Deep stair walking detection using wearable inertial sensor via long short-term memory network

Nie, Gan Wei; Ghazali, Nurul Fathiah; Shahar, Norazman; As’ari, Muhammad Amir

doi:10.11591/eei.v9i1.1685

Cited by 6 publications

(7 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…-Gesture recognition: after performing the training phase, EMG signals were acquired, processed and windowed into 500 ms epochs in real time. For each epoch, the machine learning algorithm classifies the hand fingers gesture as flexion, extension or rest [22][23][24].…”

Section: Real Experiments and On Subjectsmentioning

confidence: 99%

A prosthetic limb managed by sensors-based electronic system: Experimental results on amputees

Gaetani¹,

Fazio

Zappatore³

et al. 2020

Bulletin EEI

View full text Add to dashboard Cite

Taking the advantages offered by smart high-performance electronic devices, transradial prosthesis for upper-limb amputees was developed and tested. It is equipped with sensing devices and actuators allowing hand movements; myoelectric signals are detected by Myo armband with 8 ElectroMyoGraphic (EMG) electrodes, a 9-axis Inertial Measurement Unit (IMU) and Bluetooth Low Energy (BLE) module. All data are received through HM-11 BLE transceiver by Arduino board which processes them and drives actuators. Raspberry Pi board controls a touchscreen display, providing user a feedback related to prosthesis functioning and sends EMG and IMU data, gathered via the armband, to cloud platform thus allowing orthopedic during rehabilitation period, to monitor users’ improvements in real time. A GUI software integrating a machine learning algorithm was implemented for recognizing flexion/extension/rest gestures of user fingers. The algorithm performances were tested on 9 male subjects (8 able-bodied and 1 subject affected by upper-limb amelia), demonstrating high accuracy and fast responses.

show abstract

Section: Real Experiments and On Subjectsmentioning

confidence: 99%

A prosthetic limb managed by sensors-based electronic system: Experimental results on amputees

Gaetani¹,

Fazio

Zappatore³

et al. 2020

Bulletin EEI

View full text Add to dashboard Cite

show abstract

“…S13 has used long-shot-term-memory (LTSM), which is based on recurrent neural network (RNN) [24]. The architecture of LSTM [40], [41] is used as it can capture long-range dependencies and non-linear dynamics as the deeper architecture of the RNN. This hypertension diagnosis system depends on many inputs that are collected for analyzing blood pressure, heartbeat rate, and physical activities.…”

Section: Techniques In Hypertension Diagnosismentioning

confidence: 99%

Review on hypertension diagnosis using expert system and wearable devices

Sani¹,

Abdullah

Rosli

2022

IJECE

View full text Add to dashboard Cite

<span>The popularity of smartphones and wearable devices is increasing in the global market. These devices track physical exercise records, heartbeat, medicines, and self-health diagnosis. The wearable devices can also collect personal health parameters include hypertension diagnosis. Hypertension is one of the risk factors for cardiovascular-related diseases among the Malaysian population. Many mobile applications are paired with wearable devices to monitor health conditions, but none of them able to diagnose hypertension. In this study, we reviewed research papers that focused on hypertension using expert systems and wearable devices. We performed a systematic literature review based on hypertension factors, expert systems, and wearable devices. We found 15 specific research papers after the filtering process. The key findings highlighted three main focuses, which are the factors of hypertension, the expert system techniques, and the types of sensors in wearable devices. Blood pressure is the most common factor of hypertension that can be collected by wearable devices. As for the expert system techniques, we determined the three most common techniques are machine learning, neural network, and fuzzy logic. Lastly, the wrist band is the most common sensor for wearable devices in hypertension-related research.</span>

show abstract

“…In this sense, the work in [ 47 ] points to any task involving gait as a major cause for falls. The works in [ 30 , 31 , 48 , 49 ] focus on the intrinsic factors that cause imbalances, such as muscle strength or the ability to posture control. Age is also a very common factor pointed out by many works of the state of the art, such as [ 14 , 16 , 23 , 24 , 33 , 36 , 41 , 45 , 50 , 51 , 52 ] or frailty [ 10 ], which is also related to age.…”

Section: Related Workmentioning

confidence: 99%

“…Age is also a very common factor pointed out by many works of the state of the art, such as [ 14 , 16 , 23 , 24 , 33 , 36 , 41 , 45 , 50 , 51 , 52 ] or frailty [ 10 ], which is also related to age. Regarding the extrinsic factors, the presence of obstacles [ 44 , 53 ], bedtime [ 39 , 54 ], stair architecture design, and stair obstacles, such as the absence of a handrail, irregular riser height and an object left on stairs [ 49 ], are more commonly mentioned.…”

Section: Related Workmentioning

confidence: 99%

Bedtime Monitoring for Fall Detection and Prevention in Older Adults

Ruiz

Chaparro²,

Santofimia³

et al. 2022

IJERPH

View full text Add to dashboard Cite

Life expectancy has increased, so the number of people in need of intensive care and attention is also growing. Falls are a major problem for older adult health, mainly because of the consequences they entail. Falls are indeed the second leading cause of unintentional death in the world. The impact on privacy, the cost, low performance, or the need to wear uncomfortable devices are the main causes for the lack of widespread solutions for fall detection and prevention. This work present a solution focused on bedtime that addresses all these causes. Bed exit is one of the most critical moments, especially when the person suffers from a cognitive impairment or has mobility problems. For this reason, this work proposes a system that monitors the position in bed in order to identify risk situations as soon as possible. This system is also combined with an automatic fall detection system. Both systems work together, in real time, offering a comprehensive solution to automatic fall detection and prevention, which is low cost and guarantees user privacy. The proposed system was experimentally validated with young adults. Results show that falls can be detected, in real time, with an accuracy of 93.51%, sensitivity of 92.04% and specificity of 95.45%. Furthermore, risk situations, such as transiting from lying on the bed to sitting on the bed side, are recognized with a 96.60% accuracy, and those where the user exits the bed are recognized with a 100% accuracy.

show abstract

Deep stair walking detection using wearable inertial sensor via long short-term memory network

Cited by 6 publications

References 17 publications

A prosthetic limb managed by sensors-based electronic system: Experimental results on amputees

A prosthetic limb managed by sensors-based electronic system: Experimental results on amputees

Review on hypertension diagnosis using expert system and wearable devices

Bedtime Monitoring for Fall Detection and Prevention in Older Adults

Contact Info

Product

Resources

About