Wearable Sensor Gait Analysis of Fall Detection using Attention Network

Yhdego, Haben; Li, Jiang; Paolini, Christopher; Audette, Michel

doi:10.1109/bibm52615.2021.9669795

Cited by 13 publications

(8 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another aspect of future work would be in the domain of deep learning algorithm development. In this regard, transformer networks have been found to be very useful for natural language processing applications and have been getting attention in applications relating to time series signals as well [ 52 ]. Attention networks have the capability to assign weights important parts of a signal more and therefore allow for potentially better performance than traditional deep learning approaches.…”

Section: Discussionmentioning

confidence: 99%

A Deep Convolutional Neural Network-XGB for Direction and Severity Aware Fall Detection and Activity Recognition

Syed

Sierra-Sosa

Kumar

et al. 2022

Sensors

View full text Add to dashboard Cite

Activity and Fall detection have been a topic of keen interest in the field of ambient assisted living system research. Such systems make use of different sensing mechanisms to monitor human motion and aim to ascertain the activity being performed for health monitoring and other purposes. Towards this end, in addition to activity recognition, fall detection is an especially important task as falls can lead to injuries and sometimes even death. This work presents a fall detection and activity recognition system that not only considers various activities of daily living but also considers detection of falls while taking into consideration the direction and severity. Inertial Measurement Unit (accelerometer and gyroscope) data from the SisFall dataset is first windowed into non-overlapping segments of duration 3 s. After suitable data augmentation, it is then passed on to a Convolutional Neural Network (CNN) for feature extraction with an eXtreme Gradient Boosting (XGB) last stage for classification into the various output classes. The experiments show that the gradient boosted CNN performs better than other comparable techniques, achieving an unweighted average recall of 88%.

show abstract

Section: Discussionmentioning

confidence: 99%

A Deep Convolutional Neural Network-XGB for Direction and Severity Aware Fall Detection and Activity Recognition

Syed

Sierra-Sosa

Kumar

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

Section: Methodsmentioning

confidence: 99%

“…The use of SPs for this study was strictly for obtaining ECG signal data and testing site detection's accuracy and real-time capabilities. Among the 19 males and 22 females tested, the average age of SPs was 42 (in the range of 27-61), and the average body mass index was 26 (in the range of [23][24][25][26][27][28][29][30][31][32][33][34][35][36][37][38][39]. A Welch Allyn Meditron stethoscope apparatus was used to collect 10 s of heart sounds from each of the four auscultation sites.…”

Section: Subjects Equipment and Data Acquisitionmentioning

confidence: 99%

“…However, as our input time series has scalar values than distinct words in NLP, we have to encode the sequence of time which is hidden in our signal data. 29 We use and implement the existing method that helps us to learn the vector representation of time-Time2Vec for time embedding. 30 Our input to the models is 3D sequential data, where the dimensions are the feature size (which is one in our case), batch size of sequences (number of windows), and sequence length (200).…”

Section: Cnn-lstmmentioning

confidence: 99%

See 1 more Smart Citation

Development of deep-learning models for a hybrid simulation of auscultation training on standard patients using an ECG-based virtual pathology stethoscope

et al. 2023

View full text Add to dashboard Cite

Cardiac auscultation (CA), the act of listening to the heart’s sound, is a critical skill that provides valuable information for identifying serious heart diseases. Proficiency in cardiac auscultation requires repeated stethoscope practice and experience in identifying abnormal or irregular cardiac rhythms. However, nowadays, most hospital admissions are short and intensely focused, with fewer opportunities for medical trainees to learn and practice bedside examination skills. It is common practice in many institutions to incorporate standardized patients (SPs) into CA training because these actors are able to represent the patient and convey the symptoms. However, SPs are typically healthy individuals, limiting the kinds of abnormalities that students can hear. In this work, we develop a novel real-time simulation-based method for virtual pathology stethoscope (VPS) detection. The VPS system uses augmented reality (AR) to teach medical students how to perform cardiac examinations by listening to abnormal heart sounds in SPs who are otherwise healthy. A digital stethoscope with two electrodes on the chest piece collects electrocardiogram (ECG) signal data sets from SPs at the four primary auscultation sites. Next, different deep-learning methods are evaluated for classifying the location of the stethoscope by taking advantage of subtle differences in the ECG signals. This study would significantly extend the simulation capabilities of SPs by allowing medical students and trainees to perform realistic CA and hear CA in a clinical environment.

show abstract

“…In the last decade, many fall-detection methods have been developed using classical machine learning techniques [14] and deep learning [15][16][17]. Some of the developed falldetection systems use logistic regression [14], naive Bayes [18,19], decision tree [18,19], support vector machines [18], and k-nearest neighbors [18][19][20].…”

Section: Introductionmentioning

confidence: 99%

Toward Real-Time, Robust Wearable Sensor Fall Detection Using Deep Learning Methods: A Feasibility Study

2023

Self Cite

View full text Add to dashboard Cite

Real-time fall detection using a wearable sensor remains a challenging problem due to high gait variability. Furthermore, finding the type of sensor to use and the optimal location of the sensors are also essential factors for real-time fall-detection systems. This work presents real-time fall-detection methods using deep learning models. Early detection of falls, followed by pneumatic protection, is one of the most effective means of ensuring the safety of the elderly. First, we developed and compared different data-segmentation techniques for sliding windows. Next, we implemented various techniques to balance the datasets because collecting fall datasets in the real-time setting has an imbalanced nature. Moreover, we designed a deep learning model that combines a convolution-based feature extractor and deep neural network blocks, the LSTM block, and the transformer encoder block, followed by a position-wise feedforward layer. We found that combining the input sequence with the convolution-learned features of different kernels tends to increase the performance of the fall-detection model. Last, we analyzed that the sensor signals collected by both accelerometer and gyroscope sensors can be leveraged to develop an effective classifier that can accurately detect falls, especially differentiating falls from near-falls. Furthermore, we also used data from sixteen different body parts and compared them to determine the better sensor position for fall-detection methods. We found that the shank is the optimal position for placing our sensors, with an F1 score of 0.97, and this could help other researchers collect high-quality fall datasets.

show abstract

Wearable Sensor Gait Analysis of Fall Detection using Attention Network

Cited by 13 publications

References 12 publications

A Deep Convolutional Neural Network-XGB for Direction and Severity Aware Fall Detection and Activity Recognition

A Deep Convolutional Neural Network-XGB for Direction and Severity Aware Fall Detection and Activity Recognition

Development of deep-learning models for a hybrid simulation of auscultation training on standard patients using an ECG-based virtual pathology stethoscope

Toward Real-Time, Robust Wearable Sensor Fall Detection Using Deep Learning Methods: A Feasibility Study

Contact Info

Product

Resources

About