The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
It has been 50 years since the idea popped up that calculating systems can be made on the replica of the biological neural networks. Still, the development of this science branch made the improvement of these systems possible only in the last 25-30 years. Nowadays, neural computing is a very extensive, separate science. Its solid theory basis made it possible to use them to solve many kind of problems...
A new fault diagnosis system is proposed to recognize the faults of gear box in this paper by using the NMF-based characteristics extracting method and the neural networks technique. The results show that this method is effective for the fault diagnosis of gear box.
In this paper we have proposed a new way to achieve the optimum learning rate that can reduce the learning time of the multi layer feed forward neural network. The effect of optimum numbers of inner iterations and numbers of hidden nodes on learning time and recognition rate has been shown. The Principal Component Analysis and Multilayer Feed Forward Neural Network are applied in face recognition...
A novel method to diagnose the bearing fault is presented. The proposed method is based on the analysis of the bearing vibration signals using Singular Spectrum Analysis (SSA). SSA is a non-parametric technique of time series analysis that decomposes the acquired bearing vibration signals into an additive set of time series to extract information correlated with the condition of the bearing. Information...
A hybrid particle swarm optimization (PSO)-based wavelet neural network (WNN) for Video OCR is presented in this paper. Video OCR is an important task towards enabling automatic content-based retrieval of digital video databases. However, since text is often displayed against a complex background, its detection and extraction is a challenging problem. In this paper, wavelet transformation is done...
In order to improve the recognition rate of the early fire, this paper analyzed the relationship between the image resolution and fire recognition rate from the application point of view. On this basis, we have adopted the Dempster-Shafer evidence theory and carried on the recognition experiment to the different resolution fire image under different environmental conditions. The simulation experimental...
This paper presents an off-line signature verification system composed of a combination of several different classifiers. Identity authentication is a very important characteristics specially in systems that requires a high degree of security such as in bank transactions. In our experiments, one-class classifier was used to create a signature verification system, consequently only genuine signatures...
In this work, we proposed a novel authentication system based on facial features. The proposed method is based on PCA and LDA for feature extraction, these extracted features are combined using wavelet fusion. In this work we use neural networks to classify extracted features of faces. The proposed method consists of six steps: i) Extraction of images from the database, ii) Preprocessing, iii) Feature...
In this paper, we further develop the idea of subject specific mental tasks selection process as a necessary prerequisite in any EEG-based brain computer interface (BCI) application. While, in two previous researches we proved - using the EEG-extracted auto-regressive (AR) parameters and twelve different mental tasks -, the major gains one can obtain in tasks classification performance only by selecting...
HVS theory plays important role in the application of digital image watermarking technique. When inserting watermarking, the visual masking feature of HVS could be fully used to design digital watermarking algorithm with good perceived performance. When extracting watermarking from the damaged image, human's visual feature could be combined to recover the damaged image so as to obtain better effect...
In this paper we are using Devanagari script OCR for recognition. The handwritten data set is created by us and for printed characters we have used ISM font. Here we are using gradient and curvature based feature extraction method. We have compared Nearest Neighbor, K-Nearest Neighbor, Euclidian Distance-based K-NN, Cosine Similarity -based K-NN, Condensed Nearest Neighbor, Reduced Nearest neighbor,...
Relation Extraction is an important research field in Information Extraction. In this paper, we present a novel mixed model to extract relation between named entities in Chinese, which combines the merits of both feature based method and tree kernel based method. Feature based method captures the language information of the text, while, the tree kernel based method shows the structured information...
Under the competition pressure and driven by the technology development, the number of value-added services will increase very rapidly to improve the ARPU (average revenue per user) of the telecom industries. That makes the feature interaction (FI) problem more serious in the emerging telecom system. Besides, to make the creation of a feature easier, service design is open to the third party in a...
Illumination and expression variation are the major challenges in the face recognition. This paper presents comparative analysis of two normalization techniques namely, DCT in Log domain and 2-point normalization method.. The DCT is employed to compensate for illumination variations in the logarithm domain. Since illumination variation lies mainly in the low frequency band, an appropriate number of...
In order to improve the recognition rate of the early fire, this paper analyzed the relationship between the image resolution and fire recognition rate from the application point of view. On this basis, we have adopted the Dmpster-Shafer evidence theory and carried on the recognition experiment to the different resolution fire image under different environmental conditions. The simulation experimental...
This paper explores Bhattacharyya Distance principle and introduces it to recognize stego algorithms in use. First of all, we select the most important features by the means of applying Bhattacharyya distance. Then, BP neural network is used to classify cover and stego images. Extensive experimental works show that the proposed schemes have satisfactory performance on Jpeg steganography like F5, Outguess,...
Recent advances in neuroimaging demonstrate the potential use of functional near infrared spectroscopy (fNIRS) in the field of brain machine interface. An fNIRS uses light in the near infrared range to measure brain surface hemoglobin concentrations to determine a neural activity. The current study presents our empirical results in realizing fNIRS - BCI system. We analyze the hemodynamic responses...
In the last decade significant progress in computer vision based control of unmanned ground vehicles (UGV) has been achieved. However, until now textural information has been somewhat less effective than color or laser range information. In this paper we propose a computer vision based cross country segmentation system that is capable of distinguishing cross-country road, grass and trees during day-time...
Intelligent Space (IS), a kind of intelligent home, is one of the popular of the applying RT into our daily life. In intelligent space environment, human behavior is one of the meaningful information for interpretation of our intention and needs. In this paper, we proposed the human posture recognition approach which focuses on a top-view vision. A top-view vision enables our system to observe the...
This research aims at developing an optimal neural network based DSS, which is aimed at precise and reliable diagnosis of chronic active hepatitis (CAH) and cirrhosis (CRH). The principal component analysis neural network is designed scrupulously for classification of these diseases. The neural network is trained by eight quantified texture features, which were extracted from five different region...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.