فهرست مطالب

  • Volume:4 Issue: 4, 2011
  • تاریخ انتشار: 1389/12/11
  • تعداد عناوین: 8
|
  • Davood Gharavian, Mansour Sheikhan Page 1
    Emotion has an important role in naturalness of man-machine communication. So, computerized emotion recognition from speech is investigated by many researchers in the recent decades. In this paper, the effect of formant-related features on improving the performance of emotion detection systems is experimented. To do this, various forms and combinations of the first three formants are concatenated to a popular feature vector and Gaussian mixture models are used as classifiers. Experimental results show average recognition rate of 69% in four emotional states and noticeable performance improvement by adding only one formant-related parameter to feature vector. The architecture of hybrid emotion recognition/spotting is also proposed based on the developed models.
  • Nazirah Ramli, Daud Mohammad Page 9
    Jaccard index similarity measure which applies the extension principle approach in obtaining the fuzzy maximum and fuzzy minimum has been proposed in ranking the fuzzy numbers. However, the extension principle used is only applicable to normal fuzzy numbers and, therefore, fails to rank the non-normal fuzzy numbers. Apart from that, the extension principle does not preserve the type of membership function of the fuzzy numbers and also involves laborious mathematical operations. In this paper, a simple vertex fuzzy arithmetic operation, namely function principle, is applied. This paper also proposes the degree of optimism concept in aggregating the fuzzy evidence. The method is capable to rank both normal and non-normal fuzzy numbers in a simpler manner with all types of decision makers’ perspective
  • Hossein Pourghassem Page 16
    The ever-increasing number of logo (trademark) in official automation systems for information management, archiving and retrieval application has created greater demand for an automatic detection and recognition logo. In this paper, a classification hierarchical structure based on Bayesian classifier is proposed to logo detection and recognition. In this hierarchical structure, using two measures false accept and false reject, a novel and straightforward training scheme is presented to extract optimum parameters of the trained Bayesian classifier. In each level of the hierarchical structure, a separable feature set of shape and texture features is used to train and test classifier based on complexity of the logo pattern. The candidate regions for logo are extracted from document images by a wavelet-based segmentation algorithm, and then recognized in the proposed structure. The proposed structure is evaluated on a variety and vast database consisting of the document and non-document images with Persian and international logos. The obtained results show efficiency of the proposed structure in the real and operational conditions.
  • Mansour Sheikhan, Amir Khalili Page 24
    Knowledge embedded within artificial neural networks (ANNs) is distributed over the connections and weights of neurons. So, the user considers ANN as a black box system. There are many researches investigating the area of rule extraction by ANNs. In this paper, a dynamic cell structure (DCS) neural network and a modified version of LERX algorithm are used for rule extraction. On the other hand, intrusion detection system (IDS) is known as a critical technology to secure computer networks. So, the proposed algorithm is used to develop an IDS and classify the patterns of intrusion. To compare the performance of the proposed system with other machine learning algorithms, a multi layer perceptron (MLP) and an Elman neural network are employed with selected inputs based on the results of a feature relevance analysis. Empirical results show the superior performance of the IDS based on rule extraction from DCS in recognizing hard-detectable attack categories, e.g. user-to-root (U2R). Although, MLP with 15 selected input features, instead of 41 standard features introduced by knowledge discovery and data mining group (KDD), has better classification rates for other attack categories. This network performs better in terms of detection rate (DR), false alarm rate (FAR), and cost per example (CPE) when compared with some other machine learning methods, as well.
  • Ghazanfar Shahgholian, Adel Deriszadeh Page 35
    The direct thrust force control which is the direct torque control linear type method is modified in this article in order to eliminate the defects that are variable switching frequency and existing large ripples of force and flux, by keeping the advantages of thrust force control method which include simplicity of structure, low dependency to motor parameters and no requirement to coordination transformations. In previous works, the structure simplicity of DTC and low calculations, to reduce the force ripples and fixing switching frequency are disaffirmed, but with regards to keeping DTC advantages, a new method is presented in this article to eliminate the defects by the aid of neural network. for the first time, in this article, the precise non-linear behavior of PMLSM motor and effect of speed in voltage vectors selection in DTC has been considered by using space vector modulation and it has been shown that despite considering motors non-linear behavior, the results concluded by the submitted intelligent DTC-SVM method, is more satisfactory than other method
  • Mohammadreza Zare, Mousa Marzband Page 42
    In permanent magnet (PM) linear motor, there is force ripple, which is detrimental to positioning. This force ripple is mainly due to cogging force and mutual force ripple. These forces are affected by geometric parameters of brushless PM motor, such as width of magnet, height of magnet, shifted length of magnet pole, length and height of armature and slot width. If flux density distribution can be described by geometric parameters that are related to the force ripple and force ripple is described by the flux density distribution, the optimal design can be done by considering force ripple as cost function and geometric parameters as design variables. In this paper, at first, flux density distribution in the air gap is calculated by analytic solution of Laplace and Possion equations in the function of geometric parameters. Cogging force is obtained by integrating Maxwell stress tensor, which is described by flux density distribution, on slot face and end face of iron core of armature. Secondly, a finite element method is presented in order to compare the previous method with this method.
  • Forough Taki, Ali Shishebori, Saeed Abazari, Gholamreza Arab Markadeh Page 48
    This paper presents the comparative performance of neuro- Fuzzy controlled Voltage Source Converters (VSC) based Flexible AC Transmission System (FACTS) devices, such as Static Synchronous Series Compensator (SSSC), Static Synchronous Compensator (STATCOM), and Unified Power Flow Controller (UPFC) in terms of improvement in transient stability. In neuro-fuzzy control method the simplicity of fuzzy systems and the ability of training in neural networks have been combined. The training data set the parameters of membership functions in fuzzy controller. This Adaptive Network Fuzzy Inference System (ANFIS) can track the given input-output data in order to conform to the desired controller. The maximization of energy function of UPFC is used as an objective function to generate the training data. Proposed method is tested on a single machine infinitive bus system to confirm its performance through simulation. The results prove the noticeable influence of ANFIS controlled UPFC on increasing Critical Clearing Time (CCT) of system.
  • Amaia Mendez, Noha El-Zehiry, Bego, Ntilde, A. Garc, Iacute, A. Zapirain, Adel Elmaghraby Page 55
    This paper presents the study of vocal videostroboscopic videos to detect morphological pathologies using an active contour segmentation and objective measurements. The ad-hoc designed active contour algorithm permits to obtain a robust and fast segmentation using vocal folds images in RGB format. In this work, we have employed connected component analysis as a post-processing tool. After the segmentation process the image is analyzed and the pathology can be localized automatically and we can extract some features of each fold (such as the size of the polyp or cyst, the glottal space, the position…). Experimental results demonstrate that the proposed method is effective. Our proposal segments correctly the 95% of database test videos and it shows a great advance in design. The objective measurements complete a new method to diagnose vocal folds pathologies