Department of ECE, Delhi Technological University, Delhi 110042, India.
Department of Electronics & Communication Engineering, MNIT, Jaipur.
Math Biosci Eng. 2021 Oct 13;18(6):8727-8757. doi: 10.3934/mbe.2021431.
Healthcare systems constitute a significant portion of smart cities infrastructure. The aim of smart healthcare is two folds. The internal healthcare system has a sole focus on monitoring vital parameters of patients. The external systems provide proactive health care measures by the surveillance mechanism. This system utilizes the surveillance mechanism giving impetus to healthcare tagging requirements on the general public. The work exclusively deals with the mass gatherings and crowded places scenarios. Crowd gatherings and public places management is a vital challenge in any smart city environment. Protests and dissent are commonly observed crowd behavior. This behavior has the inherent capacity to transform into violent behavior. The paper explores a novel and deep learning-based method to provide an Internet of Things (IoT) environment-based decision support system for tagging healthcare systems for the people who are injured in crowd protests and violence. The proposed system is intelligent enough to classify protests into normal, medium and severe protest categories. The level of the protests is directly tagged to the nearest healthcare systems and generates the need for specialist healthcare professionals. The proposed system is an optimized solution for the people who are either participating in protests or stranded in such a protest environment. The proposed solution allows complete tagging of specialist healthcare professionals for all types of emergency response in specialized crowd gatherings. Experimental results are encouraging and have shown the proposed system has a fairly promising accuracy of more than eight one percent in classifying protest attributes and more than ninety percent accuracy for differentiating protests and violent actions. The numerical results are motivating enough for and it can be extended beyond proof of the concept into real time external surveillance and healthcare tagging.
医疗保健系统构成智慧城市基础设施的重要组成部分。智能医疗保健的目的有两个。内部医疗系统仅专注于监测患者的重要参数。外部系统通过监控机制提供主动的医疗保健措施。该系统利用监控机制推动对公众的医疗保健标记要求。这项工作专门针对大规模集会和拥挤场所的情况。人群聚集和公共场所管理是任何智慧城市环境中的一个重要挑战。抗议和异议是常见的观察到的人群行为。这种行为有内在的能力转化为暴力行为。本文探索了一种新颖的基于深度学习的方法，为在人群抗议和暴力中受伤的人提供基于物联网 (IoT) 环境的决策支持系统，以标记医疗保健系统。拟议的系统足够智能，可以将抗议活动分为正常、中等和严重抗议类别。抗议活动的级别直接标记到最近的医疗保健系统，并生成对专业医疗保健专业人员的需求。该系统是参与抗议活动或被困在这种抗议环境中的人的优化解决方案。该解决方案允许为各种特殊人群聚集的紧急情况完全标记专业医疗保健专业人员。实验结果令人鼓舞，表明所提出的系统在分类抗议属性方面具有相当高的准确性，超过 81%，在区分抗议和暴力行为方面具有超过 90%的准确性。数值结果令人鼓舞，它可以从概念验证扩展到实时外部监控和医疗保健标记。
