scholarly journals IMPLEMENTATION OF ENSEMBLE TECHNIQUES FOR DIARRHEA CASES CLASSIFICATION OF UNDER-FIVE CHILDREN IN INDONESIA

2021 ◽  
Vol 6 (2) ◽  
pp. 175-180
Author(s):  
Andriansyah Muqiit Wardoyo Saputra ◽  
Arie Wahyu Wijayanto
Keyword(s):  
Data Analysis ◽  
Imbalanced Data ◽  
Classification Performance ◽  
Adaptive Boosting ◽  
Under Five ◽  
Under Five Children ◽  
Analysis Process ◽  
Ensemble Techniques ◽  
Lack Of Information

Diarrhea is an endemic disease in Indonesia with symptoms of three or more defecations with the consistency of liquid stool. According to WHO, diarrhea is the second largest contributor to the death of under-five children. Data and cases of children under five years who have diarrhea are very difficult to find, so the data analysis process becomes difficult due to the lack of information obtained. Difficulties in the data analysis process can be overcome by rebalancing, so the category ratios are balanced. The method that is popularly used is SMOTE. To solve imbalanced data and improve classification performance, this study implements the combination of SMOTE with several ensemble techniques in diarrhea cases of under-five children in Indonesia. Ensemble models that are used in this study are Random Forest, Adaptive Boosting, and XGBoost with Decision Tree as a baseline method. The results show that all SMOTE-based methods demonstrate a competitive performance whereas SMOTE-XGB gains a slightly higher accuracy (0.88), precision (0.96), and f1-score (0.86). The implementation of the SMOTE strategy improved the recall, precision, and f1-score metrics and give higher AUC of all methods (DT, RF, ADA, and XGB). This study is useful to solve the imbalanced problems in official statistics data provided by BPS Statistics Indonesia

scholarly journals Environment Monitoring of Rose Crops Greenhouse Based on Autonomous Vehicles with a WSN and Data Analysis

Sensors ◽  
2020 ◽  
Vol 20 (20) ◽  
pp. 5905
Author(s):  
Paul D. Rosero-Montalvo ◽  
Vanessa C. Erazo-Chamorro ◽  
Vivian F. López-Batista ◽  
María N. Moreno-García ◽  
Diego H. Peluffo-Ordóñez
Keyword(s):  
Data Analysis ◽  
Environmental Conditions ◽  
Autonomous Vehicles ◽  
Intelligent System ◽  
Autonomous Vehicle ◽  
Classification Performance ◽  
Analysis Process ◽  
Cultivation Process

This work presents a monitoring system for the environmental conditions of rose flower-cultivation in greenhouses. Its main objective is to improve the quality of the crops while regulating the production time. To this end, a system consisting of autonomous quadruped vehicles connected with a wireless sensor network (WSN) is developed, which supports the decision-making on type of action to be carried out in a greenhouse to maintain the appropriate environmental conditions for rose cultivation. A data analysis process was carried out, aimed at designing an in-situ intelligent system able to make proper decisions regarding the cultivation process. This process involves stages for balancing data, prototype selection, and supervised classification. The proposed system produces a significant reduction of data in the training set obtained by the WSN while reaching a high classification performance in real conditions—amounting to 90% and 97.5%, respectively. As a remarkable outcome, it is also provided an approach to ensure correct planning and selection of routes for the autonomous vehicle through the global positioning system.

scholarly journals On the Effectiveness of Leukocytes Classification Methods in a Real Application Scenario

AI ◽  
2021 ◽  
Vol 2 (3) ◽  
pp. 394-412
Author(s):  
Andrea Loddo ◽  
Lorenzo Putzu
Keyword(s):  
Blood Cells ◽  
White Blood Cells ◽  
Classification Performance ◽  
Machine Learning Techniques ◽  
Image Descriptors ◽  
Analysis Process ◽  
Learning Techniques ◽  
Model Training ◽  
Reliable Classification

Automating the analysis of digital microscopic images to identify the cell sub-types or the presence of illness has assumed a great importance since it aids the laborious manual process of review and diagnosis. In this paper, we have focused on the analysis of white blood cells. They are the body’s main defence against infections and diseases and, therefore, their reliable classification is very important. Current systems for leukocyte analysis are mainly dedicated to: counting, sub-types classification, disease detection or classification. Although these tasks seem very different, they share many steps in the analysis process, especially those dedicated to the detection of cells in blood smears. A very accurate detection step gives accurate results in the classification of white blood cells. Conversely, when detection is not accurate, it can adversely affect classification performance. However, it is very common in real-world applications that work on inaccurate or non-accurate regions. Many problems can affect detection results. They can be related to the quality of the blood smear images, e.g., colour and lighting conditions, absence of standards, or even density and presence of overlapping cells. To this end, we performed an in-depth investigation of the above scenario, simulating the regions produced by detection-based systems. We exploit various image descriptors combined with different classifiers, including CNNs, in order to evaluate which is the most suitable in such a scenario, when performing two different tasks: Classification of WBC subtypes and Leukaemia detection. Experimental results have shown that Convolutional Neural Networks are very robust in such a scenario, outperforming common machine learning techniques combined with hand-crafted descriptors. However, when exploiting appropriate images for model training, even simpler approaches can lead to accurate results in both tasks.

scholarly journals PENGARUH DUKUNGAN PEMBEKALAN PANGKALAN TNI ANGKATAN LAUT TERHADAP OPERASI PENGAMANAN PERBATASAN

2019 ◽  
Vol 7 (3) ◽  
Author(s):  
Constantius Rusmaji ◽  
Edi Suhardono
Keyword(s):  
Data Analysis ◽  
Hypothesis Test ◽  
Border Security ◽  
Analysis Process ◽  
Regression Test ◽  
Independent Variable ◽  
Security Operations ◽  
Duration Of Operation ◽  
Naval Base

<em>This study explains the support variables for Naval Base supplies for border security operations. The research method used is a quantitative method by distributing questionnaire.The number of samples taken was 80 samples from the total population of 371 persons. The research was carried out starting from the classification of samples respondents based on gender, age, education and years of service. The research variables in this study are supporting variables in the supply as independent variables (X) and border security operations variables as cooperation variables (Y). Indicators for variable X include: personnel involved in the supply, infrastructure for the supply of equipment, supporting facilities for the supplies and types of supplies that can be supported. While indicators on the Y variables include: personnel involved in the operation, operating facilities, area of operation and duration of operation. The data analysis process is carried out with several tests, among others: validity test, namely testing the data analysis process to determine whether the research instrument is valid or not. The next test is the reliability test, the data analysis process to answer the accuracy of the research instruments. The normality of the trial is tested. The next data analysis process is the hypothesis test in the regression test. Regression test is a process of analyzing data to study the influence between research variables. The regression test conducted in this study is a partial regression test because the independent variable used is one variable. After it was implemented, everything was proven. Supports provisioning variables. Naval Base determines positive and significant impact on border security operations.</em>

scholarly journals ESTIMASI KERUGIAN EKONOMI AKIBAT STATUS GIZI BURUK DAN BIAYA PENANGGULANGANNYA PADA BALITA DI BERBAGAI PROVINSI DI INDONESIA

2007 ◽  
Vol 1 (2) ◽  
pp. 26 ◽  
Author(s):  
Muhammad Aries ◽  
Drajat Martianto
Keyword(s):  
Data Analysis ◽  
Price Index ◽  
Protein Energy Malnutrition ◽  
Secondary Data ◽  
Descriptive Study ◽  
Age Group ◽  
Font Size ◽  
Under Five ◽  
Under Five Children ◽  
Protein Energy

<p class="MsoNormal" style="margin: 0cm 12.6pt 6pt 18pt; text-align: justify; text-indent: 27pt;"><span style="font-size: 10pt;" lang="en-us" xml:lang="en-us">The study was aimed to estimate  GDP lost due to Protein Energy Malnutrition (PEM) among under five children at various provinces in Indonesia. It was a descriptive study used secondary data.  Data analysis was conducted in Bogor, from January to March 2006. The data uses are prevalence of PEM among under five children in various provinces in 2003, Gross Regional Domestic Product (GRDP) of provinces in Indonesia by industrial origin 2000 - 2004, population by province, sex and age group 2003, composite Consumers Price Index (CPI) of 45 cities (2002 = 100). The study showed that the economic lost due to malnutrition (PEM) among under five children in Indonesia was ranged from 0.27% to 1.21% GDP.</span></p>

scholarly journals Knowledge, attitude and practice of fever and febrile illness among parents of under five children

2019 ◽  
Vol 6 (5) ◽  
pp. 2103
Author(s):  
Achinta K.R. Mallick ◽  
Shalu S. Kumar ◽  
Janki Bangari ◽  
Himani Suyal
Keyword(s):  
Febrile Illness ◽  
Parental Knowledge ◽  
Cross Sectional ◽  
Under Five ◽  
Under Five Children ◽  
Attitude And Practice ◽  
Lack Of Information ◽  
Peripheral Hospital ◽  
Fever Management ◽  
Knowledge Attitude And Practice

Background: Fever in children is the commonest cause for outpatient and inpatient admissions in the health care setup. Though most fever episodes are benign with self-limiting course, it is often a reason for anxiety and concerning for parents. The aim of the study was to assess the parental knowledge, attitude and practice regarding fever in children under five years of age.Methods: A cross-sectional question based survey, conducted in the pediatric department of a peripheral hospital in Pune, Maharashtra from parents of under five children, presenting for any consultation from July 2018 to December 2018.Results: There were 636 respondents who completed the study. 38.1% were males. Mean age of responders was 26.85 years (SD 5.12 Range 18 to 37 years). Most of the population were educated lot. 55.5% responders defined fever correctly. There was a huge gap in the parent’s knowledge attitude and practice in fever and it’s management. Lack of information and fear of any untoward incident occurring due to fever were the reason for parental anxiety, frequent medication & combination antipyretic use, and pressure on part of health professionals to increase antibiotic prescriptions.Conclusions: Lack of parental knowledge of fever and fever management in younger children is of concern in the community in spite of improvement in the educational level of parents. There is a utmost need to spread awareness in the community about the benign and the self-limiting nature of most febrile illnesses.

scholarly journals Modeling non-Gaussian data analysis on determinants of underweight among under five children in rural Ethiopia: Ethiopian demographic and health survey 2016 evidences

PLoS ONE ◽  
2021 ◽  
Vol 16 (5) ◽  
pp. e0251239
Author(s):  
Sara Abera Bekele ◽  
Moges Zerihun Fetene
Keyword(s):  
Data Analysis ◽  
Rural Areas ◽  
Wealth Index ◽  
Under Five ◽  
Factors Associated ◽  
Under Five Children ◽  
Rural Ethiopia ◽  
Under Nutrition ◽  
Non Gaussian ◽  
Gaussian Data

Background Childhood under-nutrition is a major global health problem. Although the rate of under-nutrition in Ethiopia has declined in the last decade, but it still remains being the major causes of morbidity and mortality of children under-five years. The problem is even worse in rural areas. The prevalence of underweight among rural children was 25% compared with 13% among urban children. To alleviate this problem, it is necessary to determine the magnitude and determinants of underweight. The study models non-Gaussian data analysis to identify risk factors associated with underweight among under-five children in rural Ethiopia. Methodology The data source for this study was secondary data, which was retrieved from EDHS 2016 database. It was analyzed using two model families; one with marginal models (GEE and ALR) in which responses are modeled and marginalized overall other responses, and the other is random effects model (GLMM) which is useful when the interest of the analyst lies in the individual’s response profiles as well as to evaluate within and between regional variations of underweight. Result From fitting non-Gaussian data analysis to identify risk factors associated with underweight among under five children in rural Ethiopia, the independent variable which have significant effect on underweight were:—Age of child, birth interval, mothers education, fathers education, wealth index, diarrhea in last two weeks, fever in last two weeks are significant and also father’s work status shows that difference in significance among the category. Conclusion Child age, preceding birth interval, mother’s education, household’s wealth index, fever, diarrhea, father’s education and father’s work status were associated with child underweight. Furthermore, there is both within and between regional heterogeneity of underweight among children in rural Ethiopia. Therefore, rigorous community-based interventions (such as uplifting mother’s education by providing formal education and preventing infectious diseases that cause diarrhea and fever) should be developed and executed throughout the country to improve this grave situation of underweight prevalence in rural areas of Ethiopia.

scholarly journals PENGGUNAAN EJAAN PADA JURNAL BUANA PENDIDIKAN, FKIP, UNIVERSITAS PGRI ADI BUANA SURABAYA

2018 ◽  
Vol 11 (21) ◽  
Author(s):  
Ira Eko Retnosari
Keyword(s):  
Data Analysis ◽  
Data Collection ◽  
Qualitative Approach ◽  
The Other ◽  
Analysis Process ◽  
New Information ◽  
Data Source ◽  
Descriptive Method

university can communicate new information, ideas, studies, and research results. This journal aims to describe the use of the spelling of Buana Pendidikan journal. This study applies a qualitative approach. The data source of this study is the spelling of Buana Pendidikan journal. The data collecting in this research is done by documentation method. The data collection techniques are (1) the journal collection, (2) copying journal, (3) reading journal, (4) marking with highlighter, (5) classification, (6) coding, and (7) making cards. The data analysis used descriptive method. The stages of data analysis process include (1) the data collection, (2) classification of data, (3) the determination of errors frequency, (4) explanation. The result of this journal which is the use of spelling that contained in Buana Pendidikan journal is good. It can be proved from the inaccuracy use of spelling that mostly are the use of comma, while other punctuations are relatively little. In addition, the other inaccuracies use of spelling are (1) writing capital letters, (2) writing italics, (3) the writing of numbers, (4) writing the word, (5) the use of dots, and (7) the use of commas. This journal is expected to give inputs to the lecturers to be able to use spelling correctly when writing a journal. In writing a journal, the use of spelling should be applied properly

scholarly journals Classification of Imbalanced Data Represented as Binary Features

2021 ◽  
Vol 11 (17) ◽  
pp. 7825
Author(s):  
Kunti Robiatul Mahmudah ◽  
Fatma Indriani ◽  
Yukiko Takemori-Sakai ◽  
Yasunori Iwata ◽  
Takashi Wada ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Imbalanced Data ◽  
Extraction Methods ◽  
Classification Performance ◽  
Machine Learning Algorithms ◽  
Classification Algorithms ◽  
Benchmark Datasets ◽  
Binary Features ◽  
Classification Tasks

Typically, classification is conducted on a dataset that consists of numerical features and target classes. For instance, a grayscale image, which is usually represented as a matrix of integers varying from 0 to 255, enables one to apply various classification algorithms to image classification tasks. However, datasets represented as binary features cannot use many standard machine learning algorithms optimally, yet their amount is not negligible. On the other hand, oversampling algorithms such as synthetic minority oversampling technique (SMOTE) and its variants are often used if the dataset for classification is imbalanced. However, since SMOTE and its variants synthesize new minority samples based on the original samples, the diversity of the samples synthesized from binary features is highly limited due to the poor representation of original features. To solve this problem, a preprocessing approach is studied. By converting binary features into numerical ones using feature extraction methods, succeeding oversampling methods can fully display their potential in improving the classifiers’ performances. Through comprehensive experiments using benchmark datasets and real medical datasets, it was observed that a converted dataset consisting of numerical features is better for oversampling methods (maximum improvements of accuracy and F1-score were 35.11% and 42.17%, respectively). In addition, it is confirmed that feature extraction and oversampling synergistically contribute to the improvement of classification performance.

Sign in / Sign up

Export Citation Format

Share Document