Special Issue "Artificial Neural Networks and Evolutionary Computation in Remote Sensing"
A special issue of Remote Sensing (ISSN 2072-4292).
Deadline for manuscript submissions: 31 March 2020.
Interests: remote sensing; machine learning algorithms; data mining; digital image processing; object-based image classification; feature selection
Artificial neural networks (ANNs) offer great potential to get insight and to uncover the underlying relationships and structures existing in datasets. ANNs imitate the physical process of learning in the human brain in a simple way. A model is formed by artificial neurons on several layers that emulate biological neurons and the synaptic connections. ANNs are effective in identifying patterns and other underlying data structures in multidimensional data, particularly for remotely sensed data. They are also good at dealing with a large set of variables possessing non-linearity, categorical data, and complex structures. Once a neural net is trained, the network is capable of processing new and unseen datasets. At this point, it should be stated that the robustness of the trained neural nets lies in the optimization of the chosen learning algorithm, the parameters controlling the training phase, and, of course, the quality of the training data, which can be considers as their representativeness for the problem under consideration. Over the past decade, there have been considerable increases in both the quantity of remotely sensed data, and the use of neural networks for remote sensing research problems. Initially called black-box methods, neural nets are now more popular, with new network types and algorithms, and they are more interpretable. Up until now, ANNs have been applied to many tasks, not only for statistical regressions or image classification, but also for image segmentation, feature extraction, data fusion, or dimensionality reduction. Although significant progress has been made in the analysis of remotely sensed imagery using neural nets, a number of issues remain to be resolved. This Special Issue aims to showcase the variety and relevance of the recent developments in the theory and application of neural networks and evolutionary computation in remote sensing. Thus, the latest and most advanced ideas and findings related to the application of neural nets will be shared with the remote sensing community. Authors are encouraged to submit original papers of both a theoretical- and application-based nature.
Prof. Dr. Taskin Kavzoglu
Manuscript Submission Information
Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All papers will be peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.
Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Remote Sensing is an international peer-reviewed open access semimonthly journal published by MDPI.
Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2000 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.
- Image processing
- Artificial neural networks
- Machine learning
- Image classification
- Object-based classification
- Deep learning
- Extreme learning
- Convolutional neural networks
- Data mining
- Image fusion
- Dimensionality reduction
- Parameter estimation
- Spectral unmixing