Healthcare industry is the leading domain that has been revolutionized by the incorporation of Internet of Things (IoT) technology resulting in smart medical applications. Conspicuously, this study presents an effective system of home-centric Urine-based Diabetes (UbD) monitoring system. Specifically, the proposed system comprises of 4-layers for predicting and monitoring diabetes-oriented urine infection. The system layers including Diabetic Data Acquisition (DDA) layer, Diabetic Data Classification (DDC) layer, Diabetic-Mining and Extraction (DME) layer, and Diabetic Prediction and Decision Making (DPDM) layer allow an individual not exclusively to track his/her diabetes measure on regular basis but the prediction procedure is also accomplished so that prudent steps can be taken at early stages. Additionally, probabilistic measurement of UbD monitoring in terms of Level of Diabetic Infection (LoDI), which is cumulatively quantified as Diabetes Infection Measure (DIM) has been performed for predictive purposes using Recurrent Neural Network (RNN). Moreover, the existence of UbD is visualized based on the Self-Organized Mapping (SOM) procedure. To validate the proposed system, numerous experimental simulations were performed on datasets of 4 individuals. Based on the experimental simulation, enhanced results in terms of temporal delay, classification efficiency, prediction efficiency, reliability and stability were registered for the proposed system in comparison to state-of-the-art decision-making techniques.

医疗保健行业是领先的领域，它通过结合物联网 (IoT) 技术实现了智能医疗应用。值得注意的是，这项研究提出了一个有效的以家庭为中心的尿基糖尿病（UbD）监测系统。具体来说，所提出的系统由 4 层组成，用于预测和监测以糖尿病为导向的尿液感染。包括糖尿病数据采集 (DDA) 层、糖尿病数据分类 (DDC) 层、糖尿病挖掘和提取 (DME) 层以及糖尿病预测和决策 (DPDM) 层在内的系统层允许个人不仅仅跟踪他/她定期测量糖尿病，但也完成了预测程序，以便在早期阶段采取谨慎的步骤。此外，UbD 监测在糖尿病感染水平 (LoDI) 方面的概率测量，其累积量化为糖尿病感染测量 (DIM)，已使用循环神经网络 (RNN) 进行预测。此外，UbD 的存在是基于自组织映射 (SOM) 过程可视化的。为了验证所提出的系统，对 4 个人的数据集进行了大量实验模拟。基于实验模拟，与最先进的决策技术相比，所提出的系统在时间延迟、分类效率、预测效率、可靠性和稳定性方面得到了增强的结果。已经使用循环神经网络 (RNN) 进行了糖尿病感染测量 (DIM) 的累积量化，用于预测目的。此外，UbD 的存在是基于自组织映射 (SOM) 过程可视化的。为了验证所提出的系统，对 4 个人的数据集进行了大量实验模拟。基于实验模拟，与最先进的决策技术相比，所提出的系统在时间延迟、分类效率、预测效率、可靠性和稳定性方面得到了增强的结果。已经使用循环神经网络 (RNN) 进行了糖尿病感染测量 (DIM) 的累积量化，用于预测目的。此外，UbD 的存在是基于自组织映射 (SOM) 过程可视化的。为了验证所提出的系统，对 4 个人的数据集进行了大量实验模拟。基于实验模拟，与最先进的决策技术相比，所提出的系统在时间延迟、分类效率、预测效率、可靠性和稳定性方面得到了增强的结果。对 4 个人的数据集进行了大量实验模拟。基于实验模拟，与最先进的决策技术相比，所提出的系统在时间延迟、分类效率、预测效率、可靠性和稳定性方面得到了增强的结果。对 4 个人的数据集进行了大量实验模拟。基于实验模拟，与最先进的决策技术相比，所提出的系统在时间延迟、分类效率、预测效率、可靠性和稳定性方面得到了增强的结果。