Search

IAn important problem of pattern recognition is to extract or select feature set, which is included in the pre-processing stage. In order to extract feature set, Principal component analysis has been usually used and SFS(Sequential Forward Selection) and SBS(Sequential Backward Selection) have been used as a feature selection method. This paper applies genetic algorithm which is a popular method for nonlinear optimization problem to the feature selection problem. So, we call it Genetic Algorithm Feature Selection(GAFS) and this algorithm is compared to other methods in the performance aspect.

This paper presents the novel feature selection method for Emotion Recognition, which may include a lot of original features. Specially, the emotion recognition in this paper treated speech signal with emotion. The feature selection has some benefits on the pattern recognition performance and `the curse of dimension`. Thus, We implemented a simulator called `IFS` and those result was applied to a emotion recognition system(ERS), which was also implemented for this research. Our novel feature selection method was basically affected by Reinforcement Learning and since it needs responses from human user, it is called `Interactive feature Selection`. From performing the IFS, we could get 3 best features and applied to ERS. Comparing those results with randomly selected feature set, The 3 best features were better than the randomly selected feature set.

In this paper, we apply several pattern recognition algorithms to emotion recognition system with speech signal and compare the results. Firstly, we need emotional speech databases. Also, speech features for emotion recognition is determined on the database analysis step. Secondly, recognition algorithms are applied to these speech features. The algorithms we try are artificial neural network, Bayesian learning, Principal Component Analysis, LBG algorithm. Thereafter, the performance gap of these methods is presented on the experiment result section. Truly, emotion recognition technique is not mature. That is, the emotion feature selection, relevant classification method selection, all these problems are disputable. So, we wish this paper to be a reference for the disputes.

In the sensor network, a lot of sensor nodes are scattered sparsely and organizes a united communication network between each node. After that, environmental information around each sensor node are gathered and analyzed. Because each node operates under resource constraint, the efficiency and hardware specification of a node should be maximized. There exist technical constraints until now but recent technical progress in IC fabrication and wireless network enables to construct a tiny embedded system, which has the properties of low cost, low power consumption, multi functions. Wireless sensor network becomes a modern research field with technical improvements, is studied in numerous laboratories, and is called as diverse different project names - Wireless Integrated Network Sensors (WINS), Mobile Ad hoc NETwork (MANET), Ubiquitous Sensor Network (USN). TinyOS is one of leading project and is widely used. In this paper, we suggest a sensor network, which uses TinyOS platforms and aims for context awareness in a home environment.

This paper presents capacitive tactile sensor that can detect normal and shear forces. This tactile sensor consists of index plate, sensing plate, and elastic dielectric layer. The calculated sensing character is based on the changes of space between two horizontal plate. Larger overlap areas and narrow space between top and bottom plate guarantees higher sensitivity. Tactile sense information can be calculated from the changes of phase of output signal. The symmetric arrangement of sensing plates makes the manufacturing process easier and guarantees the stability of the structure. In this paper, the sensor structure is designed, the mechanism of the Proposed sensor is theoretically explained, and the simulated result is presented.

The highly popular algorithm to determine routing path for the multi-hopping wireless sensor network is DSR(Dynamic Source Routing), which is one of the Demand-Driven way to makes the route only when there is a request for sending data. However, because DSR attaches the route`s record on the sending packet, the bigger number of sensor node is, the heavier packet in DSR becomes. In this paper, we try to propose the new optimal routing path selecting algorithm which does not make the size of packet bigger by using proper routing table even though the number of sensor node increases, and we try to show our algorithm is more stable and reliable because it is based on the cost function considering some network resources of each sensor node such as power consumption, mobility, traffic in network, distance(hop) between source and destination.

This paper presents a robotic agent design and application in the ubiquitous intelligent space. We set up an experimental environment with Bluetooth host, Bluetooth client, furniture and home appliance, and robotic agents. First, the agents basically performed patrol guard to detect unexpected penetration, and to keep home safely from gas-leakage, electric leakage, and so on. They were out to patrol fur a robbery while navigating in a living room and a private room. In this task, we used an area-based action making and a hexagon-based Q-learning to control the agents. Second, the agents communicate with Bluetooth host device to access and control a home appliance. The Bluetooth host offers a manual control to person by inquiring a client robot when one would like to check some place especially. In this exercise, we organize asynchronous connection less (ACL) between the host and the client robots and control the robot maneuver by Bluetooth host controller interface (HCI).

Usually genetic algorithms are used to design optimal system. However the performance of the algorithm is determined by the fitness function and the system environment. It is expected that a co-evolutionary algorithm, two populations are constantly interact and co-evolve, is one of the solution to overcome these problems. In this paper we propose three types of co-evolutionary algorithm to solve GA-Hard problem. The first model is a competitive co-evolutionary algorithm that solution and environment are competitively co-evolve. This model can prevent the solution from falling in local optima because the environment are also evolve according to the evolution of the solution. The second algorithm is schema co-evolutionary algorithm that has host population and parasite (schema) population. Schema population supply good schema to host population in this algorithm. The third is game model-based co-evolutionary algorithm that two populations are co-evolve through game. Each algorithm is applied to visual servoing, robot navigation, and multi-objective optimization problem to verify the effectiveness of the proposed algorithms.

With the development of techniques, robots are getting smaller, and the number of robots needed for application is greater and greater. How to coordinate large number of autonomous robots through local interactions has becoming an important research issue in robot community. In swarm robot systems, each robot must behaves by itself according to the its states and environments, and if necessary, must cooperates with other robots in order to carry out a given task. Therefore it is essential that each robot has both learning and evolution ability to adapt the dynamic environments. In this paper, reinforcement learning method with cascade Support Vector Machine based on structural risk minimization and distributed genetic algorithms is proposed for behavior learning and evolution of collective autonomous mobile robots. By distributed genetic algorithm exchanging the chromosome acquired under different environments by communication each robot can improve its behavior ability. Specially, in order to improve the performance of evolution, selective crossover using the characteristic of reinforcement learning that basis of cascade Support Vector Machine is adopted in this paper.

With the development of techniques, robots are getting smaller, and the number of robots needed for application is greater and greater. How to coordinate large number of autonomous robots through local interactions has becoming an important research issue in robot community. In swarm robot systems, each robot must behaves by itself according to the its states and environments, and if necessary, must cooperates with other robots in order to carry out a given task. Therefore it is essential that each robot has both learning and evolution ability to adapt the dynamic environments. In this paper, reinforcement learning method with cascade Support Vector Machine based on structural risk minimization and distributed genetic algorithms is proposed for behavior learning and evolution of collective autonomous mobile robots. By distributed genetic algorithm exchanging the chromosome acquired under different environments by communication each robot can improve its behavior ability. Specially, in order to improve the performance of evolution, selective crossover using the characteristic of reinforcement learning that basis of cascade Support Vector Machine is adopted in this paper.