We propose a time series prediction system of agricultural products price based on recurrent neural networks and their time alignment. The purpose of the system is to provide a way to make the price movements stable by sharing the information of price between producers and consumers of agricultural products. For the purpose, we designed a time alignment mechanism of recurrent neural networks to predict time series of prices, where each predicted results is evaluated not only by the accuracy but also by probability distribution of price movement (statistical characteristic). For the stability of agricultural products, price movements have the same importance as accuracy of predicted prices. This is the reason why we focus on not only the accuracy but also probability distribution. Although we show the results where only past price information is used as input of learning for the first step, the framework is designed to reflect other related information such as meteorological and social information on learning in future.

For understanding human activities in urban public spaces, we have been developing a sensing platform for visualizing data derived from sensor devices in the spaces. The platform collects sensing data from sensor devices installed in public spaces, and provide a simple communication interface to access the sensor data for client systems. In this demo abstract, we describe a working prototype of a sensor data streaming service for visualizing urban public spaces. The streaming data includes the number of pedestrians, pedestrian flows, and sound pressures of the human activities in the sensing area. As an application of the streaming service, we will show a client system that visualizes the current pedestrian flows in the sensing area with very little delay. The flows are visualized like a view of live camera without pedestrians' appearances. The system has a search interface to retrieve the sensing data in a past period and also visualizes them.

Recently we have developed an eigenvector method (EVM) which can achieve the blind deconvolution (BD) for MIMO systems. The attractive features of the proposed algorithm are that the BD can be achieved by calculating the eigenvectors of a matrix and by using reference signals. However, the performance accuracy of the EVM depends highly on the computational result of the eigenvectors. In this paper, by modifying the EVM, we propose an algorithm which can achieve the BD without calculating the eigenvectors. Then the pseudo-inverse which is needed to carry out the BD is calculated by our proposed matrix pseudo-inversion lemma. Simulation results will be presented for showing the validity of the proposed method.

Highly-functional mobile devices, such a smart phone, have appeared. Location based services of the mobile devices are assimilated in a variety of ways. Then, Indoor localization sensor is necessary to access the location based services seamlessly. This paper researched the performance of indoor localization with ZigBee based particle filter. This paper showed this method can localize a resting target within 2.0 meter accuracy and can localize a moving target with an area levels localization. ZigBee based particle filter can be one of some options for location based services in indoor spaces.

In this paper, we propose a system that can detect unusual sounds and directions by observing sound environment with microphone arrays. One of the attractive features of the system is to detect the unusual information through daily environmental sound measurement. Therefore the system does not require such troublesome processes that the detected sounds must be predefined, the predefined sounds must be collected, and using the collected sounds, their features must be modeled, where the conventional systems have such troublesomeness. Moreover, unlike conventional systems using video cameras, our system is not limited by video camera angles. A simple experimental result shows the validity of the proposed system.

Typically, studies of ubiquitous computing environments focus on context-aware assistance for activities in a closed domain, such as guide systems in museums, and ignore ways of coordinating services between two different service environments. However, it is important to provide them with personalized assistance services that seamlessly coordinate two service environments for the users who move from an open ubiquitous computing environment to other. This study specifically examines seamless personalized services for mobile users and presents a framework of role-based agent coordination to provide services for them. In that framework, personal agents, which are always with the users, play roles assigned by a role manager agent when they participate in new environments. We show a new agent coordination protocol, which is an extension of the contract-net protocol, to perform context-aware role assignments to realize those services.

A fundamental issue of human-centered coordinating services in ubiquitous computing is concerned with dynamic service coordination according to users' intentions. How can we coordinate the services to assist the user in receiving a coordinated service to maximize the user's satisfaction in an environment? In order to solve this issue, we have been developing a sort of agent-based coordination framework, called "location-mediated agent coordination," that orchestrates Web services embedded in the real world and Web services on the Internet. In this paper, we show a prototype application of the framework, context-aware information assist services in a museum.

We discuss a smart navigation system by route planning which makes active use of spatial semantics. The central concept of the system is coordination of lightweight components as services, such as business process modeling. Our proposed navigation system consists of three main components: a route planner, an object repository, and a space functionality retriever (SFR). The route planner is the component for inquisitions. The object repository deals with real-world information. Then, the SFR deals with knowledge about space represented by XML-based descriptions. Using these components, we realize a smart navigation system that enables a route planner to suggest alternate solutions to end-users. Our final target is to develop advanced location-based information services that surpass conventional ones, thereby realizing an intelligent space.