DC-29 - Volunteered Geographic Information
Volunteered geographic information (VGI) refers to geo-referenced data created by citizen volunteers. VGI has proliferated in recent years due to the advancement of technologies that enable the public to contribute geographic data. VGI is not only an innovative mechanism for geographic data production and sharing, but also may greatly influence GIScience and geography and its relationship to society. Despite the advantages of VGI, VGI data quality is under constant scrutiny as quality assessment is the basis for users to evaluate its fitness for using it in applications. Several general approaches have been proposed to assure VGI data quality but only a few methods have been developed to tackle VGI biases. Analytical methods that can accommodate the imperfect representativeness and biases in VGI are much needed for inferential use where the underlying phenomena of interest are inferred from a sample of VGI observations. VGI use for inference and modeling adds much value to VGI. Therefore, addressing the issue of representativeness and VGI biases is important to fulfill VGI’s potential. Privacy and security are also important issues. Although VGI has been used in many domains, more research is desirable to address the fundamental intellectual and scholarly needs that persist in the field.
CP-04 - Artificial Intelligence Tools and Platforms for GIS
Artificial intelligence is the study of intelligence agents as demonstrated by machines. It is an interdisciplinary field involving computer science as well as, various kinds of engineering and science, for example, robotics, bio-medical engineering, that accentuates automation of human acts and intelligence through machines. AI represents state-of-the-art use of machines to bring about algorithmic computation and understanding of tasks that include learning, problem solving, mapping, perception, and reasoning. Given the data and a description of its properties and relations between objects of interest, AI methods can perform the aforementioned tasks. Widely applied AI capabilities, e.g. learning, are now achievable at large scale through machine learning (ML), large volumes of data and specialized computational machines. ML encompasses learning without any kind of supervision (unsupervised learning) and learning with full supervision (supervised learning). Widely applied supervised learning techniques include deep learning and other machine learning methods that require less data than deep learning e.g. support vector machines, random forests. Unsupervised learning examples include dictionary learning, independent component analysis, and autoencoders. For application tasks with less labeled data, both supervised and unsupervised techniques can be adapted in a semi-supervised manner to produce accurate models and to increase the size of the labeled training data.