![]() ![]() We finally conclude with a brief discussion of the emerging and future directions of GSP. Second, we discuss the impact of GSP on applications, including neuroscience and image and video processing. First, we look at the use of GSP in data science problems, including graph learning and graph-based deep learning. In the second half, we shift focus to review the impact of GSP on other disciplines. ![]() A key message is that GSP has been critical to develop novel and technically sound tools, theory, and algorithms that, by leveraging analogies with and the insights of DSP, provide new ways to analyze, process, and learn from graph signals. The first half is devoted to reviewing the history of GSP and explaining how it gave rise to an encompassing framework that shares multiple similarities with SP, and especially digital SP (DSP). In this article, we provide an overview of the evolution of GSP, from its origins to the challenges ahead. It is a research domain pursued by a broad community, the subject of not only many journal and conference articles, but also of textbooks, special issues of different journals, symposia, workshops, and special sessions at ICASSP and other SP conferences. Although the theory and application domains of GSP continue to expand, GSP has become a technology with wide use. As a result, GSP is a broad framework that encompasses and extends classical SP methods, tools, and algorithms to application domains of the modern technological world, including social, transportation, communication, and brain networks recommender systems financial engineering distributed control and learning. In many other cases, the graph is implicit, capturing some notion of dependence or similarity across nodes, and the links must be inferred from the data themselves. In some scenarios, the supporting graph is a physical, technological, social, information, or biological network where the links can be explicitly observed. Graph signals are well-suited to model measurements/information/data associated with (indexed by) a set where 1) the elements of the set belong to the same class (regions of the cerebral cortex, members of a social network, weather stations across a continent) 2) there exists a relation (physical or functional) of proximity, influence, or association among the different elements of that set and 3) the strength of such a relation among the pairs of elements is not homogeneous. Since these papers were published, GSP-related problems have drawn significant attention, not only within the SP community but also in machine learning (ML) venues, where research in graph-based learning has increased significantly. The term graph signal processing was coined a decade ago in the seminal works of, ,, and. Graphs are versatile, able to model irregular interactions, easy to interpret, and endowed with a corpus of mathematical results, rendering them natural candidates to serve as the basis for a theory of processing signals in more irregular domains. Graph SP (GSP) generalizes SP tasks to signals living on non-Euclidean domains whose structure can be captured by a weighted graph. ![]() With the digitalization of the modern world and the increasing pervasiveness of data-collection mechanisms, information of interest in current applications oftentimes arises in non-Euclidean, irregular domains. Indeed, the last 75 years have shown how SP has made an impact in areas such as communications, acoustics, sensing, image processing, and control, to name a few. Signal processing (SP) excels at analyzing, processing, and inferring information defined over regular (first continuous, later discrete) domains such as time or space. Moura, Antonio Ortega, David I Shuman 40msp04-leus-opener-3262906 Graph Signal Processing History, development, impact, and outlook
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |