Search results for " DRIFT"
showing 10 items of 156 documents
Adaptive time window linear regression algorithm for accurate time synchronization in wireless sensor networks
2015
In this article we propose a new algorithm for time synchronization in wireless sensor networks. The algorithm is based on linear regression to achieve long-term synchronization between the clocks of different network motes. Since motes are built using low-cost hardware components, usually their internal local clocks are not very accurate. In addition, there are other effects that affect the clock precision, such as: environmental conditions, supply voltage, aging, manufacturing process. Because some of these causes are external and unpredictable, the clock drift between two motes can change in a random way. Due to these changes, the optimum time window used for performing the linear regres…
Concept Drift Detection Using Online Histogram-Based Bayesian Classifiers
2016
In this paper, we present a novel algorithm that performs online histogram-based classification, i.e., specifically designed for the case when the data is dynamic and its distribution is non-stationary. Our method, called the Online Histogram-based Naïve Bayes Classifier (OHNBC) involves a statistical classifier based on the well-established Bayesian theory, but which makes some assumptions with respect to the independence of the attributes. Moreover, this classifier generates a prediction model using uni-dimensional histograms, whose segments or buckets are fixed in terms of their cardinalities but dynamic in terms of their widths. Additionally, our algorithm invokes the principles of info…
Online Estimation of Discrete Densities
2013
We address the problem of estimating a discrete joint density online, that is, the algorithm is only provided the current example and its current estimate. The proposed online estimator of discrete densities, EDDO (Estimation of Discrete Densities Online), uses classifier chains to model dependencies among features. Each classifier in the chain estimates the probability of one particular feature. Because a single chain may not provide a reliable estimate, we also consider ensembles of classifier chains and ensembles of weighted classifier chains. For all density estimators, we provide consistency proofs and propose algorithms to perform certain inference tasks. The empirical evaluation of t…
Handling local concept drift with dynamic integration of classifiers : domain of antibiotic resistance in nosocomial infections
2006
In the real world concepts and data distributions are often not stable but change with time. This problem, known as concept drift, complicates the task of learning a model from data and requires special approaches, different from commonly used techniques, which treat arriving instances as equally important contributors to the target concept. Among the most popular and effective approaches to handle concept drift is ensemble learning, where a set of models built over different time periods is maintained and the best model is selected or the predictions of models are combined. In this paper we consider the use of an ensemble integration technique that helps to better handle concept drift at t…
Conservation genetics of an endemic from the Mediterranean Basin: high genetic differentiation but no genetic diversity loss from the last population…
2013
The Mediterranean Basin is a biodiversity hotspot, housing > 11.000 narrowly endemic plant species, many of which are declining due to mass tourism and agricultural intensification. To investigate the genetic resource impacts of ongoing habitat loss and degradation, we characterized the genetic variation in the last known populations of Leopoldia gussonei, a self-compatible endangered Sicilian Grape Hyacinth numbering less than 3,000 remaining individuals, using AFLP. Results demonstrated significant genome-wide genetic differentiation among all extant populations (I broken vertical bar(ST) = 0.05-0.56), and genetic clustering according to geographic location. Gene diversity was fairly c…
Precambrian crustal evolution and continental drift
1981
One of the major questions of Precambrian research is whether present-day plate tectonic models can be applied to the evolution of the ancient continental crust or whether the tectonic style suggests a unidirectional and therefore non-uniformitarian development in response to gradual changes in the global thermal regime through time.
Multiple solutions with sign information for semilinear Neumann problems with convection
2019
We consider a semilinear Neumann problem with convection. We assume that the drift coefficient is indefinite. Using the theory of nonlinear operators of monotone type, together with truncation and comparison techniques and flow invariance arguments, we prove a multiplicity theorem producing three nontrivial smooth solutions (positive, negative and nodal).
Black Hole Shadow Drift and Photon Ring Frequency Drift
2021
The apparent angular size of the shadow of a black hole in an expanding Universe is redshift-dependent. Since cosmological redshifts change with time - known as the redshift drift - all redshift-dependent quantities acquire a time-dependence, and a fortiori so do black hole shadows. We find a mathematical description of the black hole shadow drift and show that the amplitude of this effect is of order $10^{-16}$ per day for M87$^{\star}$. While this effect is small, we argue that its non-detection can be used to constrain the accretion rate around supermassive black holes, as well as a novel probe of the equivalence principle. If general relativity is assumed, we infer from the data obtaine…
Prototype-based learning on concept-drifting data streams
2014
Data stream mining has gained growing attentions due to its wide emerging applications such as target marketing, email filtering and network intrusion detection. In this paper, we propose a prototype-based classification model for evolving data streams, called SyncStream, which dynamically models time-changing concepts and makes predictions in a local fashion. Instead of learning a single model on a sliding window or ensemble learning, SyncStream captures evolving concepts by dynamically maintaining a set of prototypes in a new data structure called the P-tree. The prototypes are obtained by error-driven representativeness learning and synchronization-inspired constrained clustering. To ide…
Stochastic dynamics of nonlinear systems with a fractional power-law nonlinear term: The fractional calculus approach
2011
Fractional power-law nonlinear drift arises in many applications of engineering interest, as in structures with nonlinear fluid viscous–elastic dampers. The probabilistic characterization of such structures under external Gaussian white noise excitation is still an open problem. This paper addresses the solution of such a nonlinear system providing the equation governing the evolution of the characteristic function, which involves the Riesz fractional operator. An efficient numerical procedure to handle the problem is also proposed.