Search

This paper is concerned with a multi-resolution tool for analysis of a time series aiming to detect abnormalities in various frequency regions. The task is treated as a kernel based novelty detection applied to a multi-level time series representation obtained from the discrete wavelet transform. Having a priori knowledge that the abnormalities manifest themselves in several frequency regions, a committee of detectors utilizing data dependent aggregation weights is build by combining outputs of detectors operating in those regions. [ABSTRACT FROM AUTHOR]

Several features of today's grid are based on centralized or hierarchical services. However, as the grid size increasing, some of their functions especially resource discovery should be decentralized to avoid performance bottlenecks and guarantee scalability. A novel grid resource discovery method based on adaptive k-Nearest Neighbors clustering is presented in this paper. A class is formed by a collection of nodes with some similarities in their characteristics, each class is managed by a leader and consists of members that serve as workers. Resource requests are ideally forwarded to an appropriate class leader that would then direct it to one of its workers. This method can handle resource requests by searching a small subset out of a large number of nodes by resource clustering which can improve the resource query efficiency; on the other hand, it also achieves well scalability by managing grid resources with adaptive mechanism. It is shown from a series of experiments that the method presented in this paper achieves more scalability and efficient lookup performance than other existing methods. [ABSTRACT FROM AUTHOR]

In this paper we propose a two-pass classification method and apply it to face recognitions. The method is obtained by integrating together two approaches, the hyper-ellipsoid neural networks (HENN's) and the SVM's with error correcting codes. This method realizes a classification operation in two passes: the first one is to get an intermediate classification result for an input sample by using the HENN's, and the second pass is followed by using the SVM's to re-classify the sample based on both the input data and the intermediate result. Simulations conducted in the paper for applications to face recognition showed that the two-pass method can maintain the advantages of both the HENN's and the SVM's while remedying their disadvantages. Compared with the HENN's and the SVM's, a significant improvement of recognition performance over them has been achieved by the new method. [ABSTRACT FROM AUTHOR]

This paper introduces a new paradigm to realize various types of cryptographic primitives such as authenticated key exchange and key encapsulation in the standard model under three standard assumptions: the decisional Diffie-Hellman (DDH) assumption, target collision resistant (TCR) hash functions and pseudo-random functions (PRFs). We propose the first (PKI-based) two-pass authenticated key exchange (AKE) protocol that is comparably as efficient as the existing most efficient protocols like MQV and that is secure in the standard model (under these standard assumptions), while the existing efficient two-pass AKE protocols such as HMQV, NAXOS and CMQV are secure in the random oracle model. Our protocol is shown to be secure in the (currently) strongest security definition, the extended Canetti-Krawczyk (eCK) security definition introduced by LaMacchia, Lauter and Mityagin. This paper also proposes a CCA-secure key encapsulation mechanism (KEM) under these assumptions, which is almost as efficient as the Kurosawa-Desmedt KEM. This scheme is also secure in a stronger security notion, the chosen public-key and ciphertext attack (CPCA) security. The proposed schemes in this paper are redundancy-free (or validity-check-free) and the implication is that combining them with redundancy-free symmetric encryption (DEM) will yield redundancy-free (e.g., MAC-free) CCA-secure hybrid encryption. [ABSTRACT FROM AUTHOR]

This paper presents an approach for solving the driving load forecasting problem based on Cascade Neural Networks with node-decoupled extended Kalman Filtering (CNN-NDEKF). Because of the inherent advantages, hybrid electric vehicles (HEV) are being given more and more attention. The power control strategy of HEVs is the key technology which determines the HEV's efficiency and pollutive emission level. Since the extent of improvement involved with HEV power control strategies greatly depends on the future driving load forecasting, in this paper, we attempt to achieve driving load forecasting using CNN-NDEKF. Instead of forecasting the entire load sequence, we define 5 load levels by a fuzzy logic method and then we forecast the load level. Simulation study is given to illustrate the feasibility of the driving load forecasting approach. [ABSTRACT FROM AUTHOR]

Aiming at improving the convergence performance of conventional BP neural network, this paper presents an improved PSO algorithm instead of gradient descent method to optimize the weights and thresholds of BP network. The strategy of the algorithm is that in each iteration loop, on every dimension d of particle swarm containing n particles, choose the particle whose velocity decreases most quickly to mutate its velocity according to some probability. Simulation results show that the new algorithm is very effective. It is successful to apply the algorithm to gas turbine fault diagnosis. [ABSTRACT FROM AUTHOR]

In this paper, we study the Cohen-Grossberg neural networks with mixed time-varying delays. By applying the Lyapunov functional method and combining with the inequality 3abc ≤ a3 + b3 + c3 (a,b,c > 0) technique, a series of new and useful criteria on the existence of equilibrium point and its global asymptotical stability are established. The results obtained in this paper extend and generalize the corresponding results existing in previous literature. [ABSTRACT FROM AUTHOR]

This paper studies a general class of neural networks with time-varying delays and the neuron activations belong to the set of discontinuous monotone increasing functions. The discontinuities in the activations are an ideal model of the situation where the gain of the neuron amplifiers is very high. Because the delay in combination with high-gain nonlinearities is a particularly harmful source of potential instability, in the paper, conditions which ensure the global convergence of the neural network are derived. [ABSTRACT FROM AUTHOR]

Electromagnetic (EM)-based neural network (NN) approaches have recently gained recognition as unconventional and useful methods for radio frequency (RF) components modeling. In this paper, several improvement techniques including a new data preprocessing technique and an improved training algorithm are presented. Comprehensive cases are compared in this paper. The experimental results indicate that with these techniques, the modified model has better performance. [ABSTRACT FROM AUTHOR]

Raster map should be corrected after scanned because of the errors caused by paper map deformation. In the paper, the deficiency of the polynomial fitting method is analyzed. The paper introduces an ANN (Artificial Neural Network) correcting method that utilizes the advantage of its function approximation ability. In the paper, two types of ANNs, BP and GRNN, are designed for the correcting. The comparing experiment is done with the same data by the polynomial fitting and ANN methods, utilizing the MALAB. The experiment results show that the ANN methods, especially the GRNN method, performances far better than the polynomial fitting method does. [ABSTRACT FROM AUTHOR]

In this paper, we present some new results on impossible differential cryptanalysis of reduced AES, which update the best known impossible differential attacks on reduced AES. First, we present some new attacks on 6-round AES (for all the three key length). Second, we extend to 7-round AES, also for all the three key variants. Especially for 128-bit keys, the best known results can attack up to 7 rounds using square attack and collision attack respectively, but their complexity are both marginal either on data or on time (ie. require nearly the entire codebook, or close to key exhaustive search). In this sense, our attack is the first non-marginal one on 7-round AES with 128-bit keys. Thirdly, we extend to 8 rounds for 256-bit keys, which is also non-marginal compared with the best non-related-key attacks so far. Finally, we give an improvement of the 7-round attack for 192-bit keys in R.C.W.Phan's paper, which makes the time complexity reduced greatly. [ABSTRACT FROM AUTHOR]

An optimization algorithm for dynamic Bayesian networks (DBN) based on Bayesian optimization algorithm (BOA) is developed for learning and constructing the DBN structure. In this paper, we first introduce some basic theories and concepts of probability model evolutionary algorithm. Then we describe, the basic mode for constructing DBN diagram and the mechanism of DBN structure learning based on BOA. The DBN structure learning based on BOA consists of two parts. The first part is to obtain the structure and parameters of DBN in terms of a good solution, and the second part is to produce new groups according to the obtained DBN structure. In this paper, the DBN learning is achieved by genetics algorithm based on a greedy mechanism. The DBN inference is performed by a forward-simulation algorithm. Simulation results are provided to demonstrate the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Generalization problem is a key problem in NN society, which can be grouped into two classes: the generalization problem with unlimited size of training sample and that with limited size of training sample. The generalization problem with limited size of training sample is considered in this paper. Similar to margin maximization criterion in SVM, we propose a margin maximization training algorithm for BP network to further improve the generalization ability of BP network. Experimental results show that the margin maximization training algorithm proposed in this paper does improve the performance of BP network, and shows a comparable performance with SVM. [ABSTRACT FROM AUTHOR]

Chaotic noise cancellation has potential application in both secret communication and radar target identification. To solve the problem of parameter estimation in chaotic noise, a novel radial basis function neural network (RBF-NN) -based chaotic time series data modeling method is presented in this paper. Together with the spectral analysis technique, the algorithm combines neural network's ability to approximate any nonlinear function. Based on the flexibility of RBF-NN predictor and classical amplitude spectral analysis technique, this paper proposes a new algorithm for parameter estimation in chaotic noise. Analysis of the proposed algorithm's principle and simulation experiments results are given out, which show the effective of the proposed method. We conclude that the study has potential application in various fields as in secret communication for narrow band interference rejection or attenuation and in radar signal processing for weak target detection and identification in sea clutter. [ABSTRACT FROM AUTHOR]

The controlled system is an uncertain nonlinear differential-algebraic subsystem (DASs) in a large-scale system. The problem of robust stabilization for such class of uncertain nonlinear DASs is considered in this paper. The robust stabilization controller is proposed based on backstepping approach using two-layer Artificial Neural Networks (ANN) whose weights are updated on-line. The closed-loop error systems are uniformly ultimately bounded (UUB) and the error of convergence can be made arbitrarily small. Finally, using the design scheme proposed in this paper, a governor controller is designed for one synchronous generator in a multi-machine power systems. The simulation results demonstrate the effectiveness of the proposed scheme. [ABSTRACT FROM AUTHOR]

This paper develops a new blind channel identification method in frequency domain. Oversampled signal has the property of spectral redundancy in frequency domain which is corresponding to the cyclostationarity property in time domain. This method exploits the cyclostationarity of oversampled signals to identify possibly non-minimum phase FIR channels. Unlike many existing methods, this method doesn't need EVD or SVD of correlation matrix. Several polynomials are constructed and zeros of channels are identified through seeking for common zeros of those polynomials. It is in the similar spirit of Tong's frequency approach, but this new algorithm is much simpler and computationally more efficient. A sufficient and necessary condition for channel identification is also provided in this paper. This condition is quite similar to Tong's time domain theory but it is derived from a novel point of view. [ABSTRACT FROM AUTHOR]

Most of the algorithms proposed in the literature deal with the problem of digital modulation classification and consider classic probabilistic or decision tree classifiers. In this paper, we compare and analyze the performance of 2 neural network classifiers and 3 support vector machine classifiers (i.e. 1-v-r type, 1-v-1 type and DAG type multi-class classifier). This paper also deals with the modulation classification problems of classifying both analog and digital modulation signals in military and civilian communications applications. A total of 7 statistical signal features are extracted and used to classify 9 modulation signals. It is known that the existing technology is able to classify reliably (accuracy ≥ 90%) only at SNR above 10dB when a large range of modulation types including both digital and analog is being considered. Numerical simulations were conducted to compare performance of classifiers. Results indicated an overall success rate of over 95% at the SNR of 10dB in all classifiers. Especially, it was shown that 3 support vector machine classifiers can achieve the probabilities of correct classification (Pcc) of 96.0%, 97.3% and 97.8% at the SNR of 5dB, respectively. [ABSTRACT FROM AUTHOR]

Currently, there is little quantitative research on macroscopic real estate finance at home and abroad. Seen from the whole system of real estate finance, this paper chooses 14 main indexes to compose an evaluation index system. Based on the evaluation index system, an error -back-propagation BP network model is built to evaluate the growth of real estate finance. Data of real estate financial system from 1997-2005 are used as train and test samples of BP neural network. After training, the BP neural network is used to evaluate and forecast by simulation. Through the good accuracy of evaluation and forecasting, the model is proved to be very efficient. By comparing the growing difference of two adjacent years and analyzing the related macro financial policies in related years, the running effect of related real estate financial policies in related years is gained. So by using the evaluation model of this paper, decision makers can decide to use what kind of macro adjusting and controlling policies to gain anticipated aim of real estate finance in the future. [ABSTRACT FROM AUTHOR]

Recently, the distribution and using of the digital multimedia contents are easy by developing the internet application program and related technology. However, the digital signal is easily duplicated and the duplicates have the same quality compare with original digital signal. To solve this problem, there is the multimedia fingerprint which is studied for the protection of copyright. Fingerprinting scheme is a technique which supports copyright protection to track redistributors of electronic information using cryptographic techniques. Only regular user can know the inserted fingerprint data in fingerprinting schemes differ from a symmetric/asymmetric scheme and the scheme guarantee an anonymous before re-contributed data. In this paper, we present a new scheme which is the detection of colluded multimedia fingerprint by neural network. This proposed scheme is consists of the anti-collusion code generation and the neural network for the error correction. Anti-collusion code based on BIBD(Balanced Incomplete Block Design) was made 100% collusion code detection rate about the average linear collusion attack, and the Hopfield neural network using (n,k) code designing for the error bits correction confirmed that can correct error within 2bits. [ABSTRACT FROM AUTHOR]

Code reuse in software reuse has several limitations such as difficulties of understanding and retrieval of the reuse code written by other developers. To overcome these problems, it should be possible to reuse the analysis/design information than source code itself. In this paper, I present analogical matching techniques for the reuse of object models and design patterns. We have suggested the design patterns as reusable components and the representation techniques to store them. The contents of the paper are as follows. 1) Analogical matching functions to retrieve analogous design patterns from reusable libraries. 2) The representation of reusable components to be stored in the library in order to support the analogical matching. [ABSTRACT FROM AUTHOR]

According to analysis of both neuro-electrophysiological experimental data and the biophysical properties of neurons, in early research paper we proposed a new biophysical model that reflects the property of energy coding in neuronal activity. On the based of the above research work, in this paper the proposed biophysical model can reproduce the membrane potentials and the depolarizing membrane current by means of neuro-electrophysiological experimental data. Combination with our previous research results, the proposed biophysical model is demonstrated again to be more effective compared with known biophysical models of neurons. [ABSTRACT FROM AUTHOR]

The existence and global asymptotic stability of a large class of Cohen-Grossberg neural networks is discussed in this paper. Previous papers always assume that the amplification function has positive lower and upper bounds, which excludes a large class of functions. In our paper, it is only needed that the amplification function is positive. Also, the model discussed is general, the method used is direct and the conditions needed are weak. [ABSTRACT FROM AUTHOR]

The paper investigates the existence and global stability of periodic solution of non-autonomous neural networks with delay. Then the existence and uniqueness of periodic solutions of the neural networks are discussed in the paper. Moreover, criterion on stability of periodic solutions of the neural networks is obtained by using matrix function inequality, and algorithm for the criterion on the neural networks is provided. Result in the paper generalizes and improves the result in the existing references. In the end, an illustrate example is given to verify our results. [ABSTRACT FROM AUTHOR]

This paper mainly discusses a generic scheme for on-line adaptive critic design for nonlinear system based on neural dynamic programming (NDP), more exactly, an improved action-depended dual heuristic dynamic programming (ADDHP) method. The principal merit of the proposed method is to avoid the model neural network which predicts the state of next time step, and only use current and previous states in the method, as makes the algorithm more suitable for real-time or on-line application for process control. In this paper, convergence proof of the method will also be given to guarantee the control to reach the optimal. At last, simulation result verifies the performance. [ABSTRACT FROM AUTHOR]

This paper discusses a new application of adaptive dynamic programming (ADP). Meanwhile, traffic control as an important factor in social development is a valuable research topic. Considering with advancement of ADP and importance of traffic control, this paper present a new signal control in a single intersection. Simulation results show that the proposed signal control is valid. [ABSTRACT FROM AUTHOR]

This paper presents a model predictive control (MPC) based on a neural network (NN) model for air/fuel ration (AFR) control of automotive engines. The novelty of the paper is that the severe nonlinearity of the engine dynamics are modelled by a NN to a high precision, and adaptation of the NN model can cope with system uncertainty and time varying effects. A single dimensional optimization algorithm is used in the paper to speed up the optimization so that it can be implemented to the engine fast dynamics. Simulations on a widely used mean value engine model (MVEM) demonstrate effectiveness of the developed method. [ABSTRACT FROM AUTHOR]

This paper considers the quantum query complexity of ε-biased oracles that return the correct value with probability only 1/2 + ε. In particular, we show a quantum algorithm to compute N-bit OR functions with $O(\sqrt{N}/{\varepsilon})$ queries to ε-biased oracles. This improves the known upper bound of $O(\sqrt{N}/{\varepsilon}^2)$ and matches the known lower bound; we answer the conjecture raised by the paper [1] affirmatively. We also show a quantum algorithm to cope with the situation in which we have no knowledge about the value of ε. This contrasts with the corresponding classical situation, where it is almost hopeless to achieve more than a constant success probability without knowing the value of ε. [ABSTRACT FROM AUTHOR]

It is often believed that the performance of ant system, and in general of ant colony optimization algorithms, depends somehow on the scale of the problem instance at hand. The issue has been recently raised explicitly [1] and the hyper-cube framework has been proposed to eliminate this supposed dependency. In this paper, we show that although the internal state of ant system—that is, the pheromone matrix—depends on the scale of the problem instance under analysis, this does not affect the external behavior of the algorithm. In other words, for an appropriate initialization of the pheromone, the sequence of solutions obtained by ant system does not depend on the scale of the instance. As a second contribution, the paper introduces a straightforward variant of ant system in which also the pheromone matrix is independent of the scale of the problem instance under analysis. [ABSTRACT FROM AUTHOR]

This paper analyses the chaotic characteristics of violent abnormal vibration signals of a large rolling mill, and studies phase space reconstruction techniques of the signals. On this basis, the vibration model of wavelet neural networks and the model of backpropagation neural networks are set up, respectively, through inversion methods. The properties of these two models are tested and compared with each other. The result shows that the wavelet neural networks have an advantage over the backpropagation neural networks in rapid convergence and high accuracy. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new framework to provide continuous services to users by a collection of mobile servers distributed over an interconnection network. We model those mobile servers as a subset of host computers, and assume that a user host can receive the service if at least one adjacent host computer (including itself) plays the role of a server; i.e., we assume that the service could not be routed via the interconnection network. The main results obtained in this paper are summarized as follows: For the class of trees with n hosts, ⌈(n+1)/2⌉ mobile servers are necessary and sufficient to realize continuous services by the mobile servers, and for the class of Hamiltonian graphs with n hosts, ⌈(n+1)/3⌉ mobile servers are necessary and sufficient. [ABSTRACT FROM AUTHOR]

In an orthogonal projection of a convex polyhedron P the visibility ratio of a face f (similarly of an edge e) is the ratio of orthogonally projected area of f (length of e) and its actual area (length). In this paper we give algorithms for nice projections of P such that the minimum visibility ratio over all visible faces (over all visible edges) is maximized. [ABSTRACT FROM AUTHOR]

In a planar straight-line drawing of a tree T on k layers, each vertex is placed on one of k horizontal lines called layers and each edge is drawn as a straight-line segment. A planar straight-line drawing of a rooted tree T on k layers is called an upward drawing of T on k layers if, for each vertex u of T, no child of u is placed on a layer vertically above the layer on which u has been placed. For a tree T having pathwidth h, a linear-time algorithm is known that produces a planar straight-line drawing of T on ⌈3h/2⌉ layers. A necessary condition characterizing trees that admit planar straight-line drawings on k layers for a given value of k is also known. However, none of the known algorithms focuses on drawing a tree on the minimum number of layers. Moreover, although an upward drawing is the most useful visualization of a rooted tree, the known algorithms for drawing trees on k layers do not focus on upward drawings. In this paper, we give a linear-time algorithm to compute the minimum number of layers required for an upward drawing of a given rooted tree T. If T is not a rooted tree, then we can select a vertex u of T in linear time such that an upward drawing of T rooted at u would require the minimum number of layers among all other upward drawings of T rooted at the vertices other than u. We also give a linear-time algorithm to obtain an upward drawing of a rooted tree T on the minimum number of layers. [ABSTRACT FROM AUTHOR]

This paper deals with the Circular Pattern Matching Problem (CPM). In CPM, we are interested in pattern matching between the text $\mathcal T$ and the circular pattern $\mathcal C(\mathcal P)$ of a given pattern $\mathcal P = \mathcal P_1 \ldots \mathcal P_m$. The circular pattern $\mathcal C(\mathcal P)$ is formed by concatenating $\mathcal P_1$ to the right of $\mathcal P_m$. We can view $\mathcal C(\mathcal P)$ as a set of m patterns starting at positions j ∈ [1..m] and wrapping around the end and if any of these patterns matches $\mathcal T$, we find a match for $\mathcal C(\mathcal P)$. In this paper, we present two efficient data structures to index circular patterns. This problem has applications in pattern matching in geometric and astronomical data as well as in computer graphics and bioinformatics. [ABSTRACT FROM AUTHOR]

Linear Feedback Shift Registers (LFSRs) are used as building blocks for many stream ciphers, wherein, an n-degree primitive connection polynomial is used as a feedback function to realize an n-bit LFSR. This paper shows that such LFSRs are susceptible to power analysis based Side Channel Attacks (SCA). The major contribution of this paper is the observation that the state of an n-bit LFSR can be determined by making O(n) power measurements. Interestingly, neither the primitive polynomial nor the value of n be known to the adversary launching the proposed attack. The paper also proposes a simple countermeasure for the SCA that uses n additional flipflops. [ABSTRACT FROM AUTHOR]

The Data Encryption Standard (DES) is a 64-bit block cipher. Despite its short key size of 56 bits, DES continues to be used to protect financial transactions valued at billions of Euros. In this paper, we investigate the strength of DES against attacks that use a limited number of plaintexts and ciphertexts. By mounting meet-in-the-middle attacks on reduced-round DES, we find that up to 6-round DES is susceptible to this kind of attacks. The results of this paper lead to a better understanding on the way DES can be used. [ABSTRACT FROM AUTHOR]

In this paper, we study the security of AES-192 against related-key differential-linear cryptanalysis, which is the first attempt using this technique. Among our results, we present two variant attacks on 7-round AES-192 and one attack on 8 rounds using a 5-round related-key differential-linear distinguisher. One key point of the construction of the distinguisher is the special property of MC operation of AES. Compared with the best known results of related-key impossible differential attacks and related-key rectangle attacks on AES-192, the results presented in this paper are not better than them, but the work is a new attempt, and we hope further work may be done to derive better results in the future. [ABSTRACT FROM AUTHOR]

The stream cipher TPypy has been designed by Biham and Seberry in January 2007 as the strongest member of the Py-family ciphers, after weaknesses in the other members Py, Pypy, Py6 were discovered. One main contribution of the paper is the detection of related-key weaknesses in the Py-family of ciphers including the strongest member TPypy. Under related keys, we show a distinguishing attack on TPypy with data complexity 2192.3 which is lower than the previous best known attack on the cipher by a factor of 288. It is shown that the above attack also works on the other members TPy, Pypy and Py. A second contribution of the paper is design and analysis of two fast ciphers RCR-64 and RCR-32 which are derived from the TPy and the TPypy respectively. The performances of the RCR-64 and the RCR-32 are 2.7 cycles/byte and 4.45 cycles/byte on Pentium III (note that the speeds of the ciphers Py, Pypy and RC4 are 2.8, 4.58 and 7.3 cycles/byte). Based on our security analysis, we conjecture that no attacks lower than brute force are possible on the RCR ciphers. [ABSTRACT FROM AUTHOR]

We characterize the traceability properties of linear codes. It is well known that any code of length n and minimum distance d is a c-TA code if c2 < n/(n − d). In this paper, we show that a less restrictive condition can be derived. In other words, there exists a value ZC, with n − d ≤ ZC ≤ c(n − d), such that any linear code is c-TA if c < n/ZC. We also prove that in many cases this condition is also necessary. These results are applied to cyclic and Reed-Solomon codes. [ABSTRACT FROM AUTHOR]

Detecting the boundaries of protein domains has been an important and challenging problem in experimental and computational structural biology. In this paper the domain detection is first taken as an imbalanced data learning problem. A novel undersampling method using distance-based maximal entropy in the feature space of SVMs is proposed. On multiple sequence alignments that are derived from a database search, multiple measures are defined to quantify the domain information content of each position along the sequence. The overall accuracy is about 87% together with high sensitivity and specificity. Simulation results demonstrate that the utility of the method can help not only in predicting the complete 3D structure of a protein but also in the machine learning system on general imbalanced datasets. [ABSTRACT FROM AUTHOR]

Provide these intelligent medical services, it is necessary to understand the situation information generated in a hospital. There should be infra technologies that can classify and control the information for processing situation data, not mere collection of conceptual information, with clear standards. This paper, as a study to seize the information generated from medical situation more clearly, understood the property of data using neural network and applied the security ratings of information so that the system to provide the user appropriate to designated rating with analyzed medical information is established. It will be an effective measure to enhance the effectiveness of medical devices and backup data already introduced and understand the various medical data that will be generated from medical devices to be introduced. [ABSTRACT FROM AUTHOR]

An edge detection method by combining image entropy and Self -Organizing Map (SOM) is proposed in this paper. First, according to information theory image entropy is used to curve up the smooth region and the region of gray level abruptly changed. Then we transform the gray level image to ideal binary pattern of pixels. We define six classes' edge and six edge prototype vectors. These edge prototype vectors are fed into input layer of the Self-Organizing Map (SOM). Classifying the type of edge through this network, the edge image is obtained. At last, the speckle edges are discarded from the edge image. Experimental results show that it gained better edge image compared with Canny edge detection method. [ABSTRACT FROM AUTHOR]

With the development of Intelligent Transport Systems (ITS), automatic license plate recognition (LPR) plays an important role in numerous applications in reality. In this paper, a coarse to fine algorithm to detect license plates in images and video frames with complex background is proposed. First, the method based on Component Connect (CC) is used to detect the possible license plate regions in the coarse detection. Second, the method based on texture analysis is applied in the fine detection. Finally, a BP Neural Network is adopted as classifier, parts of the features is selected based on statistic diagram to make the network efficient. The average accuracy of detection is 95.3% from the images with different angles and different lighting conditions. [ABSTRACT FROM AUTHOR]

In this paper, synchronization is investigated for an array of nonlinearly coupled identical connected neural networks with delay. By employing the Lyapunov functional method and the Kronecker product technique, several sufficient conditions are derived. It is shown that global exponential synchronization of the coupled neural networks is guaranteed by a suitable design of the coupling matrix, the inner linking matrix and some free matrices representing the relationships between the system matrices. The conditions obtained in this paper are in the form of linear matrix inequalities, which can be easily computed and checked in practice. A typical example with chaotic nodes is finally given to illustrate the effectiveness of the proposed synchronization scheme. [ABSTRACT FROM AUTHOR]

Of the possible interactions between human and robot, touch is an important means of providing human beings with emotional relief. However, most previous studies have focused on interactions based on voice and images. In this paper, a method of recognizing human touching behaviors is proposed for developing a robot that can naturally interact with humans through touch. In this method, the recognition process is divided into pre-process phase and recognition phase. In the pre-process phase, recognizable characteristics are calculated from the data generated by the touch detector which was fabricated using force sensors. The force sensor used an FSR (force sensing register). The recognition phase classifies human touching behaviors using a multi-layer perceptron which is a neural network model. We measured three different human touching behaviors for six men. The human touching behaviors are ‘hitting,' 'stroking,' and ‘tickling'. In the test conducted with recognizers generated for each user, the average recognition rate was 93.8%, while the test conducted with a single recognizer showed a 79.8% average recognition rate. These results show the feasibility of the proposed human touching behavior recognition method. [ABSTRACT FROM AUTHOR]

This paper investigates the construction of a wide class of singlehidden layer neural networks (SLNNs) with or without tunable parameters in the hidden nodes. It is a challenging problem if both the parameter training and determination of network size are considered simultaneously. Two alternative network construction methods are considered in this paper. Firstly, the discrete construction of SLNNs is introduced. The main objective is to select a subset of hidden nodes from a pool of candidates with parameters fixed ‘a priori'. This is called discrete construction since there are no parameters in the hidden nodes that need to be trained. The second approach is called continuous construction as all the adjustable network parameters are trained on the whole parameter space along the network construction process. In the second approach, there is no need to generate a pool of candidates, and the network grows one by one with the adjustable parameters optimized. The main contribution of this paper is to show that the network construction can be done using the above two alternative approaches, and these two approaches can be integrated within a unified analytic framework, leading to potentially significantly improved model performance and/or computational efficiency. [ABSTRACT FROM AUTHOR]

At present, most of the algorithms for learning Bayesian Networks (BNs) use EM algorithm to deal with incomplete data. They are of low efficiency because EM algorithm has to perform iterative process of probability reasoning to complete the incomplete data. In this paper we present an efficient BN learning algorithm, which use the combination of EMI method and a scoring function based on mutual information theory. The algorithm first uses EMI method to estimate, from incomplete data, probability distributions over local structures of BNs, then evaluates BN structures with the scoring function and searches for the best one. The detailed procedure of the algorithm is depicted in the paper. The experimental results on Asia and Alarm networks show that when achieving high accuracy, the algorithm is much more efficient than two EM based algorithms, SEM and EM-EA algorithms. [ABSTRACT FROM AUTHOR]

Fuzzy Petri net (FPN) is a powerful modeling tool for fuzzy production rules based knowledge systems. But it is lack of learning mechanism, which is the main weakness while modeling uncertain knowledge systems. Fuzzy neural Petri net (FNPN) is proposed in this paper, in which fuzzy neuron components are introduced into FPN as a sub-net model of FNPN. For neuron components in FNPN, back propagation (BP) learning algorithm of neural network is introduced. And the parameters of fuzzy production rules in FNPN neurons can be learnt and trained by this means. At the same time, different neurons on different layers can be learnt and trained independently. The FNPN proposed in this paper is meaningful for Petri net models and fuzzy systems. [ABSTRACT FROM AUTHOR]

Consumer demand for intelligent battery charges is increasing as portable electronic applications continue to grow. Fast charging of battery packs is a problem which is difficult, and often expensive, to solve using conventional techniques. Conventional techniques only perform a linear approximation of a nonlinear behavior of a battery packs. The battery charging is a nonlinear electrochemical dynamic process and there is no exact mathematical model of battery. Better techniques are needed when a higher degree of accuracy and minimum charging time are desired. In this paper we propose soft computing approach based on fuzzy recurrent neural networks (RFNN) training by genetic algorithms to control batteries charging process. This technique does not require mathematical model of battery packs, which are often difficult, if not impossible, to obtain. Nonlinear and uncertain dynamics of the battery pack is modeled by recurrent fuzzy neural network. On base of this FRNN model, the fuzzy control rules of the control system for battery charging is generated. Computational experiments show that the suggested approach gives least charging time and least Tend-Tstart results according to the other intelligent battery charger works. [ABSTRACT FROM AUTHOR]

The small world phenomenon, a.k.a. the six degree of separation between individuals, was identified by Stanley Milgram at the end of the 60s. Milgram experiment demonstrated that letters from arbitrary sources and bound to an arbitrary target can be transmitted along short chains of closely related individuals, based solely on some characteristics of the target (professional occupation, state of leaving, etc.). In his paper on small world navigability, Jon Kleinberg modeled this phenomenon in the framework of augmented networks, and analyzed the performances of greedy routing in augmented multi-dimensional meshes. This paper objective is to survey the results that followed up Kleinberg seminal work, including results about: extensions of the augmented network model, and variants of greedy routing,designs of ${\mbox{\rm polylog}}$-navigable graph classes,the quest for universal augmentation schemes, anddiscussions on the validation of the model in the framework of doubling metrics. [ABSTRACT FROM AUTHOR]

This paper studies the problem of computing an upward topological book embedding of an upward planar digraph G, i.e. a topological book embedding of G where all edges are monotonically increasing in the upward direction. Besides having its own inherent interest in the theory of upward book embeddability, the question has applications to well studied research topics of computational geometry and of graph drawing. The main results of the paper are as follows. Every upward planar digraph G with n vertices admits an upward topological book embedding such that every edge of G crosses the spine of the book at most once.Every upward planar digraph G with n vertices admits a point-set embedding on any set of n distinct points in the plane such that the drawing is upward and every edge of G has at most two bends.Every pair of upward planar digraphs sharing the same set of n vertices admits an upward simultaneous embedding with at most two bends per edge. [ABSTRACT FROM AUTHOR]