Takashi Imamichi

X10-based massive parallel large-scale traffic flow simulation

Optimizing city transportation for smarter cities can have a major impact on the quality of life in urban areas in terms of economic merits and low environmental load. In many cities of the world, transport authorities are facing common challenges such as worsening congestion, insufficient transport infrastructure, increasing carbon emissions, and growing customer needs. To tackle these challenges, it is highly necessary to have fine-grained and large-scale agent simulation for designing smarter cities. In this paper we propose a large-scale traffic simulation platform built on top of X10, a new distributed and parallel programming language. Experimental results demonstrate linear scalable performance in simulating large-scale traffic flows of the national Japanese road network and a hundred of cities of the world using thousands of CPU cores.

Toward simulating entire cities with behavioral models of traffic

Resilient transportation systems enable quick evacuation, rescue, distribution of relief supplies, and other activities for reducing the impact of natural disasters and for accelerating the recovery from them. The resilience of a transportation system largely relies on the decisions made during a natural disaster. We developed an agent-based traffic simulator for predicting the results of potential actions taken with respect to the transportation system to quickly make appropriate decisions. For realistic simulation, we govern the behavior of individual drivers of vehicles with foundational principles learned from probe-car data. For example, we used the probe-car data to estimate the personality of individual drivers of vehicles in selecting their routes, taking into account various metrics of routes such as travel time, travel distance, and the number of turns. This behavioral model, which was constructed from actual data, constitutes a special feature of our simulator. We built this simulator using the X10 language, which enables massively parallel execution for simulating traffic in a large metropolitan area. We report the use cases of the simulator in three major cities in the context of disaster recovery and resilient transportation.

Modeling Patent Quality: A System for Large-scale Patentability Analysis using Text Mining

Current patent systems face a serious problem of declining quality of patents as the larger number of ap- plications make it difficult for patent officers to spend enough time for evaluating each application. For building a better patent system, it is necessary to define a public consensus on the quality of patent applications in a quantitative way. In this article, we tackle the problem of assessing the quality of patent applications based on machine learning and text mining techniques. For each patent application, our tool automatically computes a score called patentability, which indicates how likely it is that the application will be approved by the patent office. We employ a new statis- tical prediction model to estimate examination results (approval or rejection) based on a large data set including 0.3 million patent applications. The model computes the patentability score based on a set of feature variables including the text contents of the specification documents. Experimental results showed that our model outperforms a conven- tional method which uses only the structural properties of the documents. Since users can access the estimated result through a Web-browser-based GUI, this system allows both patent examiners and applicants to quickly detect weak applications and to find their specific flaws.

Simple and fast trip generation for large scale traffic simulation

A large-scale traffic simulator with microscopic model requires trip generation for millions of vehicles. To achieve a realistic result, the trip generation should provide a variety of trips between pairs of locations from Origin-Destination (OD) table reflecting the choices of drivers. Shortest paths take long time to generate and often differ from the choices of drivers. We propose a simple and fast tree-based algorithm in this paper. Our algorithm mixes shortest path trees starting from some location nodes in each subarea of the OD table as preprocessing and then generates trips by probabilistically traversing the mixed shortest path trees. Experiments reveal that the tree-based algorithm runs much faster than the naive one. We also confirm that, under certain conditions on the granularity of the OD table, the results of simulation using trips generated by our algorithm do not differ much from traffic conditions observed in the real world.

Nonlinear optimization to generate non-overlapping random dot patterns

We have devised a method to generate non-overlapping random dot patterns for light guides and diffuser films in liquid crystal displays (LCDs). Molecular-dynamics-based algorithms are being for this purpose and have been proven to generate high quality dot patterns. The key technical challenge is how to remove inter-dot overlap that leads to visible roughness in the luminance distribution. In this paper, we describe a new overlap removal method that penalizes the overlap of dots and minimizes the sum of the penalties by using a nonlinear optimization technique. Through computational experiments with real world data, we show that our optimization-based method runs faster than an existing simulation-based method and generates dot patterns with comparable quality.

Bus trajectory identification by map-matching

We study the problem of identifying vehicle trajectories from the sequences of noisy geospatial-temporal datasets. Nowadays we witness the accumulation of vehicle trajectory datasets in the form of the sequences of GPS points. However, in many cases the sequences of GPS points are sparse and noisy so that identifying the actual trajectories of vehicles is hard. Although there are many advanced map-matching techniques claiming to achieve high accuracy to deal with the problem, only few public datasets that come with ground truth trajectories for supporting the claims. On the other hand, some cities are releasing their bus datasets for real-time monitoring and analytics. Since buses are expected to run on predefined routes, such datasets are highly valuable for map-matching and other pattern recognition applications. Nevertheless, some buses in reality appear not following their predefined routes and behave anomalously. We propose a simple and robust technique based on the combination of map-matching, bag-of-roads, and dimensionality reduction for their route identification. Experiments on datasets of buses in the city of Rio de Janeiro confirm the high accuracy of our method.