In 2019, the outbreak of Acute Encephalitis Syndrome (AES) outbreak occurred in the Bihar region of India. AES, a viral infection that affects the immune system of the human, is recognized as public health concern globally. The objective of this study is to monitor and prevent the spread of Encephalitis (ENCPH). Spatio-temporal-based Temporal-Recurrent Neural Network (T-RNN) prediction model is used to control the outbreak and generate an alarming signal to the medical caregiver in case of abnormality. T-RNN model is appended with novel Self-Organized Mapping (SOM) technique for outbreak visualization geographically. The current work presents a Tri-logical IoT-fog-cloud (TIFC) model to collect AES data for monitoring, and controlling the outbreak over the Spatio-temporal manner. Different events are correlated over the Spatio-temporal patterns in the form of a time-series granule at a different timestamps. Fuzzy C-Means (FCM) classifier is used to analyze the category of a patient based on health-related data parameters. Henceforth, for effective health-oriented decision-making and information deliverance to the user, a prediction model based on Spatio-temporal is used to manage the medical resources. For validation purposes, numerous simulations have been performed over real-data sets, and the results are compared with different state-of-the-art prediction models. Based on simulations, it can be concluded that the proposed system has outperformed other decision models in terms of statistical parameters including accuracy, f-measure, and reliability. Future research needs to focus on the security aspect for prevention and control for infectious viruses.

2019年，印度比哈尔邦爆发了急性脑炎综合症（AES）。AES是一种影响人类免疫系统的病毒感染，已被全球公认为公共健康问题。这项研究的目的是监测和预防脑炎（ENCPH）的传播。基于时空的时空递归神经网络（T-RNN）预测模型用于控制爆发并在发生异常情况时向医疗护理人员生成警报信号。T-RNN模型附加了新颖的自组织映射（SOM）技术，可在地理上可视化爆发。当前的工作提出了一种三态物联网雾云模型（TIFC），以收集AES数据进行监视，并控制时空方式的爆发。在不同的时间戳上，不同的事件以时间序列颗粒的形式在时空模式上相关。模糊C均值（FCM）分类器用于基于与健康相关的数据参数来分析患者的类别。此后，为了有效地进行面向健康的决策和向用户的信息传递，基于时空的预测模型用于管理医疗资源。为了进行验证，已经对真实数据集执行了许多模拟，并将结果与​​不同的最新预测模型进行了比较。基于仿真，可以得出结论，该系统在统计参数（包括准确性，f度量和可靠性）方面优于其他决策模型。