Pediatric Nutrition Assessment is a pervasive global health crisis that severely affects both physical growth and cognitive development in children. Existing manual assessment methods for evaluating nutritional status are often inefficient, inconsistent, and unable to support timely intervention. To address these challenges, this project proposes the development of a Child Nutrition Monitoring Deficiency Alert System (CNDAS), an automated solution that integrates multiple data sources to provide comprehensive nutritional analysis. The system uses an Anthropometric Feature Extraction Engine to process key indicators such as height, weight, and BMI. This data, along with dietary logs, is evaluated using a Rule-Based Model based on WHO standards to determine nutritional status and detect deficiencies. For advanced analysis, a Machine Learning module using a Weighted Random Forest classifier predicts the severity of malnutrition accurately. Furthermore, the system includes a Behavioral Analysis Module and Context-Aware Recommendation Logic to generate personalized, adaptive, and cost-effective dietary and remedial suggestions. These recommendations consider not only conventional medical guidance but also holistic approaches such as Ayurveda, naturopathy, homeopathy, and home remedies. All system interactions and data processing are managed through a Conversational AI Chabot Framework, which provides care-givers with real-time assistance, personalized guidance, and answers to nutritional queries, ensuring a scalable and data-driven platform for effective child nutrition monitoring and intervention.

This study presents a machine learning-driven framework for detecting malnutrition levels in children by analyzing a combination of health, dietary, and behavioral parameters. The system utilizes features such as age, height, weight, BMI, food intake patterns, and lifestyle factors to evaluate a child’s nutri-tional condition. The architecture of the system is organized into multiple layers, including the user interface, processing module, and data storage component. Users can input child-related data through the interface, while the processing layer handles data validation, preprocessing, feature extraction, and prediction using the Weighted Random Forest model. The out-comes are then displayed and stored for future reference. The selection of the Weighted Random Forest algorithm is based on its ability to effectively manage complex datasets and address class imbalance issues. Additionally, the system incorporates rule-based evaluation aligned with standard health guidelines, which enhances the interpretability and consistency of the predictions. Experimental results indicate that the proposed approach performs well in identifying malnutrition levels. By evaluating multiple factors simultaneously, the system can detect potential risks at an early stage and provide suitable recommendations. Beyond prediction, the system supports caregivers by offering actionable guidance for improving child nutrition.

[1]Lavanya M, A. Ashwini, G. Preemi, B. P. Prathaban, A. A. Alvin, and J. S. Shemona, “A Deep Dive into Smart-Based Malnutrition Detection Using DenseNet-121 Deep Learning Algorithm,” in Pro-ceedings of the 2025 International Conference on Circuit, Power and Computing Technologies (ICCPCT), IEEE, 2025. Available: https://ieeexplore.ieee.org/document/11176513 [2]F. H. Bitew, C. S. Sparks, and S. H. Nyarko, “Machine Learn-ing Algorithms for Predicting Undernutrition among Under-Five Children in Ethiopia,” Public Health Nutrition, 2021. Available: https://doi.org/10.1017/S1368980021004262 [3]T. Tran, C. Vo, H. Nguyen, T. Tran, and N. Nguyen, “Development of Effective Malnutrition Level Detection Models,” in Proceedings of the 2025 Biomedical Engineering International Conference (BMEiCON), IEEE, 2025. Available: https://doi.org/10.1109/BMEICON66226.2025.11113717 [4]C. Anjanamma, K. Shilpa, G. Sirisha, C. V. Lakshmi Narayana, B. Sravani, and V. Vivekanandhan, “Personalized Food Nutrient Recommendations for Kids using AI and Behavior Analysis,” in Proceedings of the 2024 International Conference on Communi-cation and Electronics Systems (ICCES), IEEE, 2024. Available: https://doi.org/10.1109/ICCES63552.2024.10859422 [5]A. Thapar and M. Goyal, “A fuzzy expert system for diagnosis of malnutrition in children,” in Proceedings of IEEE Conference, IEEE. Available: https://ieeexplore.ieee.org/document/7415677 [6]D. Lo´pez-Carr, K. M. Mwenda, N. G. Pricope, P. C. Kyriakidis, M. M. Jankowska, J. Weeks, C. Funk, G. Husak, and J. Michaelsen, “A Spatial Analysis of Climate-Related Child Malnutrition in the Lake Victoria Basin,” in Proceedings of IEEE International Geoscience and Remote Sensing Symposium (IGARSS), IEEE, 2015. Available: https://doi.org/10.1109/IGARSS.2015.7326465 [7]A. S. Vaidya, G. Makkena, V. Srihari, M. B. Srinivas, and S. K. Rao, “A Sustainable Solution for Monitoring Malnutrition in Children in Developing Countries,” in Proceedings of IEEE Conference, IEEE, 2013. Available: https://ieeexplore.ieee.org/document/6556940 [8]S. Mannolkar, S. M. George, M. R, N. P. Divanapu, and D. P. Bharathi, “Assistive System for Monitoring Malnutrition in Children: MalnoCare,” in Proceedings of the 5th International Conference on Soft Computing for Security Applications (ICSCSA), IEEE, 2025. Available: https://doi.org/10.1109/ICSCSA66339.2025.11171179 [9]V. G. Biradar and K. K. Naik, “Classification of Children as Malnour-ished and Healthy Category Using ResNet18 Model,” in Proceedings of the 2023 International Conference on Ambient Intelligence, Knowledge Informatics and Industrial Electronics (AIKIIE), IEEE, 2023. Available: https://doi.org/10.1109/AIKIIE60097.2023.10390460 [10]R. A. Putri, S. Sendari, and T. Widiyaningtyas, “Classification of Toddler Nutrition Status with Anthropometry Calculation Using Na¨ıve Bayes Algorithm,” in Proceedings of IEEE Conference,IEEE,2018.Available: https://ieeexplore.ieee.org/document/8626140 [11]S. N. Ariyadasa, L. K. Munasinghe, S. H. D. Senanayake, and N. A. S. Fernando, “Data Mining Approach to Minimize Child Malnutrition in Developing Countries: Sri Lankan Context,” in Proceedings of the Inter-national Conference on Advances in ICT for Emerging Regions (ICTer), IEEE,2012.Available: https://ieeexplore.ieee.org/document/6423082 [12]B. Tejavardhan, S. M. George, and J. V. Alamelu, “Deep Learning based Detection and Classification of Child Malnutrition,” in Proceed-ings of the 2024 Second International Conference on Self Sustain-able Artificial Intelligence Systems (ICSSAS), IEEE, 2024. Available: https://doi.org/10.1109/ICSSAS64001.2024.10760891 [13]C. Aguilar, J. Tucta, and J. Santisteban, “Detection of Malnutrition in Children Under 5 Years of Old Using Deep Learning,” in Proceedings of the 2025 International Conference on Digital Arts, Media and Technology (DAMT) and ECTI Northern Section Conference (NCON), IEEE, 2025. Available: https://doi.org/10.1109/ECTIDAMTNCON64748.2025.10962087 [14]M. T. Zumma, M. A. Rahaman, N. N. I. Prova, T. Haque, J. C. J. Bose, and R. A. Youki, “Early Detection of Childhood Mal-nutrition using Survey Data and Machine Learning Approaches,” in Proceedings of the 2025 International Conference on Sentiment Analysis and Deep Learning (ICSADL), IEEE, 2025. Available: https://doi.org/10.1109/ICSADL65848.2025.10933198 [15]A.F.Najwa, Indwiarti, and P.H.Gunawan, “Enhancing Multiclass Clas-sification of Child Nutritional Status Using KNN and Random Forest with SMOTE,” in Proc. IEEE Int. Conf. Intelligent Cy-bernetics Technology & Applications (ICICyTA), 2024. Available: https://doi.org/10.1109/ICICYTA64807.2024.10912991 [16]H. M. C. Nirmani and U. P. Kudagamage, “Ensemble Approach for Early Prediction of Malnutrition Level of Children: A Case Study on Children Under Five Years Old,” in Proceedings of the 2024 4th International Conference on Advanced Research in Computing (ICARC), IEEE, 2024. Available: https://doi.org/10.1109/ICARC61713.2024.10499742 [17]M. K. I. Al-juboori and M. Ilyas, “Expert System for Clas-sification of Nutrition in Young Children,” in Proceedings of the 2022 International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT), IEEE, 2022. Available: https://doi.org/10.1109/ISMSIT56059.2022.9932657 [18]M. Singh, H. Gupta, R. Chaudhary, A. K. Khan, S. Shukla, and K. Singh, “Integrating ResNet-101 for the Prediction of Malnutrition in Children,” in Proceedings of the 2025 12th International Conference on Reliability, Infocom Technologies and Optimization (ICRITO), IEEE, 2025. Available: https://doi.org/10.1109/ICRITO66076.2025.11241626 [19]Ibraheem, Q. N. Kamal, A. Raza, S. Ayaz, and M. Mubarik, “NutriVision: Early Detection of Malnutrition Using Advanced Deep Learning,” in Proceedings of the 2025 International Conference on Emerging Technologies in Electronics, Computing, and Communication (ICETECC), IEEE, 2025. Available: https://doi.org/10.1109/ICETECC65365.2025.11070276 [20]M.Zarlis, F.Ernawan, T.Oktavia, R.Buaton, and Z.Hidayat, “Optimizing the Discovery of Stunting Time Series Rules Using the Rule Base Time Series (RBT) and J-Measure Methods,” in Proc. IEEE 5th Int. Conf. Computational Science & Information Management (ICoCSIM), 2024. Available: https://doi.org/10.1109/ICOCSIM65098.2024.00046