Search

In this paper, a system based on Artificial Neural Network (ANN) for classifying automobile parts with different shapes is presented. The system gets the original information from an image sensor, classifies two sorts of automobile parts with different shapes after processing these images. The classifier designed in this paper adopts the ANN with an improved BP algorithm. The perimeter, acreage and the degree of the decentralization of the automobile parts in the intensity image are taken as the input feature vectors. For the No.1 part and No.2 part, the experimental result indicates that the recognition accuracy rate can reach up to 99% in this system and the productivity will be improved obviously comparing with the checking result in the off-line system manually. [ABSTRACT FROM AUTHOR]

A novel Fuzzy PID controller is proposed in this paper, which is used for treating the control of pulp level and brightness in flotation de-inking column. The essential part of fuzzy PID controller is the fuzzy logic control, which is a multi-input-multi-output controller. A design method of the fuzzy PID controller is presented. The simulation results show that the proposed Fuzzy PID controller has preferable performance and significant advantages over the traditional PID controller. [ABSTRACT FROM AUTHOR]

The speed and convenience of the Internet facilitated the development of electronic commerce (e-commerce). E-commerce research and technologies have always drawn the attention of researchers. Among them, the application of mobile agent on e-commerce has drawn much attention in recent years. Mobile agents can roam freely over different execution environments to execute tasks assigned to them. However, a mobile agent may be attacked when it requests services from other servers or when comes in contact with and exchange information with another agents while roaming on the internet. Hence, a mobile agent user may be concerned that his mobile agent could be corrupted or private information tapped and pirated by other agents. To ensure the security of mobile agents in public network environment, this paper proposes a security scheme that is suitable for mobile agents. The scheme includes access control and key management; it is also an improvement on the key management and access control for mobile agent scheme of Volker and Mehrdad. The proposed scheme corrects the drawback in Volker and Mehrdad's scheme which is the need of a large amount of storage for storing the secret keys. Security and performance analysis of our scheme proves the proposed scheme to be more efficient and secure. [ABSTRACT FROM AUTHOR]

This paper describes efficient word meaning acquisition for infant agents (IAs) based on learning biases that are observed in children's language development. An IA acquires word meanings through learning the relations among visual features of objects and acoustic features of human speech. In this task, the IA has to find out which visual features are indicated by the speech. Previous works introduced stochastic approaches to do this, however, such approaches need many examples to achieve high accuracy. In this paper, firstly, we propose a word meaning acquisition method for the IA based on an Online-EM algorithm without learning biases. Then, we implement two types of biases into it to accelerate the word meaning acquisition. Experimental results show that the proposed method with biases can efficiently acquire word meanings. [ABSTRACT FROM AUTHOR]

Semiconductor Technology and multimedia communication has been developed to interest in high quality video and multi channels audio. Especially, it is trend to important technology so that DVD market grows rapidly. Mpeg audio standard is available support for any bit rate. In this paper, the design of Field Programmable Gate Array(FPGA) is presented mpeg audio synthesis filter by Distributed Arithmetic Look Up Table(DALUT) method. In order to design for high speed filter that operated from 10MHz to 30MHz and DALUT is used instead of multiplier. In this paper, the output is designed by VHDL and is verification using C language. VHDL simulation used Model-sim SE 5.7f and synthesis is used Synplify Pro 7.2Ver. Target library is used XC4010E, XC4020EX, XC4052XL and P&R tool used XACT M1.4. [ABSTRACT FROM AUTHOR]

The variance minimization dual adaptive control approach with unknown parameters for stochastic system is studied in this paper. First,the problem is proposed for solving the optimal dual control law. Furthermore, the differential equation is transferred into state space model, the suboptimal dual control law is obtained through DUL algorithm. Finally, the example is given to verify the method developed in this paper. It is shown that the method is effective and practical. Keywords: dual control; adaptive control; stochastic systems. [ABSTRACT FROM AUTHOR]

There are restrictions of complete rationality and information symmetry, which is difficult to work in reality, in the traditional game theory. However, the evolutionary game theory, based on bounded rationality, can compensate these defects. In this paper, we set up an asymmetric model of the evolutionary game between a supplier and a retailer with asymmetric information. The evolutionary stable strategies and their premises were obtained with the replicator dynamics mechanism. The analysis in this paper has significance of explanation and direction for the supply chain management. [ABSTRACT FROM AUTHOR]

The paper presents a new framework of oligopolistic market simulation based on coevolutionary computation. The coevolutionary compu-tation architecture can be regarded as a special model of the agent-based computational economics (ACE), which is a computational study of economies modeled as dynamic systems of interacting agents. The supply function equilibrium (SFE) model of an oligopolistic market is used in simulation. The piece-wise affine and continuous supply functions which have a large number of pieces are used to numerically estimate the equilibrium supply functions of any shapes. An example based on the cost data from the real-world electricity industry is used to validate the approach presented in this paper. Simulation results show that the coevolutionary approach robustly converges to SFE in different cases. The approach is robust and flexible and has the potential to be used to solve the complicated equilibrium problems in real-world oligopolistic markets. [ABSTRACT FROM AUTHOR]

This paper proposes a new blind watermarking scheme in which a watermark is embedded into the discrete wavelet transform (DWT) domain. The method uses the HVS model, and radial basis function neural networks (RBF). RBF will be implemented while embedding and extracting watermark. The human visual system (HVS) model is used to determine the watermark insertion strength. The inserted watermark is a random sequence. The secret key determines the beginning position of the image where the watermark is embedded. This process prevents possible pirates from removing the watermark easily. Experimental results show that the proposed method has good imperceptibility and high robustness to common image processing attacks. [ABSTRACT FROM AUTHOR]

According to the basic emotions theory, the paper presents personality,mood, and emotion space. The mapping relationship among personality , mood and emotion is built. The equations for updating the affective and mood states are induced and a generic computing model for personality ,mood and emotion simulation for virtual human is constructed. The simulation results demonstrate that the affective model can better simulate the dynamic process of emotion and mood change under various environment stimulus. The model provides a valid method to the emotional robot modelling and affective decision system. [ABSTRACT FROM AUTHOR]

A new robust controller based on linear-paremeter-neural-networks is designed for a class of nonlinear unkonwn chaotic systems which could be turned to "standard block control type" by using backstepping method. It was proved by constructing Lyapunov function step by step that all signals of the system are bounded and exponentially converge to the neighborhood of the origin globally and the weights of neural network converge to the optimal weights eventually. The assumption for unknown control function is reduced which stand for the innovation of our method compared with the traditional method. Also the unknown control function needn't to be positive or negative strictly in our paper. This assumption in the other papers is so strict that it couldn't be satisfied by many practical systems. So our method can be applied to a more extensive nonlinear systems. At last, take the unknown Duffing chaotic system for example, simulation study is given to demonstrate that the proposed method is effective. [ABSTRACT FROM AUTHOR]

A novel immunotronic approach to fault detection in hardware based on symbiotic evolution is proposed in this paper. In the immunotronic system, the generation of tolerance conditions corresponds to the generation of antibodies in the biological immune system. In this paper, the principle of antibody diversity, one of the most important concepts in the biological immune system, is employed and it is realized through symbiotic evolution. Symbiotic evolution imitates the generation of antibodies in the biological immune system more than the standard genetic algorithm(SGA) does. It is demonstrated that the suggested method outperforms the previous immunotronic methods with less running time. The suggested method is applied to fault detection in a decade counter (typical example of finite state machines) and MCNC finite state machines and its effectiveness is demonstrated by the computer simulation. Keywords: immunotronic system, hardware fault detection, tolerance conditions, antibody diversity, symbiotic evolution. [ABSTRACT FROM AUTHOR]

In this paper, keyword map-based relevance feedback is applied to interactive Blog search.There exists vast amount of information in the Web, from which users usually gather information without definite information needs. In particular, when exploring the Blog space, the range of user's interests is expected to be broader than usual Web browsing process. The relevance feedback techniques have been studied in the field of document retrieval, aiming to generate appropriate queries for users' information needs.Although this approach is effective when the assumption that a user has a concrete criteria on the relevance of retrieved documents holds, it could not always hold when searching Blog, which consists of vast number of short articles about various topics. Compared with the previous work on keyword map-based relevance feedback, the algorithm proposed in this paper can consider multiple topics, in which a user is interested on the keyword map. [ABSTRACT FROM AUTHOR]

Web-based information portals provide a point of access onto an integrated and structured body of information about some domain. Knowledge portals are information portals, which make an important contribution to enabling enterprise knowledge management by providing users with a consolidated, personalized user interface that allows efficient access to various types of information. Portlets are mainly ways to present contents in knowledge portals. They are a group of components, which can be involved by a portal container. However, there are lacks no interaction between those portlets. This paper discusses information integration aspects within knowledge portals and presents an approach for communicating the user context (revealing the user's information need) among portlets, utilizing ontologies technologies. [ABSTRACT FROM AUTHOR]

In this paper, we investigate how the seemingly chaotic behavior of stock markets could be well represented using neural network, TS fuzzy system and hierarchical TS fuzzy techniques. To demonstrate the different techniques, we considered Nasdaq-100 index of Nasdaq Stock MarketSM and the S&P CNX NIFTY stock index. We analyzed 7 year's Nasdaq 100 main index values and 4 year's NIFTY index values. The parameters of the different techniques are optimized by the particle swarm optimization algorithm. This paper briefly explains how the different learning paradigms could be formulated using various methods and then investigates whether they can provide the required level of performance, which are sufficiently good and robust so as to provide a reliable forecast model for stock market indices. Experiment results reveal that all the models considered could represent the stock indices behavior very accurately. [ABSTRACT FROM AUTHOR]

The paper presents a permutation-based algorithm for predicting RNA secondary structure. It is practicable, and can be used to predict real RNA molecules. The conception of permutation is introduced, which is the start point of our algorithm. Individual is represented as a permutation of stem list. Crossover operator, mutation operator, and selection strategy are designed to be compatible with such an individual representation. At the end of the paper, a comparison between our result and that from RNAstructure is outlined. It is proved that our algorithm has achieved comparable or better result than RNAstructure. [ABSTRACT FROM AUTHOR]

A wavelet-based fuzzy multiscale edge detection scheme (WFMED) is presented in this paper. The dyadic wavelet transform is employed to produce the multiscale representation of the image, fuzzy logic is applied in wavelet domain and it can synthesize the information of image across scales effectively, an optimal result of edge detection can be acquired. WFMED method is used to extract the edge of pulp fibre image; the paper compares the performance of WFMED to the Canny edge detector and to Mallat's algorithm. The results show the superiority of WFMED to these other methods. [ABSTRACT FROM AUTHOR]

The matching similarity measures that can be used in image target recognition are surveyed and a novel similarity measure is proposed in this paper. Two basic factors that affect the image matching performance and the merits and faults of two common types of image matching algorithm are firstly analyzed. Then, based on the systematic study of similarity measures, image matching projection similarity measure is defined by simplify the classical normalized correlation measure. An example of the application of the proposed matching similarity measure in image target recognition and position is given at the end of this paper; the experimental results show its feasibility and effectivity. [ABSTRACT FROM AUTHOR]

This paper is concerned with dynamic modeling, prediction and analysis of cell cytotoxicity. A real-time cell electronic sensing (RT-CES) system has been used for label-free, dynamic measurements of cell responses to toxicant. Cells were grown onto the surfaces of the microelectronic sensors. Changes in cell number expressed as cell index (CI) have been recorded on-line as time series. The CI data are used for dynamic modeling in this paper. The developed models are verified using data that do not participate in the modeling. Optimal multi-step ahead predictions are calculated and compared with the actual CI. A new framework for dynamic cytotoxicity system analysis is established. Through the analysis of the system impulse response, we have observed that there are considerably similarities between the impulse response curves and the raw dynamic data, but there are also some striking differences between the two, particularly in terms of the initial and final cell killing effects. It is shown that dynamic modeling has great potential in modeling cell dynamics in the presence of toxicant and predicting the response of the cells. [ABSTRACT FROM AUTHOR]

Space applications' users have been relying for the past decades on custom developed software tools capable of addressing short term necessities during critical Spacecraft control periods. Advances in computing power and storage solutions have made possible the development of innovative decision support systems. These systems are capable of providing high quality integrated data to both near real time and historical data analysis applications. This paper describes the implementation of a new approach for a distributed and loosely coupled data extraction and transformation solution capable of extracting, transforming and perform loading of relevant real-time and historical Space Weather and Spacecraft data from semi-structured text files into an integrated space-domain decision support system. The described solution takes advantage of XML and Web Service technologies and is currently working under operational environment at the European Space Agency as part of the Space Environment Information System for Mission Control Purposes (SEIS) project. [ABSTRACT FROM AUTHOR]

We consider the problem of estimating the location of a moving target in a 2-D plane. In this paper, we focus attention on selecting an appropriate 3rd sensor, given two sensors, with a view to minimize the estimation error. Only the selected sensors need to measure distance to the target and communicate the same to the central "tracker". This minimizes bandwidth and energy consumed in measurement and communication while achieving near minimum estimation error. In this paper, we have proposed that the 3rd sensor be selected based on three measures viz. (a) collinearity, (b) deviation from the ideal direction in which the sensor should be selected, and (c) proximity of the sensor from the target. We assume that the measurements are subject to multiplicative error. Further, we use least square error estimation technique to estimate the target location. Simulation results show that using the proposed algorithm it is possible to achieve near minimum error in target location. [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]

For the purpose of extending the Web that is able to understand and process information by machine, Semantic Web shared knowledge in the ontology form. For exquisite query processing, this paper proposes a method to use semantic relations in the ontology as relevance feedback information to query expansion. We made experiment on pharmacy domain. And in order to verify the effectiveness of the semantic relation in the ontology, we compared a keyword based document retrieval system that gives weights by using the frequency information compared with an ontology based document retrieval system that uses relevant information existed in the ontology to a relevant feedback. From the evaluation of the retrieval performance, we knew that search engine used the concepts and relations in ontology for improving precision effectively. Also it used them for the basis of the inference for improvement the retrieval performance. [ABSTRACT FROM AUTHOR]

How face pose (rotating from right to left) influence the fusion authentication accuracy in face and fingerprint identity authentication system? This paper firstly tries to answer this question. The maximum rotating degree that fusion system can bear is given out by experiment. Furthermore, theoretical analysis deals with how face pose influence the fusion performance is proposed in this paper. Experiment results show that faces with big rotated degree can not be helpful but harmful to fusion system. And the maximum rotated angle of face that fusion system can bear is 20 degree. On the other hand, theoretical analysis proved that the mathematical inherence of influence of face pose on fusion system is not only the reduction of variance but also the decrease of distance between the genuine and imposter classes. [ABSTRACT FROM AUTHOR]

The paper presents the application of the wavelet transform of the frequency histogram of connected elements to the detection of very thin cracks in used pallets. First, the paper presents this novel concept and introduces the parameters that define a connected element, showing that the conventional grayscale intensity histogram of a digital image is a particular case of the histogram of connected elements. Then, the discriminant capability of the wavelet transform of this generalized histogram is analyzed. In particular, the information conveyed by the histogram of connected elements is exploited to detect very thin cracks in used pallets. An artificial neural network classifier to discriminate sound wood from defective wood with very thin cracks has been designed. The exhaustive experimental test carried out with numerous boards of used pallets has validated the proposed method, in particular its remarkably low ratio of false alarms. [ABSTRACT FROM AUTHOR]

This paper presents and application of Genetic Programming (GP) for time series forecast. Although this kind of application has been carried out with a wide range of techniques and with very good results, this paper presents a different approach. In most of the experiments done in time series forecasting the objective is, from a consecutive set of samples or time interval, to obtain the value of the sample in the next time step. The aim of this paper is to study the forecasting not only on the next sample, but in general several samples forward. This will allow the building of more complete prediction systems. With this objective, one of the most widely used series for this kind of application has been used, the Mackey-Glass series. [ABSTRACT FROM AUTHOR]

As shown in the bibliography, training an ensemble of networks is an interesting way to improve the performance with respect to a single network. However there are several methods to construct the ensemble. In this paper we present some new results in a comparison of twenty different methods. We have trained ensembles of 3, 9, 20 and 40 networks to show results in a wide spectrum of values. The results show that the improvement in performance above 9 networks in the ensemble depends on the method but it is usually low. Also, the best method for a ensemble of 3 networks is called "Decorrelated" and uses a penalty term in the usual Backpropagation function to decorrelate the network outputs in the ensemble. For the case of 9 and 20 networks the best method is conservative boosting. And finally for 40 networks the best method is Cels. [ABSTRACT FROM AUTHOR]

Given the theoretical hardness of classical planning, the chance of developing practically usable solution algorithms appears slim. However, modern planning systems developed since the 1990s such as Graphplan [14], SATPLAN [75-78], HSP [16] and FF [68] have demonstrated their ability to solve planning tasks of considerable size. Their efficiency, or - put a bit more carefully - their perceived efficiency is somewhat at odds with the theoretical hardness of planning. To understand why we can observe such good planner performance, we must consider the methods with which the performance of planning systems is evaluated. This is the topic of the following Sect. 1.1, which will lead us to a discussion of planning benchmarks in Sect. 1.2 and their theoretical properties in Sect. 1.3. In the penultimate Sect. 1.4, we briefly introduce a set of standard benchmarks. The chapter concludes with an overview of Part I in Sect. 1.5. [ABSTRACT FROM AUTHOR]

In this paper we introduce a Prover-Verifier model for analyzing the computational complexity of a class of Constraint Satisfaction problems termed Binary Boolean Constraint Satisfaction problems (BBCSPs). BBCSPs represent an extremely general class of constraint satisfaction problems and find applications in a wide variety of domains including constraint programming, puzzle solving and program testing. We establish that each instance of a BBCSP admits a coin-flipping Turing Machine that halts in time polynomial in the size of the input. The prover P in the Prover-Verifier model is endowed with very limited powers; in particular, it has no memory and it can only pose restricted queries to the verifier. The verifier on the other hand is both omniscient in that it is cognizant of all the problem details and insincere in that it does not have to decide a priori on the intended proof. However, the verifier must stay consistent in its responses. Inasmuch as our provers will be memoryless and our verifiers will be asked for extremely simple certificates, our work establishes the existence of a simple, randomized algorithm for BBCSPs. Our model itself serves as a basis for the design of zero-knowledge machine learning algorithms in that the prover ends up learning the proof desired by the verifier. [ABSTRACT FROM AUTHOR]

We initiate a study on automata recognizing labelled posets constructed from scattered and countable linear orderings. More precisely, the class of labelled posets considered in this paper is the smallest containing letters, closed under finite parallel operation and sequential product indexed by all countable and scattered linear orderings. The first result of this paper establishes that those labelled posets are precisely the N-free ones. The second result is a Kleene-like theorem, which establishes that the class of languages of labelled posets accepted by branching automata is exactly the class of rational languages. This generalizes both the finite [9] and ω-labelled posets [2,6] cases, and the Kleene-like theorem on words on linear orderings [3]. [ABSTRACT FROM AUTHOR]

The aim of this paper is to study communication in networks where nodes fail in a random dependent way. In order to capture fault dependencies, we introduce the neighborhood fault model, where damaging events, called spots, occur randomly and independently with probability p at nodes of a network, and cause faults in the given node and all of its neighbors. Faults at distance at most 2 become dependent in this model and are positively correlated. We investigate the impact of spot probability on feasibility and time of communication in the fault-free part of the network. We show a network which supports fast communication with high probability, if p ≤ 1/clogn. We also show that communication is not feasible with high probability in most classes of networks, for constant spot probabilities. For smaller spot probabilities, high probability communication is supported even by bounded degree networks. It is shown that the torus supports communication with high probability when p decreases faster than 1/n1/2, and does not when p ∈ 1/O(n1/2). Furthermore, a network built of tori is designed, with the same fault-tolerance properties and additionally supporting fast communication. We show, however, that networks of degree bounded by a constant d do not support communication with high probability, if p ∈ 1/O(n1/d). While communication in networks with independent faults was widely studied, this is the first analytic paper which investigates network communication for random dependent faults. [ABSTRACT FROM AUTHOR]

Compression is most important when space is in short supply, so compression algorithms are often implemented in limited memory. Most analyses ignore memory constraints as an implementation detail, however, creating a gap between theory and practice. In this paper we consider the effect of memory limitations on compression algorithms. In the first part of the paper we assume the memory available is fixed and prove nearly tight upper and lower bound on how much is needed to compress a string close to its k-th order entropy. In the second part we assume the memory available grows (slowly) as more and more characters are read. In this setting we show that the rate of growth of the available memory determines the speed at which the compression ratio approaches the entropy. In particular, we establish a relationship between the rate of growth of the sliding window in the LZ77 algorithm and its convergence rate. [ABSTRACT FROM AUTHOR]

The central problem in training a radial basis function neural network is the selection of hidden layer neurons, which includes the selection of the center and width of those neurons. In this paper, we propose a new method to construct an adaptive RBF neural network classifier based on artificial immune network algorithm. A multiple granularities immune network (MGIN) algorithm is employed to get the candidate hidden neurons and construct an original RBF network including all candidate neurons, and a removing redundant neurons procedure is used to simplify the classifier finally. Some experimental results show that the network obtained tends to generalize well. [ABSTRACT FROM AUTHOR]

A novel feature extraction method based on cloud model for EEG classification is proposed in the paper. The cloud model can transform numerical data to qualitative concept described by a group of characteristics. It provides a new way for concept induction in machine learning. Classification of single trial EEG recorded in a ‘self-paced key typing' experiment is made through feature extraction based on cloud model and linear regression method for the classification of feature vectors. Results of up to 90% classification accuracy on test data set were obtained. The results show that compared with other methods, the feature extraction and translation method for EEG classification in this paper is simple and effective. [ABSTRACT FROM AUTHOR]

During the memorizing process, knowledge is memorized closely related to the emotional state. The emotional factor also effects on the decision making process as well as memorization. Accordingly in this paper Reticular Activating System was designed and the knowledge management strategy considering the emotional switching was proposed. We applied this system to the virtual memory and tested the results. [ABSTRACT FROM AUTHOR]

Based on the 'bottom-up' programming approach in Artificial Life, Finite-State Machine is adopted to describe the behavior of the individual bee, and the behavior in different period was realized in this paper. As a result, the interaction of the individual bee each other, individual bee and virtual environment produce the Emergence of swarm's collective behaviors. Finally, we apply the graphical interfaces to realize the simulation. [ABSTRACT FROM AUTHOR]

In mammals, the master circadian pacemaker is considered the suprachiasmatic nucleus (SCN) of the hypothalamus. Individual cellular clocks in SCN, the circadian center, are integrated into a stable and robust pacemaker with a period length of about 24 hours, which are remarkably accurate at timing biological events despite the randomness of their biochemical reactions. In this paper, we study the effect of the Light-Dark cycle and environment noise on the daily rhythms of mammals and give some numerical analysis. The results show that the environment noise makes for phase synchronization but it can not make the oscillators get phase synchronization with period of 24-h. On the contrary, the threshold of the strength of light that makes the oscillators to get the phase synchronization with period of 24-h with environment noise is larger than that in the case without environment noise. [ABSTRACT FROM AUTHOR]

This paper introduces strong bisimulation for continuous-time Markov decision processes (CTMDPs), a stochastic model which allows for a nondeterministic choice between exponential distributions, and shows that bisimulation preserves the validity of CSL . To that end, we interpret the semantics of CSL —a stochastic variant of CSL for continuous-time Markov chains—on CTMDPs and show its measure-theoretic soundness. The main challenge faced in this paper is the proof of logical preservation that is substantially based on measure theory. [ABSTRACT FROM AUTHOR]

The Extensible Authentication protocol (EAP), is the main component of the standard AAA (Authentication Authorization and Accounting) framework for network access control. AAA frameworks support cross-domain authentication that enables a certain access network to authenticate a roaming client that belongs to a remote network. The cross-domain authentication requires message exchange between the AAA server of the visited network and the AAA server of the client's home network. Because these inter-domain exchanges occur over the Internet, they are subject to degradations such as packet loss and network delays thus increasing the overall authentication time. When the client changes of access point, the same authentication procedure takes place again, disrupting the user traffic at each hand-off. In this paper, we examine the performance of inter-domain EAP authentication in terms of authentication delay using an emulated environment. Moreover, in an effort to understand the performance of Inter-domain authentication over the Internet, we model the authentication time using mathematical approach and we define basis of future research items focusing on the estimation of inter-domain EAP authentication delays. [ABSTRACT FROM AUTHOR]

Ovarian cancer is a primary gynecological cancer which pathological stages include benign, borderline and invasive stages cause death in many countries. In this paper, linear regression, analysis of variance (ANOVA) and support vector machine (SVM) are used to identify the gene markers of ovarian cancer for an authentic cDNA expression datasets among 8 normal ovarian tumors, 6 borderline of cancers, 7 ovarian cancer at stage I and 9 ovarian cancer at stage III samples. First, the linear regression analysis obtains 200 useful genes with largest residuals. Further select 14 genes by ANOVA and Scheffe when P-value is less than 0.000005. Then, we use support vector machine to classify the pathological stages by gene expressions. Five experiments are performed with clustering conditions. In the first clustering experiment, the cluster 1 includes BOT, and other pathological stages are in cluster 2. They have significant differences at BOT stage and can get average accuracy about 95.686% in cross-validation. It is quite precise for classifying pathological stages by gene expressions. The average accuracy of all clustering experiments is about 88.541% in cross-validation. Besides, we also develop a statistical analysis system including linear regression and ANOVA function for gene expression analysis. The experimental results and our analysis system can assist biologists and doctors to research and diagnose ovarian cancer by gene expressions. [ABSTRACT FROM AUTHOR]

This paper describes the effects of adding gene reincarnation to a biologically inspired evolutionary algorithm. When using the biologically inspired part of the algorithm we are able to draw on experience from real life. Reincarnation capabilities, however, must be constructed without any real life experience to guide us. This paper addresses the question ‘can reincarnation be added to a genetic algorithm in such a way as to modify the resulting evolutionary process'? Reincarnation in this context requires that genetic information, saved from earlier generations, be bought back and reintroduced into the population at a later time. A simple algorithm is introduced that selects particular genetic material to add to the storage, performs regular culls of the stored material and inserts some of the stored material back into targeted individuals in later generations. Preliminary experiments show that while much of the reinserted material vanishes without having any obvious evolutionary effect, a small proportion remains for many generations and changes the course of the evolution compared to a genetic algorithm identical in all respects except that it lacks reincarnation. [ABSTRACT FROM AUTHOR]

In this paper we will study the naïve Bayes, one of the popular machine learning algorithms, and improve its accuracy without seriously affecting its computational efficiency. Naïve Bayes assumes positional independence, which makes the computation of the joint probability value easier at the expense of the accuracy or the underlying reality. In addition, the prior probabilities of positive and negative instances are computed from the training instances, which often do not accurately reflect the real prior probabilities. In this paper we address these two issues. We have developed algorithms that automatically perturb the computed prior probabilities and search around the neighborhood to maximize a given objective function. To improve the prediction accuracy we introduce limited dependency on the underlying pattern. We have demonstrated the importance of these extensions by applying them to solve the problem in discriminating a TATA box from putative TATA boxes found in promoter regions of plant genome. The best prediction accuracy of a naïve Bayes with 10 fold cross validation was 69% while the second extension gave the prediction accuracy of 79% which is better than the best solution from an artificial neural network prediction. [ABSTRACT FROM AUTHOR]

This paper proposes a novel ranking function, called RFHOS by incorporating higher order cumulants into the ranking function for finding differentially expressed genes. Traditional ranking functions assume a data distribution (e.g., Normal) and use only first two cumulants for statistical significance analysis. Ranking functions based on second order statistics are often inadequate in ranking small sampled data (e.g., Microarray data). Also, relatively small number of samples in the data makes it hard to estimate the parameters accurately causing inaccuracies in ranking of the genes. The proposed ranking function is based on higher order statistics (RFHOS) that account for both the amplitude and the phase information by incorporating the HOS. The incorporation of HOS deviates from implicit symmetry assumed for Gaussian distribution. In this paper the performance of the RFHOS is compared against other well known ranking functions designed for ranking the genes in two sample microarray experiments. [ABSTRACT FROM AUTHOR]

This paper presents an approach for speech information hiding based on G.721 scheme. This approach proposes an Analysis-By-Synthesis (ABS)-based speech information hiding and extracting algorithm, is called ABS algorithm, which form the theoretical basis for designing a secure speech communication system. The ABS algorithm adopts a speech synthesizer in a speech coder. Speech embedding and coding are synchronous, i.e. fusing of secret speech information data into speech coding. Dynamic secret speech information data bits can be embedded into original carrier speech data, with high efficiency in steganography and good quality in output speech. This method is superior to available classical algorithms on hiding capacity and robustness. This paper implements the proposed approach based on speech coding scheme G.721 and the experiments show that this approach meets the requirements of information hiding, satisfies the constraints of speech quality for secure communication, and achieves high hiding capacity of 1.6Kbps with an excellent speech quality and complicating speakers' recognition. [ABSTRACT FROM AUTHOR]

In this paper, an efficient approach to search for the global threshold of image using Gaussian mixture model is proposed. Firstly, a gray-level histogram of an image is represented as a function of the frequencies of gray-level. Then to fit the Gaussian mixtures to the histogram of image, the Expectation Maximisation (EM) algorithm is developed to estimate the number of Gaussian mixture of such histograms. Finally, the optimal threshold which is the average of these means is chosen. The paper compares the new method with the classical discriminate analysis method of Otsu's. And the experimental results show that the new algorithm performs better than that of Otsu's. [ABSTRACT FROM AUTHOR]

In this paper, we proposed image processing technique for automatic real time fire and smoke detection in tunnel environment. To avoid the large scale of damage of fire occurred in the tunnel, it is necessary to have a system to minimize and to discover the incident as fast as possible. However it is impossible to keep the human observation of Closed-Circuit Television (CCTV) in tunnel for 24 hour. So if the fire and smoke detection system through image processing can warn fire state, it will be very convenient, and it can be possible to minimize damage even when people is not in front of monitor. The fire and smoke detection is different from the forest fire detection as there are elements such as car and tunnel lights and others that are different from the forest environment so that an indigenous algorithm has to be developed. The two algorithms proposed in this paper, are able to detect the exact position, at the earlier stage of incident. In addition, by comparing properties of each algorithm throughout experiment, we have proved the validity and efficiency of proposed algorithm. [ABSTRACT FROM AUTHOR]

In speaker recognition fields, score normalization is a widely used and effective technique to enhance the recognition performances and is developing further. In this paper, we are focused on the comparison among many kinds of candidates of score normalization methods and a new implementation of the speaker adaptive test normalization (ATnorm) based on a cross similarity measurement is presented which doesn't need an extra corpus for speaker adaptive impostor cohort selection. The use of ATnorm for the language robustness of the multi-language speaker verification is also investigated. Experiments are conducted on the core task of the 2006 NIST Speaker Recognition Evaluation (SRE) corpus. The experimental results indicate that all the score normalization methods mentioned can improve the recognition performances and ATnorm behaves best. Moreover, ATnorm can further contribute to the performance as a means of language robustness. [ABSTRACT FROM AUTHOR]

Based on neural network with favorable adaptability to handwritten Chinese character multi-features, in this paper a new method is proposed, using existing multi-features as inputs to structure multi neural network recognition subsystems and these subsystems are integrated with parallel connection mode. The integrated system has the lowest false recognition rate. When using traditional von Neumann architecture computer to implement this system, the system response time is longer as a result of serial computation. This paper introduces a kind of parallel computation method of using pc cluster to implement multi subsystems. It can reduce effectively recognition system's response time. [ABSTRACT FROM AUTHOR]

According to Cachin's steganography security criterion, if the statistical distributions of cover and stego images are identical, the hidden message is assumed undetectable. However, any steganographic method will surely cause some statistical distortions, which gives steganalyst a hint. This paper presents a steganalysis method for JPEG images based on Cachin criterion. It estimates the cover image from the stego one by using a small-scale geometrical transform, and then detects the statistical distortions between the cover and stego images based on some features, which are sensitive to the steganographic modifications. Then a classifier is trained on these features. Three different modern steganographic schemes are tested. Experimental results show that the proposed steganalysis scheme has better performance compared to the current steganalysis methods. [ABSTRACT FROM AUTHOR]

Traditional speech recognition systems have relied on power spectral densities, Mel-frequency cepstral, linear prediction coding and formant analysis. This paper introduces two novel input feature sets and their extraction methods for intelligent phoneme identification. These input sets are based on intrinsic phonetic characteristics of Arabic speech comprising of the dimensionally reduced Power Spectral Densities (DPSD) and Location, Trend, Gradient (LTG) values of the captured speech signal spectrum. These characteristics have been subsequently utilized as inputs to four different neural network based recognition classifiers. The classifiers have been tested for twenty-eight Arabic phonemes utterances from over one hundred non-native speakers. The results obtained using the proposed feature sets have been compared and it has been observed that LTG based input feature set provides an average phoneme identification accuracy of 86% as compared to 70% obtained through applying DPSD based inputs for similar classifiers. It is worthwhile to note that the methods proposed in this paper are generic and are equally applicable to other regional languages such as Persian and Urdu. [ABSTRACT FROM AUTHOR]