During pregnancy calcium demand increases due to increase requirement by the developing foetus. This demand is met by dietary calcium intake. Physiological changes in pregnancy tend to lower calcium and calcium homeostasis is maintained by various hormones. The present study was done to find association of sociodemographic factors of the pregnant women with hypocalcaemia. Material and methods: 100 women in their third trimester of pregnancy were included in the study after obtaining written informed consent. After detail history and examination, 5 ml venous blood is collected to measure serum ionic calcium. Data were entered in to MS Excel sheet and analysed. Results: Normal serum ionic calcium range is 4.2 – 5.5 mg%. Out of 100 women 36% women had hypocalcaemia. There was no significant association between hypocalcaemia and age (p=0.8), residence (p=0.6), religion (p=0.1), socio-economic status (p=0.8). There was significant association between hypocalcaemia and literacy status (p-0.02). Women with past history of preterm birth and abortion had more risk of having hypocalcaemia. There was a negative correlation between maternal age and mean serum ionic calcium level. Conclusion: Hypocalcaemia is common in pregnancy. Hypocalcaemia was more common in women who were above 25 years of age, muslim, illiterate, belonging to lower and middle socio-economic status and multiparous. Risk of hypocalcaemia was more in women with gestational age below 34 weeks. All women in their antenatal period should be screened for hypocalcaemia and calcium should be supplemented routinely to all women during antenatal period. Keywords: Hypocalcaemia, pregnancy, socio-demographic factors

This study presents the development of a Feed-Forward Neural Network (FFNN)-based model for security of Internet of Things (IoT) network protocols. The proposed method applied in the execution of the study involves data collection, preprocessing, feature selection, and model training using the CIC-IoT 2022 dataset, which includes normal and attack traffic from various IoT devices. In the study, Synthetic Minority Oversampling Technique (SMOTE) was used for data balancing, Principal Component Analysis (PCA) technique was used for feature selection and hyperparameter optimization were employed to enhance the performance of the model during training. The system was simulated in the NS-3 environment to replicate real-world IoT network conditions, and its effectiveness was evaluated using metrics such as accuracy, precision, recall, and F1-score. The results demonstrated that the FFNN-based model achieves an average validation accuracy of 89.7%, precision of 88.9%, recall of 86.9%, and an F1-score of 87.9%. The system results showcased robustness in detecting various attacks, including DoS, brute force and RTSP attacks in mixed traffic scenarios, meanwhile this study serves as a strong foundation for leveraging deep learning techniques to enhance IoT network security protocols.