Yoshihide Sekimoto

PFlow: Reconstructing People Flow Recycling Large-Scale Social Survey Data

Understanding people flow on a macroscopic scale requires reconstructing it from various forms of existing fragmentary spatiotemporal data. This article illustrates a process for reconstructing such data using existing person-trip survey data.

Prediction of human emergency behavior and their mobility following large-scale disaster

The frequency and intensity of natural disasters has significantly increased over the past decades and this trend is predicted to continue. Facing these possible and unexpected disasters, accurately predicting human emergency behavior and their mobility will become the critical issue for planning effective humanitarian relief, disaster management, and long-term societal reconstruction. In this paper, we build up a large human mobility database (GPS records of 1.6 million users over one year) and several different datasets to capture and analyze human emergency behavior and their mobility following the Great East Japan Earthquake and Fukushima nuclear accident. Based on our empirical analysis through these data, we find that human behavior and their mobility following large-scale disaster sometimes correlate with their mobility patterns during normal times, and are also highly impacted by their social relationship, intensity of disaster, damage level, government appointed shelters, news reporting, large population flow and etc. On the basis of these findings, we develop a model of human behavior that takes into account these factors for accurately predicting human emergency behavior and their mobility following large-scale disaster. The experimental results and validations demonstrate the efficiency of our behavior model, and suggest that human behavior and their movements during disasters may be significantly more predictable than previously thought.

Modeling and probabilistic reasoning of population evacuation during large-scale disaster

The Great East Japan Earthquake and the Fukushima nuclear accident cause large human population movements and evacuations. Understanding and predicting these movements is critical for planning effective humanitarian relief, disaster management, and long-term societal reconstruction. In this paper, we construct a large human mobility database that stores and manages GPS records from mobile devices used by approximately 1.6 million people throughout Japan from 1 August 2010 to 31 July 2011. By mining this enormous set of Auto-GPS mobile sensor data, the short-term and long-term evacuation behaviors for individuals throughout Japan during this disaster are able to be automatically discovered. To better understand and simulate human mobility during the disasters, we develop a probabilistic model that is able to be effectively trained by the discovered evacuations via machine learning technique. Based on our training model, population mobility in various cities impacted by the disasters throughout the country is able to be automatically simulated or predicted. On the basis of the whole database, developed model, and experimental results, it is easy for us to find some new features or population mobility patterns after the recent severe earthquake, tsunami and release of radioactivity in Japan, which are likely to play a vital role in future disaster relief and management worldwide.

Weather Effects on the Patterns of People's Everyday Activities: A Study Using GPS Traces of Mobile Phone Users

This study explores the effects that the weather has on peoples everyday activity patterns. Temperature, rainfall, and wind speed were used as weather parameters. Peoples daily activity patterns were inferred, such as place visited, the time this took place, the duration of the visit, based on the GPS location traces of their mobile phones overlaid upon Yellow Pages information. Our analysis of 31,855 mobile phone users allowed us to infer that people were more likely to stay longer at eateries or food outlets, and (to a lesser degree) at retail or shopping areas when the weather is very cold or when conditions are calm (non-windy). When compared to peoples regular activity patterns, certain weather conditions affected peoples movements and activities noticeably at different times of the day. On cold days, peoples activities were found to be more diverse especially after 10AM, showing greatest variations between 2PM and 6PM. A similar trend is observed between 10AM and midnight on rainy days, with peoples activities found to be most diverse on days with heaviest rainfalls or on days when the wind speed was stronger than 4 km/h, especially between 10AM–1AM. Finally, we observed that different geographical areas of a large metropolis were impacted differently by the weather. Using data of urban infrastructure to characterize areas, we found strong correlations between weather conditions upon peoples accessibility to trains. This study sheds new light on the influence of weather conditions on human behavior, in particular the choice of daily activities and how mobile phone data can be used to investigate the influence of environmental factors on urban dynamics.

Understanding tourist behavior using large-scale mobile sensing approach

This article describes a framework that capitalizes on the large-scale opportunistic mobile sensing approach for tourist behavior analysis. The article describes the use of massive mobile phone GPS location records to study tourist travel behavior, in particular, number of trips made, time spent at destinations, and mode of transportation used. Moreover, this study examined the relationship between personal mobility and tourist travel behavior and offered a number of interesting insights that are useful for tourism, such as tourist flows, top tourist destinations or origins, top destination types, top modes of transportation in terms of time spent and distance traveled, and how personal mobility information can be used to estimate the likelihood in tourist travel behavior, i.e., number of trips, time spent at destinations, and trip distance. Furthermore, the article describes an application developed based on the analysis in this study that allows the user to observe touristic, non-touristic, and commuting trips along with home and workplace locations as well as tourist flows, which can be useful for urban planners, transportation management, and tourism authorities.

Large-Scale Auto-GPS Analysis for Discerning Behavior Change during Crisis

Auto-GPS is a new type of mobile sensing data used to discern human mobility and behavior during a large-scale crisis. Using data collected after the 2011 Great Japan Earthquake, useful information is revealed on how humans react in disaster scenarios and how the evacuation process can be monitored in near real time.

Anomalous event detection on large-scale GPS data from mobile phones using hidden markov model and cloud platform

Anomaly detection is an important issue in various research fields. An uncommon trajectory or gathering of people in a specific area might correspond to a special event such as a festival, traffic accident or natural disaster. In this paper, we aim to develop a system for detecting such anomalous events in grid-based areas. A framework based on a hidden Markov model is proposed to construct a pattern of spatio-temporal movement of people in each grid during each time period. The numbers of GPS points and unique users in each grid were used as features and evaluated. We also introduced the use of local score to improve the accuracy of the event detection. In addition, we utilized Hadoop, a cloud-computing platform, to accelerate the processing speed and allow the handling of large-scale data. We evaluated the system using a dataset of GPS trajectories of 1.5 million individual mobile phone users accumulated over a one-year period, which constitutes approximately 9.2 billion records.

Lightweight lane positioning of vehicles using a smartphone GPS by monitoring the distance from the center line

This paper presents a simple method for using the separation distance (offset) between a smartphone GPS and the center line on a digital road map to determine the lane position of a car. The method was verified.

Prediction and Simulation of Human Mobility Following Natural Disasters

In recent decades, the frequency and intensity of natural disasters has increased significantly, and this trend is expected to continue. Therefore, understanding and predicting human behavior and mobility during a disaster will play a vital role in planning effective humanitarian relief, disaster management, and long-term societal reconstruction. However, such research is very difficult to perform owing to the uniqueness of various disasters and the unavailability of reliable and large-scale human mobility data. In this study, we collect big and heterogeneous data (e.g., GPS records of 1.6 million users1 over 3 years, data on earthquakes that have occurred in Japan over 4 years, news report data, and transportation network data) to study human mobility following natural disasters. An empirical analysis is conducted to explore the basic laws governing human mobility following disasters, and an effective human mobility model is developed to predict and simulate population movements. The experimental results demonstrate the efficiency of our model, and they suggest that human mobility following disasters can be significantly more predictable and be more easily simulated than previously thought.

Spatiotemporal route estimation consistent with human mobility using cellular network data

Continuous personal position information has been attracting attention in a variety of service and research areas. In recent years, many studies have applied the telecommunication histories of mobile phones (CDRs: call detail records) to position acquisition. Although large-scale and long-term data are accumulated from CDRs through everyday use of mobile phones, the spatial resolution of CDRs is lower than that of existing positioning technologies. Therefore, interpolating spatiotemporal positions of such sparse CDRs in accordance with human behavior models will facilitate services and researches. In this paper, we propose a new method to compensate for CDR drawbacks in tracking positions. We generate as many candidate routes as possible in the spatiotemporal domain using trip patterns interpolated using road and railway networks and select the most likely route from them. Trip patterns are feasible combinations between stay places that are detected from individual location histories in CDRs. The most likely route could be estimated through comparing candidate routes to observed CDRs during a target day. We also show the assessment of our method using CDRs and GPS logs obtained in the experimental survey.