Fall detection and human activity classification using wearable sensors and compressed sensing

Kerdjidj, Oussama; Ramzan, Naeem; Ghanem, Khalida; Amira, Abbes; Chouireb, Fatima

doi:10.1007/s12652-019-01214-4

Cited by 85 publications

(50 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It is more robust than other conventional distance measure techniques, followed in existing fall detection systems. Kerdjidj et al [17] put forward an efficient automatic fall detection system, which is also fit for the detection of different activities of daily living (ADL) and relies on a wearable shimmer device to transmit some inertial signals via a wireless connection to a computer.…”

Section: A Methods Based On Wearable Devicesmentioning

confidence: 99%

A Two-Stream Approach to Fall Detection With MobileVGG

et al. 2020

View full text Add to dashboard Cite

The existing deep learning methods for human fall detection have difficulties to distinguish falls from similar daily activities such as lying down because of not using the 3D network. Meanwhile, they are not suitable for mobile devices because they are heavyweight methods and consume a large number of memories. In order to alleviate these problems, a two-stream approach to fall detection with the MobileVGG is proposed in this paper. One stream is based on the motion characteristics of the human body for detection of falls, while the other is an improved lightweight VGG network, named the MobileVGG, put forward in the paper. The MobileVGG is constructed as a lightweight network model through replacing the traditional convolution with a simplified and efficient combination of point convolution, depth convolution and point convolution. The residual connection between layers is designed to overcome the gradient disappeared and the obstruction of gradient reflux in the deep model. The experimental results show that the proposed two-stream lightweight fall classification model outperforms the existing methods in distinguishing falls from similar daily activities such as lying and reducing the occupied memory. Therefore, it is suitable for mobile devices. INDEX TERMS Deep learning, fall detection, motion characteristics, the two-stream model, the MobileVGG.

show abstract

Section: A Methods Based On Wearable Devicesmentioning

confidence: 99%

A Two-Stream Approach to Fall Detection With MobileVGG

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Researchers have particularly considered how data from sensors can be used to investigate fall and activities of daily living (ADL) [9], [34], [23]. General research on activity recognition with sensor technology can be categorised into three general themes: wearable sensors, vision-based detection and environmental sensors [23], [21], [36], [4]. There is also interest in vision-based detection sensors for identifying patterns using image processing techniques.…”

Section: Activity Classificationmentioning

confidence: 99%

“…By using a wearable Shimmer device, Kerdjidj et al [23] proposed a system for fall detection and detection of activities of daily living (ADL). Their experiment employed 17 subjects performing a set of movements.…”

Section: Activity Classificationmentioning

confidence: 99%

“Chatty Devices” and Edge-based Activity Classiﬁcation

Lakoju

Javed

Rana

et al. 2020

Preprint

View full text Add to dashboard Cite

With increasing automation of manufacturing processes (focusing on technologies such as robotics and human-robot interaction), there is a realisation that the manufacturing process and the artefacts/products it produces can be better connected post-production. Built on this requirement, a “chatty” factory involves creating products which are able to send data back to the manufacturing/ production environment as they are used, whilst still ensuring user privacy. The intended use of a product during design phase may diﬀerent signiﬁcantly from actual usage. Understanding how this data can be used to support continuous product reﬁnement, and how the manufacturing process can be dynamically adapted based on the availability of this data provides a number of opportunities. We describe how data collected on product use be used to: (i) classify product use; (ii) associate a label with product use using unsupervised learning – making use of edge-based analytics; (iii) transmission of this data to a cloud environment where labels can be compared across diﬀerent products of the same type. Federated learning strategies are used on edge devices to ensure that any data captured from a product can be analysed locally (ensuring data privacy). Using a 6th gen. Apple iPad as a “chatty device” (with acceleration, orientation, angular velocity and magnetic ﬁeld sensors) we demonstrate how product use activities can achieve a classiﬁcation accuracy of 99.35%. A comparison is also undertaken with the Human Activity Recognition (HAR) data set, achieving an accuracy of 98%. Our approach demonstrates how semantic activity labels can be associated with product use, and subsequently used to improve product design.

show abstract

“…The SensorTile® device is employed in run‐time detection to investigate and validate the memory occupation, power consumption, and computational load. Kerdjidj et al [9] proposed an automatic fall detection system that relies on Shimmer wearable device connected wirelessly to a computer to transmit the measured data continuously. The compressing sensing technique is used to minimise the data size and to reduce the energy consumption.…”

Section: Introductionmentioning

confidence: 99%