2021 International Conference on Information and Communication Technologies for Disaster Management (ICT-DM)最新文献

{"title":"Big Data assisted Strategy for Resuming of Work and Production during COVID-19","authors":"Jie Gao, Zhendong Han, Xinzhou Cheng, T. Zhang, Lexi Xu, Yang Wu, Chen Cheng, Yunyun Wang, Xin He","doi":"10.1109/ict-dm52643.2021.9664042","DOIUrl":"https://doi.org/10.1109/ict-dm52643.2021.9664042","url":null,"abstract":"In April 2020, with the development of the nationwide epidemic prevention and control work, the epidemic situation of New Coronavirus has entered a stable stage. However, the resumption of production and recovery is crucial to maintain the stable development of economy and society. Imminent. Therefore, how to co-ordinate the epidemic prevention and control and return to work has become another major challenge for governments at all levels. The joint prevention and control mechanism of the State Council issued a document requiring all localities to “conduct accurate prevention and control in different regions and levels, and coordinate the prevention and control of epidemic situation and the restoration of economic and social order”. In this context, China Unicom gives full play to the unique advantages of multi-source, massive and integrated big data of operators, and helps enterprises to resume work and production from four aspects: real-time insight of regional return to work rate, grid risk index assessment, risk analysis of regional population inflow, and risk analysis of employees' travel mode, so as to provide support for enterprise decision makers and formulate scientific policies and means, gradually realize the full return to work.","PeriodicalId":337000,"journal":{"name":"2021 International Conference on Information and Communication Technologies for Disaster Management (ICT-DM)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130569444","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":"Research on Coverage Ability Assessment of High and Low Frequency based on Machine Learning","authors":"Tian Xiao, Guanghai Liu, Guo-Min Xu, Yi Li, Xinzhou Cheng, Lexi Xu, Chen Cheng, Shiyu Zhou","doi":"10.1109/ict-dm52643.2021.9664166","DOIUrl":"https://doi.org/10.1109/ict-dm52643.2021.9664166","url":null,"abstract":"With the rapid construction of 5G network in China, how to guide reasonable network planning and construction through accurate network coverage ability assessment, and build a 5G high-low-frequency hybrid network with low cost and high efficiency, has become an important topic urgently needed to be studied by telecommunication suppliers. Firstly, the propagation models applicable to 2.1G and 3.5G are studied and theoretically calculated. Next, reasonable suggestions are put forward for the problems existed in the calibration for traditional Propagation Model, and the accuracy of the propagation model is improved by adopting the machine learning algorithm and model. Finally, based on outfield test results, the propagation model calibrations for 3.5G and 2.1G bands are conducted, and reasonable suggestions are put forward for 5G high and low frequency hybrid networking scheme.","PeriodicalId":337000,"journal":{"name":"2021 International Conference on Information and Communication Technologies for Disaster Management (ICT-DM)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121646112","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":"5GC Network and MEC UPF Data Collection Scheme Research","authors":"Jinghui Li, Xiao-dong Cao, Shengli Guo, Runsha Dong, Chuntao Song, Tianyi Wang, Zelin Wang","doi":"10.1109/ict-dm52643.2021.9664122","DOIUrl":"https://doi.org/10.1109/ict-dm52643.2021.9664122","url":null,"abstract":"A rapid development of 5G network has led to the explosive growth of 5G data, the growth of data makes operators face opportunities and challenges. In order not to make operators become pipeline providers, it is very important to understand the content of data in pipelines. DPI data collection has always been an important means for operators to understand network data operation, because 5G SA network is a regional network, compared with 4G and 5G NSA network, data collection methods have a great difference, while soft collection relative to traditional DPI collection also has the characteristics of flexibility, convenient and accurate correlation, so how to choose different collection methods based on different scenarios is very important content. This paper elaborates the scheme of data collection of 5G SA network and MEC UPF network, compares the characteristics and differences of hard and soft collection in detail according to the characteristics of different network structures combined with hard and soft collection, and gives some suggestions for the construction scheme of 5G SA network and MEC UPF network.","PeriodicalId":337000,"journal":{"name":"2021 International Conference on Information and Communication Technologies for Disaster Management (ICT-DM)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133035092","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 Reinforcement Learning based Edge Cloud Collaboration","authors":"Hiroki Kobari, Zhaoyang Du, Celimuge Wu, T. Yoshinaga, Wugedele Bao","doi":"10.1109/ict-dm52643.2021.9664025","DOIUrl":"https://doi.org/10.1109/ict-dm52643.2021.9664025","url":null,"abstract":"Recently, edge computing has attracted more and more attention. Compared with traditional cloud computing, edge computing can reduce communication delay. However, the processing capability of edge computing is not as good as cloud computing. The proposed method combines the advantage of the low communication delay of edge computing and the high processing capability of cloud computing. We use the Q-learning algorithm to balance network load between the edge server and the cloud server to reduce the average service time. Simulation results show that the proposed method suppresses the task failure rate while reducing the average service time.","PeriodicalId":337000,"journal":{"name":"2021 International Conference on Information and Communication Technologies for Disaster Management (ICT-DM)","volume":"81 20","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133355728","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":"Telecom Big Data assisted Identification Algorithm for Poverty Stricken Students in Colleges","authors":"Chen Cheng, Xinzhou Cheng, Xin Zhao, Yuhui Han, T. Zhang, Jie Gao, Tianjian Xiao, Lexi Xu, Runsha Dong, Feibi Lyu, Chuntao Song","doi":"10.1109/ict-dm52643.2021.9664154","DOIUrl":"https://doi.org/10.1109/ict-dm52643.2021.9664154","url":null,"abstract":"The identification and financial aid for poverty stricken students in colleges is significant for poverty alleviation and education equity while the traditional identification method based on voluntary reporting or subjective factors is not accurate enough. In this paper, we propose an identification architecture for poverty stricken students in colleges based on telecom big data and XGBoost (eXtreme Gradient Boosting) Algorithm. XGBoost is an ensemble learning algorithm while its ordinary parameters adjusting algorithm cannot improve the performance of this model significantly. Thus we propose an algorithm of parameters adjusting based on QBFO (Quantum Bacterial Foraging Optimization), called QBFO-XGBoost, improving the performance of XGBoost. The experimental results show that the proposed QBFO has advantages of both convergence accurate and convergence rate compared with other swarm intelligence algorithms. In addition, QBFO-XGBoost applied in identification for poverty stricken students in colleges proves higher recall and precision compared with XGBoost based on grid parameter adjustment method.","PeriodicalId":337000,"journal":{"name":"2021 International Conference on Information and Communication Technologies for Disaster Management (ICT-DM)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128053639","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":"Dynamic Evacuation System for the Intelligent Building Based on Beacons and Handheld Devices","authors":"Timm Wächter, J. Rexilius, Matthias König, Martin Hoffmann","doi":"10.1109/ict-dm52643.2021.9664046","DOIUrl":"https://doi.org/10.1109/ict-dm52643.2021.9664046","url":null,"abstract":"Mobile evacuation routing in a smart building offers a great opportunity to evacuate buildings more efficiently and safely compared to the most commonly used evacuation systems (static mounted evacuation signs). Our system is based on the mobile operating system Android and the cross-platform game engine Unity. Beacons were used for indoor localization. The app reacts to emergency situations and guides people safely out of the building. Based on the current position and the position of the hazard, the system detects blocked escape route sections and bypasses them. Static obstacles can be added and are taken into account in the escape route calculation. The user can see the building plan, the escape route, the danger, and the current position during evacuation.","PeriodicalId":337000,"journal":{"name":"2021 International Conference on Information and Communication Technologies for Disaster Management (ICT-DM)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121327694","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":"Capturing and labelling the experiences of survivors of disasters triggered by natural hazards","authors":"Ricardo Gacitúa, M. Klafft, Ivana Harari, Agnieszka Dudziniska-Jarmoliniska, Solhanlle Bonilla-Duarte","doi":"10.1109/ict-dm52643.2021.9664188","DOIUrl":"https://doi.org/10.1109/ict-dm52643.2021.9664188","url":null,"abstract":"Disasters triggered by natural hazards pose significant dangers to the economy, society, personal property, and people's well-being. In order to mitigate these hazards, disaster education is critical. Few studies have concentrated on recording qualitative experiences from disaster survivors in order to make them available as open educational materials for risk communication in a structured way or to compare them scientifically using qualitative data analytic methods. The goal of this study is to provide a novel approach for capturing the experiences of disaster survivors in a structured way and to provide this structure as machine-readable metadata so that information may be easily analysed, searched, shared, and extracted by software applications. The findings of this study suggest that the proposed method for gathering citizen knowledge and experiences about historical disasters and making them usable as educational tools is effective. It can add to better disaster preparedness in the future.","PeriodicalId":337000,"journal":{"name":"2021 International Conference on Information and Communication Technologies for Disaster Management (ICT-DM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130658995","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":"An Intelligent cloud ecosystem for disaster response and management leveraging opportunistic IoT mesh networks","authors":"J. Lohokare, R. Dani","doi":"10.1109/ict-dm52643.2021.9664137","DOIUrl":"https://doi.org/10.1109/ict-dm52643.2021.9664137","url":null,"abstract":"Access to emergency services like police, fire, rescue, and EMS is life or death during natural disasters. Disaster management faces three critical problems for emergency services - technology constraints (Network infrastructure), demand-supply management (a large number of victims to respond to, but limited on-field agents), information access (for on-field agents). In this paper, we present an end-to-end framework to enable reliable disaster response for emergency services. This framework solves the three problems described by introducing a unique system of collecting SOS messages from disaster victims, presenting and aggregating the messages to control center operators, and making this data alongside various offline tools available to on-field agents. The framework leverages a combination of Ad-hoc mobile networks based on widely used/readily available protocols and hardware to solve the technology constraints. We introduce a novel smartphone-based mesh network that leverages the radio modules already present in smartphones (BLE, Sound, Wi-Fi, Bluetooth) to complement custom hardware-based mesh networks (based on LoRa). SOS messages travel over multiple smartphones until they reach an internet-enabled device. On reaching the internet, we use contextual intelligence for determining the request context and helping emergency service agents prioritize and solve the request. We design an intelligent interface for control center agents to get an aggregated view on disaster victims and on-field agents, helping them make data-driven decisions to help the victims. The framework also provides the on-field agents with an interface to access data and communicate with the disaster victims, even in offline conditions leveraging the mesh network. The critical contribution of this paper is the framework's three-prong approach to support the victims, control center operators, and on-field agents. We present a walk-through for a pilot deployment of our framework alongside its qualitative and quantitative results and show how it can integrate with services like 911.","PeriodicalId":337000,"journal":{"name":"2021 International Conference on Information and Communication Technologies for Disaster Management (ICT-DM)","volume":"406 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124938874","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":"Cell Load and Resource-aware Flow Shifting Scheme based on Heterogeneous Mobile Networks Data","authors":"Lexi Xu, Gaofeng Cui, Chaowei Wang, Xin Hu, Huanlai Xing, Chen Cheng, Xinzhou Cheng, T. Zhang, Jie Gao, Xin He, Kun Chao","doi":"10.1109/ict-dm52643.2021.9664175","DOIUrl":"https://doi.org/10.1109/ict-dm52643.2021.9664175","url":null,"abstract":"In the past decade, 4G networks have been widely deployed, meanwhile, 5G networks start to deploy recently. 4G and 5G heterogeneous mobile networks envisage the challenge of imbalanced user distribution with uneven resource utilization. Above challenge will become deteriorated under emergency scenarios (e.g., disaster, crisis). In order to address the imbalanced user distribution with uneven resource utilization, this paper designs a novel 4G/5G heterogeneous mobile networks data (HMND) system. On the basis of this HMND system, we propose cell load and resource-aware flow shifting (CLRFS) scheme. The HMND system and CLRFS scheme are deployed in a city to verify the performance. Results show that the HMND system and CLRFS scheme can evaluate both the 4G cells and 5G cells precisely, as well as assist telecom operator to shift traffic among 4G and 5G.","PeriodicalId":337000,"journal":{"name":"2021 International Conference on Information and Communication Technologies for Disaster Management (ICT-DM)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117171576","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":"In-Network Aggregation for Privacy-Preserving Federated Learning","authors":"Fahao Chen, Peng Li, T. Miyazaki","doi":"10.1109/ict-dm52643.2021.9664035","DOIUrl":"https://doi.org/10.1109/ict-dm52643.2021.9664035","url":null,"abstract":"Cross-silo federated learning becomes popular in various fields due to its great promises in protecting training data. By carefully examining the interaction among distributed training nodes, we find that existing federated learning still suffers from security weakness and network bottleneck during model synchronization. It has no protection on training models, which also contain significant private information. In addition, many evidences have shown that model synchronization over wide-area network is slow, bottlenecking the whole learning process. To fill this research gap, we propose a novel cross-silo federated learning architecture that can protect both training data and model by using homomorphic encryption (HE). Instead of sharing the model parameters in plaintexts, we encrypt them using the HE, so that they can be aggregated in ciphertexts. In order to handle the inflated network traffic incurred by HE, we apply the in-network aggregation by exploiting the strong capability of programmable switches. A fast algorithm that jointly considers in-network aggregator placement and traffic engineering has been proposed and evaluated by extensive simulations.","PeriodicalId":337000,"journal":{"name":"2021 International Conference on Information and Communication Technologies for Disaster Management (ICT-DM)","volume":"366 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123946926","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}