An Improved Multi-label k-Nearest Neighbour Algorithm with Prototype Selection using DENCLUE

2021 ◽  
Author(s):  
Monia ◽  
Himanshu Suyal ◽  
Aditya Gupta
Keyword(s):  
Nearest Neighbour ◽  
Prototype Selection

scholarly journals Extensions to rank-based prototype selection in k-Nearest Neighbour classification

2019 ◽  
Vol 85 ◽  
pp. 105803 ◽  
Author(s):  
Juan Ramón Rico-Juan ◽  
Jose J. Valero-Mas ◽  
Jorge Calvo-Zaragoza
Keyword(s):  
Nearest Neighbour ◽  
Prototype Selection

scholarly journals Parallel MCNN (pMCNN) with Application to Prototype Selection on Large and Streaming Data

2017 ◽  
Vol 7 (3) ◽  
pp. 155-169 ◽  
Author(s):  
V. Susheela Devi ◽  
Lakhpat Meena
Keyword(s):  
Streaming Data ◽  
Nearest Neighbour ◽  
Prototype Selection ◽  
Time Requirement ◽  
Incremental Algorithms ◽  
Distributed Approach

AbstractThe Modified Condensed Nearest Neighbour (MCNN) algorithm for prototype selection is order-independent, unlike the Condensed Nearest Neighbour (CNN) algorithm. Though MCNN gives better performance, the time requirement is much higher than for CNN. To mitigate this, we propose a distributed approach called Parallel MCNN (pMCNN) which cuts down the time drastically while maintaining good performance. We have proposed two incremental algorithms using MCNN to carry out prototype selection on large and streaming data. The results of these algorithms using MCNN and pMCNN have been compared with an existing algorithm for streaming data.

scholarly journals DIAGNOSE EFFECTIVE EVOLUTIONARY PROTOTYPE SELECTION USING AN OVERLAPPING MEASURE

2009 ◽  
Vol 23 (08) ◽  
pp. 1527-1548 ◽  
Author(s):  
SALVADOR GARCÍA ◽  
JOSÉ-RAMÓN CANO ◽  
ESTER BERNADÓ-MANSILLA ◽  
FRANCISCO HERRERA
Keyword(s):  
Computational Cost ◽  
Complexity Measure ◽  
Selection Strategy ◽  
Nearest Neighbour ◽  
Prototype Selection ◽  
Classification Problems ◽  
The Past ◽  
Nearest Neighbour Classifier ◽  
Selection Algorithms

Evolutionary prototype selection has shown its effectiveness in the past in the prototype selection domain. It improves in most of the cases the results offered by classical prototype selection algorithms but its computational cost is expensive. In this paper, we analyze the behavior of the evolutionary prototype selection strategy, considering a complexity measure for classification problems based on overlapping. In addition, we have analyzed different k values for the nearest neighbour classifier in this domain of study to see its influence on the results of PS methods. The objective consists of predicting when the evolutionary prototype selection is effective for a particular problem, based on this overlapping measure.

The structure of amorphous and polycrystalline materials using energy-filtered RDF analysis

1992 ◽  
Vol 50 (2) ◽  
pp. 1190-1191
Author(s):  
David Cockayne ◽  
David McKenzie
Keyword(s):  
Electron Diffraction ◽  
Diffraction Pattern ◽  
Density Function ◽  
Electron Diffraction Pattern ◽  
Polycrystalline Materials ◽  
Nearest Neighbour ◽  
X Ray ◽  
Selected Area Electron Diffraction ◽  
Reduced Density ◽  
System F

The technique of Electron Reduced Density Function (RDF) analysis has ben developed into a rapid analytical tool for the analysis of small volumes of amorphous or polycrystalline materials. The energy filtered electron diffraction pattern is collected to high scattering angles (currendy to s = 2 sinθ/λ = 6.5 Å-1) by scanning the selected area electron diffraction pattern across the entrance aperture to a GATAN parallel energy loss spectrometer. The diffraction pattern is then converted to a reduced density function, G(r), using mathematical procedures equivalent to those used in X-ray and neutron diffraction studies.Nearest neighbour distances accurate to 0.01 Å are obtained routinely, and bond distortions of molecules can be determined from the ratio of first to second nearest neighbour distances. The accuracy of coordination number determinations from polycrystalline monatomic materials (eg Pt) is high (5%). In amorphous systems (eg carbon, silicon) it is reasonable (10%), but in multi-element systems there are a number of problems to be overcome; to reduce the diffraction pattern to G(r), the approximation must be made that for all elements i,j in the system, fj(s) = Kji fi,(s) where Kji is independent of s.

The Distribution of Hospitality Services in Uyo Urban, Nigeria

2018 ◽  
pp. 137-150
Author(s):  
Violet Bassey Eneyo
Keyword(s):  
Data Collection ◽  
Global Positioning System ◽  
Central Area ◽  
Positioning System ◽  
Nearest Neighbour ◽  
Global Positioning ◽  
Neighbour Analysis

This paper examines the distribution of hospitality services in Uyo Urban, Nigeria. GIS method was the primary tool used for data collection. A global positioning system (GPS) Garmin 60 model was used in tracking the location of 102 hospitality services in the study area. One hypothesis was stated and tested using the nearest neighbour analysis. The finding shows evidence of clustering of the various hospitality services. The tested hypothesis further indicated that hospitality services clustered in areas that guarantee a sustainable level of patronage to maximize profit. Thus, the hospitality services clustered in selected streets in the metropolis while limited numbers were found outside the city’s central area.

Sign in / Sign up

Export Citation Format

Share Document