CRISP-DM for Data Quality Improvement to Support Machine Learning of Stunting Prediction in Infants and Toddlers

Purbasari, Ayi; Rinawan, Fedri Ruluwedrata; Zulianto, Arief; Susanti, Ari Indra; Komara, Hendra

doi:10.1109/icaicta53211.2021.9640294

Cited by 7 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The machine learning method uses data to build an intelligent system. Data quality is the main course of this method for creating a model [56]. However, raw data is not clean [57].…”

Section: Discussionmentioning

confidence: 99%

Posyandu Application for Monitoring Children Under-Five: A 3-Year Data Quality Map in Indonesia

Rinawan

Faza

Susanti

et al. 2022

IJGI

Self Cite

View full text Add to dashboard Cite

Posyandu is an Indonesian mother-child health, community-based healthcare. The provision of the Posyandu data quality map is crucial for analyzing results but is limited. This research aimed to (a) demonstrate data quality analysis on its completeness, accuracy, and consistency and (b) map the data quality in Indonesia for evaluation and improvement. An observational study was conducted using the Posyandu application. We observed data in Indonesia from 2019 to 2021. Data completeness was identified using children’s visits/year. Data accuracy was analyzed using WHO anthropometry z-score and implausible z-score values analyzing the outliers. Cronbach’s α of variables was used to know data consistency. STATA 15.1 SE and QGIS 3.10 was used to analyze and map the quality. Data completeness and accuracy in three years show a good start for the pilot project area, continued with declines in pandemic time, while some other areas demonstrated a small start, then slightly increased. The overall consistency decreased through the study period. A good report on data completeness can occur initially in a pilot project area, followed by others. Data accuracy and consistency can decrease during the pandemic. The app can be promising when synchronized with the government health information system.

show abstract

“…The machine learning method uses data to build an intelligent system. Data quality is the main course of this method for creating a model [56]. However, raw data is not clean [57].…”

Section: Discussionmentioning

confidence: 99%

Posyandu Application for Monitoring Children Under-Five: A 3-Year Data Quality Map in Indonesia

Rinawan

Faza

Susanti

et al. 2022

IJGI

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this work, we use AutoML to automate algorithm selection and hyperparameter tuning for the modeling phase of CRISP-DM. The usage of AutoML intends to reduce the time needed for the modeling phase and allowed us to focus on other key phases, such as data understanding and data preparation [15].…”

Section: Automlmentioning

confidence: 99%

Production Time Prediction for Contract Manufacturing Industries Using Automated Machine Learning

Sousa

Ferreira

Ribeiro

et al. 2022

IFIP Advances in Information and Communication Technology

View full text Add to dashboard Cite

The estimation of production time is an essential part of the manufacturing domain, allowing companies to optimize their production plan and meet the dates required by the customers. In the last years, there have been several approaches that use Machine Learning (ML) to predict the time needed to finish production orders. In this paper, we use the CRISP-DM methodology and Automated Machine Learning (Au-toML) to address production time prediction for a Portuguese contract manufacturing company that produces metal containers. We performed three CRISP-DM iterations using real data provided by the company related to production orders and production operations. We compared four open-source modern AutoML technologies to predict production time across the three iterations: AutoGluon, H2O AutoML, rminer, and TPOT. Overall, the best results were achieved in the third CRISP-DM iteration by the H2O AutoML tool, which obtained an average error of 3.03 days. The obtained results suggest that the inclusion of data about individual manufacturing operations is useful for improving production time for the entire production order.

show abstract

“…Even though it has become a regional and national program, currently there are still many parents who are not concerned with the development of their children's growth, including in terms of stunting. This is because most parents now do not know this information and they are reluctant to check their child's growth regularly because of difficulties in taking the time to have their child checked at the Puskesmas or Posyandu (Purbasari et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Design and Development of Information Systems for Data Collection and Monitoring of Children's Growth and Development as an Effort to Prevent Stunting in Kotapari Village

Muttaqin,

Mayasari,

Pratama

2023

IJECOM

View full text Add to dashboard Cite

Stunting is one of the problems being faced by Kotapari Village. The absence of an information system about stunting that is easily accessible to the public is one of the aspects that has slowed down the resolution of the stunting problem. To accelerate the resolution of the stunting problem, it is considered necessary to have an information system that can help the community easily and quickly. Methods of data collection is done by interviews and observation. In this study the system development method used is waterfall with the supporting software used are PHP and MySQL. Seeing the reality above, it is deemed necessary to build a website-based information system that is useful to facilitate Kotapari Village and the Community in working to resolve the stunting problem in Serdang Bedagai Regency. Apart from being able to provide stunting information to the community, this application also has a child health check menu related to child growth and a discussion menu that can be used by the community to communicate with Kotapari Village.

show abstract

CRISP-DM for Data Quality Improvement to Support Machine Learning of Stunting Prediction in Infants and Toddlers

Cited by 7 publications

References 11 publications

Posyandu Application for Monitoring Children Under-Five: A 3-Year Data Quality Map in Indonesia

Posyandu Application for Monitoring Children Under-Five: A 3-Year Data Quality Map in Indonesia

Production Time Prediction for Contract Manufacturing Industries Using Automated Machine Learning

Design and Development of Information Systems for Data Collection and Monitoring of Children's Growth and Development as an Effort to Prevent Stunting in Kotapari Village

Contact Info

Product

Resources

About