Detecting Postpartum Depression Stages in New Mothers: A Comparative Study of Novel LSTM-CNN vs. Random Forest

P. Srivatsav, S. Nanthini

2023

Abstract

A Novel long-short term memory with convolutional neural networks (LSTM-CNN) is used to predict postpartum depression and compared it with Random forest (RF) Algorithm. Materials and Methods: For this research two groups were taken: The Novel Long-Short Term Memory with Convolutional Neural Networks (LSTM-CNN) and for comparison the Random forest (RF) Algorithm was considered. After careful consideration each with a sample size of 20 to help in this research. Results: The outcomes of the study are shown in the following table (LSTM-CNN). The mean accuracy of the LSTM -CNN is 77.75% and the Random Forest (RF) Algorithm model is 72.12%, respectively. The significance of the Independent sample t-test is evident with a p-value of 0.04 (p < 0.05), underscoring the statistical significance of the comparison between the LSTM-CNN model and the Random Forest algorithm in the study. Conclusion: The LSTM-CNN technique outperformed the Random Forest(RF) Algorithm and other machine learning algorithms in terms of accuracy, and deep learning algorithms have generally showed promise in the prediction of Postpartum depression.

Paper Citation

in Harvard Style

Srivatsav P. and Nanthini S. (2023). Detecting Postpartum Depression Stages in New Mothers: A Comparative Study of Novel LSTM-CNN vs. Random Forest. In Proceedings of the 1st International Conference on Artificial Intelligence for Internet of Things: Accelerating Innovation in Industry and Consumer Electronics - Volume 1: AI4IoT; ISBN 978-989-758-661-3, SciTePress, pages 109-115. DOI: 10.5220/0012569700003739

in Bibtex Style

@conference{ai4iot23,
author={P. Srivatsav and S. Nanthini},
title={Detecting Postpartum Depression Stages in New Mothers: A Comparative Study of Novel LSTM-CNN vs. Random Forest},
booktitle={Proceedings of the 1st International Conference on Artificial Intelligence for Internet of Things: Accelerating Innovation in Industry and Consumer Electronics - Volume 1: AI4IoT},
year={2023},
pages={109-115},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012569700003739},
isbn={978-989-758-661-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Artificial Intelligence for Internet of Things: Accelerating Innovation in Industry and Consumer Electronics - Volume 1: AI4IoT
TI - Detecting Postpartum Depression Stages in New Mothers: A Comparative Study of Novel LSTM-CNN vs. Random Forest
SN - 978-989-758-661-3
AU - Srivatsav P.
AU - Nanthini S.
PY - 2023
SP - 109
EP - 115
DO - 10.5220/0012569700003739
PB - SciTePress