Kishiko Maruyama

Agent-based parallel recognition method of contour lines

We propose an agent-based parallel recognition method for digitizing contour lines. In this method, we introduce two kinds of agents, a supervisor agent and vector trace agents, and compose a cooperative negotiable environment between agents to pass through irregular parts of contour lines. This method is implemented in a new man-machine oriented digitizing system, and we confirm that an operator can simultaneously select multiple contour lines and continuously recognize routes of contour lines without interruption. These properties will reduce the high cost of inputting contour drawings.

Acceleration technique of snake-shaped regions retrieval method for telematics navigation service system

Telematics services, which provide traffic information such as route guidance, congestion warnings, etc. via a wireless communication network, have spread recently. The demand is growing for graphical guide information to be provided in addition to the conventional service that provides text only guidance. To improve graphical service, we propose a new retrieval method. This method enables fast extraction of map objects within a snake-shaped region (SSR) along a driving route from a geo-spatial database that stores map data without rectangular mesh boundaries. For this retrieval method, we have considered three techniques. The first is based on simplification of the snake-shaped route region through point elimination, and the second is based on reduction of the processing load of the geometrical intersection detection processes. This second technique is accomplished by dividing the snake-shaped region into multiple cells, and the third is multiple distributions of the SSR retrieval result to terminals for quick start of navigation processing. We have developed a prototype to evaluate the performance of the proposed methods. The prototype provides route guidance information for an actual terminal, and uses information taken from United States road maps. Even in an urban area, we managed to provide an approximately 200-mile route of guide information within 10 seconds. We are convinced that the proposed method can be applied to actual telematics services.

Macroscopic Structural Summarization of Road Networks for Mobile Traffic Information Services

The need for traffic information service systems that warn about traffic congestion and accidents through mobile devices, such as cellular phones, is increasing greatly now. To display clearly these informations for these services, a well-formed map is more useful than a detailed one in many cases. Although methods to generate well-formed map automatically are known as map summarization methods, summarization of road maps that cover wide areas has not been studied sufficiently. Therefore, we developed a new algorithm that summarizes the network structure of a detailed road network into a simple macroscopic structure. Further, we evaluated this algorithm’s effectiveness by experiments with 40 samples of road routes from the main road networks in Japan. The proposed method reduced the link number by 41.3% and reduced the fractal indices by 62.6%, and this proved simplification. And the proposed method improved the well-formed map by user evaluation. From these results obtained by our evaluation, we found that our method is effective for constructing a system for providing practical mobile traffic information services.

Evaluation of Trajectory Clustering Based on Information Criteria for Human Activity Analysis

In this paper, we discuss statistical analysis of human trajectories measured by GPS-like positioning devices. Our goal is to develop a system of trajectory analysis that distributes information optimized for each user. For such a system, we need a method to estimate a users status from his/her trajectories. First, a trajectory needs to be divided into short temporal segments, which will be matched to action model patterns, to estimate a users status. Second, we tried dividing actual human trajectories using a conventional trajectory-clustering method. Moreover, we adjusted parameters of the trajectory clustering by using information criteria experimentally. After the experiment, we confirmed that only a criterion in which noise data are counted worked well. However, we also confirmed that the number of clusters generated by the method is too small. Therefore, we conclude that an improvement in deciding which data are noise in trajectory clustering is necessary for estimating the status of users.

Forecasting Intermittent Demand with Generalized State-Space Model

We propose a method for forecasting intermittent demand with generalized state-space model using time series data. Specifically, we employ mixture of zero and Poisson distributions. To show the superiority of our method to the Croston, Log Croston and DECOMP models, we conducted a comparison analysis using actual data for a grocery store. The results of this analysis show the superiority of our method to the other models in highly intermittent demand cases.