Using data mining techniques to address critical information exchange needs in disaster affected public-private networks

Zheng, Li; Shen, Chao; Tang, Liang; Li, Tao; Luis, Steven; Chen, Shu‐Ching; Hristidis, Vagelis

doi:10.1145/1835804.1835823

Cited by 28 publications

(26 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In order to reduce such loss, emergency managers are required to not only be well prepared but also provide rapid response activities [29].…”

Section: A Disaster Emergency Managementmentioning

confidence: 99%

Web Multimedia Object Classification Using Cross-Domain Correlation Knowledge

et al. 2013

IEEE Trans. Multimedia

Self Cite

View full text Add to dashboard Cite

Abstract-Given a collection of web images with the corresponding textual descriptions, in this paper, we propose a novel cross-domain learning method to classify these web multimedia objects by transferring the correlation knowledge among different information sources. Here, the knowledge is extracted from unlabeled objects through unsupervised learning and applied to perform supervised classification tasks. To mine more meaningful correlation knowledge, instead of using commonly used visual words in the traditional bag-of-visual-words (BoW) model, we discover higher level visual components (words and phrases) to incorporate the spatial and semantic information into our image representation model, i.e., bag-of-visual-phrases (BoP). By combining the enriched visual components with the textual words, we calculate the frequently co-occurring pairs among them to construct a cross-domain correlated graph in which the correlation knowledge is mined. After that, we investigate two different strategies to apply such knowledge to enrich the feature space where the supervised classification is performed. By transferring such knowledge, our cross-domain transfer learning method can not only handle large scale web multimedia objects, but also deal with the situation that the textual descriptions of a small portion of web images are missing. Empirical experiments on two different datasets of web multimedia objects are conducted to demonstrate the efficacy and effectiveness of our proposed cross-domain transfer learning method.

show abstract

“…In order to reduce such loss, emergency managers are required to not only be well prepared but also provide rapid response activities [29].…”

Section: A Disaster Emergency Managementmentioning

confidence: 99%

Web Multimedia Object Classification Using Cross-Domain Correlation Knowledge

et al. 2013

IEEE Trans. Multimedia

Self Cite

View full text Add to dashboard Cite

show abstract

“…We have designed and implemented a web-based prototype of disaster information sharing platform and a disaster situation awareness and community organization application running on iOS-based mobile devices utilizing the data processing power of advanced information technologies for disaster planning and recovery under hurricane scenarios [3][4][5]. They can largely help people discover, collect, organize, search and disseminate realtime disaster information.…”

Section: Motivation For Integrated Disaster Information Analysis Toolsmentioning

confidence: 99%

“…Thin margins and lack of a well-designed and regularly tested disaster plan make companies, particularly small businesses, especially vulnerable [1][2]. Our previous work [4][5] also demonstrates that building robust and intelligent disaster information extraction and analysis platform can help the public and private sectors work together to apply world class computing tools to deliver the right information to the right people at the right time.…”

Section: Introductionmentioning

confidence: 99%

Disaster SitRep - A vertical search engine and information analysis tool in disaster management domain

Zheng

Shen

Tang

et al. 2012

2012 IEEE 13th International Conference on Information Reuse &Amp; Integration (IRI)

Self Cite

View full text Add to dashboard Cite

show abstract

“…an estimated 550,000 buildings collapsed or were severely damaged. In order to reduce such loss, emergency managers are required to not only be well prepared but also provide rapid response activities [204,205].…”

Section: Discussionmentioning

confidence: 99%

“…hence the urgent need of additional multimedia information, such as pictures and videos taken at the disaster scene, for enhancing the text-based reports and providing more details of the disaster event [205]. A system that integrates multi-source information, such as textual reports and multimedia data, would greatly assist emergency managers in making a better assessment of a disaster situation and performing efficient and timely responses correspondingly [206].…”

Section: Discussionmentioning

confidence: 99%

Exploring Hidden Coherent Feature Groups and Temporal Semantics for Multimedia Big Data Analysis

Yang¹

View full text Add to dashboard Cite

Using data mining techniques to address critical information exchange needs in disaster affected public-private networks

Cited by 28 publications

References 6 publications

Web Multimedia Object Classification Using Cross-Domain Correlation Knowledge

Web Multimedia Object Classification Using Cross-Domain Correlation Knowledge

Disaster SitRep - A vertical search engine and information analysis tool in disaster management domain

Exploring Hidden Coherent Feature Groups and Temporal Semantics for Multimedia Big Data Analysis

Contact Info

Product

Resources

About