China
Africa
Explore chapters and articles related to this topic
Markets that Matter
Published in Oscar H. Gandy, Coming to Terms with Chance, 2016
Geodemographic clustering is an analytic technique that generates systems of classification for neighborhoods or communities on the basis of the characteristics of its residents. Clustering models are designed to maximize similarity within clusters, while at the same time, maximizing the statistical distance between clusters. The primary demographic characteristics of communities, often as not defined so as to match a ZIP code or other formal boundary, are then overlaid with information about purchase, consumption, and recreational, as well as political activities.
Anomaly Detection and Fault Diagnosis
Published in Yu Ding, Data Science for Wind Energy, 2019
The Mahalanobis distance [140] used in Chapter 7 is also known as the statistical distance. A statistical distance is to measure the distance between a data point from a distribution or two data points in a vector space by accounting for the variance structure associated with the vector space.
A new divergence measure for belief functions and its applications
Published in International Journal of General Systems, 2023
Manpreet Kaur, Amit Srivastava
The divergence between probability distributions often known as the statistical distance between the probability distributions gives an idea of how one distribution differs from another. It is always non-negative and vanishes only for identical distributions. The divergence between probability distributions is not always symmetric and does not satisfy the triangle inequality. Thus, the divergence is not a distance measure (Bronevich and Rozenberg 2020). For quantifying the dissimilarity between two pieces of evidence in D-S evidence theory, a measure of divergence between them is widely used. Defining a divergence measure between BPAs that is symmetric as well as satisfies the triangle inequality is still an open issue. Some of the well-known measures of divergence proposed by various researchers are presented below.
Structural displacement monitoring using deep learning-based full field optical flow methods
Published in Structure and Infrastructure Engineering, 2020
Chuan-Zhi Dong, Ozan Celik, F. Necati Catbas, Eugene J. O’Brien, Su Taylor
Tian and Pan (2016) combined the use of LED targets and a coupled bandpass optical filter to mitigate the ambient light interference. Colour based template matching is not robust to colour change and the application is limited to the close-range displacement measurements. For long distances, the colour condition of the measurement area could easily be affected by the light and shading, which makes it hard to get the right measurement results. To improve the measurement performance, artificial targets with specific colours could be utilised. Key point matching is a non-target method which calculates the displacement by averaging location change of the robust key points extracted from images. The method relies on calculating the similarities of the descriptors of key points in consecutive images based on statistical distance. Once similar key point pairs are recognised, the locations are confirmed to be the continuation of the former motion.
Data-driven distributionally robust risk parity portfolio optimization
Published in Optimization Methods and Software, 2022
A statistical distance measure can be used to quantify the similarity between two probability distributions. We limit our choice of statistical distance measures to a subset of convex functions that operate on discrete distributions.