from experiments. To estimate thermal performances of solar air collectors an artificial neural network (ANN) model is designed. The measured data and calculated performance values are used at the design of Levenberg–Marquardt (LM) based multi-layer perceptron (MLP) in Matlab nftool module. Calculated values of thermal performances are compared to predicted values. Statistical error analysis is used to evaluate results. Comparing and statistical results demonstrate effectiveness of the proposed ANN. Also reliability of ANN and meaningfulness of input variables are tested via applying stepwise regression method to the data used in designing ANN.     

HFE gene mutation is a risk factor for tissue iron accumulation in hemodialysis patients

Introduction: HFE gene mutations are responsible from iron overload in general population. Studies in hemodialysis patients investigated the effect of presence of HFE gene mutations on serum ferritin and transferrin saturation (TSAT) with conflicting results. However effect of HFE mutations on iron overload in hemodialysis patients was not previously extensively studied. Methods: 36 hemodialysis patients (age 51.3 ± 15.6, (18/18) male/female) and 44 healthy control subjects included in this cross sectional study. Hemoglobin, ferritin, TSAT in the preceding 2 years were recorded. Iron and erythropoietin (EPO) administered during this period were calculated. Iron accumulation in heart and liver was detected by MRI. Relationship between HFE gene mutation, hemoglobin, iron parameters and EPO doses, and tissue iron accumulation were determined. Findings: Iron overload was detected in nine (25%) patients. Hemoglobin, iron parameters, weekly EPO doses, and monthly iron doses of patients with and without iron overload were similar. There was no difference between control group and hemodialysis patients with respect to the prevalence of HFE gene mutations. Iron overload was detected in five of eight patients who had HFE gene mutations, but iron overload was present in 4 of 28 patients who had no mutations (P = 0.01). Hemoglobin, iron parameters, erythropoietin, and iron doses were similar in patients with and without gene mutations. HFE gene mutations remained the main determinant of iron overload after multivariate logistic regression analysis (P = 0.02; OR, 11.6). Discussion: Serum iron parameters were not adequate to detect iron overload and HFE gene mutation was found to be an important risk factor for iron accumulation.     

A fuzzy approach to define sample size for attributes control chart in multistage processes: An application in engine valve manufacturing process

Control charts are a basic means for monitoring the quality characteristics of processes to ensure the required quality level. Determine the sample size is a problem for attribute control charts (ACC). Kaya and Engin [I. Kaya, O. Engin, A new approach to define sample size at attributes control chart in multistage processes: an application in engine piston manufacturing process, J. Mater. Process. Technol. 183 (2007) 38–48] developed a model to determine sample size in multistage process and it was solved by Genetic Algorithms (GAs). In their model, the parameters such as defective item rates for raw materials and benches were assumed to be known exactly. But in many real world applications, these parameters may be changed very dynamically due to material, human factors or operating faults. In this study a fuzzy approach for ACC in multistage process is presented and it is solved by GAs. Formulations of this model are calculated based on acceptance sampling approach and, two main parameters are determined for every stage by GAs. These are: sample size, n, and acceptance number, c. The sample size, n, is suggested for ACC. The main contributions of this paper are to develop a fuzzy model for ACC in multistage processes. The proposed approach is applied in an engine valve manufacturing firm and the model is solved by GAs.     

Ahp model for the selection of partner companies in virtual enterprises

Rising product variety and complexity, shorter time frames to respond, and the continual need to gain new capabilities through innovativeness force the trend of outsourcing to be replaced by strategic alliances, where enterprises or individuals work together towards a common goal and share their responsibilities as well as their profits. Recent developments in information technology have enabled relatively inexpensive, reliable and fast networking to support such alliances in real time. In this context, the virtual enterprise (VE) represents an appropriate cooperation alternative and competitive advantage for the enterprises. VE is a temporary network of independent companies -- suppliers, customers, even rivals -- linked by information technology (IT) to share skills, costs and access to one another’s markets. In this emerging business model of virtual enterprise, the decision support functionality, which addresses issues such as partner company selection, is an important domain to be studied. In this paper, we propose an analytic hierarchy process model to contribute in the selection of the partner companies in the virtual enterprises. A case example is also covered to validate the feasibility of the adoption of the model in virtual enterprise situations.     

Directional solidification and physical properties measurements of the zinc-aluminum eutectic alloy

Zn-5wt％ Al eutectic alloy was directionally solidified with different growth rates (5.32-250.0 tm/s) at a constant temperature gradient of 8.50 K/mm using a Bridgman-type growth apparatus.The values of eutectic spacing were measured from transverse sections of the samples.The dependences of the eutectic spacing and undercooling on growth rate are determined as λ=9.21 V-0.53 and △T=0.0245 V0.53,respectively.The results obtained in this work were compared with the Jackson-Hunt eutectic theory and the similar experimental results in the literature.Microhardness of directionally solidified samples was also measured by using a microhardness test device.The dependency of the microhardness on growth rate is found as Hv=115.64V0.13.Afterwards,the electrical resistivity (r) of the casting alloy changes from 40× 10-9 to 108× 10-9 Ω·m with the temperature rising in the range of 300-630 K.The enthalpy of fusion (△H) and specific heat (Cp) for the Zn-Al eutectic alloy are calculated to be 113.37 J/g and 0.309 J/(g.K),respectively by means of differential scanning calorimetry (DSC) from heating trace during the transformation from liquid to solid.     

A robust technique based on invariant moments – ANFIS for recognition of human parasite eggs in microscopic images

In this study, we propose a robust technique based on invariant moments – adaptive network based fuzzy inference system (IM-ANFIS). In this technique, some digital image processing methods such as noise reduction, contrast enhancement, segmentation, and morphological process are used for feature extraction stage of IM-ANFIS approach used in this study. Recently, the pattern recognition principles have come into prominence. The pattern recognition includes operation and design of systems that recognize patterns in data sets. Important application areas of pattern recognition techniques are character recognition, speech analysis, image segmentation, man and machine diagnostics and industrial inspection. The technique presented in this study enables to classify 16 different parasite eggs from their microscopic images. This proposed recognition method includes three stages. In first stage, a preprocessing subsystem is realized for obtaining unique features from the same group of patterns. In second stage, a feature extraction mechanism which is based on the invariant moments is used. In third stage, an adaptive network based fuzzy inference system (ANFIS) classifier is used for recognition process. We conduct computer simulations on MATLAB environment. The overall success rate is almost 95%.