Abstract
This work introduces a new classification method in the remote sensing domain, suitably adapted to dealing with the challenges posed by the big data processing and analytics framework. The method is based on symbolic learning techniques, and it is designed to work in complex and information-abundant environments, where relationships among different data layers are assessed in model-free and computationally-effective modalities. The two main stages of the method are the data reduction-sequencing and the association analysis. The former refers to data representation; the latter searches for systematic relationships between data instances derived from images and spatial information encoded in supervisory signals. Subsequently, a new measure named the evidence-based normalized differential index, inspired by the probability-based family of objective interestingness measures, evaluates these associations. Additional information about the computational complexity of the classification algorithm and some critical remarks are briefly introduced. An application of land cover mapping where the input image features are morphological and radiometric descriptors demonstrates the capacity of the method; in this instructive application, a subset of eight classes from the Corine Land Cover is used as the reference source to guide the training phase.
Highlights
Since the 1970s, Earth observation or remote sensing (RS) data have been acknowledged as relevant sources of information for a long list of disciplines, including Earth sciences and geology, environmental sciences, water and coastal management, territorial planning, forestry and agriculture [1,2]
By analogy with the genetic association applied in bio-informatics, the symbolic machine learning (SML) association classifier searches for relevant, systematic relationships between sequenced image data instances and supervisory information encoded in selected reference sets
The output of the association analysis is the Φ values given by an interestingness measure; these values are mapped to the single spatial sample and used as the decision criterion translating the feature space into the final classification output
Summary
Since the 1970s, Earth observation or remote sensing (RS) data have been acknowledged as relevant sources of information for a long list of disciplines, including (but not limited to) Earth sciences and geology, environmental sciences, water and coastal management, territorial planning, forestry and agriculture [1,2]. These drawbacks are largely amplified in the case of complex and ill-defined target classes’ analytics and in the case of partially-inconsistent, global fine-scale data scenarios This manuscript introduces in the remote sensing domain a new generic supervised classification framework that may contribute to solving geo-spatial big data problems. By analogy with the genetic association applied in bio-informatics, the SML association classifier searches for relevant, systematic relationships between sequenced image data instances and supervisory (spatial) information encoded in selected reference sets These paradigms have been very rarely applied in the remote sensing community that is dominated by continuous numeric representation of the input signal, which is typically postulated by physical causal-explanatory paradigms [9,16,17]. Discussions and conclusions are included in the last Section 4
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
