Using Neural Networks with Different Target Settings to Predict Maternal Health Risks

Sarawut Meesri; Somkid Amornsamankul; Pawalai Kraipeerapun

doi:10.1109/CICN67655.2025.11368035

Using Neural Networks with Different Target Settings to Predict Maternal Health Risks

Sarawut Meesri
, Somkid Amornsamankul
, Pawalai Kraipeerapun

Ramkhamhaeng University
Mahidol University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

This paper proposes a technique for training neural networks with multiple outputs using different target settings. Three neural networks with the same configuration are set up with different targets. They are trained using the same data to predict different outputs, which are then combined to produce the final result. Maternal health risk dataset from the UC Irvine machine learning repository is used to test the proposed technique. This technique can achieve better accuracy than an ensemble neural network and stacking neural network trained with the original targets. In addition, the proposed technique can give better accuracy when combined with cascade generalization.

Original language	English
Title of host publication	2025 17th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2025
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	2284-2288
Number of pages	5
ISBN (Electronic)	9798331587338
DOIs	https://doi.org/10.1109/CICN67655.2025.11368035
Publication status	Published - 2025
Externally published	Yes
Event	17th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2025 - Hybrid, Goa, India Duration: 20 Dec 2025 → 21 Dec 2025

Publication series

Name	2025 17th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2025

Conference

Conference	17th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2025
Country/Territory	India
City	Hybrid, Goa
Period	20/12/25 → 21/12/25

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

backpropagation
cascade generalization
maternal health;
multiclass classification
neural network

Access to Document

10.1109/CICN67655.2025.11368035

Cite this

Meesri, S., Amornsamankul, S., & Kraipeerapun, P. (2025). Using Neural Networks with Different Target Settings to Predict Maternal Health Risks. In 2025 17th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2025 (pp. 2284-2288). (2025 17th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2025). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CICN67655.2025.11368035

Meesri, Sarawut ; Amornsamankul, Somkid ; Kraipeerapun, Pawalai. / Using Neural Networks with Different Target Settings to Predict Maternal Health Risks. 2025 17th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2025. Institute of Electrical and Electronics Engineers Inc., 2025. pp. 2284-2288 (2025 17th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2025).

@inproceedings{9f040ae2d8274b0da9d8d81bdb07cea6,

title = "Using Neural Networks with Different Target Settings to Predict Maternal Health Risks",

abstract = "This paper proposes a technique for training neural networks with multiple outputs using different target settings. Three neural networks with the same configuration are set up with different targets. They are trained using the same data to predict different outputs, which are then combined to produce the final result. Maternal health risk dataset from the UC Irvine machine learning repository is used to test the proposed technique. This technique can achieve better accuracy than an ensemble neural network and stacking neural network trained with the original targets. In addition, the proposed technique can give better accuracy when combined with cascade generalization.",

keywords = "backpropagation, cascade generalization, maternal health;, multiclass classification, neural network",

author = "Sarawut Meesri and Somkid Amornsamankul and Pawalai Kraipeerapun",

note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; 17th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2025 ; Conference date: 20-12-2025 Through 21-12-2025",

year = "2025",

doi = "10.1109/CICN67655.2025.11368035",

language = "English",

series = "2025 17th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2025",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "2284--2288",

booktitle = "2025 17th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2025",

}

Meesri, S, Amornsamankul, S & Kraipeerapun, P 2025, Using Neural Networks with Different Target Settings to Predict Maternal Health Risks. in 2025 17th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2025. 2025 17th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2025, Institute of Electrical and Electronics Engineers Inc., pp. 2284-2288, 17th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2025, Hybrid, Goa, India, 20/12/25. https://doi.org/10.1109/CICN67655.2025.11368035

Using Neural Networks with Different Target Settings to Predict Maternal Health Risks. / Meesri, Sarawut; Amornsamankul, Somkid; Kraipeerapun, Pawalai.
2025 17th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2025. Institute of Electrical and Electronics Engineers Inc., 2025. p. 2284-2288 (2025 17th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2025).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Using Neural Networks with Different Target Settings to Predict Maternal Health Risks

AU - Meesri, Sarawut

AU - Amornsamankul, Somkid

AU - Kraipeerapun, Pawalai

PY - 2025

Y1 - 2025

N2 - This paper proposes a technique for training neural networks with multiple outputs using different target settings. Three neural networks with the same configuration are set up with different targets. They are trained using the same data to predict different outputs, which are then combined to produce the final result. Maternal health risk dataset from the UC Irvine machine learning repository is used to test the proposed technique. This technique can achieve better accuracy than an ensemble neural network and stacking neural network trained with the original targets. In addition, the proposed technique can give better accuracy when combined with cascade generalization.

AB - This paper proposes a technique for training neural networks with multiple outputs using different target settings. Three neural networks with the same configuration are set up with different targets. They are trained using the same data to predict different outputs, which are then combined to produce the final result. Maternal health risk dataset from the UC Irvine machine learning repository is used to test the proposed technique. This technique can achieve better accuracy than an ensemble neural network and stacking neural network trained with the original targets. In addition, the proposed technique can give better accuracy when combined with cascade generalization.

KW - backpropagation

KW - cascade generalization

KW - maternal health;

KW - multiclass classification

KW - neural network

UR - https://www.scopus.com/pages/publications/105034669517

U2 - 10.1109/CICN67655.2025.11368035

DO - 10.1109/CICN67655.2025.11368035

M3 - Conference contribution

AN - SCOPUS:105034669517

T3 - 2025 17th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2025

SP - 2284

EP - 2288

BT - 2025 17th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2025

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 17th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2025

Y2 - 20 December 2025 through 21 December 2025

ER -

Meesri S, Amornsamankul S, Kraipeerapun P. Using Neural Networks with Different Target Settings to Predict Maternal Health Risks. In 2025 17th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2025. Institute of Electrical and Electronics Engineers Inc. 2025. p. 2284-2288. (2025 17th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2025). doi: 10.1109/CICN67655.2025.11368035

Using Neural Networks with Different Target Settings to Predict Maternal Health Risks

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this