Arata Miyauchi

Synchronization-based data gathering scheme using chaotic pulse-coupled neural networks in wireless sensor networks

Wireless sensor networks (WSNs) have attracted significant interests of many researchers because they have great potential as a means of obtaining information of various environments remotely. WSNs have their wide range of applications, such as natural environmental monitoring in forest regions and environmental control in office buildings. In WSNs, hundreds or thousands of micro-sensor nodes with such resource limitation as battery capacity, memory, CPU, and communication capacity are deployed without control in a region and used to monitor and gather sensor information of environments. Therefore, scalable and efficient network control and/or data gathering scheme for saving energy consumption of each sensor node is needed to prolong WSN lifetime. In this paper, assuming that sensor nodes synchronize to intermittently communicate with each other only when they are active for realizing the long-term employment of WSNs, we propose a new synchronization scheme for gathering sensor information using chaotic pulse-coupled neural networks (CPCNN). We evaluate the proposed scheme using computer simulation and discuss its development potential. In simulation experiment, the proposed scheme is compared with previous synchronization scheme based on a pulse-coupled oscillator model to verify its effectiveness.

An Artificial Bee Colony algorithm for solving dynamic optimization problems

Artificial Bee Colony (ABC) is a fast and robust algorithm to solve various optimization problems with complex nonlinearity. Especially, ABC is effective for high dimensional problems, compared with the other metaheuristic algorithms. However, the basic ABC is assumed to be used to static optimization problems and has not been sufficiently considered for dynamic optimization problems including temporal changes of environments. Recently, improved ABC methods for solving dynamic optimization problems have been proposed. However, it is difficult for these methods to balance the flexibility to temporal changes of environments and the convergent speed to solutions. This paper proposes an ABC algorithm for solving dynamic optimization problems with simple procedures. The proposed method can realize fast solution search for various dynamic optimization problems, suppressing excessive convergence to limited solutions. In the numerical simulations, the effectiveness of the proposed method is verified.

A method to interpret 3D motion using neural networks

This study proposes a 3D motion interpretation method which uses a neural network system consisting of three kinds of neural networks. This system estimates the solutions of 3D motion of an object by interpreting three optical flow (OF - motion vector field calculated from images) patterns of the same object obtained from three different view points. Though the interpretation system is trained using only basic 3D motions consisting of a single motion component, the system can interpret unknown multiple 3D motions consisting of several motion components. The generalization capacity of the proposed system is confirmed using diverse test patterns. Also the robustness of the system to noise is proved experimentally. The experimental results show that this method has suitable features for applying to real images.<<ETX>>

Prolonging lifetime of multiple-sink wireless sensor networks using chaos-based data gathering scheme

This paper studies chaos synchronization-based data transmission scheme in multiple sink wireless sensor networks. 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. 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. We evaluate the proposed scheme using computer simulations. Through simulation experiments, we show effectiveness of the proposed scheme and discuss its development potential.

An artificial bee colony algorithm with a memory scheme for Dynamic Optimization Problems

In Dynamic Optimization Problems (DOPs), the characteristics of the problems change dynamically due to various kinds of factors. In these problems, basic optimization algorithms decrease the searching performances, because the effective solutions obtained in the past search process change into ineffective ones. For high-order dimensional DOPs, we have proposed an Improved ABC (IABC) algorithm. In this paper, the IABC algorithm is farther modified in order to develop the searching performances for DOPs. In the proposed algorithm, basically, two schemes are added to the conventional IABC: a simple memory scheme and a simple detection scheme for dynamic changes. By performing the numerical experiments, the effectiveness of the proposed algorithm is confirmed.

A learning method for dynamic Bayesian network structures using a multi-objective particle swarm optimizer

In this article, we present a multi-objective discrete particle swarm optimizer (DPSO) for learning dynamic Bayesian network (DBN) structures. The proposed method introduces a hierarchical structure consisting of DPSOs and a multi-objective genetic algorithm (MOGA). Groups of DPSOs find effective DBN sub-network structures and a group of MOGAs find the whole of the DBN network structure. Through numerical simulations, the proposed method can find more effective DBN structures, and can obtain them faster than the conventional method.

A competitive PSO based on evaluation with priority for finding plural solutions

In this paper, we propose a simple competitive PSO for finding plural solutions. In the proposed PSO, particles are divided into groups corresponding to the required number of solutions. Each group simultaneously searches solutions having a priority search region. This region affects to prohibit that different groups search the same solutions. The proposed PSO can effectively find desired plural acceptable solutions with a high accuracy and with a low computation cost, and can easily control combinations of these solutions by adjusting a parameter. Also, the proposed PSO is applied to a problem in wireless sensor networks (WSNs). The simulation results show that obtained results can contribute to prolonging lifetime of WSNs.

Solving Performances of Piecewise-Linear Particle Swarm Optimizer with Chaotic Dynamics

In this paper, we propose piecewise-linear particle swarm optimizer (PPSO). PPSO is one of the deterministic PSO. Each particle of PPSO has two dynamics which is convergence dynamics and divergence dynamics. The trajectory of each particle is switched between these two dynamics and the particle exhibits chaotic behavior. We investigate the solving performances of PPSO for these two dynamics. Furthermore, the solving performances of PPSO are compared with those of the other PSO methods in the numerical experiments.

An effective sink node allocation scheme for long-term operation of Wireless Sensor Networks using adaptive suppression PSO

Wireless Sensor Networks (WSNs) have attracted a significant amount of interests from many researchers for a wide range of applications, such as natural environmental monitoring and environmental control in residential spaces or factories. To realize long-term operation of WSNs, we discuss in this study a method of suppressing the communication load on sensor nodes by effectively placing a limited number of sink nodes in an observation area that integrate sensing data from sensor nodes around them. As a technique of solving effective locations for sink nodes, in past studies, we have proposed a search method based on particle swarm optimization that is one of the swarm intelligence algorithms, named the Suppression Particle Swarm Optimization (SPSO). This paper proposes a new technique, named the Advanced Suppression Particle Swarm Optimization (ASPSO) having an adaptive control scheme for its parameters.

A Sink Node Allocation Scheme in Wireless Sensor Networks Using Suppression Particle Swarm Optimization

A wireless sensor network, which is a key network to facilitate ubiquitous information environments, has attracted a significant amount of interest frommany researchers (Akyildiz et al., 2002). A wireless sensor network has a wide range of applications, such as natural environmental monitoring, environmental control in residential spaces or plants, object tracking, and precision agriculture. In a general wireless sensor network, hundreds or thousands of micro sensor nodes, which are generally compact and inexpensive, are placed in a large scale observation area and sensing data of each node is gathered to a sink node by inter-node wireless multi-hop communication. Each sensor node consists of a sensing function to measure the status (temperature, humidity, motion, etc.) of an observation point or object, a limited function on information processing, and a simplified wireless communication function, and generally operates on a resource of a limited power-supply capacity such as a battery. Therefore, a data gathering scheme and/or a routing protocol capable of meeting the following requirements has been mainly studied to prolong the lifetime of a wireless sensor network.