A healthcare monitoring system using random forest and internet of things (IoT)

Kaur, Pavleen; Kumar, Rajesh; Kumar, Munish

doi:10.1007/s11042-019-7327-8

Cited by 200 publications

(65 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3) Monitor cable forces. The cable force of the cable-stayed bridge, the main cable of the suspension bridge and the suspension bridge of the suspension bridge are important parameters for design and the main content of safety monitoring of steel frame construction [25]. 4) Pressure monitoring.…”

Section: ) Contents Of Health Monitoring In the Projectmentioning

confidence: 99%

Internet of Things Health Detection System in Steel Structure Construction Management

et al. 2020

View full text Add to dashboard Cite

In recent years, the development of computer network technology, especially the hot Internet of things, has brought great convenience and comfort to people's life. Steel structure is also more and more widely used in the field of construction in China. The purpose of this study is to explore the application of Internet of things health monitoring system in steel structure construction management. In this study, through the use of example analysis, comprehensive data analysis and other methods, combined with steel structure health monitoring system and construction process management analysis. The results show that the relative deviation of the data within 1-33 is mostly less than 10%, but the relative deviation of 34-40 suddenly increases to 60%, and the actual data suddenly decreases, resulting in the deviation of about 50%. It is concluded that the time series model established in this study can objectively reflect the change trend and law of strain data, has certain prediction accuracy, and has certain value significance for monitoring data analysis and construction management of steel building structures.

show abstract

Section: ) Contents Of Health Monitoring In the Projectmentioning

confidence: 99%

Internet of Things Health Detection System in Steel Structure Construction Management

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The use of decision trees in medicine is described in [Podgorelec et al 2002]. A more recent studies using decision trees in healthcare is shown in [Game et al 2019] and [Kaur et al 2019].…”

Section: Machine Learning Models For Predictionmentioning

confidence: 99%

“…The user can define how many decision trees will be created in his model, and the final classification is achieved by combining individual results. Some previous works that use Random Forests are described in [Kaur et al 2019] and [Imani et al 2019].…”

Section: Machine Learning Models For Predictionmentioning

confidence: 99%

Matched-Pair Analysis Using Machine Learning to Predict 1-year Mortality in Newborn Twins

Jesus¹,

Calais-Ferreira²,

Barreto³

2020

Anais Principais Do Simpósio Brasileiro De Computação Aplicada À Saúde (SBCAS 2020)

View full text Add to dashboard Cite

A análise de pares de gêmeos é uma ferramenta importante para avaliar fatores de risco familiares relacionados a diversos problemas, inclusive doenças. Modelos de aprendizado de máquina são ferramentas consolidadas utilizadas em diversas tarefas de predição nas mais diversas áreas. Porém, elas não são totalmente adequadas para a análise de conjuntos de dados onde os pares de registros possuem forte correlação entre si, como é o caso de gêmeos. Este artigo avalia a adequabilidade de modelos de aprendizado de máquina para predizer a mortalidade até um ano de gêmeos nascidos no Brasil, utilizando dados extraídos de bases de dados públicas. Além disso, também é avaliado um método para análise de dados pareados, criando uma base de dados alternativa para verificar se a aplicação dos modelos de aprendizado de máquina promove ganhos no processo de classificação. OS resultados demonstraram que i) o modelo de aprendizado de máquina Gradient Boosting obteve os melhores resultados na tarefa de classificação e ii) a estratégia para análise de dados pareados não melhorou os resultados conforme esperado.

show abstract

“…Usage of machine learning algorithms such as KNN, support vector, Machine Trees, Random Forest and MLP improve interactivity between patient and doctor as stated in [10]. They analyzed and concluded that Random Forest provides good accuracy among all other algorithms.…”

Section: Literature Surveymentioning

confidence: 99%

Patient Monitoring System with Miniaturization of Sensors

Geetha,

Deepalakshmi,

Pande

et al. 2019

IJEAT

View full text Add to dashboard Cite

The quality of human life has improved with the technological advancement and miniaturization of sensors. Healthcare sector has adopted the new technology with the results of related research. Still, healthcare services are not easily affordable in developing countries. This paper aims to reduce the expenses of healthcare system through designing a remote healthcare system comprising of three modules. The first module deals with detection of patient’s vitals using sensors. Second module is to collect and analyze the data and can be sent back to the doctor or guardian through Email and/or SMS alerts in case of any emergencies using Arduino. Third module implemented by K nearest neighbor classification algorithm is used to make runtime decisions if the alert message is not answered by doctors. By implementing these three modules, we achieved a better results in prediction and accuracy than the Attribute based credential and Amrita IoT-based Medical.

show abstract

A healthcare monitoring system using random forest and internet of things (IoT)

Cited by 200 publications

References 13 publications

Internet of Things Health Detection System in Steel Structure Construction Management

Internet of Things Health Detection System in Steel Structure Construction Management

Matched-Pair Analysis Using Machine Learning to Predict 1-year Mortality in Newborn Twins

Patient Monitoring System with Miniaturization of Sensors

Contact Info

Product

Resources

About