SlideShare a Scribd company logo
Developing Predictive Model for Infant Mortality Based on Maternal Determinants and
Nutrition Status of 0-59 Month Older Children using a Deep Learning Approach in Ethiopia
Dawit Shibabaw*
, University of Gondar, Ethiopia, Dep’t of Data science
Email: - dawit.shibabaw@uog.edu.et
Abstract
Deaths of infants between one day and five years old are referred to as infant mortality. According
to the world health organization (WHO) report in 2019, an estimated 5.4 million children under
the age of five are said to have died. This problem is also severe in developing countries like
Ethiopia. According to a federal ministry of health report from 2019, Ethiopia has an estimated
annual death rate of roughly 472,000 children under the age of five, placing Ethiopia sixth globally
in terms of the absolute number of under-five deaths.
As the researcher reviewed different literature, there are some gaps in the research does not conduct
by using deep learning based on maternal detriment and nutrition status. The researcher conducted
data preprocessing techniques accordingly to get the quality of data for model development. In our
study researcher employed four such as, Random forest, an Artificial Neural network, XGBoost,
and a decision tree besides of ANN classifier, among the algorithm’s best accuracy, scored
Random forest with an accuracy of 93.29%. Besides the best-performed algorithm, we deployed
on cloud computing framework on Heroku.
Keywords:- Deep learning, nutrition, maternal determinants, ANN
I. Introduction
Deaths of infants between one day and five years old are referred to as infant mortality[1].
Globally, according to the world health organization (WHO) report in 2019, UNICEF, and World
Bank, an estimated 5.4 million children under the age of five are said to have died[2]. Despite
significant progress over the previous few decades, sub-Saharan Africa continues to have the
highest rate of under-five mortality in the world, accounting for almost half of the total burden,
according to a WHO report from 2021 [2][3]. Following India, Pakistan, Nigeria, and the
Democratic Republic of the Congo, Ethiopia seems to have the fifth-highest rate of infant fatalities
worldwide. According to a federal ministry of health report from 2019, Ethiopia has an estimated
annual death rate of roughly 472,000 children under the age of five, placing Ethiopia sixth globally
in terms of the absolute number of under-five deaths[2]. Despite this progress toward achieving
Millennium Development Goal 4 (MDG 4), Ethiopia's under-five mortality rate continues to be
greater than that of many other low- and middle-income nations[4]. Through every stage of life,
nutrition is the most important factor supporting human health and physical growth [5]. Perhaps
the most accurate indicator of a child's well-being is their nutritional status. The causes of
undernutrition in children are numerous and complex [6]. The risk of nutritional deficiency is
higher in children under five than in any other age group[7]. A healthy lifestyle depends on having
a good diet [8]. One of the issues with world health is malnutrition, particularly when it comes to
child survival. Half of all deaths globally among children under five are directly or indirectly
attributable to malnutrition, a major issue in developing countries [8].
I. Related work
Several studies investigated perinatal mortality in Ethiopia using different methods. Dhaka et al
[6], For a developing country like Bangladesh, malnutrition might be seen as a major problem.
Since tomorrow's workforce will be made up of today's children, this directly affects Bangladesh's
economic development [6][9]. Therefore, the most important area of research at present time is the
prevention of childhood malnutrition. The purpose of the project is to categorize malnutrition using
a deep learning technique to predictive modeling on important malnutrition traits to determine a
child's malnutrition status who is between the ages of 0-59 months. To achieve this, the children's
data from the Bangladesh Demographic and Health Survey (BDHS) 2014 are subjected to an
Artificial Neural Network (ANN) technique[6][10]. This study delineates the categories used by a
predictive algorithm to categorize nutritional status. For wasting, underweight, and stunting, the
ANN technique exhibits the highest degree of accuracy. Finally, for both policymakers and
physicians, determining the condition of malnutrition using a deep learning approach is the most
scientific course of action.
In order to identify the nutritional risk variables that are responsible, several statistical techniques
have been examined. Among the techniques, linear regression and logistic regression are
extensively researched for the detection of malnutrition in 0 to 59-month-old children [11] [12]
[13]. Rule induction classifier with receiver operating curve (ROC), Nave Bayes [14], decision
tree [15], and association rules are some of the models that can be used to explain a child's nutrition
measurement level. Few studies have employed least squares calculations and variable analysis to
determine the relationship between the chosen factors and malnutrition [16] [17] [18] [19].
As researcher knowledge, there is only study conducted based on either nutritional factors or
maternal determinants to predict infant mortality and identify the risk factors by using statistical
techniques, since statistical techniques its weakness of limited dataset to analysis and do not
extract hidden patterns from the complex dataset. As the researcher’s knowledge, there is no
research conducted by taking nutritional and maternal determinants to predict infant mortality.
II. Methodology
A quick summary of the dataset is given in the next section. The preparation of data and suggested
strategies for doing so using different tools and languages will be discussed in the sections that
follow
A. Data source
The source of raw data was taken from the Ethiopian demographics health survey (EDHS) since
from 2016 and 2019. It has been designed to cover both rural and urban under every division of
Ethiopia country. Among rural and urban areas EDHS consists of a birth record, nutrition record,
maternal record, and household record. Ethiopia’s central statistical agency collects raw data five
years’ intervals and provides research for further analysis. In this study researcher used 16,283 raw
data.
B. Data preprocessing
In data preprocessing researchers, to get the quality of data for model development researchers to
follow the different steps of data preprocessing, filling missing values, outlier detection, removing
redundancy, data transformation, imbalance problem handling, feature selection, and model
deployment. For missing value handling, we used mode and imputation methods since the nature
of the data is categorical. To detect and fill outliers researcher used a box plot and remove them
by using the interquartile range (IQR). To transform data researcher used binning and
discretization techniques. In these studies we have an imbalance in which 87% alive and 13% died,
to handle this problem, according to [20] [21][22], we applied systematic minority over sampling
techniques(SMOTE). After we applied SMOTE have to get data 30,014 datasets. For finally all
attributes do not use model development researcher used feature selection, in this study we used
wrapper feature selection techniques which are a step forward and step backward feature selection
applied. The step backward feature section scored the best accuracy of feature selection by taking
18 features and 2 features we recommended by domain experts. We deploy the model on flask
framework python library and front end of HTML on a Heroku cloud platform.
C. Proposed model
Preprocessed data is now prepared to fit the deep learning model. Our deep learning model has
been implemented with the Tensor flow. Data flow graphs are used by Tensor flow to create
models. Building massive layers in an Artificial Neural Network (ANN) is necessary in order to
examine our model. Our model is constructed using "Keras," a well-known package, and Tensor
Flow is utilized to train the factors at the model's backend.
Figure 1: Proposed Model Framework
After initializing the artificial network, the model took 20 neurons as features in the input layer
and 10 in the hidden layer. In the proposed model, ANN used three hidden layers after testing
gradually one by one. As the researcher proposed to classify infant mortality from trained data, it
sets the range (0, 1) of a linear function in ANN using the rectifier activation function applied in
the hidden layer and sigmoid activation function in the output layer. As 80% of the data is taken
as training data and fits a model which runs 1000-2000 epochs. Here each epoch is considered as
one forward and one backward propagation. Finally the most potent stochastic gradient descent
optimizer parameter “adam” in which a perfect gradient descent algorism is used.
Figure 2: Artificial neural network framework based on Tensor flow
III. Result and discussion
The purpose of the study is to determine being alive and died child from trained data, Random
forest approaches show the best result with an accuracy of 93.29%, and also Decision Tree,
Extreme Gradient Boosting, and ANN, with an accuracy of 91.47%, 91.44%, and 81.91%
respectively. These test have done by 20% of the data with K-fold (k=10). We mainly implemented
ANN on our datasets whereas other machine learning algorithms have been used such as Random
forest, Decision tree, and Extreme Gradient boosting beside of ANN classifier.
Evaluation Criteria Algorithms
Random
forest
XGBoost Artificial neural
network
Decision Tree
Accuracy (%) 93.29 91.44 81.91 91.47
Precision (%) 95.43 94.53 79.17 93.86
Recall (%) 90.87 87.88 86.39 88.67
ROC (%) 94.23 90.21 87.36 94.98
Table 1: Overall Algorithms Evaluation
Figure 3: Accuracy of all algorithms
Besides of Best performed algorithm (Random forest by ANN classifier) we have deployed on
Cloud computing framework Heroku, which was designed by the front end by HTML and back
end by python flask framework for potential users. As shown image and link” ”.
IV. Conclusion
The human brainpower may have restricted intellectual ability to predict infant mortality. At the
same time, artificial intelligence can iterate considerable data but that may lack of logical ability.
One of the most effective scientific approaches is to use deep learning mechanisms to determine
infant mortality. This strategy may lower the number of deaths, particularly in a developing
country like Ethiopia where a huge number of kids are affected by it. Maternal and child health is
Bangladesh's top priority to achieve the Sustainable Development Goals (SDGs). Consequently,
decision-makers and Healthcare professionals can quickly benefit from the depth learning of how
to foresee infant mortality youngster in advance
Reference
[1] NICHD, “About Menstruation | NICHD - Eunice Kennedy Shriver National Institute of
Child Health and Human Development.” pp. 1–1, 2019. Accessed: Jul. 20, 2022. [Online].
Available: https://www.nichd.nih.gov/health/topics/infant-mortality
[2] F. H. Bitew, S. H. Nyarko, L. Potter, and C. S. Sparks, “Machine learning approach for
predicting under-five mortality determinants in Ethiopia: evidence from the 2016
Ethiopian Demographic and Health Survey,” Genus, vol. 76, no. 1, 2020, doi:
10.1186/s41118-020-00106-2.
[3] S. P. Nyoni and T. Nyoni, “Forecasting Infant Mortality Rate in Ghana Using a Machine
Learning Algorithm,” Int. Res. J. Innov. Eng. Technol., vol. 5, no. 3, pp. 622–626, 2021,
[Online]. Available: https://doi.org/10.47001/IRJIET/2021.503107
[4] S. Khare, S. Kavyashree, D. Gupta, and A. Jyotishi, “Investigation of Nutritional Status of
Children based on Machine Learning Techniques using Indian Demographic and Health
Survey Data,” Procedia Comput. Sci., vol. 115, pp. 338–349, 2017, doi:
10.1016/j.procs.2017.09.087.
[5] M. Shahriar, M. S. Iqubal, S. Mitra, and A. K. Das, “A Deep Learning Approach to
Predict Malnutrition Status of 0-59 Month ’ s Older Children in,” pp. 145–149, 2019.
[6] A. Talukder and B. Ahammed, “Machine Learning Algorithms for Predicting Malnutrition
among Under-Five Children in Bangladesh,” Nutrition, p. 110861, 2020, doi:
10.1016/j.nut.2020.110861.
[7] M. Shahriar, M. S. Iqubal, S. Mitra, and A. K. Das, “A deep learning approach to predict
malnutrition status of 0-59 month’s older children in Bangladesh,” Proc. - 2019 IEEE Int.
Conf. Ind. 4.0, Artif. Intell. Commun. Technol. IAICT 2019, pp. 145–149, 2019, doi:
10.1109/ICIAICT.2019.8784823.
[8] S. Khare, S. Kavyashree, D. Gupta, and A. Jyotishi, “ScienceDirect ScienceDirect
Investigation of Nutritional Status of Children based on Machine Learning Techniques
using Indian Demographic and Health Survey Data,” Procedia Comput. Sci., vol. 115, pp.
338–349, 2017, doi: 10.1016/j.procs.2017.09.087.
[9] C. E. Beluzo, L. C. Alves, E. Silva, R. Bresan, N. Arruda, and T. Carvalho, “Machine
learning to predict neonatal mortality using public health data from São Paulo - Brazil,”
medRxiv, pp. 0–30, 2020.
[10] M. Podda, D. Bacciu, A. Micheli, R. Bellù, G. Placidi, and L. Gagliardi, “A machine
learning approach to estimating preterm infants survival: development of the Preterm
Infants Survival Assessment (PISA) predictor,” Sci. Rep., vol. 8, no. 1, pp. 1–9, 2018, doi:
10.1038/s41598-018-31920-6.
[11] A. K. Das et al., “Big media healthcare data processing in cloud: a collaborative resource
management perspective,” Cluster Comput., vol. 20, no. 2, pp. 1599–1614, Mar. 2017,
doi: 10.1007/s10586-017-0785-8.
[12] L. Abera, T. Dejene, and T. Laelago, “Prevalence of malnutrition and associated factors in
children aged 6-59 months among rural dwellers of damot gale district, south Ethiopia:
Community based cross sectional study,” Int. J. Equity Health, vol. 16, no. 1, pp. 1–8,
2017, doi: 10.1186/s12939-017-0608-9.
[13] S. Das and R. M. Rahman, “Application of ordinal logistic regression analysis in
determining risk factors of child malnutrition in Bangladesh,” 2011. doi: 10.1186/1475-
2891-10-124.
[14] Z. Markos, “Predicting Under Nutrition Status of Under-Five Children Using Data Mining
Techniques: The Case of 2011 Ethiopian Demographic and Health Survey,” J. Heal. Med.
Informatics, vol. 5, no. 2, 2014, doi: 10.4172/2157-7420.1000152.
[15] S. Vijayakumar, M. G. Deepika, A. Jyotishi, and D. Gupta, “Factors affecting infant
mortality rate in India: An analysis of Indian states,” Adv. Intell. Syst. Comput., vol. 530,
pp. 707–719, 2016, doi: 10.1007/978-3-319-47952-1_57.
[16] A. Tashnim, S. Nowshin, F. Akter, and A. K. Das, “Interactive interface design for
learning numeracy and calculation for children with autism,” in 2017 9th International
Conference on Information Technology and Electrical Engineering, ICITEE 2017, Jul.
2017, vol. 2018-Janua, pp. 1–6. doi: 10.1109/ICITEED.2017.8250507.
[17] A. Tashnim, S. Nowshin, F. Akter, and A. K. Das, “Interactive interface design for
learning numeracy and calculation for children with autism,” in 2017 9th International
Conference on Information Technology and Electrical Engineering, ICITEE 2017, 2017,
vol. 2018-Janua, pp. 1–6. doi: 10.1109/ICITEED.2017.8250507.
[18] M. Arimond and M. T. Ruel, “Community and International Nutrition Dietary Diversity Is
Associated with Child Nutritional Status: Evidence from 11 Demographic and Health
Surveys 1,2,” J. Nutr, vol. 134, no. August 2004, pp. 2579–2585, 2004, [Online].
Available: https://academic.oup.com/jn/article-abstract/134/10/2579/4688437
[19] B. A. Abuya, J. Ciera, and E. Kimani-Murage, “Effect of mother’s education on child’s
nutritional status in the slums of Nairobi,” BMC Pediatr., vol. 12, no. 1998, 2012, doi:
10.1186/1471-2431-12-80.
[20] H. A. Khorshidi and U. Aickelin, “A Synthetic Over-sampling with the Minority and
Majority classes for imbalance problems,” arXiv, pp. 1–12, 2020.
[21] N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, “snopes.com: Two-
Striped Telamonia Spider,” J. Artif. Intell. Res., vol. 16, no. Sept. 28, pp. 321–357, 2002,
[Online]. Available:
https://arxiv.org/pdf/1106.1813.pdf%0Ahttp://www.snopes.com/horrors/insects/telamonia.
asp
[22] N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, “SMOTE: Synthetic
minority over-sampling technique,” J. Artif. Intell. Res., vol. 16, pp. 321–357, Jun. 2002,
doi: 10.1613/jair.953.

More Related Content

Similar to malnutration.pdf

Student Alcohol Consumption Prediction: Data Mining Approach
Student Alcohol Consumption Prediction: Data Mining Approach Student Alcohol Consumption Prediction: Data Mining Approach
Student Alcohol Consumption Prediction: Data Mining Approach
IJCSIS Research Publications
 
UTILIZATION OF IMMUNIZATION SERVICES AMONG CHILDREN UNDER FIVE YEARS OF AGE I...
UTILIZATION OF IMMUNIZATION SERVICES AMONG CHILDREN UNDER FIVE YEARS OF AGE I...UTILIZATION OF IMMUNIZATION SERVICES AMONG CHILDREN UNDER FIVE YEARS OF AGE I...
UTILIZATION OF IMMUNIZATION SERVICES AMONG CHILDREN UNDER FIVE YEARS OF AGE I...
AM Publications
 
Ijpsr14 05-11-015
Ijpsr14 05-11-015Ijpsr14 05-11-015
Ijpsr14 05-11-015alem teka
 
IRJET- Detect Malnutrition in Underage Children by using Tensorflow Algor...
IRJET-  	  Detect Malnutrition in Underage Children by using Tensorflow Algor...IRJET-  	  Detect Malnutrition in Underage Children by using Tensorflow Algor...
IRJET- Detect Malnutrition in Underage Children by using Tensorflow Algor...
IRJET Journal
 
Optimising maternal & child healthcare in India through the integrated use of...
Optimising maternal & child healthcare in India through the integrated use of...Optimising maternal & child healthcare in India through the integrated use of...
Optimising maternal & child healthcare in India through the integrated use of...
Skannd Tyagi
 
gaze%20bro.docx
gaze%20bro.docxgaze%20bro.docx
gaze%20bro.docx
TewodrosBiru1
 
Nutrition Information Aggregatior | Final Year Project
Nutrition Information Aggregatior | Final Year ProjectNutrition Information Aggregatior | Final Year Project
Nutrition Information Aggregatior | Final Year Project
shubham ghimire
 
mini proposal PSNP.ppt
mini proposal PSNP.pptmini proposal PSNP.ppt
mini proposal PSNP.ppt
DaniWondimeDers
 
Mobile Decision Support System to Determine Toddler's Nutrition using Fuzzy S...
Mobile Decision Support System to Determine Toddler's Nutrition using Fuzzy S...Mobile Decision Support System to Determine Toddler's Nutrition using Fuzzy S...
Mobile Decision Support System to Determine Toddler's Nutrition using Fuzzy S...
IJECEIAES
 
Aytenew publication
Aytenew publicationAytenew publication
Aytenew publication
aytenewgetabalew
 
science research journal.pdf
science research journal.pdfscience research journal.pdf
science research journal.pdf
KSAravindSrivastava
 
science research journal.pdf
science research journal.pdfscience research journal.pdf
science research journal.pdf
KSAravindSrivastava
 
Factors Influencing Immunization Coverage among Children 12- 23 Months of Age...
Factors Influencing Immunization Coverage among Children 12- 23 Months of Age...Factors Influencing Immunization Coverage among Children 12- 23 Months of Age...
Factors Influencing Immunization Coverage among Children 12- 23 Months of Age...
iosrjce
 
Abebe et al-2020-systematic_reviews
Abebe et al-2020-systematic_reviewsAbebe et al-2020-systematic_reviews
Abebe et al-2020-systematic_reviews
Thomas Ayalew
 
Prevalence and affecting factors of stunting in toddlers in Bandar Lampung Ci...
Prevalence and affecting factors of stunting in toddlers in Bandar Lampung Ci...Prevalence and affecting factors of stunting in toddlers in Bandar Lampung Ci...
Prevalence and affecting factors of stunting in toddlers in Bandar Lampung Ci...
AJHSSR Journal
 
Monitoring Indonesian online news for COVID-19 event detection using deep le...
Monitoring Indonesian online news for COVID-19 event  detection using deep le...Monitoring Indonesian online news for COVID-19 event  detection using deep le...
Monitoring Indonesian online news for COVID-19 event detection using deep le...
IJECEIAES
 
Use of Mobile Phone for Knowledge Update among Nurses in Primary and Secondar...
Use of Mobile Phone for Knowledge Update among Nurses in Primary and Secondar...Use of Mobile Phone for Knowledge Update among Nurses in Primary and Secondar...
Use of Mobile Phone for Knowledge Update among Nurses in Primary and Secondar...
iosrjce
 
PREDICTION OF ANEMIA USING MACHINE LEARNING ALGORITHMS
PREDICTION OF ANEMIA USING MACHINE LEARNING ALGORITHMSPREDICTION OF ANEMIA USING MACHINE LEARNING ALGORITHMS
PREDICTION OF ANEMIA USING MACHINE LEARNING ALGORITHMS
AIRCC Publishing Corporation
 
Prediction of Anemia using Machine Learning Algorithms
Prediction of Anemia using Machine Learning AlgorithmsPrediction of Anemia using Machine Learning Algorithms
Prediction of Anemia using Machine Learning Algorithms
AIRCC Publishing Corporation
 
Leonard Kingwara publication
Leonard Kingwara publicationLeonard Kingwara publication
Leonard Kingwara publicationLeonard Kingwara
 

Similar to malnutration.pdf (20)

Student Alcohol Consumption Prediction: Data Mining Approach
Student Alcohol Consumption Prediction: Data Mining Approach Student Alcohol Consumption Prediction: Data Mining Approach
Student Alcohol Consumption Prediction: Data Mining Approach
 
UTILIZATION OF IMMUNIZATION SERVICES AMONG CHILDREN UNDER FIVE YEARS OF AGE I...
UTILIZATION OF IMMUNIZATION SERVICES AMONG CHILDREN UNDER FIVE YEARS OF AGE I...UTILIZATION OF IMMUNIZATION SERVICES AMONG CHILDREN UNDER FIVE YEARS OF AGE I...
UTILIZATION OF IMMUNIZATION SERVICES AMONG CHILDREN UNDER FIVE YEARS OF AGE I...
 
Ijpsr14 05-11-015
Ijpsr14 05-11-015Ijpsr14 05-11-015
Ijpsr14 05-11-015
 
IRJET- Detect Malnutrition in Underage Children by using Tensorflow Algor...
IRJET-  	  Detect Malnutrition in Underage Children by using Tensorflow Algor...IRJET-  	  Detect Malnutrition in Underage Children by using Tensorflow Algor...
IRJET- Detect Malnutrition in Underage Children by using Tensorflow Algor...
 
Optimising maternal & child healthcare in India through the integrated use of...
Optimising maternal & child healthcare in India through the integrated use of...Optimising maternal & child healthcare in India through the integrated use of...
Optimising maternal & child healthcare in India through the integrated use of...
 
gaze%20bro.docx
gaze%20bro.docxgaze%20bro.docx
gaze%20bro.docx
 
Nutrition Information Aggregatior | Final Year Project
Nutrition Information Aggregatior | Final Year ProjectNutrition Information Aggregatior | Final Year Project
Nutrition Information Aggregatior | Final Year Project
 
mini proposal PSNP.ppt
mini proposal PSNP.pptmini proposal PSNP.ppt
mini proposal PSNP.ppt
 
Mobile Decision Support System to Determine Toddler's Nutrition using Fuzzy S...
Mobile Decision Support System to Determine Toddler's Nutrition using Fuzzy S...Mobile Decision Support System to Determine Toddler's Nutrition using Fuzzy S...
Mobile Decision Support System to Determine Toddler's Nutrition using Fuzzy S...
 
Aytenew publication
Aytenew publicationAytenew publication
Aytenew publication
 
science research journal.pdf
science research journal.pdfscience research journal.pdf
science research journal.pdf
 
science research journal.pdf
science research journal.pdfscience research journal.pdf
science research journal.pdf
 
Factors Influencing Immunization Coverage among Children 12- 23 Months of Age...
Factors Influencing Immunization Coverage among Children 12- 23 Months of Age...Factors Influencing Immunization Coverage among Children 12- 23 Months of Age...
Factors Influencing Immunization Coverage among Children 12- 23 Months of Age...
 
Abebe et al-2020-systematic_reviews
Abebe et al-2020-systematic_reviewsAbebe et al-2020-systematic_reviews
Abebe et al-2020-systematic_reviews
 
Prevalence and affecting factors of stunting in toddlers in Bandar Lampung Ci...
Prevalence and affecting factors of stunting in toddlers in Bandar Lampung Ci...Prevalence and affecting factors of stunting in toddlers in Bandar Lampung Ci...
Prevalence and affecting factors of stunting in toddlers in Bandar Lampung Ci...
 
Monitoring Indonesian online news for COVID-19 event detection using deep le...
Monitoring Indonesian online news for COVID-19 event  detection using deep le...Monitoring Indonesian online news for COVID-19 event  detection using deep le...
Monitoring Indonesian online news for COVID-19 event detection using deep le...
 
Use of Mobile Phone for Knowledge Update among Nurses in Primary and Secondar...
Use of Mobile Phone for Knowledge Update among Nurses in Primary and Secondar...Use of Mobile Phone for Knowledge Update among Nurses in Primary and Secondar...
Use of Mobile Phone for Knowledge Update among Nurses in Primary and Secondar...
 
PREDICTION OF ANEMIA USING MACHINE LEARNING ALGORITHMS
PREDICTION OF ANEMIA USING MACHINE LEARNING ALGORITHMSPREDICTION OF ANEMIA USING MACHINE LEARNING ALGORITHMS
PREDICTION OF ANEMIA USING MACHINE LEARNING ALGORITHMS
 
Prediction of Anemia using Machine Learning Algorithms
Prediction of Anemia using Machine Learning AlgorithmsPrediction of Anemia using Machine Learning Algorithms
Prediction of Anemia using Machine Learning Algorithms
 
Leonard Kingwara publication
Leonard Kingwara publicationLeonard Kingwara publication
Leonard Kingwara publication
 

More from kwadwoAmedi

IndabaX2022Agishaposter.pdf
IndabaX2022Agishaposter.pdfIndabaX2022Agishaposter.pdf
IndabaX2022Agishaposter.pdf
kwadwoAmedi
 
POSTER_Ewonye.pdf
POSTER_Ewonye.pdfPOSTER_Ewonye.pdf
POSTER_Ewonye.pdf
kwadwoAmedi
 
Dengue Fever Presentation.pdf
Dengue Fever Presentation.pdfDengue Fever Presentation.pdf
Dengue Fever Presentation.pdf
kwadwoAmedi
 
IndabaX Ghana Poster.pdf
IndabaX Ghana Poster.pdfIndabaX Ghana Poster.pdf
IndabaX Ghana Poster.pdf
kwadwoAmedi
 
PosterPresentations.Henock_Makumbu.pdf
PosterPresentations.Henock_Makumbu.pdfPosterPresentations.Henock_Makumbu.pdf
PosterPresentations.Henock_Makumbu.pdf
kwadwoAmedi
 
Poster Presentation GDSS 2022 (IndabaX Ghana) Adjei Boateng.pdf
Poster Presentation GDSS 2022 (IndabaX Ghana)  Adjei Boateng.pdfPoster Presentation GDSS 2022 (IndabaX Ghana)  Adjei Boateng.pdf
Poster Presentation GDSS 2022 (IndabaX Ghana) Adjei Boateng.pdf
kwadwoAmedi
 
GDSS_IndabaX_Maranatha.pdf
GDSS_IndabaX_Maranatha.pdfGDSS_IndabaX_Maranatha.pdf
GDSS_IndabaX_Maranatha.pdf
kwadwoAmedi
 

More from kwadwoAmedi (7)

IndabaX2022Agishaposter.pdf
IndabaX2022Agishaposter.pdfIndabaX2022Agishaposter.pdf
IndabaX2022Agishaposter.pdf
 
POSTER_Ewonye.pdf
POSTER_Ewonye.pdfPOSTER_Ewonye.pdf
POSTER_Ewonye.pdf
 
Dengue Fever Presentation.pdf
Dengue Fever Presentation.pdfDengue Fever Presentation.pdf
Dengue Fever Presentation.pdf
 
IndabaX Ghana Poster.pdf
IndabaX Ghana Poster.pdfIndabaX Ghana Poster.pdf
IndabaX Ghana Poster.pdf
 
PosterPresentations.Henock_Makumbu.pdf
PosterPresentations.Henock_Makumbu.pdfPosterPresentations.Henock_Makumbu.pdf
PosterPresentations.Henock_Makumbu.pdf
 
Poster Presentation GDSS 2022 (IndabaX Ghana) Adjei Boateng.pdf
Poster Presentation GDSS 2022 (IndabaX Ghana)  Adjei Boateng.pdfPoster Presentation GDSS 2022 (IndabaX Ghana)  Adjei Boateng.pdf
Poster Presentation GDSS 2022 (IndabaX Ghana) Adjei Boateng.pdf
 
GDSS_IndabaX_Maranatha.pdf
GDSS_IndabaX_Maranatha.pdfGDSS_IndabaX_Maranatha.pdf
GDSS_IndabaX_Maranatha.pdf
 

Recently uploaded

Algorithmic optimizations for Dynamic Levelwise PageRank (from STICD) : SHORT...
Algorithmic optimizations for Dynamic Levelwise PageRank (from STICD) : SHORT...Algorithmic optimizations for Dynamic Levelwise PageRank (from STICD) : SHORT...
Algorithmic optimizations for Dynamic Levelwise PageRank (from STICD) : SHORT...
Subhajit Sahu
 
Quantitative Data AnalysisReliability Analysis (Cronbach Alpha) Common Method...
Quantitative Data AnalysisReliability Analysis (Cronbach Alpha) Common Method...Quantitative Data AnalysisReliability Analysis (Cronbach Alpha) Common Method...
Quantitative Data AnalysisReliability Analysis (Cronbach Alpha) Common Method...
2023240532
 
The affect of service quality and online reviews on customer loyalty in the E...
The affect of service quality and online reviews on customer loyalty in the E...The affect of service quality and online reviews on customer loyalty in the E...
The affect of service quality and online reviews on customer loyalty in the E...
jerlynmaetalle
 
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
Timothy Spann
 
一比一原版(Bradford毕业证书)布拉德福德大学毕业证如何办理
一比一原版(Bradford毕业证书)布拉德福德大学毕业证如何办理一比一原版(Bradford毕业证书)布拉德福德大学毕业证如何办理
一比一原版(Bradford毕业证书)布拉德福德大学毕业证如何办理
mbawufebxi
 
Adjusting primitives for graph : SHORT REPORT / NOTES
Adjusting primitives for graph : SHORT REPORT / NOTESAdjusting primitives for graph : SHORT REPORT / NOTES
Adjusting primitives for graph : SHORT REPORT / NOTES
Subhajit Sahu
 
一比一原版(UofS毕业证书)萨省大学毕业证如何办理
一比一原版(UofS毕业证书)萨省大学毕业证如何办理一比一原版(UofS毕业证书)萨省大学毕业证如何办理
一比一原版(UofS毕业证书)萨省大学毕业证如何办理
v3tuleee
 
一比一原版(UniSA毕业证书)南澳大学毕业证如何办理
一比一原版(UniSA毕业证书)南澳大学毕业证如何办理一比一原版(UniSA毕业证书)南澳大学毕业证如何办理
一比一原版(UniSA毕业证书)南澳大学毕业证如何办理
slg6lamcq
 
Best best suvichar in gujarati english meaning of this sentence as Silk road ...
Best best suvichar in gujarati english meaning of this sentence as Silk road ...Best best suvichar in gujarati english meaning of this sentence as Silk road ...
Best best suvichar in gujarati english meaning of this sentence as Silk road ...
AbhimanyuSinha9
 
一比一原版(Deakin毕业证书)迪肯大学毕业证如何办理
一比一原版(Deakin毕业证书)迪肯大学毕业证如何办理一比一原版(Deakin毕业证书)迪肯大学毕业证如何办理
一比一原版(Deakin毕业证书)迪肯大学毕业证如何办理
oz8q3jxlp
 
一比一原版(Adelaide毕业证书)阿德莱德大学毕业证如何办理
一比一原版(Adelaide毕业证书)阿德莱德大学毕业证如何办理一比一原版(Adelaide毕业证书)阿德莱德大学毕业证如何办理
一比一原版(Adelaide毕业证书)阿德莱德大学毕业证如何办理
slg6lamcq
 
做(mqu毕业证书)麦考瑞大学毕业证硕士文凭证书学费发票原版一模一样
做(mqu毕业证书)麦考瑞大学毕业证硕士文凭证书学费发票原版一模一样做(mqu毕业证书)麦考瑞大学毕业证硕士文凭证书学费发票原版一模一样
做(mqu毕业证书)麦考瑞大学毕业证硕士文凭证书学费发票原版一模一样
axoqas
 
Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...
Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...
Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...
Subhajit Sahu
 
Adjusting OpenMP PageRank : SHORT REPORT / NOTES
Adjusting OpenMP PageRank : SHORT REPORT / NOTESAdjusting OpenMP PageRank : SHORT REPORT / NOTES
Adjusting OpenMP PageRank : SHORT REPORT / NOTES
Subhajit Sahu
 
Data_and_Analytics_Essentials_Architect_an_Analytics_Platform.pptx
Data_and_Analytics_Essentials_Architect_an_Analytics_Platform.pptxData_and_Analytics_Essentials_Architect_an_Analytics_Platform.pptx
Data_and_Analytics_Essentials_Architect_an_Analytics_Platform.pptx
AnirbanRoy608946
 
Ch03-Managing the Object-Oriented Information Systems Project a.pdf
Ch03-Managing the Object-Oriented Information Systems Project a.pdfCh03-Managing the Object-Oriented Information Systems Project a.pdf
Ch03-Managing the Object-Oriented Information Systems Project a.pdf
haila53
 
Criminal IP - Threat Hunting Webinar.pdf
Criminal IP - Threat Hunting Webinar.pdfCriminal IP - Threat Hunting Webinar.pdf
Criminal IP - Threat Hunting Webinar.pdf
Criminal IP
 
一比一原版(NYU毕业证)纽约大学毕业证成绩单
一比一原版(NYU毕业证)纽约大学毕业证成绩单一比一原版(NYU毕业证)纽约大学毕业证成绩单
一比一原版(NYU毕业证)纽约大学毕业证成绩单
ewymefz
 
一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理
一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理
一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理
g4dpvqap0
 
Q1’2024 Update: MYCI’s Leap Year Rebound
Q1’2024 Update: MYCI’s Leap Year ReboundQ1’2024 Update: MYCI’s Leap Year Rebound
Q1’2024 Update: MYCI’s Leap Year Rebound
Oppotus
 

Recently uploaded (20)

Algorithmic optimizations for Dynamic Levelwise PageRank (from STICD) : SHORT...
Algorithmic optimizations for Dynamic Levelwise PageRank (from STICD) : SHORT...Algorithmic optimizations for Dynamic Levelwise PageRank (from STICD) : SHORT...
Algorithmic optimizations for Dynamic Levelwise PageRank (from STICD) : SHORT...
 
Quantitative Data AnalysisReliability Analysis (Cronbach Alpha) Common Method...
Quantitative Data AnalysisReliability Analysis (Cronbach Alpha) Common Method...Quantitative Data AnalysisReliability Analysis (Cronbach Alpha) Common Method...
Quantitative Data AnalysisReliability Analysis (Cronbach Alpha) Common Method...
 
The affect of service quality and online reviews on customer loyalty in the E...
The affect of service quality and online reviews on customer loyalty in the E...The affect of service quality and online reviews on customer loyalty in the E...
The affect of service quality and online reviews on customer loyalty in the E...
 
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
 
一比一原版(Bradford毕业证书)布拉德福德大学毕业证如何办理
一比一原版(Bradford毕业证书)布拉德福德大学毕业证如何办理一比一原版(Bradford毕业证书)布拉德福德大学毕业证如何办理
一比一原版(Bradford毕业证书)布拉德福德大学毕业证如何办理
 
Adjusting primitives for graph : SHORT REPORT / NOTES
Adjusting primitives for graph : SHORT REPORT / NOTESAdjusting primitives for graph : SHORT REPORT / NOTES
Adjusting primitives for graph : SHORT REPORT / NOTES
 
一比一原版(UofS毕业证书)萨省大学毕业证如何办理
一比一原版(UofS毕业证书)萨省大学毕业证如何办理一比一原版(UofS毕业证书)萨省大学毕业证如何办理
一比一原版(UofS毕业证书)萨省大学毕业证如何办理
 
一比一原版(UniSA毕业证书)南澳大学毕业证如何办理
一比一原版(UniSA毕业证书)南澳大学毕业证如何办理一比一原版(UniSA毕业证书)南澳大学毕业证如何办理
一比一原版(UniSA毕业证书)南澳大学毕业证如何办理
 
Best best suvichar in gujarati english meaning of this sentence as Silk road ...
Best best suvichar in gujarati english meaning of this sentence as Silk road ...Best best suvichar in gujarati english meaning of this sentence as Silk road ...
Best best suvichar in gujarati english meaning of this sentence as Silk road ...
 
一比一原版(Deakin毕业证书)迪肯大学毕业证如何办理
一比一原版(Deakin毕业证书)迪肯大学毕业证如何办理一比一原版(Deakin毕业证书)迪肯大学毕业证如何办理
一比一原版(Deakin毕业证书)迪肯大学毕业证如何办理
 
一比一原版(Adelaide毕业证书)阿德莱德大学毕业证如何办理
一比一原版(Adelaide毕业证书)阿德莱德大学毕业证如何办理一比一原版(Adelaide毕业证书)阿德莱德大学毕业证如何办理
一比一原版(Adelaide毕业证书)阿德莱德大学毕业证如何办理
 
做(mqu毕业证书)麦考瑞大学毕业证硕士文凭证书学费发票原版一模一样
做(mqu毕业证书)麦考瑞大学毕业证硕士文凭证书学费发票原版一模一样做(mqu毕业证书)麦考瑞大学毕业证硕士文凭证书学费发票原版一模一样
做(mqu毕业证书)麦考瑞大学毕业证硕士文凭证书学费发票原版一模一样
 
Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...
Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...
Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...
 
Adjusting OpenMP PageRank : SHORT REPORT / NOTES
Adjusting OpenMP PageRank : SHORT REPORT / NOTESAdjusting OpenMP PageRank : SHORT REPORT / NOTES
Adjusting OpenMP PageRank : SHORT REPORT / NOTES
 
Data_and_Analytics_Essentials_Architect_an_Analytics_Platform.pptx
Data_and_Analytics_Essentials_Architect_an_Analytics_Platform.pptxData_and_Analytics_Essentials_Architect_an_Analytics_Platform.pptx
Data_and_Analytics_Essentials_Architect_an_Analytics_Platform.pptx
 
Ch03-Managing the Object-Oriented Information Systems Project a.pdf
Ch03-Managing the Object-Oriented Information Systems Project a.pdfCh03-Managing the Object-Oriented Information Systems Project a.pdf
Ch03-Managing the Object-Oriented Information Systems Project a.pdf
 
Criminal IP - Threat Hunting Webinar.pdf
Criminal IP - Threat Hunting Webinar.pdfCriminal IP - Threat Hunting Webinar.pdf
Criminal IP - Threat Hunting Webinar.pdf
 
一比一原版(NYU毕业证)纽约大学毕业证成绩单
一比一原版(NYU毕业证)纽约大学毕业证成绩单一比一原版(NYU毕业证)纽约大学毕业证成绩单
一比一原版(NYU毕业证)纽约大学毕业证成绩单
 
一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理
一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理
一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理
 
Q1’2024 Update: MYCI’s Leap Year Rebound
Q1’2024 Update: MYCI’s Leap Year ReboundQ1’2024 Update: MYCI’s Leap Year Rebound
Q1’2024 Update: MYCI’s Leap Year Rebound
 

malnutration.pdf

  • 1. Developing Predictive Model for Infant Mortality Based on Maternal Determinants and Nutrition Status of 0-59 Month Older Children using a Deep Learning Approach in Ethiopia Dawit Shibabaw* , University of Gondar, Ethiopia, Dep’t of Data science Email: - dawit.shibabaw@uog.edu.et Abstract Deaths of infants between one day and five years old are referred to as infant mortality. According to the world health organization (WHO) report in 2019, an estimated 5.4 million children under the age of five are said to have died. This problem is also severe in developing countries like Ethiopia. According to a federal ministry of health report from 2019, Ethiopia has an estimated annual death rate of roughly 472,000 children under the age of five, placing Ethiopia sixth globally in terms of the absolute number of under-five deaths. As the researcher reviewed different literature, there are some gaps in the research does not conduct by using deep learning based on maternal detriment and nutrition status. The researcher conducted data preprocessing techniques accordingly to get the quality of data for model development. In our study researcher employed four such as, Random forest, an Artificial Neural network, XGBoost, and a decision tree besides of ANN classifier, among the algorithm’s best accuracy, scored Random forest with an accuracy of 93.29%. Besides the best-performed algorithm, we deployed on cloud computing framework on Heroku. Keywords:- Deep learning, nutrition, maternal determinants, ANN I. Introduction Deaths of infants between one day and five years old are referred to as infant mortality[1]. Globally, according to the world health organization (WHO) report in 2019, UNICEF, and World Bank, an estimated 5.4 million children under the age of five are said to have died[2]. Despite significant progress over the previous few decades, sub-Saharan Africa continues to have the highest rate of under-five mortality in the world, accounting for almost half of the total burden, according to a WHO report from 2021 [2][3]. Following India, Pakistan, Nigeria, and the Democratic Republic of the Congo, Ethiopia seems to have the fifth-highest rate of infant fatalities worldwide. According to a federal ministry of health report from 2019, Ethiopia has an estimated
  • 2. annual death rate of roughly 472,000 children under the age of five, placing Ethiopia sixth globally in terms of the absolute number of under-five deaths[2]. Despite this progress toward achieving Millennium Development Goal 4 (MDG 4), Ethiopia's under-five mortality rate continues to be greater than that of many other low- and middle-income nations[4]. Through every stage of life, nutrition is the most important factor supporting human health and physical growth [5]. Perhaps the most accurate indicator of a child's well-being is their nutritional status. The causes of undernutrition in children are numerous and complex [6]. The risk of nutritional deficiency is higher in children under five than in any other age group[7]. A healthy lifestyle depends on having a good diet [8]. One of the issues with world health is malnutrition, particularly when it comes to child survival. Half of all deaths globally among children under five are directly or indirectly attributable to malnutrition, a major issue in developing countries [8]. I. Related work Several studies investigated perinatal mortality in Ethiopia using different methods. Dhaka et al [6], For a developing country like Bangladesh, malnutrition might be seen as a major problem. Since tomorrow's workforce will be made up of today's children, this directly affects Bangladesh's economic development [6][9]. Therefore, the most important area of research at present time is the prevention of childhood malnutrition. The purpose of the project is to categorize malnutrition using a deep learning technique to predictive modeling on important malnutrition traits to determine a child's malnutrition status who is between the ages of 0-59 months. To achieve this, the children's data from the Bangladesh Demographic and Health Survey (BDHS) 2014 are subjected to an Artificial Neural Network (ANN) technique[6][10]. This study delineates the categories used by a predictive algorithm to categorize nutritional status. For wasting, underweight, and stunting, the ANN technique exhibits the highest degree of accuracy. Finally, for both policymakers and physicians, determining the condition of malnutrition using a deep learning approach is the most scientific course of action. In order to identify the nutritional risk variables that are responsible, several statistical techniques have been examined. Among the techniques, linear regression and logistic regression are extensively researched for the detection of malnutrition in 0 to 59-month-old children [11] [12] [13]. Rule induction classifier with receiver operating curve (ROC), Nave Bayes [14], decision tree [15], and association rules are some of the models that can be used to explain a child's nutrition
  • 3. measurement level. Few studies have employed least squares calculations and variable analysis to determine the relationship between the chosen factors and malnutrition [16] [17] [18] [19]. As researcher knowledge, there is only study conducted based on either nutritional factors or maternal determinants to predict infant mortality and identify the risk factors by using statistical techniques, since statistical techniques its weakness of limited dataset to analysis and do not extract hidden patterns from the complex dataset. As the researcher’s knowledge, there is no research conducted by taking nutritional and maternal determinants to predict infant mortality. II. Methodology A quick summary of the dataset is given in the next section. The preparation of data and suggested strategies for doing so using different tools and languages will be discussed in the sections that follow A. Data source The source of raw data was taken from the Ethiopian demographics health survey (EDHS) since from 2016 and 2019. It has been designed to cover both rural and urban under every division of Ethiopia country. Among rural and urban areas EDHS consists of a birth record, nutrition record, maternal record, and household record. Ethiopia’s central statistical agency collects raw data five years’ intervals and provides research for further analysis. In this study researcher used 16,283 raw data. B. Data preprocessing In data preprocessing researchers, to get the quality of data for model development researchers to follow the different steps of data preprocessing, filling missing values, outlier detection, removing redundancy, data transformation, imbalance problem handling, feature selection, and model deployment. For missing value handling, we used mode and imputation methods since the nature of the data is categorical. To detect and fill outliers researcher used a box plot and remove them by using the interquartile range (IQR). To transform data researcher used binning and discretization techniques. In these studies we have an imbalance in which 87% alive and 13% died, to handle this problem, according to [20] [21][22], we applied systematic minority over sampling techniques(SMOTE). After we applied SMOTE have to get data 30,014 datasets. For finally all
  • 4. attributes do not use model development researcher used feature selection, in this study we used wrapper feature selection techniques which are a step forward and step backward feature selection applied. The step backward feature section scored the best accuracy of feature selection by taking 18 features and 2 features we recommended by domain experts. We deploy the model on flask framework python library and front end of HTML on a Heroku cloud platform. C. Proposed model Preprocessed data is now prepared to fit the deep learning model. Our deep learning model has been implemented with the Tensor flow. Data flow graphs are used by Tensor flow to create models. Building massive layers in an Artificial Neural Network (ANN) is necessary in order to examine our model. Our model is constructed using "Keras," a well-known package, and Tensor Flow is utilized to train the factors at the model's backend.
  • 5. Figure 1: Proposed Model Framework After initializing the artificial network, the model took 20 neurons as features in the input layer and 10 in the hidden layer. In the proposed model, ANN used three hidden layers after testing
  • 6. gradually one by one. As the researcher proposed to classify infant mortality from trained data, it sets the range (0, 1) of a linear function in ANN using the rectifier activation function applied in the hidden layer and sigmoid activation function in the output layer. As 80% of the data is taken as training data and fits a model which runs 1000-2000 epochs. Here each epoch is considered as one forward and one backward propagation. Finally the most potent stochastic gradient descent optimizer parameter “adam” in which a perfect gradient descent algorism is used. Figure 2: Artificial neural network framework based on Tensor flow III. Result and discussion The purpose of the study is to determine being alive and died child from trained data, Random forest approaches show the best result with an accuracy of 93.29%, and also Decision Tree, Extreme Gradient Boosting, and ANN, with an accuracy of 91.47%, 91.44%, and 81.91% respectively. These test have done by 20% of the data with K-fold (k=10). We mainly implemented ANN on our datasets whereas other machine learning algorithms have been used such as Random forest, Decision tree, and Extreme Gradient boosting beside of ANN classifier.
  • 7. Evaluation Criteria Algorithms Random forest XGBoost Artificial neural network Decision Tree Accuracy (%) 93.29 91.44 81.91 91.47 Precision (%) 95.43 94.53 79.17 93.86 Recall (%) 90.87 87.88 86.39 88.67 ROC (%) 94.23 90.21 87.36 94.98 Table 1: Overall Algorithms Evaluation Figure 3: Accuracy of all algorithms Besides of Best performed algorithm (Random forest by ANN classifier) we have deployed on Cloud computing framework Heroku, which was designed by the front end by HTML and back end by python flask framework for potential users. As shown image and link” ”. IV. Conclusion The human brainpower may have restricted intellectual ability to predict infant mortality. At the same time, artificial intelligence can iterate considerable data but that may lack of logical ability.
  • 8. One of the most effective scientific approaches is to use deep learning mechanisms to determine infant mortality. This strategy may lower the number of deaths, particularly in a developing country like Ethiopia where a huge number of kids are affected by it. Maternal and child health is Bangladesh's top priority to achieve the Sustainable Development Goals (SDGs). Consequently, decision-makers and Healthcare professionals can quickly benefit from the depth learning of how to foresee infant mortality youngster in advance Reference [1] NICHD, “About Menstruation | NICHD - Eunice Kennedy Shriver National Institute of Child Health and Human Development.” pp. 1–1, 2019. Accessed: Jul. 20, 2022. [Online]. Available: https://www.nichd.nih.gov/health/topics/infant-mortality [2] F. H. Bitew, S. H. Nyarko, L. Potter, and C. S. Sparks, “Machine learning approach for predicting under-five mortality determinants in Ethiopia: evidence from the 2016 Ethiopian Demographic and Health Survey,” Genus, vol. 76, no. 1, 2020, doi: 10.1186/s41118-020-00106-2. [3] S. P. Nyoni and T. Nyoni, “Forecasting Infant Mortality Rate in Ghana Using a Machine Learning Algorithm,” Int. Res. J. Innov. Eng. Technol., vol. 5, no. 3, pp. 622–626, 2021, [Online]. Available: https://doi.org/10.47001/IRJIET/2021.503107 [4] S. Khare, S. Kavyashree, D. Gupta, and A. Jyotishi, “Investigation of Nutritional Status of Children based on Machine Learning Techniques using Indian Demographic and Health Survey Data,” Procedia Comput. Sci., vol. 115, pp. 338–349, 2017, doi: 10.1016/j.procs.2017.09.087. [5] M. Shahriar, M. S. Iqubal, S. Mitra, and A. K. Das, “A Deep Learning Approach to Predict Malnutrition Status of 0-59 Month ’ s Older Children in,” pp. 145–149, 2019. [6] A. Talukder and B. Ahammed, “Machine Learning Algorithms for Predicting Malnutrition among Under-Five Children in Bangladesh,” Nutrition, p. 110861, 2020, doi: 10.1016/j.nut.2020.110861. [7] M. Shahriar, M. S. Iqubal, S. Mitra, and A. K. Das, “A deep learning approach to predict malnutrition status of 0-59 month’s older children in Bangladesh,” Proc. - 2019 IEEE Int.
  • 9. Conf. Ind. 4.0, Artif. Intell. Commun. Technol. IAICT 2019, pp. 145–149, 2019, doi: 10.1109/ICIAICT.2019.8784823. [8] S. Khare, S. Kavyashree, D. Gupta, and A. Jyotishi, “ScienceDirect ScienceDirect Investigation of Nutritional Status of Children based on Machine Learning Techniques using Indian Demographic and Health Survey Data,” Procedia Comput. Sci., vol. 115, pp. 338–349, 2017, doi: 10.1016/j.procs.2017.09.087. [9] C. E. Beluzo, L. C. Alves, E. Silva, R. Bresan, N. Arruda, and T. Carvalho, “Machine learning to predict neonatal mortality using public health data from São Paulo - Brazil,” medRxiv, pp. 0–30, 2020. [10] M. Podda, D. Bacciu, A. Micheli, R. Bellù, G. Placidi, and L. Gagliardi, “A machine learning approach to estimating preterm infants survival: development of the Preterm Infants Survival Assessment (PISA) predictor,” Sci. Rep., vol. 8, no. 1, pp. 1–9, 2018, doi: 10.1038/s41598-018-31920-6. [11] A. K. Das et al., “Big media healthcare data processing in cloud: a collaborative resource management perspective,” Cluster Comput., vol. 20, no. 2, pp. 1599–1614, Mar. 2017, doi: 10.1007/s10586-017-0785-8. [12] L. Abera, T. Dejene, and T. Laelago, “Prevalence of malnutrition and associated factors in children aged 6-59 months among rural dwellers of damot gale district, south Ethiopia: Community based cross sectional study,” Int. J. Equity Health, vol. 16, no. 1, pp. 1–8, 2017, doi: 10.1186/s12939-017-0608-9. [13] S. Das and R. M. Rahman, “Application of ordinal logistic regression analysis in determining risk factors of child malnutrition in Bangladesh,” 2011. doi: 10.1186/1475- 2891-10-124. [14] Z. Markos, “Predicting Under Nutrition Status of Under-Five Children Using Data Mining Techniques: The Case of 2011 Ethiopian Demographic and Health Survey,” J. Heal. Med. Informatics, vol. 5, no. 2, 2014, doi: 10.4172/2157-7420.1000152. [15] S. Vijayakumar, M. G. Deepika, A. Jyotishi, and D. Gupta, “Factors affecting infant mortality rate in India: An analysis of Indian states,” Adv. Intell. Syst. Comput., vol. 530,
  • 10. pp. 707–719, 2016, doi: 10.1007/978-3-319-47952-1_57. [16] A. Tashnim, S. Nowshin, F. Akter, and A. K. Das, “Interactive interface design for learning numeracy and calculation for children with autism,” in 2017 9th International Conference on Information Technology and Electrical Engineering, ICITEE 2017, Jul. 2017, vol. 2018-Janua, pp. 1–6. doi: 10.1109/ICITEED.2017.8250507. [17] A. Tashnim, S. Nowshin, F. Akter, and A. K. Das, “Interactive interface design for learning numeracy and calculation for children with autism,” in 2017 9th International Conference on Information Technology and Electrical Engineering, ICITEE 2017, 2017, vol. 2018-Janua, pp. 1–6. doi: 10.1109/ICITEED.2017.8250507. [18] M. Arimond and M. T. Ruel, “Community and International Nutrition Dietary Diversity Is Associated with Child Nutritional Status: Evidence from 11 Demographic and Health Surveys 1,2,” J. Nutr, vol. 134, no. August 2004, pp. 2579–2585, 2004, [Online]. Available: https://academic.oup.com/jn/article-abstract/134/10/2579/4688437 [19] B. A. Abuya, J. Ciera, and E. Kimani-Murage, “Effect of mother’s education on child’s nutritional status in the slums of Nairobi,” BMC Pediatr., vol. 12, no. 1998, 2012, doi: 10.1186/1471-2431-12-80. [20] H. A. Khorshidi and U. Aickelin, “A Synthetic Over-sampling with the Minority and Majority classes for imbalance problems,” arXiv, pp. 1–12, 2020. [21] N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, “snopes.com: Two- Striped Telamonia Spider,” J. Artif. Intell. Res., vol. 16, no. Sept. 28, pp. 321–357, 2002, [Online]. Available: https://arxiv.org/pdf/1106.1813.pdf%0Ahttp://www.snopes.com/horrors/insects/telamonia. asp [22] N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, “SMOTE: Synthetic minority over-sampling technique,” J. Artif. Intell. Res., vol. 16, pp. 321–357, Jun. 2002, doi: 10.1613/jair.953.