Novel Mechanism to Improve Hadith Classifier Performance

2012 ◽  
Author(s):  
Kawther A. Aldhlan ◽  
Akram M. Zeki ◽  
Ahmad M. Zeki ◽  
Hamad A. Alreshidi
Keyword(s):  
Classifier Performance

Binary Spectrum Feature for Improved Classifier Performance

2020 ◽  
Author(s):  
Nalika Ulapane ◽  
Karthick Thiyagarajan ◽  
sarath kodagoda
Keyword(s):  
Machine Learning ◽  
Classification Performance ◽  
Feature Reduction ◽  
Sensor Data ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Svm Classifier ◽  
Monitoring Task ◽  
Classifier Performance ◽  
Spectrum Feature

<div>Classification has become a vital task in modern machine learning and Artificial Intelligence applications, including smart sensing. Numerous machine learning techniques are available to perform classification. Similarly, numerous practices, such as feature selection (i.e., selection of a subset of descriptor variables that optimally describe the output), are available to improve classifier performance. In this paper, we consider the case of a given supervised learning classification task that has to be performed making use of continuous-valued features. It is assumed that an optimal subset of features has already been selected. Therefore, no further feature reduction, or feature addition, is to be carried out. Then, we attempt to improve the classification performance by passing the given feature set through a transformation that produces a new feature set which we have named the “Binary Spectrum”. Via a case study example done on some Pulsed Eddy Current sensor data captured from an infrastructure monitoring task, we demonstrate how the classification accuracy of a Support Vector Machine (SVM) classifier increases through the use of this Binary Spectrum feature, indicating the feature transformation’s potential for broader usage.</div><div><br></div>

scholarly journals A Feasibility Study Evaluating the Efficiency of Fine Coal Washing Using Gravity Separation Methods

2019 ◽  
Vol 2 (4) ◽  
pp. 497
Author(s):  
Agnes Modiga ◽  
Ndabenhle Sosibo ◽  
Nirdesh Singh ◽  
Getrude Marape
Keyword(s):  
South Africa ◽  
Calorific Value ◽  
Ash Content ◽  
Gravity Separation ◽  
Export Market ◽  
Heavy Liquid ◽  
High Mass ◽  
Fine Coal ◽  
Classifier Performance ◽  
Uranium Industry

Coal mining and washing activities in South Africa often lead to the generation of fine and ultra-fine coal which is in most cases discarded due to high handling and transportation costs. Studies conducted revealed that a large quantity of these fines have market acceptable calorific values and lower ash contents. In order to reduce fines discarded, processes have been developed to re-mine and process the fine coal discards with the aim of improving the calorific value, adding them to coarse washed coal to increase the yield as well as pelletizing the fines so as to meet the market specifications in terms of size. The goal of this study was to evaluate the efficiency of fine coal washing using gravity separation methods and comparing the products thereof to the market specifications with regards to the calorific value and the ash content. Coal fines from the No.4 lower seam of the Witbank coalfield in South Africa resulting from a dry coal sorting plant were subjected to a double-stage spiral test work, heavy liquid separation and reflux classifier test work respectively. The reflux classifier achieved products with low ash content and an increased calorific value, at high mass yields. At higher fluidization water flowrate, the reflux classifier performance was superior to that of the spirals with products of lower ash content and higher calorific value. At low cut point densities, heavy liquid separation yielded the cleanest products with very low ash content but at much lower mass yields. As the density increased, the mass yields increased with the ash content while the calorific value decreased. Most of the products from the different processes met most of the local industries’ specifications but none of them met the export market as well as the gold and uranium industry specifications due to the high ash content.

Using the Kullback-Leibler Divergence and Kolmogorov-Smirnov Test to Select Input Sizes to the Fault Diagnosis Problem Based on a CNN Model

2021 ◽  
Vol 18 (2) ◽  
pp. 16-26
Author(s):  
Rodrigo Paula Monteiro ◽  
◽  
Carmelo Jose Albanez Bastos-Filho ◽  
Mariela Cerrada ◽  
Diego Cabrera ◽  
...  
Keyword(s):  
Fault Diagnosis ◽  
Classification Model ◽  
Data Sets ◽  
Frequency Spectra ◽  
Signal Representations ◽  
Input Size ◽  
Leibler Divergence ◽  
Classifier Performance ◽  
Kolmogorov Smirnov ◽  
Smirnov Test

Choosing a suitable size for signal representations, e.g., frequency spectra, in a given machine learning problem is not a trivial task. It may strongly affect the performance of the trained models. Many solutions have been proposed to solve this problem. Most of them rely on designing an optimized input or selecting the most suitable input according to an exhaustive search. In this work, we used the Kullback-Leibler Divergence and the Kolmogorov-Smirnov Test to measure the dissimilarity among signal representations belonging to equal and different classes, i.e., we measured the intraclass and interclass dissimilarities. Moreover, we analyzed how this information relates to the classifier performance. The results suggested that both the interclass and intraclass dissimilarities were related to the model accuracy since they indicate how easy a model can learn discriminative information from the input data. The highest ratios between the average interclass and intraclass dissimilarities were related to the most accurate classifiers. We can use this information to select a suitable input size to train the classification model. The approach was tested on two data sets related to the fault diagnosis of reciprocating compressors.

Derived operating conditions for classifier performance understanding

2011 ◽  
Author(s):  
Joshua P. Blackburn ◽  
Timothy D. Ross ◽  
Adam R. Nolan ◽  
John C. Mossing ◽  
John U. Sherwood ◽  
...  
Keyword(s):  
Operating Conditions ◽  
Classifier Performance
Sign in / Sign up

Export Citation Format

Share Document