Application of Decision Tree Algorithm for classification and identification of natural minerals using SEM–EDS

Akkaș, Efe; Akın, Lütfiye; Çubukçu, H. Evren; Artuner, Harun

doi:10.1016/j.cageo.2015.03.015

Cited by 47 publications

(14 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A plethora of instrumental techniques for mineral identification have been introduced during the last few decades, the most frequently used being X-ray diffraction [1,2], infrared [3,4] and Raman [5,6] spectroscopy, optical diffuse reflectance [7] and thermal analysis [8,9] as well as the microscopy-based techniques (SEM-EDS [10,11], TEM [12,13], EMPA [14,15]) which are extremely important in identifying amorphous and poorly crystalline mineral phases.…”

Section: Introductionmentioning

confidence: 99%

Minerals from Macedonia. XXX. Complementary use of vibrational spectroscopy and X-ray powder diffraction for spectra-structural study of some cyclo-, phyllo- and tectosilicate minerals. A review

Jovanovski

Makreski

2016

Maced. J. Chem. Chem. Eng.

View full text Add to dashboard Cite

A review of the results of the complementary use of vibrational spectroscopy (infrared and Raman) and X-ray powder diffraction in the process of identification and spectra-structure correlation of some cyclo-, phyllo-and tectosilicate minerals originating from the Republic of Macedonia is presented. The following minerals are studied: schorl, Na(Fe 2+ ,Mg)3Al6(BO3)3Si6O18(OH)4; beryl, (Be,Mg)3Al2Si6O18; chrysotile, Mg3Si2O5(OH)4; antigorite, (Mg,Fe 2+ )3Si2O5(OH)4; talc, (Mg,Fe 2+ )3Si4O10(OH)2; clinochlore, (Mg,Fe 2+ )5Si3(Al,Cr)2O10(OH)8; cymrite, BaAl2Si2O8H2O; montmorillonite, (K,Ca)0.3(Al,Mg)2Si4O10(OH)2nH2O; muscovite, KAl2(Si3Al)O10(OH,F)2; phlogopite, KMg3(Si3Al)O10(OH,F)2; biotite, K(Mg,Fe 2+ )3AlSi3O10(OH,F)2; sheridanite, (Mg,Al)6(Si,Al)4O10(OH)8; albite, NaAlSi3O8; microcline, KAlSi3O8; sanidine, (K,Na)(Si,Al)4O8 and stilbite, Na3Ca3Al8Si28O7230H2O. Keywords: vibrational spectroscopy; infrared; Raman; X-ray powder diffraction; identification; cyclosilicate; phyllosilicate; tectosilicate; minerals МИНЕРАЛИ ОД МАКЕДОНИЈА. XXX. КОМПЛЕМЕНТАРНО КОРИСТЕЊЕ НА ВИБРАЦИОНАТА СПЕКТРОСКОПИЈА И НА РЕНДГЕНСКАТА ДИФРАКЦИЈА ОД ПРАШОК ПРИ СПЕКТАР-СТРУКТУРНИ ИСТРАЖУВАЊА НА НЕКОИ ЦИКЛО-, ФИЛО-И ТЕКТОСИЛИКАТНИ МИНЕРАЛИ. ПРЕГЛЕДНА СТУДИЈА Даден е преглед на резултатите од комплементарното користење на вибрационата спектроскопија (инфрацрвена и раманска) и на рендгенската дифракција од прашок при идентификација и спектар-структурни корелации на некои цикло-, фило-и тектосиликатни минерали по потекло од Република Македонија. Изучувани се следните минерали: шерл, Na(Fe 2+ ,Mg)3Al6(BO3)3Si6O18(OH)4; берил, (Be,Mg)3Al2Si6O18; хризотил, Mg3Si2O5(OH)4; антигорит, (Mg,Fe 2+ )3Si2O5(OH)4; талк, (Mg,Fe 2+ )3Si4O10(OH)2; клинохлор, (Mg,Fe 2+ )5Si3(Al,Cr)2O10(OH)8; цимрит, BaAl2Si2O8H2O; монтморилонит, (K,Ca)0.3(Al,Mg)2Si4O10(OH)2nH2O; мусковит, KAl2(Si3Al)O10(OH,F)2; флогопит, KMg3(Si3Al)O10(OH,F)2; биотит, K(Mg,Fe 2+ )3AlSi3O10(OH,F)2; шериданит, (Mg,Al)6(Si,Al)4O10(OH)8; албит, NaAlSi3O8; микроклин, KAlSi3O8; санидин, (K,Na)(Si,Al)4O8 и стилбит, Na3Ca3Al8Si28O7230H2O. Клучни зборови: вибрациона спектроскопија; инфрацрвена; раманска; рендгенска дифракција од прашок; идентификација; циклосиликати; филосиликати; тектосиликати; минерали G. Jovanovski, P. Makreski Maced. J. Chem. Chem. Eng. 35 (2), 125-155 (2016)

show abstract

Section: Introductionmentioning

confidence: 99%

Minerals from Macedonia. XXX. Complementary use of vibrational spectroscopy and X-ray powder diffraction for spectra-structural study of some cyclo-, phyllo- and tectosilicate minerals. A review

Jovanovski

Makreski

2016

Maced. J. Chem. Chem. Eng.

View full text Add to dashboard Cite

show abstract

“…Among these methods, the decision tree algorithm is a typical classification algorithm used for unearthing transition rules from observations, and it is widely used to calculate transition rules for CA models (Cao et al 2013). Compared with its successor, the C4.5 algorithm, C5.0 performs better with respect to identify transition rules for CA models (Akkaş et al 2015). The latter employs the information gain ratio, a metric that tests each node and selects data subdivisions to maximize the 'entropy decrease' of the connected node (Friedl and Brodley 1997).…”

Section: 2mentioning

confidence: 99%

A partitioned and asynchronous cellular automata model for urban growth simulation

Zeng

2015

International Journal of Geographical Information Science

View full text Add to dashboard Cite

Cellular automata (CA) models are used to analyze and simulate the global phenomenon of urban growth. However, these models are characterized by ignoring spatially heterogeneous transition rules and asynchronous evolving rates, which make it difficult to improve urban growth simulations. In this paper, a partitioned and asynchronous cellular automata (PACA) model was developed by implementing the spatial heterogeneity of both transition rules and evolving rates in urban growth simulations. After dividing the study area into several subregions by k-means and knn-cluster algorithms, a C5.0 decision tree algorithm was employed to identify the transition rules in each subregion. The evolving rates for cells in each regularly divided grid were calculated by the rate of changed cells. The proposed PACA model was implemented to simulate urban growth in Wuhan, a large city in central China. The results showed that PACA performed better than traditional CA models in both a cell-to-cell accuracy assessment and a shape dimension accuracy assessment. Figure of merit of PACA is 0.368 in this research, which is significantly higher than that of partitioned CA (0.327) and traditional CA (0.247). As for the shape dimension accuracy, PACA has a fractal dimension of 1.542, which is the closest to that of the actual land use (1.535). However, fractal dimension of traditional CA (1.548) is closer to that of the actual land use than that of partitioned CA (1.285). It indicates that partitioned transition rules play an important role in the cell-to-cell accuracy of CA models, whereas the combination of partitioned transition rules and asynchronous evolving rates results in improved cell-to-cell accuracy and shape dimension accuracy. Thus, implementing partitioned transition rules and asynchronous evolving rates yields better CA model performance in urban growth simulations due to its accordance with actual urban growth processes. ARTICLE HISTORY

show abstract

“…By using early prediction, we can treat patients at early stages and cure them. The various applications of DT are efficient classification of mineral group classification and the identification of mineral members (Akkaş et al 2015), Popularity Forecast (Zeng et al 2014), Different combinations of elements, as well as many classification techniques, are used to implement the prediction model. As a result of the heart disease prediction model, they achieve an increased level of success with a level of accuracy of 90.16 percent.…”

Section: Introductionmentioning

confidence: 99%

Improving the Efficiency by Novel Feature Extraction Technique Using Decision Tree Algorithm Comparing with SVM Classifier Algorithm for Predicting Heart Disease

Sameer¹,

Sriramya²

2021

alinteri

View full text Add to dashboard Cite

Aim: The objective of the research work is to use the two machine learning algorithms Decision Tree(DT) and Support vector machine(SVM) for detection of heart disease on earlier stages and give more accurate prediction. Materials and methods: Prediction of heart disease is performed using two machine learning classifier algorithms namely, Decision Tree and Support Vector Machine methods. Decision tree is the predictive modeling approach used in machine learning, it is a type of supervised machine learning. Support-vector machines are directed learning models with related learning calculations that break down information for order and relapse investigation. The significance value for calculating Accuracy was found to be 0.005. Result and discussion: During the process of testing 10 iterations have been taken for each of the classification algorithms respectively. The experimental results shows that the decision tree algorithm with mean accuracy of 80.257% is compared with the SVM classifier algorithm of mean accuracy 75.337% Conclusion: Based on the results achieved the Decision Tree classification algorithm better prediction of heart disease than the SVM classifier algorithm.

show abstract

Application of Decision Tree Algorithm for classification and identification of natural minerals using SEM–EDS

Cited by 47 publications

References 28 publications

Minerals from Macedonia. XXX. Complementary use of vibrational spectroscopy and X-ray powder diffraction for spectra-structural study of some cyclo-, phyllo- and tectosilicate minerals. A review

Minerals from Macedonia. XXX. Complementary use of vibrational spectroscopy and X-ray powder diffraction for spectra-structural study of some cyclo-, phyllo- and tectosilicate minerals. A review

A partitioned and asynchronous cellular automata model for urban growth simulation

Improving the Efficiency by Novel Feature Extraction Technique Using Decision Tree Algorithm Comparing with SVM Classifier Algorithm for Predicting Heart Disease

Contact Info

Product

Resources

About