Human Action Monitoring for Healthcare Based on Deep Learning

Gao, Yongbin; Xiang, Xuehao; Xiong, Naixue; Huang, Bo; Lee, Hyo Jong; Alrifai, Rad; Jiang, Xiaoyan; Fang, Zhijun

doi:10.1109/access.2018.2869790

Cited by 92 publications

(37 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The performance exceeds that of board certified cardiologists in detecting a wide range of heart arrhythmias from electrocardiograms recorded with a single-lead wearable monitor. Gao et al [40] propose a novel deep learning architecture recurrent 3D convolutional neural network (R3D). R3D extracts effective and discriminative spatialtemporal features for action recognition, which enables the capturing of long-range temporal information by aggregating the 3D convolutional network entries to serve as an input to the LSTM architecture.…”

Section: ) Health Monitoringmentioning

confidence: 99%

A Survey on Deep Learning Empowered IoT Applications

Yao

et al. 2019

IEEE Access

View full text Add to dashboard Cite

The Internet of Things (IoT) is widely regarded as a key component of the Internet of the future and thereby has drawn significant interests in recent years. IoT consists of billions of intelligent and communicating ''things'', which further extend borders of the world with physical and virtual entities. Such ubiquitous smart things produce massive data every day, posing urgent demands on quick data analysis on various smart mobile devices. Fortunately, the recent breakthroughs in deep learning have enabled us to address the problem in an elegant way. Deep models can be exported to process massive sensor data and learn underlying features quickly and efficiently for various IoT applications on smart devices. In this article, we survey the literature on leveraging deep learning to various IoT applications. We aim to give insights on how deep learning tools can be applied from diverse perspectives to empower IoT applications in four representative domains, including smart healthcare, smart home, smart transportation, and smart industry. A main thrust is to seamlessly merge the two disciplines of deep learning and IoT, resulting in a wide-range of new designs in IoT applications, such as health monitoring, disease analysis, indoor localization, intelligent control, home robotics, traffic prediction, traffic monitoring, autonomous driving, and manufacture inspection. We also discuss a set of issues, challenges, and future research directions that leverage deep learning to empower IoT applications, which may motivate and inspire further developments in this promising field.

show abstract

Section: ) Health Monitoringmentioning

confidence: 99%

A Survey on Deep Learning Empowered IoT Applications

Yao

et al. 2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…It has been shown in this study that the benefits of DL can reach models that integrate external modalities and additional sources of biological data, medical imaging and other intermediate phenotypes. 24 In the thirteenth study (E13), a new Deep Learning method was reported to improve the accuracy of lung nodule classification on computed tomography (CT). (E13) This study highlighted the high quality of the DL method, even with focal loss.…”

Section: Multimodal Imaging 2019mentioning

confidence: 99%

Análise do deep learning em cuidados de saúde

Machado

Emmerick

Silva

et al. 2019

Rev enferm UFPE on line.

View full text Add to dashboard Cite

Objective: to analyze the applicability and benefits of Deep Learning in health care. Method: this is a descriptive study, reflective analysis, with articles from 2014 to 2019, published in English and peer-reviewed, in the CAPES Journal Portal, with the search equation ("Deep Learning "AND (" Health Care "OR Health-care OR Healthcare)). The results were presented in figure form followed by descriptive analysis. Results: it is revealed that 15 articles describe the applicability of Deep Learning in the health care area. This article analyzed the use of Deep Learning in different areas related to health care, highlighting the benefits found by the authors of those selected through the literature review. Conclusion: it is suggested the use of Deep Learning in health care in view of the benefits identified in the articles selected as: the prediction of disease stages; precise identification of pathological mutations and support to doctors and nurses in their daily activities. Descriptors: Benefits; Deep Learning; Health Care; Diseases; Physicians; Nurses. RESUMOObjetivo: analisar a aplicabilidade e os benefícios do Deep Learning na área de cuidados de saúde. Método: trata-se de um estudo descritivo, tipo análise reflexiva, com consulta a artigos entre os anos de 2014 a 2019, publicados em inglês e revisado por pares, no Portal de Periódicos da CAPES, com a equação de busca ("Deep Learning" AND ("Health Care" OR Health-care OR Healthcare)). Apresentaram-se os resultados em forma de figura seguida da análise descritiva. Resultados: revela-se que 15 artigos descrevem a aplicabilidade do Deep Learning na área de cuidados de saúde. Analisou-se, por este artigo, o emprego do Deep Learning em diferentes áreas referentes aos cuidados de saúde, destacando os benefícios encontrados pelos autores dos selecionados por meio da revisão de literatura. Conclusão: sugere-se o emprego do Deep Learning na área de cuidados de saúde diante dos benefícios identificados nos artigos selecionados como: a previsão dos estágios das doenças; a identificação precisa de mutações patológicas e o suporte aos médicos e aos enfermeiros em suas atividades diárias. Descritores: Benefícios; Deep Learning; Cuidados de Saúde; Doenças; Médicos; Enfermeiros. RESUMENObjetivo: analizar la aplicabilidad y los beneficios del Deep Learning en la atención médica. Método: se trata de un estudio descriptivo, tipo análisis reflexivo, con artículos de 2014 a 2019, publicados en inglés y revisados por pares, en el Portal de la revista CAPES, con la ecuación de búsqueda ("Deep Learning" Y ("Health Care" O Health-care O Healthcare)). Los resultados se presentaron en forma de figura seguida de un análisis descriptivo. Resultados: se revela que 15 artículos describen la aplicabilidad del Deep Learning en el área de la atención médica. Este artículo analizó el uso del Deep Learning en diferentes áreas relacionadas con la atención de la salud, destacando los beneficios encontrados por los autores de los seleccionados a través de la revisión de la literatura. Conclusión: s...

show abstract

“…Indeed, in the field of medicine, there is a rapidly increasing demand for systems to recognize human actions and to quickly detect patients’ physical and mental health problems. Indeed, Gao et al, 2018 [ 11 ] developed an application based on human action monitoring for healthcare. This application remotely monitors the status of patients or the elderly.…”

Section: Introductionmentioning

confidence: 99%

Prediction of Human Activities Based on a New Structure of Skeleton Features and Deep Learning Model

Jaouedi¹,

Perales

Buades

et al. 2020

Sensors

View full text Add to dashboard Cite

The recognition of human activities is usually considered to be a simple procedure. Problems occur in complex scenes involving high speeds. Activity prediction using Artificial Intelligence (AI) by numerical analysis has attracted the attention of several researchers. Human activities are an important challenge in various fields. There are many great applications in this area, including smart homes, assistive robotics, human–computer interactions, and improvements in protection in several areas such as security, transport, education, and medicine through the control of falling or aiding in medication consumption for elderly people. The advanced enhancement and success of deep learning techniques in various computer vision applications encourage the use of these methods in video processing. The human presentation is an important challenge in the analysis of human behavior through activity. A person in a video sequence can be described by their motion, skeleton, and/or spatial characteristics. In this paper, we present a novel approach to human activity recognition from videos using the Recurrent Neural Network (RNN) for activity classification and the Convolutional Neural Network (CNN) with a new structure of the human skeleton to carry out feature presentation. The aims of this work are to improve the human presentation through the collection of different features and the exploitation of the new RNN structure for activities. The performance of the proposed approach is evaluated by the RGB-D sensor dataset CAD-60. The experimental results show the performance of the proposed approach through the average error rate obtained (4.5%).

show abstract

Human Action Monitoring for Healthcare Based on Deep Learning

Cited by 92 publications

References 35 publications

A Survey on Deep Learning Empowered IoT Applications

A Survey on Deep Learning Empowered IoT Applications

Análise do deep learning em cuidados de saúde

Prediction of Human Activities Based on a New Structure of Skeleton Features and Deep Learning Model

Contact Info

Product

Resources

About