scholarly journals Classification of Unifloral Honeys from SARDINIA (Italy) by ATR-FTIR Spectroscopy and Random Forest

Molecules ◽  
2020 ◽  
Vol 26 (1) ◽  
pp. 88
Author(s):  
Marco Ciulu ◽  
Elisa Oertel ◽  
Rosanna Serra ◽  
Roberta Farre ◽  
Nadia Spano ◽  
...  
Keyword(s):  
Random Forest ◽  
Ftir Spectroscopy ◽  
Infrared Spectra ◽  
Scientific Community ◽  
Cross Validation ◽  
Phenolic Fraction ◽  
Arbutus Unedo ◽  
Average Accuracy ◽  
Asphodelus Microcarpus

Nowadays, the mislabeling of honey floral origin is a very common fraudulent practice. The scientific community is intensifying its efforts to provide the bodies responsible for controlling the authenticity of honey with fast and reliable analytical protocols. In this study, the classification of various monofloral honeys from Sardinia, Italy, was attempted by means of ATR-FTIR spectroscopy and random forest. Four different floral origins were considered: strawberry-tree (Arbutus Unedo L.), asphodel (Asphodelus microcarpus), thistle (Galactites tormentosa), and eucalyptus (Eucalyptus calmadulensis). Training a random forest on the infrared spectra allowed achieving an average accuracy of 87% in a cross-validation setting. The identification of the significant wavenumbers revealed the important role played by the region 1540–1175 cm−1 and, to a lesser extent, the region 1700–1600 cm−1. The contribution of the phenolic fraction was identified as the main responsible for this observation.

scholarly journals Comparison of Random Forest, Logistic Regression, and MultilayerPerceptron Methods on Classification of Bank Customer Account Closure

2021 ◽  
Vol 4 (1) ◽  
pp. 14
Author(s):  
Husna Afanyn Khoirunissa ◽  
Amanda Rizky Widyaningrum ◽  
Annisa Priliya Ayu Maharani
Keyword(s):  
Data Mining ◽  
Logistic Regression ◽  
Feature Selection ◽  
Random Forest ◽  
Multilayer Perceptron ◽  
Cross Validation ◽  
Early Stage ◽  
Bank Account ◽  
Credit Score

<p>The Bank is a business entity that is dealing with money, accepting deposits from customers, providing funds for each withdrawal, billing checks on the customer's orders, giving credit and or embedding the excess deposits until required for repayment. The purpose of this research is to determine the influence of age, gender, country, customer credit score, number of bank products used by the customer, and the activation of the bank members in the decision to choose to continue using the bank account that he has retained or closed the bank account. The data in this research used 10,000 respondents originating from France, Spain, and Germany. The method used is data mining with early stage preprocessing to clean data from outlier and missing value and feature selection to select important attributes. Then perform the classification using three methods, which are Random Forest, Logistic Regression, and Multilayer Perceptron. The results of this research showed that the model with Multilayer Perceptron method with 10 folds Cross Validation is the best model with 85.5373% accuracy.</p><strong>Keywords:</strong> bank customer, random forest, logistic regression, multilayer perceptron

scholarly journals Severity Classification of Multiple Sclerosis Disease: A Rough Set-Based Method

2019 ◽  
Vol 8 (9S) ◽  
pp. 307-314
Keyword(s):  
Multiple Sclerosis ◽  
Random Forest ◽  
Rough Set ◽  
Weighted Average ◽  
Support Vector ◽  
Neurologic Disorder ◽  
Severity Classification ◽  
Average Accuracy ◽  
Multiple Sclerosis Disease

Multiple sclerosis (MS) is among the world’s most common neurologic disorder. Severity classification of MS disease is necessary for treatment and medication dosage decisions and to understand the disease progression. To the best of authors’ knowledge, this is the first study for the severity classification of MS disease. In this study, Rough set (RS) approach is applied to discern the three classes (mild, moderate, and severe) of the severity of MS disease. Furthermore, the performance of the RS approach is compared with Machine learning (ML) classifiers namely, random forest, K-nearest neighbour, and support vector machine. The performance is evaluated on the dataset acquired from Multiple sclerosis outcome assessments consortium (MSOAC), Arizona, US. The weighted average accuracy, precision, recall, and specificity values for the RS approach are found to be 84.04%, 76.99%, 76.75%, and 83.84% respectively. However, among the ML classifiers, the performance of random forest classifier is found best for which the weighted average accuracy, precision, recall, and specificity values are 62.19 %, 52.65 %, 56.84 %, and 59.87 % respectively. The RS approach is found much superior to ML classifiers and may be used for MS disease severity classification. This study may be helpful for the clinicians to assess the severity of the MS patients and to take medication and dosage decisions.

scholarly journals CLASSIFICATION OF PEOPLE BY PSYCHOLOGICAL PERSONALITY TYPES BASED ON THE HISTORY OF CORRESPONDENCE

2021 ◽  
Vol 335 (1) ◽  
pp. 45-53
Author(s):  
S. Ryskulbek ◽  
O. Mamyrbayev ◽  
A. Turganbayeva
Keyword(s):  
Decision Making ◽  
Random Forest ◽  
Supervised Learning ◽  
Personality Types ◽  
Binary Classifier ◽  
Average Accuracy ◽  
History Of ◽  
The Mind ◽  
Perception Analysis

Temperament is a set of innate tendencies of the mind associated with the processes of perception, analysis and decision-making. The purpose of this article is to predict the psychotype of individuals based on chat stories and follow the Keirsi model, according to which the psycho type is classified as a craftsman, guardian, idealist and mind. The proposed methodology uses a version of LIWC, a dictionary of words, to analyze the context of words and uses supervised learning using KNN, SVM, and Random Forest algorithms to train the classifier. The average accuracy obtained was 88.37% for artisan temperament, 86.92% for caregivers, 55.61% for idealists, and 69.09% for rationality. When using the binary classifier, the average accuracy was 90.93% for artisan temperament, 88.98% for caregivers, 51.98% for idealism, and 71.42% for rationality.

CLASSIFICATION OF PEOPLE BY PSYCHOLOGICAL PERSONALITY TYPES BASED ON THE HISTORY OF CORRESPONDENCE

2021 ◽  
Vol 335 (1) ◽  
pp. 45-53
Author(s):  
S. Ryskulbek ◽  
O. Mamyrbayev ◽  
A. Turganbayeva
Keyword(s):  
Decision Making ◽  
Random Forest ◽  
Supervised Learning ◽  
Personality Types ◽  
Binary Classifier ◽  
Average Accuracy ◽  
History Of ◽  
The Mind ◽  
Perception Analysis

Temperament is a set of innate tendencies of the mind associated with the processes of perception, analysis and decision-making. The purpose of this article is to predict the psychotype of individuals based on chat stories and follow the Keirsi model, according to which the psycho type is classified as a craftsman, guardian, idealist and mind. The proposed methodology uses a version of LIWC, a dictionary of words, to analyze the context of words and uses supervised learning using KNN, SVM, and Random Forest algorithms to train the classifier. The average accuracy obtained was 88.37% for artisan temperament, 86.92% for caregivers, 55.61% for idealists, and 69.09% for rationality. When using the binary classifier, the average accuracy was 90.93% for artisan temperament, 88.98% for caregivers, 51.98% for idealism, and 71.42% for rationality.

scholarly journals Classification of batik patterns using K-Nearest neighbor and support vector machine

2020 ◽  
Vol 9 (3) ◽  
pp. 1260-1267
Author(s):  
Agus Eko Minarno ◽  
Fauzi Dwi Setiawan Sumadi ◽  
Hardianto Wibowo ◽  
Yuda Munarko
Keyword(s):  
Support Vector Machine ◽  
Data Sharing ◽  
Cross Validation ◽  
Nearest Neighbor ◽  
Experimental Result ◽  
Support Vector ◽  
Test Results ◽  
K Nearest Neighbor ◽  
Average Accuracy

This study is proposed to compare which are the better method to classify Batik image between K-Nearest neighbor and Support Vector Machine using minimum features of GLCM. The proposed steps are started by converting image to grayscale and extracting colour feature using four features of GLCM. The features include Energy, Entropy, Contras, Correlation and 0o, 45o, 90o, and 135o. The classifier features consist of 16 features in total. In the experimental result, there exist comparison of previous works regarding the classification KNN and SVM using multi texton histogram (MTH). The experiments are carried out in the form of calculation of accuracy with data sharing and cross-validation scenario. From the test results, the average accuracy for KNN is 78.3% and 92.3% for SVM in the cross-validation scenario. The scenario for the highest accuracy of data sharing is at 70% for KNN and at 100% for SVM. Thus, it is apparent that the application of the GLCM and SVM method for extracting and classifying batik motifs has been effective and better than previous work.

ON THE CLASSIFICATION OF DIGITAL TECHNOLOGIES IN CIVIL PROCESS

2019 ◽  
pp. 27-35
Author(s):  
Alexandr Neznamov
Keyword(s):  
Information Processing ◽  
Scientific Community ◽  
Digital Technologies ◽  
Significant Feature ◽  
Legal Proceedings ◽  
Civil Process ◽  
Civil Proceedings ◽  
Processing Information ◽  
The Impact

Digital technologies are no longer the future but are the present of civil proceedings. That is why any research in this direction seems to be relevant. At the same time, some of the fundamental problems remain unattended by the scientific community. One of these problems is the problem of classification of digital technologies in civil proceedings. On the basis of instrumental and genetic approaches to the understanding of digital technologies, it is concluded that their most significant feature is the ability to mediate the interaction of participants in legal proceedings with information; their differentiating feature is the function performed by a particular technology in the interaction with information. On this basis, it is proposed to distinguish the following groups of digital technologies in civil proceedings: a) technologies of recording, storing and displaying (reproducing) information, b) technologies of transferring information, c) technologies of processing information. A brief description is given to each of the groups. Presented classification could serve as a basis for a more systematic discussion of the impact of digital technologies on the essence of civil proceedings. Particularly, it is pointed out that issues of recording, storing, reproducing and transferring information are traditionally more «technological» for civil process, while issues of information processing are more conceptual.

scholarly journals Classification of Germination Images of Pear Pollen Using Random Forest and Convolution Neural Network Models

IEEE Access ◽  
2021 ◽  
Vol 9 ◽  
pp. 45993-45999
Author(s):  
Ung Yang ◽  
Seungwon Oh ◽  
Seung Gon Wi ◽  
Bok-Rye Lee ◽  
Sang-Hyun Lee ◽  
...  
Keyword(s):  
Neural Network ◽  
Random Forest ◽  
Network Models ◽  
Convolution Neural Network ◽  
Neural Network Models

scholarly journals Feasibility of Using VIS/NIR Spectroscopy and Multivariate Analysis for Pesticide Residue Detection in Tomatoes

Processes ◽  
2021 ◽  
Vol 9 (2) ◽  
pp. 196
Author(s):  
Araz Soltani Nazarloo ◽  
Vali Rasooli Sharabiani ◽  
Yousef Abbaspour Gilandeh ◽  
Ebrahim Taghinezhad ◽  
Mariusz Szymanek ◽  
...  
Keyword(s):  
Near Infrared ◽  
Cross Validation ◽  
Low Cost ◽  
Moving Average ◽  
Nir Spectroscopy ◽  
Control Treatment ◽  
Residue Detection ◽  
Non Destructive ◽  
Reflective Spectroscopy

The purpose of this work was to investigate the detection of the pesticide residual (profenofos) in tomatoes by using visible/near-infrared spectroscopy. Therefore, the experiments were performed on 180 tomato samples with different percentages of profenofos pesticide (higher and lower values than the maximum residual limit (MRL)) as compared to the control (no pesticide). VIS/near infrared (NIR) spectral data from pesticide solution and non-pesticide tomato samples (used as control treatment) impregnated with different concentrations of pesticide in the range of 400 to 1050 nm were recorded by a spectrometer. For classification of tomatoes with pesticide content at lower and higher levels of MRL as healthy and unhealthy samples, we used different spectral pre-processing methods with partial least squares discriminant analysis (PLS-DA) models. The Smoothing Moving Average pre-processing method with the standard error of cross validation (SECV) = 4.2767 was selected as the best model for this study. In addition, in the calibration and prediction sets, the percentages of total correctly classified samples were 90 and 91.66%, respectively. Therefore, it can be concluded that reflective spectroscopy (VIS/NIR) can be used as a non-destructive, low-cost, and rapid technique to control the health of tomatoes impregnated with profenofos pesticide.

Sign in / Sign up

Export Citation Format

Share Document