A proposed expert system for word sense disambiguation: deductive ambiguity resolution based on data mining and forward chaining

One of the major issues in the process of machine translation is the problem of choosing the proper translation for a multi‐sense word referred to as word sense disambiguation (WSD). Two commonly used approaches to this problem are statistical and example‐based methods. In statistical methods, ambiguity resolution is mostly carried out by making use of some statistics extracted from previously translated documents or dual corpora of source and target languages. Example‐based methods follow a similar approach as they also make use of bilingual corpora. However, they perform the task of matching at run‐time (i.e. online matching). In this paper, by looking at the WSD problem from a different viewpoint, we propose a system, which consists of two main parts. The first part includes a data mining algorithm, which runs offline and extracts some useful knowledge about the co‐occurrences of the words. In this algorithm, each sentence is imagined as a transaction in Market Basket Data Analysis problem, and the words included in a sentence play the role of purchased items. The second part of the system is an expert system whose knowledge base consists of the set of association rules generated by the first part. Moreover, in order to deduce the correct senses of the words, we introduce an efficient algorithm based on forward chaining in order to be used in the inference engine of the proposed expert system. The encouraging performance of the system in terms of precision and recall as well as its efficiency will be analysed and discussed through a set of experiments.     

Exergy analysis and optimisation of waste heat recovery systems for cement plants

In the last decades, heat recovery systems have received much attention due to the increase in fuel cost and the increase in environmental issues. In this study, different heat recovery systems for a cement plant are compared in terms of electricity generation and exergy analysis. The heat sources are available in high temperature (HT) and low temperature (LT). For the HT section a dual pressure Rankine cycle, a simple dual pressure Organic Rankine Cycle (ORC) and a regenerative dual pressure ORC are compared. Also, for the LT section, a simple ORC is compared with transcritical carbon dioxide cycle. To find the best system, an optimisation algorithm is applied to all proposed cycles. The results show that for the HT section, regenerative ORC has the highest exergy efficiency and has the capability of producing nearly 7?MW electricity for a cement factory with the capacity of 3400 ton per day. The main reason for this is introducing the regenerative heat exchanger to the cycle. For the LT section, ORC showed a better performance than the CO₂ cycle. It is worth mentioning that the generated power in this section is far lower than that of the HT section and is equal to nearly 300?kW.     

Corrosion Behavior and Microhardness of Ni-P-SiO<Subscript>2</Subscript>-Al<Subscript>2</Subscript>O<Subscript>3</Subscript> Nano-composite Coatings on Magnesium Alloy

In the present work, nano-composites of Ni-P-SiO₂-Al₂O₃ were coated on AZ91HP magnesium alloy. The surface morphology of the nano-composite coating was studied by field emission scanning electron microscopy (FESEM). The amount of SiO₂ in the coating was determined by energy-dispersive analysis of x-ray (EDX), and the crystalline structure of the coating was examined by x-ray diffractometer (XRD). All the experiments concerning the corrosion behavior of the coating carried out in 3.5 wt.% NaCl solution and evaluated by electrochemical impedance spectroscopy (EIS) and polarization technique. The results showed that an incorporation of SiO₂ and Al₂O₃ in Ni-P coating at the SiO₂ concentration of 10 g/Land 14 g/LAl₂O₃ led to the lowest corrosion rate (i _corr = 1.3 µA/cm²), the most positive E _corr and maximum microhardness (496 VH). Furthermore, Ni-P-SiO₂-Al₂O₃ nano-composite coating possesses less porosity than that in Ni-P coating, resulting in improving corrosion resistance.     

Automatic black and white film colorization using texture features and artificial neural networks

Abstract

This study represents an innovative automatic method for black and white films colorization using texture features and a multilayer perceptron artificial neural network. In the proposed method, efforts are made to remove human interference in the process of colorization and replace it with an artificial neural network (ANN) which is trained using the features of the reference frame. Later, this network is employed for automatic colorization of the remained black and white frames. The reference frames of the black and white film are manually colored. Using a Gabor filter bank, texture features of all the pixels of the reference frame are extracted and used as the input feature vector of the ANN, while the output will be the color vector of the corresponding pixel. Finally, the next frames’ feature vectors are fed respectively to the trained neural network, and color vectors of those frames are the output. Applying AVI videos and using various color spaces, a series of experiments are conducted to evaluate the proposed colorization process. This method needs considerable time to provide a reasonable output, given rapidly changing scenes. Fortunately however, due to the high correlation between consecutive frames in typical video footage, the overall performance is promising regarding both visual appearance and the calculated MSE error. Apart from the application, we also aim to show the importance of the low level features in a mainly high level process, and the mapping ability of a neural network.     

Pre-reservation based spectrum allocation for cognitive radio network

Studies on the current usage of the radio spectrum by several agencies have already revealed that a large fraction of the radio spectrum is inadequately utilized. This basic finding has led to numerous research initiatives. Cognitive radio technology is one of the key candidate technologies to solve the problems of spectrum scarcity and low spectrum utilization. However, random behavior of the primary user (PU) appears to be an enormous challenge. In this paper, a Pre-reservation based spectrum allocation method for cognitive radio network is proposed to apply a PU behavior aware joint spectrum band (SB) selection and allocation scheme. In the first step, the SB is observed in terms of PU usage statistics whereas in the second phase, a network operator (NO) using a spectrum allocation scheme is employed to allocate SBs among secondary users (SUs). We also introduce the concept of reservation and exchange functionality under the priority serving strategy in a time-varying framing process. Simulation results show that the proposed scheme outperforms existing schemes in terms of the spectrum utilization and network revenue. In addition, it helps NO to manage the spectrum on a planned basis with a systematical spectrum reservation management where the NO has the status of time slots. Moreover, SUs have an opportunity to reserve or instantly request a SB that maximizes the SUs satisfaction in terms of quality of experience.     

The influence of SiO<Subscript>2</Subscript> and Al<Subscript>2</Subscript>O<Subscript>3</Subscript> nanoparticles on corrosion resistance enhancement of Ni–P on magnesium

In this study, the influence of adding SiO₂ and Al₂O₃ to Ni–P coated on magnesium substrate and the related corrosion resistance behavior were evaluated. The surface morphology of Ni–P–SiO₂–Al₂O₃ composite coating was investigated by field emission scanning electron microscopy (FESEM). The amount of Al₂O₃ and SiO₂ in the coating was measured by energy dispersive analysis of X-ray (EDX) and the corrosion behavior of coating was monitored by electrochemical impedance spectroscopy (EIS) and polarization techniques, showing the corrosion resistance of Ni–P–SiO₂–Al₂O₃ increases compare to Ni–P–SiO₂ and Ni–P–Al₂O₃. Furthermore, the microhardness of the coating was examined and the final hardness of Ni–P–SiO₂–Al₂O₃ reached 461 VH.     

The Influence of Electrophoretic Potential on Ni—Al<Subscript>2</Subscript>O<Subscript>3</Subscript> Nano-Composite Coating

In this study, the effect of electrophoretic voltage changes on Ni—Al₂O₃ nano-composite coating via two step process electrophoretic, and electrochemically on 1100 Al substrate on morphology, corrosion and wear behaviour were studied. In the first step of deposition for determining the optimum amount of Teri Ethanol Amin activator in electrophoretic suspension Transmission Electron Microscopy (TEM) was used. The amount of alumina particles, Nickel ions in the coating and morphology were studied by Energy-dispersive X-ray spectroscopy (EDX) and Field-Emission Electron Microscopy (FESEM). Nanoparticles distribute more homogenous in deposit within using 40 V voltage. Corrosion behaviour of coating was investigated by polarization technique in 3.5 wt % NaCl which shows a decrease in corrosion current from 13.7 μA/cm² to 1.46 μA/cm² versus bare sample.     

An efficient MLP-learning algorithm using parallel tangent gradient and improved adaptive learning rates

Poor convergence is a common problem of gradient-based multi-layer perceptron (MLP)-learning algorithms. It is claimed that using a deflecting direction like momentum and adaptive learning rates (ALRs) can improve the convergence performance. For a more reliable and faster MLP learning, we introduce the parallel tangent gradient with adaptive learning rates (PTGALR) algorithm that uses parallel tangent deflecting direction instead of the momentum. Moreover, we use two independent variable learning rates, one for the gradient descent and the other for accelerating direction through the parallel tangent. Also, we propose an improved ALR computation algorithm that calculates the learning rates with a dispensable error oscillation. This adaptation algorithm has two outputs: one is the applied learning rate and the other is used for a better learning rate estimation in the next iteration. Moreover, the proposed ALR computation algorithm models the error function as a one-dimensional quadratic function of the learning rate when it is needed. The implementation results of PTGALR for some well-known binary and real MLP problems show higher and faster convergence with lower oscillations than the similar adaptive learning algorithms.     

An application of MOGW optimization for feature selection in text classification

The Journal of Supercomputing - Due to extensive web applications, sentiment classification (SC) has become a relevant issue of interest among text mining experts. The extensive online reviews...