Discovery, Analysis, and Retrieval of Multimodal Environmental Information

  title={Discovery, Analysis, and Retrieval of Multimodal Environmental Information},
  author={Anastasia Moumtzidou and Stefanos Vrochidis and Ioannis Kompatsiaris},
Environmental conditions are considered of utmost importance for human life. Citizens are increasingly aware of the important role that environmental data (i.e. weather forecast, air quality and pollen concentration) play on health issues (e.g. allergies), as well as to a variety of outdoor activities (e.g. agriculture, trip planning). Given the fact that ensembling information from several environmental providers can generate more reliable measurements, there is a need to combine environmental… 

Figures and Tables from this paper

Focussed crawling of environmental web resources: A pilot study on the combination of multimedia evidence

The combination of textual and visual evidence for predicting the benet of fetching an unvisited Web resource is proposed and results in improvements in the crawling precision over the use of textual features alone.

Evaluating E-Business Applications Priorities: The E-Business Planning and Analysis framework

An e-business planning framework is proposed here which links both strategic and operations management to improve the online service quality of a manufacturing SME. A standard systems development

Open Source Software: Opportunities and Challenges

This paper tries to lay the foundation in analyzing the FLOSS phenomenon by pointing to the real opportunities that lie ahead and the critical challenges that have to be addressed before FLOSS can claim its rightful stake in the software industry.

Business Oriented Development of the IT Landscape: Architecture Design on a Large Scale

Enterprise architecture is outlined as a means of business IT alignment, the respective domains, and fundamental design techniques, based on three basic views on architecture based on components, communication, and distribution.

Focussed crawling of environmental Web resources based on the combination of multimedia evidence

The evaluation experiments indicate the effectiveness of incorporating visual evidence in the link selection process applied by the focussed crawler over the use of textual features alone, particularly in conjunction with hyperlink exploration strategies that allow for the discovery of highly relevant pages that lie behind apparently irrelevant ones.



Discovery of Environmental Nodes in the Web

This work generates domain- specific queries using empirical information and machine learning driven query expansion in order to enhance the initial queries with domain-specific terms and employs a post processing module based on supervised machine learning to improve the precision of the final results.

Extraction of Environmental Data from On-Line Environmental Information Sources

This work addresses the task of semi-automatic extraction of environmental information based on a template configuration tool, on methodologies for data reconstruction from images, as well as on Optical Character Recognition (OCR) techniques.

Personalized Environmental Service Orchestration for Quality of Life Improvement

An environmental information platform that supports submission of user queries related to environmental conditions and orchestrates results from complementary services to generate personalized suggestions is presented.

An environmental search engine based on interactive visual classification

An interactive domain-specific search engine is proposed, which is built on top of a general purpose search engine, employing supervised machine learning and advanced interactive visualization techniques to improve the performance of the system.


Urban air quality information originates either from observations or from mathematical tools — models and estimations. While the former correspond to the current status of air quality, and may be

Ontology-Based Focused Crawling

A framework of ontology learning is presented that enables us to retrieve documents from the Web using focused crawling in a biological domain, amphibianmorphology, and uses a SVM (Support Vector Machine) classifier to identify domain-specific documents and perform text mining in order to extract useful information for the ontology enrichment process.

MetaSpider: Meta-searching and categorization on the Web

Initial results of a user evaluation study comparing MetaSpider, NorthernLight, and MetaCrawler in terms of clustering performance and of time and effort expended show that MetaSpider performed best in precision rate, but disclose no statistically significant differences in recall rate and time requirements.

Domain-specific Web search with keyword spices

This paper describes domain-specific Web search engines that use keyword spices for locating recipes, restaurants, and used cars that can be effectively discovered from Web documents using machine learning technologies.

Effective Focused Crawling Based on Content and Link Structure Analysis

This paper uses a method for traversing the irrelevant pages that met during crawling to improve the coverage of a specific topic and a similarity function is used to check the similarity of web pages w.r.t. topic keywords.