Journal of Artificial Intelligence and Data Mining
Volume:4 Issue: 1, Winter-Spring 2016

Dependency parsing is a way of syntactic parsing and a natural language that automatically analyzes the dependency structure of sentences, and the input for each sentence creates a dependency graph. Part-Of-Speech (POS) tagging is a prerequisite for dependency parsing. Generally, dependency parsers do the POS tagging task along with dependency parsing in a pipeline mode. Unfortunately, in pipeline models, a tagging error propagates, but the model is not able to apply useful syntactic information. The goal of joint models simultaneously reduce errors of POS tagging and dependency parsing tasks. In this research, we attempted to utilize the joint model on the Persian and English language using Corbit software. We optimized the model's features and improved its accuracy concurrently. Corbit software is an implementation of a transition-based approach for word segmentation, POS tagging and dependency parsing. In this research, the joint accuracy of POS tagging and dependency parsing over the test data on Persian, reached 85.59% for coarse-grained and 84.24% for fine-grained POS. Also, we attained 76.01% for coarse-grained and 74.34% for fine-grained POS on English.

For many years, researchers have studied high accuracy methods for recognizing the handwriting and achieved many significant improvements. However, an issue that has rarely been studied is the speed of these methods. Considering the computer hardware limitations, it is necessary for these methods to run in high speed. One of the methods to increase the processing speed is to use the computer parallel processing power. This paper introduces one of the best feature extraction methods for the handwritten recognition, called DPP (Derivative Projection Profile), which is employed for isolated Persian handwritten recognition. In addition to achieving good results, this (computationally) light feature can easily be processed. Moreover, Hamming Neural Network is used to classify this system. To increase the speed, some part of the recognition method is executed on GPU (graphic processing unit) cores implemented by CUDA platform. HADAF database (Biggest isolated Persian character database) is utilized to evaluate the system. The results show 94.5% accuracy. We also achieved about 5.5 times speed-up using GPU.

In this paper we address the issue of recognizing Farsi handwritten words. Two types of gradient features are extracted from a sliding vertical stripe which sweeps across a word image. These are directional and intensity gradient features. The feature vector extracted from each stripe is then coded using the Self Organizing Map (SOM). In this method each word is modeled using the discrete Hidden Markov Model (HMM). To evaluate the performance of the proposed method, FARSA dataset has been used. The experimental results show that the proposed system, applying directional gradient features, has achieved the recognition rate of 69.07% and outperformed all other existing methods.

Multi-part words in English language are hyphenated and hyphen is used to separate different parts. Persian language consists of multi-part words as well. Based on Persian morphology, half-space character is needed to separate parts of multi-part words where in many cases people incorrectly use space character instead of half-space character. This common incorrectly use of space leads to some serious issues in Persian text processing and text readability. In order to cope with the issues, this work proposes a new model to correct spacing in multi-part words. The proposed method is based on statistical machine translation paradigm. In machine translation paradigm, text in source language is translated into a text in destination language on the basis of statistical models whose parameters are derived from the analysis of bilingual text corpora. The proposed method uses statistical machine translation techniques considering unedited multi-part words as a source language and the space-edited multi-part words as a destination language. The results show that the proposed method can edit and improve spacing correction process of Persian multi-part words with a statistically significant accuracy rate.

Nowadays, due to inherent complexity of real optimization problems, it has always been a challenging issue to develop a solution algorithm to these problems. Single row facility layout problem (SRFLP) is a NP-hard problem of arranging a number of rectangular facilities with varying length on one side of a straight line with aim of minimizing the weighted sum of the distance between all facility pairs. In this paper two new algorithms of cuckoo optimization and forest optimization are applied and compared to solve SRFLP for the first time. The operators of two algorithms are adapted according to the characteristics of SRFLP and results are compared for two groups of benchmark instances of the literature. These groups consist of instances with the number of facilities less and more than 30. Results on two groups of instances show that proposed cuckoo optimization based algorithm has better performance rather than proposed forest optimization based algorithm in both aspects of finding the best solution and Computational time.

Suspended particles have deleterious effects on human health and one of the reasons why Tehran is effected is its geographically location of air pollution. One of the most important ways to reduce air pollution is to predict the concentration of pollutants. This paper proposed a hybrid method to predict the air pollution in Tehran based on particulate matter less than 10 microns (PM10), and the information and data of Aghdasiyeh Weather Quality Control Station and Mehrabad Weather Station from 2007 to 2013. Generally, 11 inputs have been inserted to the model, to predict the daily concentration of PM10. For this purpose, Artificial Neural Network with Back Propagation (BP) with a middle layer and sigmoid activation function and its hybrid with Genetic Algorithm (BP-GA) were used and ultimately the performance of the proposed method was compared with basic Artificial Neural Networks along with (BP) Based on the criteria of - R2-, RMSE and MAE. The finding shows that BP-GA has higher accuracy and performance. In addition, it was also found that the results are more accurate for shorter time periods and this is because the large fluctuation of data in long-term returns negative effect on network performance. Also, unregistered data have negative effect on predictions. Microsoft Excel and Matlab 2013 conducted the simulations.

Classification of heart arrhythmia is an important step in developing devices for monitoring the health of individuals. This paper proposes a three module system for classification of electrocardiogram (ECG) beats. These modules are: denoising module, feature extraction module and a classification module. In the first module the stationary wavelet transform (SWF) is used for noise reduction of the ECG signals. The feature extraction module extracts a balanced combination of the Hermit features and three timing interval feature. Then a number of multi-layer perceptron (MLP) neural networks with different number of layers and eight training algorithms are designed. Seven files from the MIT/BIH arrhythmia database are selected as test data and the performances of the networks, for speed of convergence and accuracy classifications, are evaluated. Generally all of the proposed algorisms have good training time, however, the resilient back propagation (RP) algorithm illustrated the best overall training time among the different training algorithms. The Conjugate gradient back propagation (CGP) algorithm shows the best recognition accuracy about 98.02% using a little amount of features.

This paper proposes a method to solve multi-objective problems using improved Particle Swarm Optimization. We propose leader particles which guide other particles inside the problem domain. Two techniques are suggested for selection and deletion of such particles to improve the optimal solutions. The first one is based on the mean of the m optimal particles and the second one is based on appointing a leader particle for any n founded particles. We used an intensity criterion to delete the particles in both techniques. The proposed techniques were evaluated based on three standard tests in multi-objective evolutionary optimization problems. The evaluation criterion in this paper is the number of particles in the optimal-Pareto set, error, and uniformity. The results show that the proposed method searches more number of optimal particles with higher intensity and less error in comparison with basic MOPSO and SIGMA and CMPSO and NSGA-II and microGA and PAES and can be used as proper techniques to solve multi-objective optimization problems.

The edges of an image define the image boundary. When the image is noisy, it does not become easy to identify the edges. Therefore, a method requests to be developed that can identify edges clearly in a noisy image. Many methods have been proposed earlier using filters, transforms and wavelets with Ant colony optimization (ACO) that detect edges. We here used ACO for edge detection of noisy images with Gaussian noise and salt and pepper noise. As the image edge frequencies are close to the noise frequency band, the edge detection using the conventional edge detection methods is challenging. The movement of ants depends on local discrepancy of image’s intensity value. The simulation results compared with existing conventional methods and are provided to support the superior performance of ACO algorithm in noisy images edge detection. Canny, Sobel and Prewitt operator have thick, non continuous edges and with less clear image content. But the applied method gives thin and clear edges.

This work proposes a neural-fuzzy sliding mode control scheme for a hydro-turbine speed governor system. Considering the assumption of elastic water hammer, a nonlinear mode of the hydro-turbine governor system is established. By linearizing this mode, a sliding mode controller is designed. The linearized mode is subject to uncertainties. The uncertainties are generated in the process of linearization. A radial basis function (RBF) neural network is introduced to compensate for the uncertainties. The update formulas for the neural networks are derived from the Lyapunov direct method. For the chattering phenomenon of the sliding mode control, a fuzzy logic inference system is adopted. In the sense of Lyapunov, the asymptotical stability of the system can be guaranteed. Compared with the internal mode control and the conventional PID control method, some numerical simulations verify the feasibility and robustness of the proposed scheme.

In recent years, underactuated nonlinear dynamic systems trajectory tracking, such as space robots and manipulators with structural flexibility, has become a major field of interest due to the complexity and high computational load of these systems. Hierarchical sliding mode control has been investigated recently for these systems; however, the instability phenomena will possibly occur, especially for long-term operations. In this paper, a new design approach of an adaptive fuzzy hierarchical terminal sliding-mode controller (AFHTSMC) is proposed. The sliding surfaces of the subsystems construct the hierarchical structure of the proposed method; in which the top layer includes all of the subsystems’ sliding surfaces. Moreover, terminal sliding mode has been implemented in each layer to ensure the error convergence to zero in finite time besides chattering reduction. In addition, online fuzzy models are employed to approximate the two nonlinear dynamic system’s functions. Finally, a simulation example of an inverted pendulum is proposed to confirm the effectiveness and robustness of the proposed controller.

The renewable energy resources such as wind power have recently attracted more researchers’ attention. It is mainly due to the aggressive energy consumption, high pollution and cost of fossil fuels. In this era, the future fluctuations of these time series should be predicted to increase the reliability of the power network. In this paper, the dynamic characteristics and short-term predictability of hourly wind speed and power time series are investigated via nonlinear time series analysis methods such as power spectral density analysis, time series histogram, phase space reconstruction, the slope of integral sums, the method, the recurrence plot and the recurrence quantification analysis. Moreover, the interactive behavior of the wind speed and wind power time series is studied via the cross correlation, the cross and joint recurrence plots as well as the cross and joint recurrence quantification analyses. The results imply stochastic nature of these time series. Besides, a measure of the short-term mimic predictability of the wind speed and the underlying wind power has been derived for the experimental data of Spain’s wind farm.

This paper proposes a discrete-time repetitive optimal control of electrically driven robotic manipulators using an uncertainty estimator. The proposed control method can be used for performing repetitive motion, which covers many industrial applications of robotic manipulators. This kind of control law is in the class of torque-based control in which the joint torques are generated by permanent magnet dc motors in the current mode. The motor current is regulated using a proportional-integral controller. The novelty of this paper is a modification in using the discrete-time linear quadratic control for the robot manipulator, which is a nonlinear uncertain system. For this purpose, a novel discrete linear time-variant model is introduced for the robotic system. Then, a time-delay uncertainty estimator is added to the discrete-time linear quadratic control to compensate the nonlinearity and uncertainty associated with the model. The proposed control approach is verified by stability analysis. Simulation results show the superiority of the proposed discrete-time repetitive optimal control over the discrete-time linear quadratic control.