{"title":"Relevancy assessment of tweets using supervised learning techniques: Mining emergency related tweets for automated relevancy classification","authors":"Matthias Habdank, N. Rodehutskors, R. Koch","doi":"10.1109/ICT-DM.2017.8275670","DOIUrl":"https://doi.org/10.1109/ICT-DM.2017.8275670","url":null,"abstract":"Social media provides an abundance of information that can be vital to emergency services. Especially during large-scale emergencies and disasters this amount of information rises even more and emergency services struggle to find relevant information that can support their current operations. The approach described in this paper uses Twitter generated data from an incident in Ludwigshafen, Germany in October 2016 to evaluate machine learning approaches for the relevancy assessment of social media content during emergencies. Not only different classifiers, but also several vectorizers and the use of n-grams are regarded. It is found that machine learning approaches can achieve very good results in the automatic relevancy classification and offer techniques that provide realtime quality assessments to emergency-services.","PeriodicalId":233884,"journal":{"name":"2017 4th International Conference on Information and Communication Technologies for Disaster Management (ICT-DM)","volume":"177 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116529416","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"When a tsunami strikes: A mobility model for coastline cities","authors":"F. Garay, Erika Rosas, Nicolás Hidalgo","doi":"10.1109/ICT-DM.2017.8275671","DOIUrl":"https://doi.org/10.1109/ICT-DM.2017.8275671","url":null,"abstract":"Every year, hundreds of natural phenomena hit the world, unleashing major disasters and compromising the welfare of millions of people and public infrastructure. On a planet made up of over 70% water, tsunamis are a latent risk that threatens civilians all over the world. Hopefully, technological advances have provided the development of monitoring systems that enable predicting this kind of phenomena and evacuating high risk flooding zones. Nowadays, mobile communication in a post disaster scenario is critical to support all the post disaster tasks. However, developing useful algorithms and applications to support problems arising on these scenarios require large scale real-life testing, which are generally out of the reach of scientists and application developers. In this context, simulation provides an effective tool to assess the performance of software solutions in close-to-real disaster scenarios. In this work, we propose a new mobility model for tsunami scenarios that includes information published by the Chilean National Office for Emergency (ONEMI) about evacuation routes and security points. We have tested and compared our proposal using the One simulator.","PeriodicalId":233884,"journal":{"name":"2017 4th International Conference on Information and Communication Technologies for Disaster Management (ICT-DM)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124929177","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Bringing technology and humanitarian values together: A framework to design and assess humanitarian information systems","authors":"P. Coletti, R. Mays, A. Widera","doi":"10.1109/ICT-DM.2017.8275687","DOIUrl":"https://doi.org/10.1109/ICT-DM.2017.8275687","url":null,"abstract":"Designing information systems (IS) in support of humanitarian work has been a challenge widely pursued for decades. However, one aspect that has been undervalued within systems design is the role of the underpinning humanitarian values and culture as part of system effectiveness. Further, it remains understudied how we might incorporate those values into the information system design process. We address both these aspects by 1) analyzing humanitarian values of effectiveness as they impact information systems design, and 2) incorporating humanitarian values as part of the design criteria. In this paper, we present the idea that the “maturity” of an IS design to be effective for the humanitarian context is assessed by how well it incorporates humanitarian values. Therefore, we move away from a product-centered design towards an approach, which features the socio-technical relationship. We present a maturity matrix, which aims to translate and communicate humanitarian effectiveness into the design and development terminology used by technology designers. This matrix is housed within a participatory framework that allows for the development of trust and shared understanding between these two domains. The framework serves as a road-map for designers and humanitarian agencies to adapt the IS design and development process to better accommodate the IS needs of the humanitarian mission, its values, and culture.","PeriodicalId":233884,"journal":{"name":"2017 4th International Conference on Information and Communication Technologies for Disaster Management (ICT-DM)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131764198","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pouyan Fotouhi Tehrani, S. Pfennigschmidt, Ulrich Kriegel, Andreas Billig, F. Fuchs-Kittowski, U. Meissen
{"title":"Multidimensional report analysis in urban incident management","authors":"Pouyan Fotouhi Tehrani, S. Pfennigschmidt, Ulrich Kriegel, Andreas Billig, F. Fuchs-Kittowski, U. Meissen","doi":"10.1109/ICT-DM.2017.8275689","DOIUrl":"https://doi.org/10.1109/ICT-DM.2017.8275689","url":null,"abstract":"In urban incidents and crises, accurate and timely information can be crucial to manage critical situations. The exponential growth of crowd sourced data has given means to access vast amounts of information on a real-time basis. However, this has complicated the task of analyzing ongoing events as the effort needed to filter relevant from irrelevant information has exponentially grown. This paper proposes a multidimensional analysis method of processing high influx of crowd sourced incident reports and creating processable pieces of information by filtering what's irrelevant and clustering what belongs together in a highly efficient way. Spatial, temporal, and semantic dimensions of an incident report constitute a basis which is taken advantage of in this work to ease the tasks which are undertaken manually in operation centers and alike.","PeriodicalId":233884,"journal":{"name":"2017 4th International Conference on Information and Communication Technologies for Disaster Management (ICT-DM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129211743","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Simulation based strategic decision making in humanitarian supply chain management","authors":"S. Ottenburger, S. Bai","doi":"10.1109/ICT-DM.2017.8275683","DOIUrl":"https://doi.org/10.1109/ICT-DM.2017.8275683","url":null,"abstract":"Strategic decision making plays an important role in disaster management. In view of an imminent or already occurring event, e.g. flood, that has the potential to stress and threaten populated regions, humanitarian supply chain management is a place where strategic decision making plays a major role. Sensible or strategic measures have to be developed in order to mitigate damages. Strategic measures should take into account available and possibly distributed resources, e.g. vehicles, storages and street networks, and of course the type of measure against the background of protection goals. Finding good or sensible measures becomes a hard task if the menaced region refers to a densely populated area, where the functionality of street network has a dynamic feature in terms of the emergence of blocked segments. This task gets even harder if the protection of certain critical infrastructures also has to be considered. Our work proposes a framework of a decision support system that is based on the synergetic coupling of a critical infrastructure and a traffic simulation module. By defining different event scenarios, different simulation runs can be triggered beforehand and according to the decision maker's preferences, sensible measures in terms of type of resources and routes are stored and displayed to the decision maker. Especially simultaneously occurring issues of different problem categories requiring decisions by various decision makers are addressed.","PeriodicalId":233884,"journal":{"name":"2017 4th International Conference on Information and Communication Technologies for Disaster Management (ICT-DM)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123558035","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A learning-based probabilistic routing protocol for vehicular delay tolerant networks","authors":"Celimuge Wu, T. Yoshinaga, Yusheng Ji","doi":"10.1109/ICT-DM.2017.8275695","DOIUrl":"https://doi.org/10.1109/ICT-DM.2017.8275695","url":null,"abstract":"Existing routing protocols for vehicular delay tolerant networks (VDTNs) do not adequately address the multi-hop delivery probability in the forwarder node selection. We propose a probabilistic routing protocol for VDTNs. The protocol takes into account the vehicle velocity, node centrality, and node buffer size using a fuzzy logic-based approach. Multi-hop forwarding probability is also considered for the next hop node selection by employing a Q-learning algorithm which discounts the encounter probability with the increase of hops. We conduct extensive simulations to evaluate the proposed protocol in various scenarios and show the advantage of the protocol over existing well-known approaches.","PeriodicalId":233884,"journal":{"name":"2017 4th International Conference on Information and Communication Technologies for Disaster Management (ICT-DM)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125675758","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Post-disaster relief by vehicle route planning and service time estimation in case of Chennai floods","authors":"Prasangsha Ganguly, Sudip Roy","doi":"10.1109/ICT-DM.2017.8275694","DOIUrl":"https://doi.org/10.1109/ICT-DM.2017.8275694","url":null,"abstract":"In a post-disaster situation several organizations carry out response and relief operations in the affected regions. These organizations have vehicles, which travel through several affected regions at different geographic locations, where the relief materials are to be distributed to the victims. In this paper, we propose an integrated method for vehicle route planning and estimation of total time of relief operation. As a case study of Chennai floods in 2015, OpenStreetMap of Chennai is processed in QGIS software to obtain the target locations in affected regions. A branch-and-bound algorithm is designed to obtain the vehicle routes among target locations such that the total traveling time is minimized. Furthermore, while estimating the optimal vehicle routes we also consider two disaster-specific constraints such as different relief-priorities of locations and broken road links between any two locations. A queuing model is used to estimate the service times at the relief camps. This integrated method is simulated to calculate vehicle arrival time and total time of relief for each target location by summing up the vehicle traveling time and serving time at the relief camp. Thus, the victims can be informed beforehand about the time when they will get relief service.","PeriodicalId":233884,"journal":{"name":"2017 4th International Conference on Information and Communication Technologies for Disaster Management (ICT-DM)","volume":"274 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122688253","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A survey of wireless sensor network security in the context of Internet of Things","authors":"Benfilali Mostefa, Gafour Abdelkader","doi":"10.1109/ICT-DM.2017.8275691","DOIUrl":"https://doi.org/10.1109/ICT-DM.2017.8275691","url":null,"abstract":"Today, the common vision of smart components is usually based on the concept of the Internet of Things (IoT). Intelligent infrastructures combine sensor networks, network connectivity and software to oversee and analyze complex systems to identify inefficiencies and inform operational decision-making. Wireless Sensor nodes collect operational information over time and provide real-time data on current conditions such as (volcano activities, disaster parameters in general). The security of wireless sensor networks in the world of the Internet of Things is a big challenge, since there are several types of attacks against different layers of OSI model, in their goal is falsified the values of the detected parameters.","PeriodicalId":233884,"journal":{"name":"2017 4th International Conference on Information and Communication Technologies for Disaster Management (ICT-DM)","volume":"217 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115963299","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Dual-mode round-robin greedy search with fair factor algorithm for relief logistics scheduling","authors":"B. Mishra, K. Dahal, Zeeshan Pervez","doi":"10.1109/ICT-DM.2017.8275675","DOIUrl":"https://doi.org/10.1109/ICT-DM.2017.8275675","url":null,"abstract":"Humanitarian support management is one of the areas of interest after any disaster cases. All the disaster affected regions need relief logistics to improve the suffered people's life. Disaster regions more often have an asymmetric level of relief logistics requirements. Because of this, even distribution of relief logistics to all disaster-affected regions becomes more challenging, particularly in the limited resources scenario. A fair distribution strategy that distributes relief logistics evenly to all disaster regions based on the demand and available resources is vital. This paper applied two basic round-robin based greedy search algorithms and hence proposed an optimized algorithm for fair distribution of relief logistics. The algorithms iteratively regulate distribution schedule in a round-robin fashion with the greedy search from various supply points to the demand regions based on demand, supply, and distance. The optimized algorithm is aimed for fair relief distribution strategy after each round of distribution. The distribution fairness is measured considering minimization of the absolute standard deviation between demand and supply at the demand regions and also considering the number of disaster regions receiving the relief logistics. A benchmark case study, school29 based on the 921 (ChiChi) earthquake in Taiwan, has been considered to evaluate the performance of the algorithm. The simulation results show that the proposed algorithm has even relief logistics distribution to all disaster regions in the limited vehicle resource scenario.","PeriodicalId":233884,"journal":{"name":"2017 4th International Conference on Information and Communication Technologies for Disaster Management (ICT-DM)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123410852","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"The integration of a modified balcik last mile distribution model using open road networks into a relief operations management information system","authors":"Lance Gabriel Putong, Marlene M. De Leon","doi":"10.1109/ICT-DM.2017.8275690","DOIUrl":"https://doi.org/10.1109/ICT-DM.2017.8275690","url":null,"abstract":"The last mile in a disaster relief distribution chain is the delivery of goods from a central warehouse to the evacuation centers assigned for a given area. Its effectiveness relies on the proper allocation of each kind of relief good amongst the demand areas based on a given schedule. Because these operations involve a limited supply of relief goods, vehicles, and time, it is important to find ways to have more data-driven operations to satisfy as much demand as possible. There are various ways to model relief operations. One of them is Balcik's Last Mile Distribution Model, which uses linear programming to minimize routing costs as well as penalty costs for unsatisfied demands. The model provides an allocation of each kind of relief good to the demand areas visited per day. The areas visited per day would depend on the capacity of the vehicle fleet as well as on the routes that can be used. Map data used for determining routes and historical data from previous disasters are used to determine the supply and demand for relief goods while providing a benchmark for results. The study compares Balcik's Last Mile Distribution Model with other programming models intended for relief distribution to see how this is most applicable in Philippine relief scenarios. The said model is modified to fit the relief operations in the Philippines, specifically in Marikina City, specifically by changing the item types that the Balcik model would read. The model is integrated into a relief operations management information system, which will also be modified to better suit the usability needs of relief practitioners. The result is an allocation of relief goods for each evacuation area, a schedule for relief operations, as well as a visualization of the route to be used. The model provides the computational backbone for relief distribution decisions in the Philippines, allowing for more data-driven operations in the future.","PeriodicalId":233884,"journal":{"name":"2017 4th International Conference on Information and Communication Technologies for Disaster Management (ICT-DM)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128563712","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}