Domestic veterinary care is contemplated as one of the significant domains of the healthcare industry. Conspicuously, this research presents a Smart Home-based healthcare monitoring framework for domesticated animals in real-time. The research work employs the Internet of Things (IoT)-based data acquisition in the ambient environment of the home. Acquired IoT-data is pre-processed for feature extraction over the Fog–Cloud computing platform. Moreover, a temporal data granule is formulated using the Temporal Data mining technique, which is used to quantify healthcare vulnerability in terms of Scale of Health Adversity (SoHA) and Temporal Adversity Estimate (TAE). Based on this, a Multi-scaled Long Short Term Memory (M-LSTM) based vulnerability prediction is performed for preventive veterinary healthcare services. Moreover, a fog-assisted real-time alert generation module is presented in the proposed framework to notify the concerned veterinary doctor in the case of a medical emergency. To validate the proposed framework, the experimental simulations are performed over challenging dataset comprising of nearly 34,120 instances. Results show that the presented framework is able to register enhanced performance in comparison to several state-of-the-art decision-making techniques in terms of Temporal Effectiveness, Classification Efficiency, Prediction Efficacy, and System Stability.

家庭兽医护理被认为是医疗保健行业的重要领域之一。引人注目的是，这项研究提出了一种基于智能家居的用于家养动物的实时医疗监控框架。该研究工作在家庭的周围环境中采用了基于物联网（IoT）的数据采集。采集的物联网数据经过预处理，以通过Fog-Cloud计算平台进行特征提取。此外，使用时间数据挖掘技术制定了时间数据颗粒，该技术用于根据健康逆境规模（SoHA）和时间逆境估计（TAE）量化医疗保健脆弱性。基于此，针对预防性兽医医疗服务执行了基于多尺度长期短期记忆（M-LSTM）的漏洞预测。此外，在提议的框架中提供了一个雾辅助实时警报生成模块，以在发生医疗紧急情况时通知有关兽医。为了验证所提出的框架，对包含近34120个实例的具有挑战性的数据集进行了实验仿真。结果表明，与几种最先进的决策技术相比，本文提出的框架在时间有效性，分类效率，预测功效和系统稳定性方面均具有更高的性能。