Recent researches have discovered a fact that most real systems have complex network structures with power-law degree distributions, that is scale-free networks. The scale-free networks fall into two categories, one includes networks with small clustering coefficients, and the other includes networks with large clustering coefficients. The networks which belong to the former category have tree-like topologies, and the networks which belong to the latter category include a lot of triangle-meshes, so the essential topologies of the networks are different between two categories. In this study, we examine how synchronization of coupled oscillator networks behave by change of clustering coefficient on these two types of scale-free networks.

View full abstract

Swarm robot control is not an easy task for a human programmer, because the robot group behavior is emerged as a result of many and asynchronous unexpected local interactions between autonomous robots. In this paper, we approach to this problem of designing robot controllers by using evolving artificial neural networks (EANNs). From our preliminary computer simulations, it has been found that the topology of the hidden layer plays an important role of the evolvability of an EANN. Therefore, we conduct a series of computer simulations to show that an EANN having the small world properties in the hidden layer performs better than EANNs with the hidden layer of regular topologies or other conventional feed forward neural network controllers from the viewpoint of the generalization capability.

View full abstract

In this paper, we developed an emotional expression system. The emotional expression is achieved by the emotional expression model of amygdala (EMA) that is the engineering model inspired by the brain mechanism of emotions. EMA can realize a recognition of sensory inputs and a classical conditioning of emotional inputs. A specific hardware of EMA was developed with a massive parallel architecture by using a FPGA, and has a calculation speed that is over 20 times faster than an embedded general-purpose computer. Finally, we demonstrated a human-robot interaction with emotions which are generated by the developed emotional expression system.

View full abstract

Robots and robotics technologies are expected as new tools, especially in extreme environments which are too dangerous to access directly by human beings such as underwater environments, volcanic areas, nuclear power plants etc. Robots for such environments should be robust and strong enough to disturbance and breakdowns. We can find out a solution to realize robust robot system from interesting approaches in creatures. Animals adapt well to environmental changes in both short and long time periods. We investigate the motion of snake and eels which move various fields by wriggling bodies.　On nervous systems of animals, it becomes clear that motion patterns, such as walking, respiration, flap, etc, are controlled by rhythm generator mechanisms called the Central Pattern Generator (CPG). We introduce Matsuoka Model as the neuron model of CPG. In this paper robot motion control system using CPG is proposed and applied to a multi link mobile robot.

View full abstract

Recently, various mechanisms have been developed combining linkage mechanisms and wheels, especially, the combination of passive linkage mechanisms and small wheels is one of main research trends, because standard wheel type mobile mechanisms have difficulties on rough terrain movements. In our research, a 6-wheeled mobile robot employing a passive linkage mechanism has been developed to enhance maneuverability and achieved climbing capability over a 0.20[m] height of bump. We designed a controller using neural network for high energy efficiency. In this paper, we propose an environment recognition system for the wheel type mobile robot which consists of multiple classification analyses. We evaluate the recognition performance by comparing Principle Component Analyses (PCA), k-means and Self-Organizing Map (SOM).

View full abstract

In this paper, a novel learning strategy based on diversive and specific curiosities are introduced. Two types of curiosities are switched by employing a concept of threshold. The desired threshold for effective learning is decided by genetic algorithm. Advantages of the proposed method are verified by simulations.

View full abstract

In this paper, we propose a generalized collaborative filtering algorithm. Recent web-based technology has been quickly developed toward the user-friendly environment and one of the important technical challenges of personalization is a recommendation to end users. Collaborative Filtering is one of the techniques of information-filtering using user's profiles and is applicable to recommendation engines. Users' profiles are, in many conventional studies, expressed as vectors. With vector- based profiling, recommendation algorithms can be mathematically clear and easy to use. However, there are some cases which vector-based profiling is inadequate to express users. Thus, we generalize user's profiles to function-based ones and extend conventional collaborative filtering algorithms for the usage of our new formats of the profiles. The proposed algorithm employs a general regression neural network (GRNN) to compose function-based profiles. To verify the algorithm, we apply the proposed algorithm to a web color preference estimation.

View full abstract

The present study considers a fuzzy color system in which two membership functions are constructed on the tone triangle. This system can process a fuzzy input (as the membership values of subjects) to a tone system and output to an RGB system. Three membership functions (anti-blackness, whiteness, and lightness) are applied to the tone triangle relationship. By treating the input parameters of chromaticness, whiteness, and blackness on the tone triangle, a target color can be easily obtained as the center of gravity of the output fuzzy set. In the present paper, the differences between fuzzy input and inference output are described, and the relationship between inference outputs for crisp inputs and inference outputs for fuzzy inputs on the RGB triangular system are shown in the present paper.

View full abstract

This paper presents a color scheme support system that enhances users' creativity. With this system, an ordinary person who does not have skill of coloring can decide color scheme and perform graphic design. This system uses interactive evolutionary computing in order to extract tacit ability of the graphic design from its user. The user repeatedly selects better ones from a set of graphic designs that the system presents and finally obtains the fine one that he/she hoped unconsciously.

View full abstract

The purpose of our work is to design a real-time multimodal emotion extraction system based on fuzzy inference, and to implement it to a multi-core processor. We have been studied emotion extraction systems from voice and facial expressions separately. In general, emotions of human being are unstable therefore emotion extraction from single source will reach a limit. Multi-modal sensing like human beings do becomes important. We implemented a multi-modal emotion extraction system based on fuzzy inference to the Cell Broadband Engine TM. Our system deals with facial expressions and voice. To extend the system in the future, processes are partitioned by making thread for each source. The system can be extended easily by adding or modifying a thread. We got a good performance by assigning processing corresponding to each source to processor cores.

View full abstract

In this paper, a human centered approach for interactive face drawing is presented. Human users of the system have the possibility to draw and retouch faces from linguistic terms. The system learns the meaning of the terms interactively from the retouching process. The system has an average face of each race, generated using anthropometric measurements of the face and the head. An average face corresponding to the race of the target face is displayed to a user as an initial face. A user describes each facial feature of the desired face using linguistic descriptors and the feature changes according to the user's description. Depending on the race of a user and the gender of the face to be drawn, the relation between the size of each facial feature and the set of the linguistic descriptors used to describe it is obtained by conceptual fuzzy sets. These fuzzy sets represent the initial meaning of the linguistic terms. Once the face is obtained, a user can retouch the drawn face. The user uses a combination of an adverb and a linguistic descriptor to retouch some features of the drawn face until the desired face is obtained. For the current user, the system interactively learns his/her meaning of the descriptors using the proposed Online Learning of Gaussian Fuzzy Sets algorithm based on the Maximum likelihood estimation (MLE) for Gaussian mixture. The system then adjusts the drawn face according to the new meaning of the descriptors.

View full abstract

On an ad-hoc network which is consisted of movable nodes, the network topology is dynamic because each node is adaptive. We apply it to the surveillance cameras system at a parking lot. A node with a camera sets on a car. And the node gets the car motion information from the acceleration sensor. In this paper, we discuss the classification of its car motion detection because there are two cases; one case is to drive the car by the driver, and the other case is to move the car by the another person. We will classify the car motion detection into two cases using Neural Networks based on acceleration sensor. And in order to detect the case as soon as possible, we discuss how long we must get the acceleration sensor data.

View full abstract

This paper presents an extension of our earlier work [12] on single-layered complex-valued neural network (CVNN). In the earlier work, we proposed a new class of activation functions for complex-valued neuron (CVN) in a view to solving real-valued classification problems. To improve the performance, we investigate the ensemble of single-layered CVNNs in this paper. We applied two ensemble methods-bagging and negative correlation learning, to create the ensembles. Experimental results on a number of real-world benchmark problems show a substantial performance improvement over an individual single-layered CVNN classifier, and thus justify the application of CVNN ensembles on the classification problems.

View full abstract

This paper presents a new feature selection (FS) approach, called constructive FS approach (CFSA), based on the wrapper approach. The vital aspect of the new approach is that it determines both a set of features and neural network architecture for the features simultaneously. CFSA first divides the original feature set representing a problem into two clusters based on the correlation information. It puts similar features in one cluster, while dissimilar ones in the other cluster. The proposed algorithm then uses a constructive approach to find a subset of features from the two clusters and hidden neurons of the neural network. Five benchmark classification problems are used to evaluate the efficacy of CFSA. The experimental results exhibit that CFSA has ability to find salient features with a small number of hidden neurons to produce robust neural classifiers.

View full abstract

The Tokyo Metropolitan Government established "Seaside park plan" and "Tokyo municipal seaside park ordinance". The Tokyo Metropolitan Government considers that the conservation of seaside, riverside and urban parks make the creation of places where residents of Tokyo can come in contact with nature. However, it seems that the planning and construction of those parks have been carried out by the administration from one-side view. The waterfront parks are public and have been used by many people. As there have been no data what components of parks are important for users of parks, eight seaside parks called waterfront parks were watched, degrees of satisfactory of eighty two residents who live in metropolitan area about components of parks were surveyed, and degrees of concern about components of the parks have been obtained by conjoint analysis. Those waterfront parks are located at Odaiba near the Tokyo bay. Here, the components of parks are as follows; 1) Hydrophile, 2)Rest space, 3) Public transport and conditions of location, 4) Recreation, 5) Scenery and outlook, 6) Maintenance situation, 7) Monument, and 8) Openness. The following main results have been obtained from the research. : a) Male and female think scenery and outlook, and hydrophile are important. b) Rest space is less important than other components for the twenties, but important for the thirties, forties and sixties. c) Public transport and location is not much important for teenager, but important for the others. d) The fifties make a point 1) Hydrophile, 3) Public transport and condition of location, and 5) Scenery and outlook. If there is a lack item in answers, we can utilize the data effectively by using the proposed method.

View full abstract

The city model that consists of a city center and built areas around it is assumed. In addition, let a unit that constitutes the built area be a built-area agent. The built-area agent moves to a place that has the convenient traffic to a city center, and the proper density of the block to which it belongs. Generally, traffic convenience and validity of city density are contradictory. It is because that the built-area agents concentrate on the urban central part convenient regarding traffic, so urban density becomes very high and becomes less proper owing to it. Then, a degree-of-satisfaction function is set up. And the independent variables of it are traffic convenience and validity of city density. When the built-area agent acts in order to improve the degree of satisfaction under the above conditions, the simulation of the urban form that they constitute is carried out.

View full abstract

Wireless sensor networks have attracted significant interests of many researchers because they have their wide range of applications, such as natural environmental monitoring in forest regions and environmental control in office buildings. In wireless sensor networks, hundreds or thousands of micro-sensor nodes with such resource limitation as battery capacity and memory are deployed in a region and used to obtain information of environments remotely. Therefore, energy-efficient data gathering measures and/or schemes are needed to prolong the lifetime of wireless sensor networks. In this study, so as to realize the long-term employment of wireless sensor networks, several relay-dedicated nodes to relay sensor information intensively are effectively placed. This paper proposes a new method based on Particle Swarm Optimization (PSO) for locating relay-dedicated nodes, named the PSO for Plural Decent Solutions (PSO-PDS). By using the PSO-PDS, which searches for plural decent solutions not one best solution, plural location candidates of relay-dedicated nodes can be obtained. We evaluate the PSO-PDS using computer simulations and discuss its development potential. In simulation experiment, the PSO-PDS is compared with conventional PSO to verify its effectiveness.

View full abstract

This paper studies chaos synchronization-based data gathering scheme in wireless sensor networks with multiple sinks. In the proposed scheme, each wireless sensor node has a simple chaotic oscillator. The oscillators generate impulsive signals with chaotic interspike intervals, and are impulsively coupled by the signals via wireless communication. Each wireless sensor node receives and transmits sensor information only in the timing of the couplings, and turns off own power supply in the other timing. The proposed scheme can exhibit various chaos synchronization, and can effectively gather sensor information with low energy consumption. Also, the proposed scheme can flexibly adapt various wireless sensor networks not only with a single sink node but also with multiple sink nodes by dynamically changing the network topology. We evaluate the proposed scheme using computer simulations. Through simulation experiments, we show effectiveness of the proposed scheme and discuss its development potential.

View full abstract

The authors have already proposed an intelligent fuzzy optimal and active control system (IFOACS), and the effectiveness of IFOACS is proved by digital simulations and shaking table tests. However, in case of a two-story specimen, control effects of shaking table tests become small when a second vibration mode stands out. To adapt these phenomena, in this paper, an IFOACS adaptable to multiple vibration modes is proposed in case of five-story buildings. The effectiveness of proposed system is discussed and clarified based on simulation results.

View full abstract

Relating gene expression profiles from microarray experiments with biological knowledge databases is an important step for understanding biological mechanism. It motivates the development of statistical techniques that quantify the significance of the expression profiles for sets of genes defined, e.g., based on pathway information. In this report we propose a new approach for gene set significance analysis. The proposed test measures the significance of gene sets using out-of-sample performance of nearest-neighbor classifiers. Our approach is computationally efficient and powerful to detect various types of differences in expression patterns. We demonstrate the advantage of our approach through the simulation studies for power analysis and an application to a public microarray data.

View full abstract

It is difficult for radiologists to identify the sentinel lymph nodes near the injection site (shine-through) mapped on lymphoscintigrams. The purpose of this study was to develop a computerized scheme for identifying the sentinel lymph nodes by using a subtraction technique based on the symmetry of the mapped injection site. Our database consisted of 78 lymphoscintigrams which were obtained by a single injection of technetium colloid. The locations of 99 sentinel lymph nodes on lymphoscintigrams were determined as "Gold standard" by the consensus of two experienced radiologists who referred to the identification results based on a gamma probe. In our computerized scheme, the mapped injection site was first segmented from lymphoscintigram by a gray-level thresholding technique. The lymphoscintigram was divided into four regions by the vertical straight line and the horizontal straight line through the center of the segmented injection site. The areas with high pixel values in the subtraction image between each region and the similar region were finally detected as sentinel lymph node. With our computerized scheme, the detection accuracy of sentinel lymph nodes and the incorrectly detected spots were 83.8% (83/99) and 1.63 per image.

View full abstract

We propose a novel technique to track the motion of the left ventricular myocardium in B-mode scan of ultrasonic RF signals. The proposed method is generally based on the traditional correlation based motion tracking, and then we introduce a new objective function to be optimized into the method. In our method, the objective function is defined from the model where multiple Regions of Interest (ROIs) are connected to each other with elastic links. The elastic links reflect both elastic and shape properties of myocardium. The proposed method is implemented and evaluated using three clinical subjects. The results show that the tracking accuracy of the proposed method is higher than that of the conventional method.

View full abstract

Recently, public interest in health is growing. In addition, the rapid development of information technology gives us much medical information, that places increased demands on the medical support systems using the information. The aim of this study is to develop a medical support system by using Hierarchical Keyword Graph (HK Graph). This system infers and shows the candidates of the name of disease with graph structure after a user inputs his/her symptoms. Then it shows appropriate hospitals considering the disease, specialty of each hospital, the distance from home, and so on. This paper focuses on the part of the inference of disease from inputted symptoms. It proposes interactive disease search support system using HK Graph which can visualize the relationship among words with network structure based on the co-occurrence information.

View full abstract

In the field of ophthalmology, it is generally important for quantitative evaluation of retinal diseases to measure the thickness between Inner Limiting Membrane (ILM) and Junction between Photoreceptor Inner and Outer Segment (IS/OS) using Optical Coherence Tomography (OCT) images. The purpose of this study is the development of Computer-Aided Diagnosis (CAD) scheme for measuring the retinal diseases with high accuracy. In our CAD scheme, spacial filters for edge enhancement and morphological operators for OCT images were proposed and ILM and IS/OS were extracted. The experimental results showed that our CAD scheme could measure the retinal diseases at rate of 75%(30/40) correctly.

View full abstract

This paper describes the vision-based system to track road signs from within a moving vehicle. Traffic signs located in the previous frame are tracked through image sequences using Particle filter. Particle filter has attracted much attention due to their robust tracking performance in cluttered environments. Particle filter maintains multiple hypotheses simultaneously and uses a probabilistic motion model to predict the position of the moving object. This paper uses Parzen window for estimating a probabilistic density function in Particle filter. The experimental results demonstrate that the proposed method performs well in tracking road signs present in complex scenes and various conditions.

View full abstract

This paper addresses the problem of 3D human pose estimation in a single real scene image. A two-step approach is proposed, first, instead of applying background subtraction to get the segmentation of human, we combine the segmentation with human detection using an ISM-based detector. Then, silhouette feature can be extracted and 3D pose estimation is solved as a regression problem. The results show the robustness and accuracy of our method.

View full abstract

A new method of image based flow analysis and synthesis from a still image is presented. We analyze the flow parts from a still image in order to get continuous video by image matting, image inpainting, projecting flow field onto the image and modulation. We project 3D flow models onto still images and propose 2D modulation methods that are more suitable and practical to our synthesis. Our technique can edit still images that have flow parts. The experiments show the method is effective.

View full abstract

A novel algorithm for automatic human body model initialization and motion tracking based on voxel data is proposed. Model initialization is to calculate the dimension of model and estimate the posture parameters using one single frame. In this paper, the process to initialize skeletal model is based on the novel idea of slicing voxel data along z axis and using some basic algorithms of image processing to extract feature points. In our algorithm, tracking is considered as a global optimization problem, and we use a novel evolutionary algorithm named Probability Evolutionary Algorithm (PEA) to solve it. The whole processes are totally automatic and experiments show this new algorithm is visually accurate and very robust to noise.

View full abstract

This paper proposes a new genetic error correcting code design method which reduces power consumption in single error correcting, double error detecting checker circuits. Power is minimized using the degrees of freedom in selecting the parity check matrix of the error correcting codes. The genetic algorithm which has the novel genetic operators tailored for this formulation is employed to solve the non-linear power optimization problem. Experiments are performed to illustrate the performance of the proposed method.

View full abstract

Use of login names and passwords is the most common mechanism to control user access to computer systems. However, this mechanism is no longer adequate and we need to investigate more advanced safeguards against unauthorized access to computer resources. Biometrics, the physical and behavioral characteristics that make each of us unique, are a natural choice for identification. Some systems have been developed based on physiological traits, but reliable systems require expensive hardware and software. Keystroke dynamics, which is a behavioral trait, is a good sign of identity, and it does not require a specialized hardware. However, unlike other access control systems based on biometric features, keystroke analysis has not led to techniques providing an acceptable level of accuracy. The main reason is probably the instability of such systems due to the variability of typing dynamics. In this paper we investigate authentication systems that use keystroke dynamics in conjunction with passwords to improve security of passwords. We present a few original methods, discuss their properties, and compare them with conventional methods. Empirical results suggest that our approach can provide a very secure and sufficient easy to use access control system.

View full abstract

The support vector machine is a classifier which is based on the statistical training theory. The twin support vector machine is a kind of binary classifier that determines two nonparallel planes by solving two related SVM-type problems. This paper proposes the TWSVM which is applied fuzzy membership called fuzzy TWSVM. We compare the performance of TWSVM and fuzzy TWSVM. In addition, we propose the vision based vehicle detection system using fuzzy TWSVM.

View full abstract

This paper proposed a new approach using a fuzzy evolutionary behavior selection algorithm to improve a performance of cleaning robot with a low computational power and low cost sensors to be sold enough on the market. To achieve a complex task like cleaning, we choose a conceptually bigger output which is called a behavior. Random reflection and wall-following motion are utilized to achieve an escaping-exploring function and back-and-forth motion for filling function. With proper combination of these two functions we can achieve an effective cleaning performance. To find optimal membership functions, we use EP algorithm before we start real experiment. And our experiment results show that proposed algorithm is more effective than random-reflection algorithm in the Roomba.

View full abstract

We have studied perception by a mobile robot that can achieve a goal in a multistory environment. To move to another floor, a mobile robot should recognize objects which are related to an elevator, e.g., elevator control and call button. In this paper, we propose an efficient object recognition method under varying illumination conditions by incorporating robust outlier rejection and on-line retraining of a neural network. For robust outlier rejection, a graph partitioning method was implemented using the relationship between recognized objects. The on-line retraining neural network offered self-adaptation to varying illumination conditions. Experimental results in daytime and nighttime demonstrated that the proposed algorithm worked well regardless of illumination conditions.

View full abstract

Service robots used for the guidance and delivery. In this paper, we present an obstacle avoidance method for a mobile robot equipped with a laser scanner in a corridor. For avoiding obstacles, we propose five different behaviors for mobile robot and these behaviors are selected by the robot, depending on the environment. Experiments were carried out in several simulated and real environments including a narrow and complex environment, a dead-end trap, and a rapidly changing situation. The robot was able to navigate in a corridor without collisions. Our method can make the robot navigate in very dense, cluttered, and complex scenarios which are a challenge for many other methods.

View full abstract

This paper deals with design of a cube-style modular robot. The modular robot can change its own form according to the working environment. Therefore it is suitable to work in the search and rescue area with a shape of snake, a legged robot and a humanoid robot. Each of modular unit has to install its own controller on the body and driving mechanism in order to give it mobility autonomously. And also they should attach and detach each other with docking mechanism and algorithm. Using this mechanism, they can make union, separation, and recombination. The other important point is that some information of each cell should be exchanged to reconfigure their shape through wireless sensor network and to make some connection of the modular cell. In this paper we suggested a design concept of our modular robot focused on the connection mechanism of the robot.

View full abstract

According to the importance of artificial life in simulating natural processes, we have modeled an ecosystem as a virtual world of predating events. In this regard, on the basis of emergence of symbolic communication, we have modeled assigning a sign to an object by an autonomous agent in the environment as a symbol, which is the relation of symbol to object. In the next step, we have modeled symbols composition, which is the relation of one symbol to the other ones or among symbols themselves, i.e. language grammar or syntax. So, we have designed an artificial prey-predator ecosystem to have reinforcement learning of a symbolic language in preys, so that it can generate an appropriate escaping behavior after hearing the symbol of each predator. Finally, we will have a self-organizing system in which symbolic communication will emerge a language of symbols without any external knowledge or central control. We have used a neural network for reinforcement learning in the first stage, and the other neural network for the second stage.

View full abstract

We have modeled an artificial prey-predator ecosystem and proposed a methodology for learning a symbolic language in preys, so that it can generate an appropriate escaping behavior related to each predator after hearing the symbol of that predator. We have used an associative memory, a neural network and finally an ensemble learning method, hybrid of the first two methods, to show a significant improvement in learning process.

View full abstract

In case of flooding, the underwater flight vehicle (UFV) executes the emergency blowing by blowing ballast tanks off using high pressure air (HPA). However, the conventional blow-off method lets the body on the surface after blowing despite slight flooding. This results in the unnecessary mission failure or body exposure. Therefore, it is necessary to keep the body at the near surface by the blowing control while reducing the overshoot depth. To solve this problem, a blowing control algorithm using the expert knowledge and the fuzzy basis function expansion (FBFE), is proposed. Simulation results for verifying the performance of the proposed algorithm show that the proposed algorithm effectively solves the problems in the UFV blowing control system.

View full abstract

the paper gives an extension to an existing approach of Hardware software co-design of embedded system by including the missed out network element commonly seen in todays embedded systems.The approach tries to provide a verification platform for networked embedded system. Virtual system modeling of networks & their interaction with hardware software is the key issue in the heterogeneous co-simulation of networked embedded system.

View full abstract

Neural network ensemble (NNE) is a collection of several neural that are trained for the same task to achieve better performance. A number of methods are proposed with different methodologies for NNE construction. However, no single method is found suitable for all problems. In another word, for a given problem, a particular method is shown better than others. It is therefore necessary to apply a trial-and-test strategy to find the best method for the given problem. The selection of the best suited method without trial-and-test is an important issue. In this study, we investigate various popular NNE methods on a large number of real world classification problems on a same defined test bed. The outcome of the investigation is to get an outline to select an NNE method that might be suitable for a particular prob-lem based on problem's characteristics.

View full abstract

This paper proposes a method for filtering frequen- cies of an electroencephalogram (EEG) on EEG analysis with a real-coded genetic algorithm (RGA). An EEG of humans has the different personal feature that contains an individual error and a change of his/her physical and mental conditions at the occasion arises. The frequencies of the EEG analyzed are the components that contain significant and immaterial information and have different importance. We express the different importance through the weighted value on frequencies. These weighted values are through to express personal feature of EEG signal. The proposed method calculates the power spectra of the frequency of the EEG signal, is weighted these frequencies, divides the frequency bands based on theta, alpha1-3, and beta rhythms, and evaluates whether the music matches mood of the user or not through EEG pattern classification. A real- coded genetic algorithm is used to specify the weighted value of frequency of the EEG. A k-nearest neighbor method is used to classify the EEG patterns. Finally, the performance of the proposed method is evaluated using real EEG data by classifying EEG patterns that listen to music matching, no matching mood of the subject, and feeling otherwise.

View full abstract

It is part that many users manage occasion and majority Embedded system approaching to Embedded system something should consider to embody Embedded system. One administrator must control Embedded equipments partially or on the whole to manage many several Embedded systems efficiently and controls. Also, discrete Embedded embodiment environment is important efficient remote manage. Also, Embedded system need user each different vicinity and control when many users utilize. We study method for access that is security enemy about Embedded system resource and efficient control.

View full abstract

In order to improve the performance of the filtering technique, we use DTW algorithm and 2D wavelet method. The main point of our approach is that to find the characteristics by using the DTW algorithm and 2D wavelet from movie contents. This paper suggest a method to filter harmful contents by analyzing the speech and image information. Future, we have combined 2D wavelet with DTW algorithm and obtain improved experimental outcome. Pitch information and image source represents the good characteristic to classify the contents. That is, we analyze the pattern of image and speech information to improve the performance.

View full abstract

We propose to promote autonomy in digital ecosystems so that it provides agents with information to improve the behaviour of the digital ecosystem in terms of stability. This work proposes that, in digital ecosystems, autonomous agents can provide fundamental services and information. The final goal is to run the ecosystem, generate novel conditions and let agents exploit them. A set of diversity measures must will be defined as well. We propose an outline of some global indicators, such as heterogeneity and diversity, and establish relationships between agent behaviour and these global indicators of system stability.

View full abstract

In this paper, a different internal fault modeling of transformer based on the physical information of the transformer (equivalent circuit parameter) using transmission line method (TLM) and an identification algorithm method FIS based on PCA in Matlab are presented. A transformer is been modeled considering non-linearities as hysteresis and saturation and an internal fault short circuit is introduced into the model as internal fault portion. Then, the transformer internal fault currents are discriminated from the rated currents and the degree and priority of transformer internal faults are obtained by the proposed method. In addition, the proposed algorithm is compared with the real-time fault of transformer.

View full abstract

Understanding of soft computing methodology often requires grasping abstract concepts or imagining complex interactions of large models over long computing cycles. But this can be difficult for students with weak background in mathematics, especially in the early stages of soft computing education. This paper introduces applying a visual programming paradigm as a tool for educational introduction to soft computing methods. For the visual programming paradigm, IntelligentPad proposed by Y.Tanaka is used. IntelligentPad defines a visual appearance to objects or classes, and allows users to operate and link different objects together using the mouse. This paper reports on using IntelligentPad to teach the basic mechanism of artificial neural networks. The proposed method was applied to 3rd year college students to verify the validity of the proposed teaching method.

View full abstract

Flow-line systems with blocking are often encountered in the real world that fills the fuzziness. This paper proposes a mixed integer nonlinear programming approach for evaluating the performances of the flow line system with blocking in fuzzy environments. The main idea is to model this system as a single-channel, multiple phase queueing model with finite capacity, in that the arrival rate and service rates are fuzzy numbers; then transform this to a family of conventional crisp queues by applying the alpha-cut approach in fuzzy theory. On the basis of alpha-cut representation and the extension principle, two pairs of mixed integer nonlinear programs are formulated to calculate the lower and upper bounds of the fuzzy performance measures at possibility level alpha, via which the membership functions of the performance measures are derived. An example is investigated successfully to illustrate the validity and the informative benefits of using the proposed approach. Since the performance measures are expressed by membership functions rather than by crisp values, the fuzziness of input information is conserved completely, and more information is provided for capacity planning in flow line systems. Furthermore, managerial implications of the analyses are also examined.

View full abstract

In distributed computing environments, there are many database applications that should share data each other such as data warehousing and data mining with autonomy on local databases. The first step to such applications is the integration of heterogeneous database schema, but there is no accepted common data model for the integration and also are difficulties on the construction of integration program. This paper approaches to automatic elements matching between XML application schemas using similarity measure and relaxation labeling to integrate marine geographic database. For an optimal matching, contextual constraints were used in the relaxation labeling method.

View full abstract

An innovative neural fuzzy system is considered for possibilistic reliability using a neural tree structure with nodes of neuronal type. The total tree structure works effectively as a fuzzy logic system where the possibility theory plays important role with Gaussian possibility distribution at the nodes. The structure of the tree is determined by domain knowledge and each node represents a component of the system of concern. The reliabilities of the nodes are dependent on the reliabilities of the preceding nodes. The relationships among the nodes form the core of possibilistic reliability. For each input reliability composition the status of the system is known and interpreted not only at the system output but also at the granulated level at the system sub-domains which are represented by node outputs. The research is described in detail and a demonstrative computer experiment is reported.

View full abstract

This paper deals with the practical approaches for ubiquitous convergence systems. To show the effective convergence systems, we analysis the ubiquitous paradigm and some application systems, and compare with them. Finally we show some good examples for the purpose

View full abstract