Intelligent System for Human Behavior Analysis and Reasoning Following Large-Scale Disasters

Song, Xuan; Zhang, Quanshi; Sekimoto, Yoshihide; Horanont, Teerayut; Ueyama, Satoshi; Shibasaki, Ryosuke

doi:10.1109/mis.2013.35

Cited by 37 publications

(21 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lu et al analyzed call detail records to investigate the predictability of evacuation destinations after the Haiti earthquake [9]. Song et al revealed the population decline in various areas after the Great East Japan Earthquake using GPS data [7]. More recent studies showed that evacuation behavior could be monitored after an earthquake by using mobile phone location data collected from evacuees [31,32,33].…”

Section: Human Mobility Analysis During Disastersmentioning

confidence: 99%

Predicting Evacuation Decisions using Representations of Individuals' Pre-Disaster Web Search Behavior

Yabe

Tsubouchi²,

Shimizu³

et al. 2019

Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery &Amp; Data Mining

Self Cite

View full text Add to dashboard Cite

Predicting the evacuation decisions of individuals before the disaster strikes is crucial for planning first response strategies. In addition to the studies on post-disaster analysis of evacuation behavior, there are various works that attempt to predict the evacuation decisions beforehand. Most of these predictive methods, however, require real time location data for calibration, which are becoming much harder to obtain due to the rising privacy concerns. Meanwhile, web search queries of anonymous users have been collected by web companies. Although such data raise less privacy concerns, they have been under-utilized for various applications. In this study, we investigate whether web search data observed prior to the disaster can be used to predict the evacuation decisions. More specifically, we utilize a session-based query encoder that learns the representations of each user's web search behavior prior to evacuation. Our proposed approach is empirically tested using web search data collected from users affected by a major flood in Japan. Results are validated using location data collected from mobile phones of the same set of users as ground truth. We show that evacuation decisions can be accurately predicted (84%) using only the users' pre-disaster web search data as input. This study proposes an alternative method for evacuation prediction that does not require highly sensitive location data, which can assist local governments to prepare effective first response strategies.

show abstract

Section: Human Mobility Analysis During Disastersmentioning

confidence: 99%

Predicting Evacuation Decisions using Representations of Individuals' Pre-Disaster Web Search Behavior

Yabe

Tsubouchi²,

Shimizu³

et al. 2019

Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery &Amp; Data Mining

Self Cite

View full text Add to dashboard Cite

show abstract

“…Therefore, it is possible to use countywide individual GPS logs to model mobility in disaster situations. For example, GPS logs can be used to model the behavior of people following large-scale disasters, such as the 2011 East Japan Great Earthquake [100].…”

Section: People Mobilitymentioning

confidence: 99%

“…Therefore, the data could serve as a valuable information source for disaster risk assessment in which the number of casualties should be estimated for a hazard. Furthermore, the data could be applied to behavior following hazards [100] to better plan mitigation and preparedness based on the behavior modeled by the mobility data.…”

Section: People Mobilitymentioning

confidence: 99%

Reviews of Geospatial Information Technology and Collaborative Data Delivery for Disaster Risk Management

Miyazaki

Nagai

Shibasaki

2015

IJGI

Self Cite

View full text Add to dashboard Cite

Due to the fact that geospatial information technology is considered necessary for disaster risk management (DRM), the need for more effective collaborations between providers and end users in data delivery is increasing. This paper reviews the following: (i) schemes of disaster risk management and collaborative data operation in DRM; (ii) geospatial information technology in terms of applications to the schemes reviewed; and (iii) ongoing practices of collaborative data delivery with the schemes reviewed. This paper concludes by discussing the future of collaborative data delivery and the progress of the technologies.

show abstract

“…According to the International Energy Agency (IEA)(2013), the transport sector has the highest growth of CO 2 emission of any sector. In the same perspective, Song et al (2013) also indicate that road transportation is a major fuel consumer and greenhouse gas emitter. It's contribution to energy related CO 2 emissions are estimated to go from one quarter today to one-third by 2050.…”

Section: Introductionmentioning

confidence: 98%

Fuel Efficiency Vehicle Adoption and Carbon Emissions in a Country Context

Namukasa¹,

Namagembe²,

Nakayima³

2020

IJGS

View full text Add to dashboard Cite

The paper aimed at establishing the relationship between age, engine capacity, fuel type and fuel efficiency and carbon emissions. The relationship was obtained using panel data on newly imported registered vehicle stock obtained from Uganda Revenue Authority. This involved collecting data on imported vehicle inventory into Uganda for the period from 2013 to 2017 which was later analysed using the stata software. The findings indicated a positive relationship between a vehicles age, engine capacity, vehicle category (Light Duty Vehicles, Medium Duty Vehicles and Heavy Duty Vehicles) and fuel efficiency and carbon emissions. A comparison with the global fuel efficiency targets indicated that more fuel was being consumed in Uganda compared to non-OECD countries. A reduction in fuel consumption and emissions was observed in petrol vehicles while diesel vehicles had increased carbon emissions and fuel consumptions due to an increase in engine capacities. The findings imply that government should develop policy options that promote vehicle fuel efficiency, transport system operators may undergo training in fuel efficiency issues that will result in an attitudinal change while academicians need to carry out more research comparing the effect of transport systems operators ages, level education and income on carbon emissions and fuel efficiency. The majority of research on fuel efficiency and carbon emissions uses survey data rather than panel data. Further, previous research is focused on vehicles that are already on the road rather than focusing on the effect of age, engine capacity, fuel type on fuel efficiency and carbon emissions.

show abstract

Intelligent System for Human Behavior Analysis and Reasoning Following Large-Scale Disasters

Cited by 37 publications

References 3 publications

Predicting Evacuation Decisions using Representations of Individuals' Pre-Disaster Web Search Behavior

Predicting Evacuation Decisions using Representations of Individuals' Pre-Disaster Web Search Behavior

Reviews of Geospatial Information Technology and Collaborative Data Delivery for Disaster Risk Management

Fuel Efficiency Vehicle Adoption and Carbon Emissions in a Country Context

Contact Info

Product

Resources

About