Internet of things-enabled real-time health monitoring system using deep learning

Wu, Xingdong; Liu, Chao; Wang, Lijun; Bilal, Muhammad

doi:10.1007/s00521-021-06440-6

Cited by 35 publications

(21 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…How to analyze the massive physiological data of the patient and extract the hidden value from it is studied. Meaningful information has become a hot and difficult problem in the current medical field and data mining field [ 3 – 5 ].…”

Section: Introductionmentioning

confidence: 99%

Application of Deep Learning Technology in Predicting the Risk of Inpatient Death in Intensive Care Unit

Li¹,

Chen²,

Yan³

et al. 2021

Journal of Healthcare Engineering

View full text Add to dashboard Cite

The Intensive Care Unit (ICU) is an important unit for the rescue of critically ill patients in hospitals, and patient mortality is an important indicator to measure the level of ICU treatment. Currently, a variety of clinical scoring systems are used to evaluate the patient's condition and predict survival, but these systems require a lot of resources. However, due to the rapid development of artificial intelligence and deep learning, machine learning based methods have been used to study the survival prediction of ICU patients. Additionally, these methods have made significant progress, but there is still a distance from clinical application, and equally metric interpretability of the deep learning method is not very mature. Therefore, in this paper, we have proposed a predicting model for the life and death of ICU patients, which is primarily based on the Fuzzy ARTMAP model. With a thorough analysis of the existing ICU patient condition assessment and life and death prediction methods, we have observed that patient’s ICU monitoring information performs integrated analysis and extracts features according to the clinical characteristics of physiological indicators. Finally, fuzzy ARTMAP neural network is used to predict the life and death of patients. Likewise, prediction results are combined with the clinical scoring system and logistic regression, artificial neural network, support vector machine, and AdaBoost. Experimental results of these algorithms were compared, which verifies that the proposed method has outperformed the existing model. The main purpose of the proposed mode is to design a life and death prediction method for ICU patients, which has high predictive performance and is an acceptable method for clinical medical staff, where ICU monitoring data is used. Experimental results show that the method proposed has achieved better prediction performance and accuracy ratio, which provide theoretical reference for clinical application.

show abstract

Section: Introductionmentioning

confidence: 99%

Application of Deep Learning Technology in Predicting the Risk of Inpatient Death in Intensive Care Unit

Li¹,

Chen²,

Yan³

et al. 2021

Journal of Healthcare Engineering

View full text Add to dashboard Cite

show abstract

“…This is done with a supervised learning approach by a modified deep belief network in conjunction with the squirrel search algorithm as a feature selection method. A health monitoring system based on deep learning in the IoT context[ 23 ] is also developed to predict CVD. Similarly, Yeh et al [ 24 ] have used deep neural networks to analyze ECG signals to assess the patient's condition and give appropriate drugs.…”

Section: System Development Preliminariesmentioning

confidence: 99%

Internet of things-based health monitoring system for early detection of cardiovascular events during COVID-19 pandemic

Dami¹

2022

WJCC

View full text Add to dashboard Cite

The coronavirus disease 2019 (COVID-19) has currently caused the mortality of millions of people around the world. Aside from the direct mortality from the COVID-19, the indirect effects of the pandemic have also led to an increase in the mortality rate of other non-COVID patients. Evidence indicates that novel COVID-19 pandemic has caused an inflation in acute cardiovascular mortality, which did not relate to COVID-19 infection. It has in fact increased the risk of death in cardiovascular disease (CVD) patients. For this purpose, it is dramatically inevitable to monitor CVD patients’ vital signs and to detect abnormal events before the occurrence of any critical conditions resulted in death. Internet of things (IoT) and health monitoring sensors have improved the medical care systems by enabling latency-sensitive surveillance and computing of large amounts of patients’ data. The major challenge being faced currently in this problem is its limited scalability and late detection of cardiovascular events in IoT-based computing environments. To this end, this paper proposes a novel framework to early detection of cardiovascular events based on a deep learning architecture in IoT environments. Experimental results showed that the proposed method was able to detect cardiovascular events with better performance (95.30% average sensitivity and 95.94% mean prediction values).

show abstract

“…The quality of learning and teaching depends on many factors, the most important being learner self-assessment and formal assessment or testing, monitoring learner success and achievement, teacher development, and teacher evaluation[ 7 ]. Reference [ 8 ] proposed a deep learning-based IoT real-time health monitoring system using cross-testing to extensively evaluate the performance of the proposed system. Reference [ 9 ] introduced two different machine learning-based algorithms for photovoltaic (PV) array fault monitoring and classification.…”

Section: Introductionmentioning

confidence: 99%

English Teaching Quality Monitoring and Multidimensional Analysis Based on the Internet of Things and Deep Learning Model

Song¹

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

With the development of the times, English as the universal language in the world has been highly valued by the society and schools, and English skills have become a basic skill in the society. The school is actively developing, and in the process of reform and development, the monitoring of teaching quality is essential. Teaching quality is a complex and vague concept. The establishment of a teaching quality monitoring system helps to ensure the quality of personnel training and improve the level of education and teaching, and the quality of classroom teaching is the core content of education quality. Teaching quality monitoring is the management process of various measures and actions taken to ensure the continuous improvement of students’ learning quality and to achieve certain quality standards by systematically supervising and controlling various factors affecting the teaching quality in the teaching process. The research results of the article show that (1) under the traditional teaching mode, the average grades of the three groups were 74, 72, 67, 62, and 62, respectively. The score of the oral test module is relatively low, the highest score is only 63 points, the overall score shows a low level, the academic achievement is hovering on the edge of passing, and the students’ English learning situation is poor. Under the new classroom quality monitoring mode, the average scores of the three groups were 96, 92, 90, 86, and 84, respectively. Compared with the ordinary teaching mode, the scores of the five detection modules were greatly improved, and the average score of the listening module was improved. The teaching contents include 22 listening modules, 20 reading modules, 23 cloze modules, 24 translation modules, and 22 speaking modules. Overall, students’ English learning level has been greatly improved. (2) Generally speaking, the overall reliability coefficient of the sample data with full English teaching content is mostly kept in the range of 0.70–0.95, and only a few parts show a low situation, which also shows the overall situation of the diversity of teaching content. The overall reliability coefficient of the sample data of good teaching methods shows a relatively high situation, the reliability coefficient of the improvement of learning interest can reach 0.93, the reliability coefficient of the understanding of the learning content can reach the highest 0.96, the problem analysis ability can reach the highest 0.97, and the innovation ability can reach 0.96. The improved reliability coefficient can reach up to 0.98, which shows the authenticity and validity of the experimental data. (3) The detection result of the new classroom quality monitoring teaching mode is the highest among several models, the accuracy rate can reach 96.42%, the recall rate can reach 97.21%, and the F1 value can reach 97.46%, indicating that the new classroom quality monitoring teaching mode is effective. Teaching performance is the highest. According to the ROC curve values of the four models, we can also conclude that the ROC value of the new classroom quality monitoring teaching has been maintained at 0.98 without major twists and turns. Whether it is in the test set or the training set, the detection results of the new classroom quality monitoring are still the highest, the accuracy rate can reach 94.42%, the recall rate can reach 94.78%, and the F1 value can reach 94.49%. After the training set runs, except the performance of the traditional teaching mode increases, the performance of the other 3 models decreases.

show abstract

Internet of things-enabled real-time health monitoring system using deep learning

Cited by 35 publications

References 21 publications

Application of Deep Learning Technology in Predicting the Risk of Inpatient Death in Intensive Care Unit

Application of Deep Learning Technology in Predicting the Risk of Inpatient Death in Intensive Care Unit

Internet of things-based health monitoring system for early detection of cardiovascular events during COVID-19 pandemic

English Teaching Quality Monitoring and Multidimensional Analysis Based on the Internet of Things and Deep Learning Model

Contact Info

Product

Resources

About