Viewing entries tagged
news

BDEM Annual Workshop to be held in October 2019

The annual workshop on Big Data for Emergency Management (BDEM 2019) will be hosted by BDEM project in Sogndal, Norway.

In two days (21 – 22 October 2019) workshop, researchers, practitioners and students will discuss on emergency management analytics open issues and provide interesting insights for future actions in the hazard response.

BDEM 2019 aims to give answers to

  • How to address challenges of current and future emergency management

  • How analytics and intelligence can support an enhanced emergency management in the future

Venue: Quality Hotel, 6856 Sogndal, Norway

Participants:

(1st day and first half of 2nd day) Invited guests, UiB students and BDEM partners.

(Second half of 2nd day) Only BDEM partners.

Accommodation: Hofslund Fjord Hotel, Fjørevegen 37, 6856 Sogndal

Programme

October 21, 2019 (Monday)

09:30 – 09:45 Welcome and Overview

09:45 – 10:45 Keynote address – 1

10:45 – 11:00 Coffee break

11:00 – 11:45 Hong Kong Polytechnic University

11:45 - 12:30 George Mason University

12:30 – 13:30 Lunch

13:30 – 14:30 Keynote address – 2

14:30 – 15:15 National Institute of Informatics

15:15 – 15:30 Coffee break

15:30 – 17:00 Group Activity for Students

19:00 – 21:00 Dinner

October 22, 2019 (Tuesday)

09:30 – 10:15 The University of Tokyo

10:15 – 10:30 Coffee break

10:30 – 11:15 University of Bergen

11:15 – 12:00 Western Norway Research Institute

12:00 - 12:30 Open discussion

12:30 – 13:30 Lunch


BDEM Steering Meeting

October 22, 2019 (Tuesday)

14:00 – 17:00 Planning for remaining project period

17:00 Closing

New publication on problem of developing a rescue plan in disaster response

paper1.jpg

Abstract

Disasters pose a serious threat to people’ lives and urban environment, affecting the sustainable development of society. Then it's crucial to quickly develop an efficient rescue plan for the disaster area. However, disaster rescue is rather difficult due to the requirement to develop the optimal rescue plan as quickly as possible according to the information of trapped people and rescue teams, and the amount of information will continue to increase as the rescue proceeds. At present, most of the rescue plans are manually made based on previous rescue experience. But obviously these plans might be the not optimal one. Considering the real-time location data of trapped people, this paper develops a Mixed Integer Non-linear Programming (MINLP) model to find the highest efficient rescue plan To solve the model accurately and efficiently, a bi-level decomposition (BLD) algorithm is presented to iteratively solve a discretized Mixed Integer Linear Programming (MILP) model and its nonconvex Non-linear Programming (NLP) model until a converged solution is obtained. In addition, since more trapped people could be found over time, the built rescue units should also be considered when making a rescue plan for a new stage. To further improve the solving efficiency, an accelerated bi-level decomposition (ABLD) algorithm is also proposed. Finally, a real-world disaster rescue is given to validate the superiority of the proposed ABLD algorithm relative to particle swarm optimization (PSO) algorithm and BLD algorithm.

Join the first BDEM Hackathon!

Hacking disaster response coordination and communication related data with Machine Learning, Data Mining and  Natural Language Processing. Pizza and soft drinks will be served during group work.

  • When: Wednesday, 24 October 2018

  • Where:  VilVite, Thormøhlens gate 51, Conference room C

  • For who: Primarily ICT-students at UiB and HVL

  • Organisers: The BDEM project and University of Bergen

  • Contact Persons: Andreas Opdahl and Hemant Purohit

  • Registration deadline: 22 October 2018, 12:00 PM (limited to 40 participants)

Programme

1000-1030  Introduction, data sources and tools, team formation (plenary)
1030-1630  Group work, up to 4 people per group
1630-1700  Preparing demos and presentations
1700-1800  Presentations (plenary)
1800-1830  Awards, closing

Rules

  • Teams will be composed

  • Teams will be formed in the Team Formation time

  • Once the team is composed, the name, surname, email of the members must be sent via email to the mentors

Deliverables

  • Each group should produce running code that uses real datasets

  • Jury will evaluate your project by the demo of your system and presentation of the system design with result analyses

  • Whenever your code runs, capture a quick video. Then you have something to show even if the code “stops working” just before the deadline

  • You won’t have the time to present your detailed code, but simple diagrams (like a dataflow and/or class diagram) may be helpful, in particular to show what you have done on the backend side

Awards

There will be 3 prizes based on creativity and innovativeness of the proposed solution as well as quality of the presentation.

First prize: NOK 3000,-

Second prize: NOK 2000,-

Third prize: NOK 1500,-

The Big Data Research Team at Vestlandsforsking is hosting two international research students

The Big Data Research Team at Vestlandsforsking is hosting two research students from the University of Tokyo (Japan) and San Diego State University (USA) for two months as part of an ongoing collaborative research-education project funded by the Research Council of Norway (RCN) and the Norwegian Centre for International Cooperation in Education (SiU).

This visit which taking place in June-July 2018  is part of an ongoing project operating under the broad theme of “Big Data in Emergency Management (BDEM)”. The BDEM project, which commenced in April 2017, involves mobility programme which enables researchers at international partner institutions to establish and develop collaborations with the Big Data Team at Vestlandsforsking with the intention of transferring knowledge and research capabilities in big data in emergency management.

(From left to right) Timothy Schempp, Haoran Zhang and Minsung Hong at Sogndal Kai

(From left to right) Timothy Schempp, Haoran Zhang and Minsung Hong at Sogndal Kai

 

Timothy Schempp is studying Master of Science in Geography, with emphasis in Geographic Information Science. His degree expected to complete in Summer 2018. His research focuses on the conceptualization and scalable development of a web-based platform that encapsulates the tri-space approach in an exploratory data analysis environment to facilitate  inductive investigation of multitemporal imagery data. He aims at leveraging techniques from machine learning, dimensionality reduction, and visualization to extract insights from a collection of imagery data. During this two-month visit he will focus on applying his tri-space analysis interface to the domain of emergency management.

Haoran Zhang is a PhD student at Center for Spatial Information Science, The University of Tokyo. His main research focus is urban informatics and research theme is Data-Driven Scheduling Optimization for Emergency Evacuation and Relief Distribution. He is focusing on scheduling optimization, system design and trajectory data mining. He has published 12 SCI Papers, 3 patents and 1 book (chapter) on scheduling algorithm, risk identification and energy system optimization. His recent 9 papers are under review on the research topics of data driven emergency prediction, public health assessment and system reliability. During this two-month visit his research will be based on the prediction or simulation model, proposing optimization model for emergency evacuation and relief distribution scheduling.

Both guest researchers will be collaborating with Minsung Hong and the BDEM coordinator, Professor Rajendra Akerkar. Professor Andreas L. Opdahl of University of Bergen,  BDEM national partner, and his research team will also participate in the joint research activity. 

Our academic standing has been secured and enhanced over the years by a series of international links, visits, exchanges and partnerships. The BDEM project mobility represents the most recent of these and the institute is delighted to play host to such scholarly guests.

Workshop on Big Data for Emergency Management (BDEM 2018)

The Workshop on Big Data for Emergency Management (BDEM 2018) will be hosted by BDEM project in Sogndal, Norway.

On two days 22 – 23 October 2018, researchers, practitioners and students will discuss on emergency management analytics open issues and provide interesting insights for future actions in the hazard response.

BDEM 2018 aims to give answers to

  • How to address challenges of current and future emergency management

  • How analytics and intelligence can support an enhanced emergency management in the future

Venue:   Vestlandsforsking, Sognahallen, Røyrgata 4, 6856 Sogndal, Norway

Participants:  (1st day and first half of 2nd day) Invited guests, UiB students, BDEM partners.

                         (Second half of 2nd day) Only BDEM partners.

Accommodation: Hofslund Fjord Hotel, Fjørevegen 37, 6856 Sogndal

Programme

October 22, 2018

09:30 – 09:45 Welcome and Introduction: Rajendra Akerkar

09:45 – 10:30 Keynote address – 1 (Kåre Harald Drager)

10:30 – 11:00 Question Answers

11:00 – 11:15 Coffee break

11:15 – 12:00 André Skupin, San Diego State University

12:00 – 13:00 Lunch

13:00 – 13:45 Aron Culotta, Illinois Institute of Technology

13:45 – 14:30 Hemant Purohit, George Mason University

14:30 – 14:45 Coffee break

14:45 – 15:30 Minsung Hong, Western Norway Research Institute

15:30 – 16:00 Discussion

19:00 – 21:00 Dinner

 

October 23, 2018

09:00 – 09:45 Keynote address – 2 (Ivar Konrad Lunde)

09:45 – 10:15 Question Answers

10:15 – 10:30 Coffee break

10:30 – 11:15 Andreas Lothe Opdahl, University of Bergen

11:15 – 12:00 Fan Zipei, The University of Tokyo

12:00 – 13:00 Lunch

 

BDEM Steering Meeting

October 23, 2018

13:30 – 16:30 Planning for 2018 - 2019

16:30   Closing  

 

October 24, 2018

Hackathon at UiB