Results 1 - 10 of 31

Support Vector Classifier with Asymmetric Kernel Functions

by Koji Tsuda - in European Symposium on Artificial Neural Networks (ESANN , 1999
"... In support vector classifier, asymmetric kernel functions are not used so far, although they are frequently used in other kernel classifiers. The applicable kernels are limited to symmetric semipositive definite ones because of Mercer's theorem. In this paper, SVM is extended to be applicab ..."
Abstract - Cited by 22 (0 self) - Add to MetaCart
In support vector classifier, asymmetric kernel functions are not used so far, although they are frequently used in other kernel classifiers. The applicable kernels are limited to symmetric semipositive definite ones because of Mercer's theorem. In this paper, SVM is extended to be applicable to asymmetric kernel functions. It is proven that, when a positive definite kernel is given, the extended SVM is identical with the conventional SVM. In the 3D object recognition experiment, the extended SVM with asymmetric kernels performed better than the conventional SVM.
(Show Context)

About the locality of kernels in highdimensional spaces

by Damien Francois, Vincent Wertz, Michel Verleysen - International Symposium on Applied Stochastic Models and Data Analysis , 2005
"... Abstract. Gaussian kernels are widely used in many data analysis tools such as Radial-Basis Function networks, Support Vector Machines and many others. Gaus-sian kernels are most often deemed to provide a local measure of similarity between vectors. In this paper, we show that Gaussian kernels are a ..."
Abstract - Cited by 10 (3 self) - Add to MetaCart
Abstract. Gaussian kernels are widely used in many data analysis tools such as Radial-Basis Function networks, Support Vector Machines and many others. Gaus-sian kernels are most often deemed to provide a local measure of similarity between vectors. In this paper, we show that Gaussian kernels are adequate measures of similarity when the representation dimension of the space remains small, but that they fail to reach their goal in high-dimensional spaces. We suggest the use of p-Gaussian kernels that include a supplementary degree of freedom in order to adapt to the distribution of data in high-dimensional problems. The use of such more flexible kernel may greatly improve the numerical stability of algorithms, and also the discriminative power of distance- and neighbor-based data analysis methods.

Keystroke-based User Identification on Smart Phones

by Saira Zahid, Muhammad Shahzad, Syed Ali Khayam, Muddassar Farooq
"... Abstract. Smart phones are now being used to store users ’ identities and sensitive information/data. Therefore, it is important to authenticate legitimate users of a smart phone and to block imposters. In this paper, we demonstrate that keystroke dynamics of a smart phone user can be translated int ..."
Abstract - Cited by 10 (1 self) - Add to MetaCart
Abstract. Smart phones are now being used to store users ’ identities and sensitive information/data. Therefore, it is important to authenticate legitimate users of a smart phone and to block imposters. In this paper, we demonstrate that keystroke dynamics of a smart phone user can be translated into a viable feature set for accurate user identification. To this end, we collect and analyze keystroke data of 25 diverse smart phone users. Based on this analysis, we select six distinguishing keystroke features that can be used for user identification. We show that these keystroke features for different users are diffused and therefore a fuzzy classifier is well-suited to cluster and classify them. We then optimize the front-end fuzzy classifier using Particle Swarm Optimizer (PSO) and Genetic Algorithm (GA) as back-end dynamic optimizers to adapt to variations in usage patterns. Finally, we provide a novel keystroke dynamics based PIN verification mode to ensure information security on smart phones. The results of our experiments show that the proposed user identification system has an average error rate of 2 % after the detection mode and the error rate of rejecting legitimate users is dropped to zero after the PIN verification mode. We also compare error rates (in terms of detecting both legitimate users and imposters) of our proposed classifier with 5 existing state-of-the-art techniques for user identification on desktop computers. Our results show that the proposed technique consistently and considerably outperforms existing schemes. 1
(Show Context)

Exploring Touchscreen Biometrics for User Identification on Smart Phones

by Julio Angulo , 2011
"... Abstract. The use of mobile smart devices for storing sensitive infor-mation and accessing online services is increasing. At the same time, methods for authenticating users into their devices and online services that are not only secure, but also privacy and user-friendly are needed. In this paper, ..."
Abstract - Cited by 9 (0 self) - Add to MetaCart
Abstract. The use of mobile smart devices for storing sensitive infor-mation and accessing online services is increasing. At the same time, methods for authenticating users into their devices and online services that are not only secure, but also privacy and user-friendly are needed. In this paper, we present our initial explorations of the use of lock pat-tern dynamics as a secure and user-friendly two-factor authentication method. We developed an application for the Android mobile platform to collect data on the way individuals draw lock patterns on a touch-screen. Using a Random Forest machine learning classier this method achieves an average Equal Error Rate (EER) of approximately 10.39%, meaning that lock patterns biometrics can be used for identifying users towards their device, but could also pose a threat to privacy if the users' biometric information is handled outside their control.
(Show Context)

Neural virtual sensor for the inferential prediction of product quality from process variables

by R. Rallo , J. Ferre-Giné , A. Arenas , Francesc Giralt , 2002
"... ..."
Abstract - Cited by 8 (2 self) - Add to MetaCart
Abstract not found

A general approach to construct RBF net-based classifier," m

by Fabien Belloir, Antoine Fache, Alain Billat - Proceedings of the 7 th European Symposium on Artificial Neural Network , 1999
"... Abstract: This paper describes a global approach to the construction of Radial Basis Function (RBF) neural net classifier. We used a new simple algorithm to completely define the structure of the RBF classifier. This algorithm has the major advantage to require only the training set (no step learnin ..."
Abstract - Cited by 6 (1 self) - Add to MetaCart
Abstract: This paper describes a global approach to the construction of Radial Basis Function (RBF) neural net classifier. We used a new simple algorithm to completely define the structure of the RBF classifier. This algorithm has the major advantage to require only the training set (no step learning, threshold or other parameters as in other methods). Tests on several benchmark datasets showed, despite its simplicity, that this algorithm provides a robust and efficient classifier. The results of this built RBF classifier are compared to those obtained with three other classifiers: a classic one and two neural ones. The robustness and efficiency of this kind of RBF classifier make the proposed algorithm very attractive. 1.
(Show Context)

An Experiment on the Design of Radial Basis Function Neural Networks for Software Cost Estimation

by Ali Idri, Abdelali Zakrani, Azeddine Zahi - in 2nd IEEE International Conference on Information and Communication Technologies: from Theory to Applications
"... In spite of the several software effort estimation models developed over the last 30 years, providing accurate estimates of the software project under development is still unachievable goal. Therefore, many researchers are working on the development of new models and the improvement of the existing ..."
Abstract - Cited by 6 (2 self) - Add to MetaCart
In spite of the several software effort estimation models developed over the last 30 years, providing accurate estimates of the software project under development is still unachievable goal. Therefore, many researchers are working on the development of new models and the improvement of the existing ones using artificial intelligence techniques such as: case-based reasoning, decision trees, genetic algorithms and neural networks. This paper is devoted to the design of Radial Basis Function Networks for software cost estimation. It shows the impact of the RBFN network structure, especially the number of neurons in the hidden layer and the widths of the basis function, on the accuracy of the produced estimates measured by means of MMRE and Pred indicators. The empirical study uses two different software
(Show Context)

Recognition of Unconstrained Handwritten Numerals by a Radial Basis Function Neural Network Classifier

by Young-Sup Hwang, Sung-Yang Bang , 1997
"... Among the neural network models RBF(Radial Basis Function) network seems to be quite effective for a pattern recognition task such as handwritten numeral recognition since it is extremely flexible to accommodate various and minute variations in data. Recently we obtained a good recognition rate for ..."
Abstract - Cited by 5 (0 self) - Add to MetaCart
Among the neural network models RBF(Radial Basis Function) network seems to be quite effective for a pattern recognition task such as handwritten numeral recognition since it is extremely flexible to accommodate various and minute variations in data. Recently we obtained a good recognition rate for handwritten numerals by using an RBF network. In this paper we show how to design an RBF network classifier for a given problem in a well defined and easy-to-follow manner. We also report on the experiments to evaluate the performance of the RBF network classifier so designed. Keywords: radial basis function network, handwritten numeral recognition, pattern classification, clustering. 1 Introduction There are various methods for pattern classification problems like a handwritten numeral recognition and each of them has pros and cons. Table 1 presents a summary of the evaluation of the representative pattern classification methods based on training time, hardware requirement and classificat...

A Neural Network based Method for Brain Abnormality Detection in MR Images Using Gabor Wavelets

by Amirehsan Lashkari
"... Nowadays, automatic defects detection in MR images is very important in many diagnostic and therapeutic applications. This paper introduces a Novel automatic brain tumor detection method that uses T1, T2_weighted and PD, MR images to determine any abnormality in brain tissues. Here, has been tried t ..."
Abstract - Cited by 4 (0 self) - Add to MetaCart
Nowadays, automatic defects detection in MR images is very important in many diagnostic and therapeutic applications. This paper introduces a Novel automatic brain tumor detection method that uses T1, T2_weighted and PD, MR images to determine any abnormality in brain tissues. Here, has been tried to give clear description from brain tissues using Gabor wavelets, energy, entropy, contrast and some other statistic features such as mean, median, variance, correlation, values of maximum and minimum intensity.It is used from a feature selection method to reduce the feature space too. this method uses from neural network to do this classification. The purpose of this project is to classify the brain tissues to normal and abnormal classes automatically, that saves the radiologist time, increases accuracy and yield of diagnosis.

Advantages of Radial Basis Function Networks for Dynamic System Design” ieee transactions on industrial electronics

by Hao Yu, Student Member, Tiantian Xie, Stanisław Paszczyñski, Senior Member, Bogdan M. Wilamowski , 2011
"... Abstract—Radial basis function (RBF) networks have advan-tages of easy design, good generalization, strong tolerance to input noise, and online learning ability. The properties of RBF networks make it very suitable to design flexible control systems. This paper presents a review on different approac ..."
Abstract - Cited by 3 (1 self) - Add to MetaCart
Abstract—Radial basis function (RBF) networks have advan-tages of easy design, good generalization, strong tolerance to input noise, and online learning ability. The properties of RBF networks make it very suitable to design flexible control systems. This paper presents a review on different approaches of designing and train-ing RBF networks. The recently developed algorithm is introduced for designing compact RBF networks and performing efficient training process. At last, several problems are applied to test the main properties of RBF networks, including their generalization ability, tolerance to input noise, and online learning ability. RBF networks are also compared with traditional neural networks and fuzzy inference systems. Index Terms—Adaptive control, fuzzy inference systems, neural networks, online learning, radial basis function (RBF) networks. I. BACKGROUND
(Show Context)