Efficient inventory management is pivotal for manufacturing companies striving to maintain operational excellence, minimize costs, and meet dynamic market demands. Traditional inventory management systems, while functional, often fall short in addressing complex supply chain challenges such as real-time visibility, demand variability, and integration with modern technologies. This study explores the development of an integrated inventory management model designed to optimize inventory control, enhance decision-making, and reduce operational inefficiencies. By leveraging advanced technologies, including IoT, AI, and ERP systems, the proposed model integrates demand forecasting, inventory optimization, and supplier collaboration into a cohesive framework. Data-driven insights and predictive analytics form the cornerstone of this approach, enabling manufacturing companies to adapt to shifting market conditions seamlessly. The research evaluates the model's performance through simulations and case studies, highlighting significant improvements in inventory turnover, cost reduction, and operational agility. This study provides a pathway for manufacturing companies to transition to scalable, efficient, and technologically advanced inventory management systems.

Aim: The main objective is to incorporate the major foetal parameters – biparietal diameter, head circumference, abdominal circumference and femur length for prediction of gestational age through ultrasonography between 10th and 42nd weeks of gestation and try to do a simultaneous comparative study with gestational age predicted by last menstrual period.

Methods: The study has been conducted particularly on the population of Bangladesh. It has been done on 229 Bangladeshi women who had usual singleton foetuses, with evidence of menstrual dates by sonography before fourteen weeks of gestation. Foetal anatomical structures have been scanned and measured at the time of sonographic inspection. For each patient, in addition to the four foetal parameters such as Biparietal Diameter (BPD), Head Circumference (HC), Abdominal Circumference (AC) and Femur Length (FL), the other parameters like Gestational Age (GA) by Last Menstrual Period (LMP) as well as by Ultrasonography (USG) have been recorded. Here we have adopted non-linear regression models in order to predict the response on gestational age. Usually, different modelling methods have been used for this purpose.

 Results: The logarithmic models normally presented better results if gestational age was predicted based on a single parameter than polynomial models whereas if all predictor variables were considered together, then Nernst model may turn out to be the best one. Also, it was seen that the accuracy level of gestational age predicted by ultrasonography was slightly more accurate than that determined by last menstrual period. 

Methods: The study has been conducted particularly on the population of Bangladesh. It has been done on 229 Bangladeshi women who had usual singleton foetuses, with evidence of menstrual dates by sonography before fourteen weeks of gestation. Foetal anatomical structures have been scanned and measured at the time of sonographic inspection. For each patient, in addition to the four foetal parameters such as Biparietal Diameter (BPD), Head Circumference (HC), Abdominal Circumference (AC) and Femur Length (FL), the other parameters like Gestational Age (GA) by Last Menstrual Period (LMP) as well as by Ultrasonography (USG) have been recorded. Here we have adopted non-linear regression models in order to predict the response on gestational age. Usually, different modelling methods have been used for this purpose.

Results: The logarithmic models normally presented better results if gestational age was predicted based on a single parameter than polynomial models whereas if all predictor variables were considered together, then Nernst model may turn out to be the best one. Also, it was seen that the accuracy level of gestational age predicted by ultrasonography was slightly more accurate than that determined by last menstrual period. 

Conclusions: There is a high degree of association among the different foetal parameters. Further, there is a high degree of association between the gestational ages by LMP and that by USG. Prediction of gestational ages by USG technique gives a good degree of accuracy and hence can be a reliable technique for estimation of gestational ages.