The theory of descriptive nearness is usually adopted when dealing with sets that share some common properties even when the sets are not spatially close, i.e., the sets have no members in common. Set description results from the use of probe functions to define feature vectors that describe a set and the nearness of sets is given by their proximities. A probe on a non-empty set., φn(x)). We establish a connection between relations on an object space X and relations on the feature space Φ(X). Having as starting point the Peters proximity, two sets are descriptively near, if and only if their descriptions intersect. In this paper, we construct a theoretical approach to a more visual form of proximity, namely, descriptive proximity, which has a broad spectrum of applications. We organize descriptive proximities on two different levels: weaker or stronger than the Peters proximity. We analyze the properties and interplay between descriptions on one side and classical proximities and overlap relations on the other side.
In this article, we present an approach to Land use and Land cover (LULC) mapping from multispectral satellite images using deep learning methods. The terms satellite image classification and map production, although used interchangeably have specific meanings in the field of remote sensing. Satellite image classification describes assignment of global labels to entire scenes, whereas LULC map production involves producing maps by assigning a class to each pixel. We show that by classifying each pixel in a satellite image into a number of LULC categories we are able to successfully produce LULC maps. This process of LULC mapping is achieved using deep neural networks pre-trained on the ImageNet Large-Scale Visual Recognition Competition (ILSVRC) datasets and fine-tuned on our target dataset, which consists of Landsat 5/7 multispectral satellite images taken of the Province of Manitoba in Canada. This approach resulted in 88% global accuracy. Performance was further improved by considering the stateof-the-art generative adversarial architecture and context module integrated with the original networks. The result is an automated deep learning framework that can produce highly accurate LULC maps images significantly faster than current semi-automated methods. The contribution of this article includes extensive experimentation of different FCN architectures with extensions on a unique dataset, high classification accuracy of 90.46%, and a thorough analysis and accuracy assessment of our results.
This paper presents a telerehabilitation system that encompasses a webcam and store-and-feedforward adaptive gaming system for tracking finger-hand movement of patients during local and remote therapy sessions. Gaming-event signals and webcam images are recorded as part of a gaming session and then forwarded to an online healthcare content management system (CMS) that separates incoming information into individual patient records. The CMS makes it possible for clinicians to log in remotely and review gathered data using online reports that are provided to help with signal and image analysis using various numerical measures and plotting functions. Signals from a 6 degree-of-freedom magnetic motion tracking system provide a basis for video-game sprite control. The MMT provides a path for motion signals between common objects manipulated by a patient and a computer game. During a therapy session, a webcam that captures images of the hand together with a number of performance metrics provides insight into the quality, efficiency, and skill of a patient.
Abstract. In this paper, the study of the evolution of approximation space theory and its applications is considered in the context of rough sets introduced by Zdzis law Pawlak and information granulation as well as computing with words formulated by Lotfi Zadeh. Central to this evolution is the rough-mereological approach to approximation of information granules. This approach is built on the inclusion relation to be a part to a degree, which generalises the rough set and fuzzy set approaches. An illustration of information granulation of relational structures is given. The contribution of this paper is a comprehensive view of the notion of information granule approximation, approximation spaces in the context of rough sets and the role of such spaces in the calculi of information granules.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.