Fall detection in older adults with mobile IoT devices and machine learning in the cloud and on the edge

Mrozek, Dariusz; Koczur, A.; Małysiak-Mrozek, Bożena

doi:10.1016/j.ins.2020.05.070

Cited by 102 publications

(41 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This outcome is established from the attained accuracy and essential hardware assets. Mrozek et al [18] proposed a scalable framework of a scheme that could observe 1000s of elder persons, identify falls, and inform the care takers. Scalability test discloses the need for enabling large scale scheme processes have been executed.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Internet of Things and Deep Learning Enabled Elderly Fall Detection Model for Smart Homecare

et al. 2021

View full text Add to dashboard Cite

Recently, the techniques of Internet of Things (IoT) and mobile communications have been developed to gather human and environment information data for a variety of intelligent services and applications. Remote monitoring of elderly and disabled people living in smart homes is highly challenging due to probable accidents which might occur due to daily activities such as falls. For elderly people, fall is considered as a major reason for death of post-traumatic complication. So, early identification of elderly people falls in smart homes is needed to increase the survival rate of the person or offer required support. Recently, the advent of artificial intelligence (AI), IoT, wearables, smartphones, etc makes it feasible to design fall detection systems for smart homecare. In this view, this paper presents an IoT enabled elderly fall detection model using optimal deep convolutional neural network (IMEFD-ODCNN) for smart homecare. The goal of the IMEFD-ODCNN model is to enable smartphones and intelligent deep learning (DL) algorithms to detect the occurrence of falls in the smart home. Primarily, the input video captured by the IoT devices is pre-processed in different ways like resizing, augmentation, and min-max based normalization. Besides, SqueezeNet model is employed as a feature extraction technique to derive appropriate feature vectors for fall detection. In addition, the hyperparameter tuning of the SqueezeNet model takes place using the salp swarm optimization (SSO) algorithm. Finally, sparrow search optimization algorithm (SSOA) with variational autoencoder (VAE), called SSOA-VAE based classifier is employed for the classification of fall and non-fall events. Finally, in case of fall event detected, the smartphone sends an alert to the caretakers and hospital management. The performance validation of the IMEFD-ODCNN model takes place on UR fall detection dataset and multiple cameras fall dataset. The experimental outcomes highlighted the promising performance of the IMEFD-ODCNN model over the recent methods with the maximum accuracy of 99.76% and 99.57% on the multiple cameras fall and UR fall detection dataset.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

“…But, in several countries, offering appropriate care could be challenging because of several reasons. The impaired and elderly populations would shortly live in smart homes [1,2]. These homes offer a pleasant and safe place for the elders.…”

Section: Introductionmentioning

confidence: 99%

Internet of Things and Deep Learning Enabled Elderly Fall Detection Model for Smart Homecare

et al. 2021

View full text Add to dashboard Cite

show abstract

“…More ambitious approaches might seek to automate larger portions of this process [ 25 – 29 ]. In that case, information from wearable devices might be an input into systems that use artificial intelligence or machine learning to monitor aspects of a person’s health, build a model of their routine functioning or their mental health [ 30 ] and attempt to predict life-threatening events before they occur.…”

Section: Covid-19 and Health Information: Wearable Devicesmentioning

confidence: 99%

Solitary death and new lifestyles during and after COVID-19: wearable devices and public health ethics

et al. 2021

View full text Add to dashboard Cite

Background Solitary death (kodokushi) has recently become recognized as a social issue in Japan. The social isolation of older people leads to death without dignity. With the outbreak of COVID-19, efforts to eliminate solitary death need to be adjusted in line with changes in lifestyle and accompanying changes in social structure. Health monitoring services that utilize wearable devices may contribute to this end. Our goals are to outline how wearable devices might be used to (1) detect emergency situations involving solitary older people and swiftly connect them with medical treatment, to (2) reduce the frequency of deaths that remain undiscovered and (3) to reduce social isolation by promoting social interaction. Methods Theoretical and philosophical approaches were adopted to examine ethical issues surrounding the application of wearable devices and cloud-based information processing systems to prevent solitary death in the world with/after COVID-19. Main body (1) Technology cannot replace social connections; without social support necessary to foster understanding of the benefits of health management through wearable devices among older adults, such devices may remain unused, or not used properly. (2) Maturity of the technology; systems face the difficult task of detecting and responding to a wide range of health conditions and life-threatening events in time to avert avoidable morbidity and mortality. (3) Autonomy and personhood; promoting the voluntary use of wearable devices that are a part of larger efforts to connect isolated individuals to a community or social services might be effective. Legal force should be avoided if possible. There is some concern that landlords may require an older person to sign a contract agreeing to wear a device. The autonomy of solitary older people should be respected. (4) Governance: policies must be developed to limit access to data from wearables and the purposes for which data can be used. Conclusion If thoughtfully deployed under proper policy constraints, wearable devices offer a way to connect solitary older people to health services and could reduce cases of solitary death while respecting the personhood of the user.

show abstract

“…With the developing technology, it is of great importance that these data kept in data sets are processed and benefit institutions, companies or users. Machine learning methods can be used to process these large data sets that come with cloud technology [2]. There are more than one machine learning method in the literature [3].…”

Section: Introductionmentioning

confidence: 99%

Investigation of Cloud Computing Based Big Data on Machine Learning Algorithms.

Yıldırım

Çınar

Cengil

2021

Bitlis Eren Üniversitesi Fen Bilimleri Dergisi

View full text Add to dashboard Cite

Cloud computing technology is a model that allows access to a common pool of configurable computing resources whenever and wherever. With the developing technology, the use of this model is increasing day by day. There are many benefits of cloud computing to its users. The data that users keep in their data sets is the simplest example of this. With the cloud technology, the size of the data stored in databases is also increasing. For this reason, cloud technology and big data concepts are intertwined due to the large amount of data stored in databases. It is of great importance that the obtained data is evaluated by machine learning methods and produces results that can be used for technical and commercial purposes. In this study, first of all, cloud technology, the big data brought by this technology and the classification of these data with machine learning methods and algorithms have been examined. Then the studies in the literature were evaluated.

show abstract

Fall detection in older adults with mobile IoT devices and machine learning in the cloud and on the edge

Cited by 102 publications

References 40 publications

Internet of Things and Deep Learning Enabled Elderly Fall Detection Model for Smart Homecare

Internet of Things and Deep Learning Enabled Elderly Fall Detection Model for Smart Homecare

Solitary death and new lifestyles during and after COVID-19: wearable devices and public health ethics

Investigation of Cloud Computing Based Big Data on Machine Learning Algorithms.

Contact Info

Product

Resources

About