Several studies have used artificial neural networks (NNs) to estimate local or regional precipitation/rainfall on the basis of relationships with coarse-resolution atmospheric variables. None these experiments satisfactorily reproduced temporal intermittency and variability in rainfall. We attempt improve performance by using two approaches: (1) couple NNs series, first determine rainfall occurrence, second intensity during rainy periods; (2) categorize into categories train NN reproduce...

In recent years, inflatable robotic arms have been developed so that physical contact with humans and working environments could be performed safety. industry, there is a growing demand for safe industrial robots to collaborate people work in various environments. general, however, the positioning accuracy of has not discussed. This paper proposes an link structure non-inflatable joint realize high such arms. experimentally demonstrates these structures can improve accuracy. addition...

Environmental monitoring data for planning, implementing and evaluating the Total Maximum Daily Loads (TMDL) management system have been measured at about 8-day intervals in a number of rivers Korea since 2004. In present study, water quality parameters such as Suspended Solids (SS), Biochemical Oxygen Demand (BOD), Dissolved (DO), Nitrogen (TN), Phosphorus (TP) corresponding runoff were collected from six stations Yeongsan River basin years transformed into monthly mean values. With primary...

Abstract. Sivakumar et al. (2000a), by employing the correlation dimension method, provided preliminary evidence of existence chaos in monthly rainfall-runoff process at Gota basin Sweden. The present study verifies and supports earlier results strengthens such evidence. analyses rainfall, runoff coefficient series using nonlinear prediction presence is investigated through an inverse approach, i.e. identifying from prediction. optimal embedding (the with best accuracy) for each three...

Inflatable robotic arms have been studied as a lightweight and flexible structure for applications to new fields. In general the motion control of inflatable is difficult, because they complicated nonlinear characteristics. This paper proposes method suitable that realizes precise position on basis visual feedback system. The effectiveness verified by results an experiment, in which arm with two degrees freedom web camera are used.

Abstract. The present paper develops linear regression models based on singular value decomposition (SVD) with the aim of downscaling atmospheric variables statistically to estimate average rainfall in Chikugo River Basin, Kyushu Island, southern Japan, a 12-hour basis. Models were designed take only significantly correlated areas into account procedure. By using particularly precipitable water combination wind speeds at 850 hPa, correlation coefficients between observed and estimated...

This paper presents a comparative study of two AR training systems for Humanitude dementia care. is multimodal comprehensive care methodology patients with and has attracted considerable attention as gentle effective technique. To provide an system Humanitude, we developed HEARTS 1, which realizes simultaneous sensing interaction by combining real entity augmented reality technology. However, experiments using 1 indicated that had certain weaknesses should be addressed, namely, the usability...

A decision support system (DSS) for the integration of hydrologic process modeling and risk evaluation surface water management alternatives in a river basin is developed. The DSS, named CTIWM, aimed at supporting testing policies facilitating user-selected scenarios into planning strategies resource Chikugo River basin, multipurpose multireservoir system. CTIWM uses module library that contains compatible modules simulating variety processes. Different numerical models are invoked through...

The authors are developing a prototype of neuro-fuzzy cooperation system that has the precision and learning ability neural network is easy to understand like fuzzy model. To help convert between systems, this with structure corresponding Knowledge acquired from experts was converted network. applied target learned data obtained during operation enhance accuracy Converting back into model helps explain inner representation will be constructed as basic rules improved step by using repetition...

Abstract During the latest several decades, there has been considerable interest in revealing relationship between El Niño–southern oscillation (ENSO) and hydro‐meteorological variables. The is characterized by a simple index, southern index (SOI). However, thus far, little evidence for influence of ENSO Korea Japan. also studied South Korea, but estimated results are still qualitative show an indirect In this study we use approaches to reveal quantitative direct correlation SOI monthly...

This paper presents an inflatable robotic arm controlled by a joystick to be used for healthcare applications. The is constructed almost entirely of plastic elements: links, air bag actuators, and acrylonitrile butadiene styrene (ABS) joints. Therefore, it softer lighter than typical arms that are made metal heavy elements. Because the softness lightness intrinsically safer, suitable In this paper, new control method proposed which allows system with joystick. To verify usefulness method, we...

SUMMARY This paper proposes a novel dynamic stable grasping method of an arbitrary polyhedral object for hand-arm system with hemispherical fingertips. makes it possible to satisfy the force/torque equilibrium condition immobilization without knowledge object. Two control signals are proposed which generate forces normal and tangential surface in final state. The dynamics overall is modeled analyzed theoretically. We demonstrate using controller through numerical simulations experiments...

The authors have developed a neuro-fuzzy system that initializes structured neural network with fuzzy logic is based on expert knowledge. gains precision through adaptive learning, and then converted back into set of rules for ease understanding. discuss bond rating application uses this process. produces ratings closely match those human experts, has higher better generalization than simple three-layer network. also makes it easier to understand the system's reasoning by translating...

This paper proposes a novel control method for stable grasping using multi-fingered hand-arm system with soft hemispherical finger tips. The proposed is simple but easily achieves of an arbitrary polyhedral object number fingers. Firstly, we formulate nonholonomic constraints between and constrained by rolling contact tips, derive condition stability analysis. A new index evaluating the possibility efficient initial relative positions tips realizing are analyzed. validity verified through...

An informationally structured environment (ISE) is a key technology for realizing service robots in daily life the near future. In ISE, information of robot and its surroundings provided to on time demand. We started development management system ISE named TMS (Town Management System) Robot Town Project 2005. Since then we are continuing our efforts improvement performance enhancement functions TMS. this paper, propose latest ROS-TMS 5.0, which adopts ROS utilize high scalability rich...

Abstract This study proposes a new software platform, called ROS2-TMS, for an informationally structured environment. An environment is vital developing intelligent service robots by embedding various sensors in the to enhance sensing capability and intelligence of robots. Thus far, we have been named ROS-TMS, environment, which connects using ROS architecture. In recent years, ROS2, next-generation version ROS, has released. ROS2 many advantages, such as enhanced security, QoS control,...

Abstract. Global climate variability affects important local hydro-meteorological variables like precipitation and temperature. The Southern Oscillation (SO) is an easily quantifiable major driving force that gives impact on regional climate. relationships between SO variation are, however, characterized by strongly nonlinear processes. Due to this, teleconnections global-scale are not well understood. In this paper, we suggest study these processes in terms of dynamics. Consequently, the...

This paper proposes a new visual servoing method for object manipulation robust to considerable time-delays of information. There still remain several problems in methods although they are quite useful and effective dexterous manipulation. For instance, obtain necessary information from images induce unstable behavior. The mainly caused by low sampling rate sensing system, computational cost image processing, latency data transmission sensor processor. makes it possible avoid such behavior...

Detection of spatial change around a robot is indispensable in several robotic applications, such as search and rescue, security, surveillance. The present paper proposes fast detection technique for mobile using an on-board RGB-D/stereo camera highly precise 3D map created by laser scanner. This first converts point clouds measured data to grid (ND voxels) normal distributions transform classifies the ND voxels into three categories. are then compared according category features voxels....

This paper proposes new software and hardware platforms named ROS-TMS Big Sensor Box, respectively, for an informationally structured environment. We started the development of a management system environment Town Management System (TMS) in Robot Project 2005. Since then we have been continuing our efforts to improve performance enhance TMS functions. Recently, launched version ROS-TMS, which resolves some critical problems by adopting Operating (ROS) utilizing high scalability numerous...

This study develops a training system for multimodal comprehensive care methodology dementia patients called Humanitude. Humanitude has attracted much attention as gentle and effective technique. It consists of four main techniques, namely, eye contact, verbal communication, touch, standing up, more than 150 elements. Learning thus requires time. To provide an Humanitude, we develop that realizes sensing interaction simultaneously by combining real entity augmented reality technology....