PDF(Pubmed)
Abstract：
The goal of this research is to create an ensemble deep learning model for Internet of Things (IoT) applications that specifically target remote patient monitoring (RPM) by integrating long short-term memory (LSTM) networks and convolutional neural networks (CNN). The work tackles important RPM concerns such early health issue diagnosis and accurate real-time physiological data collection and analysis using wearable IoT devices. By assessing important health factors like heart rate, blood pressure, pulse, temperature, activity level, weight management, respiration rate, medication adherence, sleep patterns, and oxygen levels, the suggested Remote Patient Monitor Model (RPMM) attains a noteworthy accuracy of 97.23%. The model\'s capacity to identify spatial and temporal relationships in health data is improved by novel techniques such as the use of CNN for spatial analysis and feature extraction and LSTM for temporal sequence modeling. Early intervention is made easier by this synergistic approach, which enhances trend identification and anomaly detection in vital signs. A variety of datasets are used to validate the model\'s robustness, highlighting its efficacy in remote patient care. This study shows how using ensemble models\' advantages might improve health monitoring\'s precision and promptness, which would eventually benefit patients and ease the burden on healthcare systems.
摘要：
这项研究的目标是为物联网（IoT）应用创建一个集成的深度学习模型，该模型通过集成长短期记忆（LSTM）网络和卷积神经网络（CNN）来专门针对远程患者监护（RPM）。这项工作解决了重要的RPM问题，例如早期健康问题诊断以及使用可穿戴物联网设备进行准确的实时生理数据收集和分析。通过评估心率等重要的健康因素，血压,脉搏,温度,活动水平,体重管理,呼吸频率,药物依从性,睡眠模式，和氧气水平，建议的远程患者监护模型(RPMM)达到了显著的97.23%的准确度.通过使用CNN进行空间分析和特征提取以及LSTM进行时间序列建模等新颖技术，提高了模型识别健康数据中空间和时间关系的能力。这种协同方法使早期干预变得更容易，这增强了生命体征的趋势识别和异常检测。使用各种数据集来验证模型的鲁棒性，强调其在远程患者护理中的功效。这项研究表明，使用集成模型的优势可能会提高健康监测的准确性和及时性，这最终将使患者受益并减轻医疗保健系统的负担。
