Edge Computing Transformers for Fall Detection in Older Adults

The global trend of increasing life expectancy introduces new challenges with far-reaching implications. Among these, the risk of falls among older adults is particularly significant, affecting individual health and the quality of life, and placing an additional burden on healthcare systems. Existing fall detection systems often have limitations, including delays due to continuous server communication, high false-positive rates, low adoption rates due to wearability and comfort issues, and high costs. In response to these challenges, this work presents a reliable, wearable, and cost-effective fall detection system. The proposed system consists of a fit-for-purpose device, with an embedded algorithm and an Inertial Measurement Unit (IMU), enabling real-time fall detection. The algorithm combines a Threshold-Based Algorithm (TBA) and a neural network with low number of parameters based on a Transformer architecture. This system demonstrates notable performance with 95.29% accuracy, 93.68% specificity, and 96.66% sensitivity, while only using a 0.38% of the trainable parameters used by the other approach.

Localizing EEG Recordings Associated With a Balance Threat During Unexpected Postural Translations in Young and Elderly Adults

Balance perturbations are accompanied by global cortical activation that increases in magnitude when postural perturbations are unexpected, potentially due to the addition of a startle response. A specific site for best recording the response to unexpected destabilization has not been identified. We hypothesize that a single sensor located near to subcortical brainstem mechanisms could serve as a marker for the response to unpredictable postural events. Twenty healthy young (20.8 ± 2.9 yrs) and 20 healthy elder (71.7 ± 4.2 yrs) adults stood upright on a dynamic platform with eyes open. Platform translations (20 cm at 100 cm/s) were delivered in the posterior (29 trials) and anterior (5 catch trials) directions. Active EEG electrodes were located at Fz and Cz and bilaterally on the mastoids. Following platform acceleration onset, 300 ms of EEG activity from each trial was detrended, baseline-corrected, and normalized to the first trial. Average Root-Mean-Square (RMS) values across "unpredictable" and "predictable" events were computed for each channel. EEG RMS responses were significantly greater with unpredictable than predictable disturbances: Cz ( [Formula: see text]), Fz ( [Formula: see text]), and mastoid ( [Formula: see text]). EEG RMS responses were also significantly greater in elderly than young adults at Cz ( [Formula: see text]) and mastoid ( [Formula: see text]). A significant effect of sex in the responses at the mastoid sensors ( [Formula: see text]) revealed that elderly male adults were principally responsible for the age effect. These results confirm that the cortical activity resulting from an unexpected postural disturbance could be portrayed by a single sensor located over the mastoid bone in both young and elderly adults.

Smartphones and Threshold-Based Monitoring Methods Effectively Detect Falls Remotely: A Systematic Review

In the US, at least one fall occurs in at least 28.7% of community-dwelling seniors 65 and older each year. Falls had medical costs of USD 51 billion in 2015 and are projected to reach USD 100 billion by 2030. This review aims to discuss the extent of smartphone (SP) usage in fall detection and prevention across a range of care settings. A computerized search was conducted on six electronic databases to investigate the use of remote sensing technology, wireless technology, and other related MeSH terms for detecting and preventing falls. After applying inclusion and exclusion criteria, 44 studies were included. Most of the studies targeted detecting falls, two focused on detecting and preventing falls, and one only looked at preventing falls. Accelerometers were employed in all the experiments for the detection and/or prevention of falls. The most frequent course of action following a fall event was an alarm to the guardian. Numerous studies investigated in this research used accelerometer data analysis, machine learning, and data from previous falls to devise a boundary and increase detection accuracy. SP was found to have potential as a fall detection system but is not widely implemented. Technology-based applications are being developed to protect at-risk individuals from falls, with the objective of providing more effective and efficient interventions than traditional means. Successful healthcare technology implementation requires cooperation between engineers, clinicians, and administrators.

In-Home Older Adults' Activity Pattern Monitoring Using Depth Sensors: A Review

The global population is aging due to many factors, including longer life expectancy through better healthcare, changing diet, physical activity, etc. We are also witnessing various frequent epidemics as well as pandemics. The existing healthcare system has failed to deliver the care and support needed to our older adults (seniors) during these frequent outbreaks. Sophisticated sensor-based in-home care systems may offer an effective solution to this global crisis. The monitoring system is the key component of any in-home care system. The evidence indicates that they are more useful when implemented in a non-intrusive manner through different visual and audio sensors. Artificial Intelligence (AI) and Computer Vision (CV) techniques may be ideal for this purpose. Since the RGB imagery-based CV technique may compromise privacy, people often hesitate to utilize in-home care systems which use this technology. Depth, thermal, and audio-based CV techniques could be meaningful substitutes here. Due to the need to monitor larger areas, this review article presents a systematic discussion on the state-of-the-art using depth sensors as primary data-capturing techniques. We mainly focused on fall detection and other health-related physical patterns. As gait parameters may help to detect these activities, we also considered depth sensor-based gait parameters separately. The article provides discussions on the topic in relation to the terminology, reviews, a survey of popular datasets, and future scopes.

Fall detection using accelerometer-based smartphones: Where do we go from here?

According to World Health Organization statistics, falls are the second leading cause of unintentional injury deaths worldwide. With older people being particularly vulnerable, detecting, and reporting falls have been the focus of numerous health technology studies. We screened 267 studies and selected 15 that detailed pervasive fall detection and alerting apps that used smartphone accelerometers. The fall datasets used for the analyses included between 4 and 38 participants and contained data from young and old subjects, with the recorded falls performed exclusively by young subjects. Threshold-based detection was implemented in six cases, while machine learning approaches were implemented in the other nine, including decision trees, k-nearest neighbors, boosting, and neural networks. All methods could ultimately achieve real-time detection, with reported sensitivities ranging from 60.4 to 99.3% and specificities from 74.6 to 100.0%. However, the studies had limitations in their experimental set-ups or considered a restricted scope of daily activities-not always representative of daily life-with which to define falls during the development of their algorithms. Finally, the studies omitted some aspects of data science methodology, such as proper test sets for results evaluation, putting into question whether reported results would correspond to real-world performance. The two primary outcomes of our review are: a ranking of selected articles based on bias risk and a set of 12 impactful and actionable recommendations for future work in fall detection.

Automatic fall detection using Orbbec Astra 3D pro depth images

Falls particularly among the older population has always been a matter of concern. With the steady rise of small families, the elderly is very often left alone at home. Dedicated nurses or caretakers are quite expensive. Thus, intelligent monitoring systems with automatic fall detection systems installed at home or nursing homes could be a game changer in such applications. In this paper, a simple yet effective fall detection system based on computer vision. Novelty of this paper is that it uses the Yolo v2 network on the depth videos for extracting the subject from cluttered background. The robust performance of the YOLOv2 network ensures accurate subject detection and removes the need for any complicated fall detection algorithm. Fall detection is carried out using subject’s height to width ratio and fall velocity. These parameters are simple and easy to calculate and yet provide effective results. The input data is captured using the Orbbec Astra 3D camera.

Review-Emerging Portable Technologies for Gait Analysis in Neurological Disorders

The understanding of locomotion in neurological disorders requires technologies for quantitative gait analysis. Numerous modalities are available today to objectively capture spatiotemporal gait and postural control features. Nevertheless, many obstacles prevent the application of these technologies to their full potential in neurological research and especially clinical practice. These include the required expert knowledge, time for data collection, and missing standards for data analysis and reporting. Here, we provide a technological review of wearable and vision-based portable motion analysis tools that emerged in the last decade with recent applications in neurological disorders such as Parkinson's disease and Multiple Sclerosis. The goal is to enable the reader to understand the available technologies with their individual strengths and limitations in order to make an informed decision for own investigations and clinical applications. We foresee that ongoing developments toward user-friendly automated devices will allow for closed-loop applications, long-term monitoring, and telemedical consulting in real-life environments.

S3D: Squeeze and Excitation 3D Convolutional Neural Networks for a Fall Detection System

Because of the limitations of previous studies on a fall detection system (FDS) based on wearable and ambient devices and visible light and depth cameras, the research using thermal cameras has recently been conducted. However, they also have the problem of deteriorating the accuracy of FDS depending on various environmental changes. Given these facts, in this study, we newly propose an FDS method based on the squeeze and excitation (SE) 3D convolutional neural networks (S3D). In our method, keyframes are extracted from input thermal videos using the optical flow vectors, and the fall detection is carried out based on the output of the proposed S3D, using the extracted keyframes as input. Comparative experiments were carried out on three open databases of thermal videos with different image resolutions, and our proposed method obtained F1 scores of 97.14%, 95.30%, and 98.89% in the Thermal Simulated Fall, Telerobotics and Control Lab fall detection, and eHomeSeniors datasets, respectively (the F1 score is a harmonic mean of recall and precision; it was confirmed that these are superior results to those obtained using the state-of-the-art methods of a thermal camera-based FDS.

A Sensor-Based mHealth Platform for Remote Monitoring and Intervention of Frailty Patients at Home

Frailty syndrome is an independent risk factor for serious health episodes, disability, hospitalization, falls, loss of mobility, and cardiovascular disease. Its high reversibility demands personalized interventions among which exercise programs are highly efficient to contribute to its delay. Information technology-based solutions to support frailty have been recently approached, but most of them are focused on assessment and not on intervention. This paper describes a sensor-based mHealth platform integrated in a service-based architecture inside the FRAIL project towards the remote monitoring and intervention of pre-frail and frail patients at home. The aim of this platform is constituting an efficient and scalable system for reducing both the impact of aging and the advance of frailty syndrome. Among the results of this work are: (1) the development of elderly-focused sensors and platform; (2) a technical validation process of the sensor devices and the mHealth platform with young adults; and (3) an assessment of usability and acceptability of the devices with a set of pre-frail and frail patients. After the promising results obtained, future steps of this work involve performing a clinical validation in order to quantify the impact of the platform on health outcomes of frail patients.

A Hierarchical Approach to Activity Recognition and Fall Detection Using Wavelets and Adaptive Pooling

Human activity recognition has been a key study topic in the development of cyber physical systems and assisted living applications. In particular, inertial sensor based systems have become increasingly popular because they do not restrict users’ movement and are also relatively simple to implement compared to other approaches. In this paper, we present a hierarchical classification framework based on wavelets and adaptive pooling for activity recognition and fall detection predicting fall direction and severity. To accomplish this, windowed segments were extracted from each recording of inertial measurements from the SisFall dataset. A combination of wavelet based feature extraction and adaptive pooling was used before a classification framework was applied to determine the output class. Furthermore, tests were performed to determine the best observation window size and the sensor modality to use. Based on the experiments the best window size was found to be 3 s and the best sensor modality was found to be a combination of accelerometer and gyroscope measurements. These were used to perform activity recognition and fall detection with a resulting weighted F1 score of 94.67%. This framework is novel in terms of the approach to the human activity recognition and fall detection problem as it provides a scheme that is computationally less intensive while providing promising results and therefore can contribute to edge deployment of such systems.

Saliency based human fall detection in smart home environments using posture recognition

The implementation of people monitoring system is an evolving research theme. This paper introduces an elderly monitoring system that recognizes human posture from overlapping cameras for people fall detection in a smart home environment. In these environments, the zone of movement is limited. Our approach used this characteristic to recognize human posture fastly by proposing a region-wise modelling approach. It classifies persons pose in four groups: standing, crouching, sitting and lying on the floor. These postures are obtained by calculating an estimation of the human bounding volume. This volume is estimated by obtaining the height of the person and its surface that is in contact with the ground according to the foreground information of each camera. Using them, we distinguish each postures and differentiate lying on floor posture, which can be considered as the falling posture from other postures. The global multiview information of the scene is obtaining by using homographic projection. We test our proposed algorithm on multiple cameras based fall detection public dataset and the results prove the efficiency of our method.

Empirical Mode Decomposition-Derived Entropy Features Are Beneficial to Distinguish Elderly People with a Falling History on a Force Plate Signal

Fall risk prediction is an important issue for the elderly. A center of pressure signal, derived from a force plate, is useful for the estimation of body calibration. However, it is still difficult to distinguish elderly people’s fall history by using a force plate signal. In this study, older adults with and without a history of falls were recruited to stand still for 60 s on a force plate. Forces in the x, y and z directions (Fx, Fy, and Fz) and center of pressure in the anteroposterior (COPx) and mediolateral directions (COPy) were derived. There were 49 subjects in the non-fall group, with an average age of 71.67 (standard derivation: 6.56). There were also 27 subjects in the fall group, with an average age of 70.66 (standard derivation: 6.38). Five signal series—forces in x, y, z (Fx, Fy, Fz), COPX, and COPy directions—were used. These five signals were further decomposed with empirical mode decomposition (EMD) with seven intrinsic mode functions. Time domain features (mean, standard derivation and coefficient of variations) and entropy features (approximate entropy and sample entropy) of the original signals and EMD-derived signals were extracted. Results showed that features extracted from the raw COP data did not differ significantly between the fall and non-fall groups. There were 10 features extracted using EMD, with significant differences observed among fall and non-fall groups. These included four features from COPx and two features from COPy, Fx and Fz.

Movement Tube Detection Network Integrating 3D CNN and Object Detection Framework to Detect Fall

Unlike most of the existing neural network-based fall detection methods, which only detect fall at the time range, the algorithm proposed in this paper detect fall in both spatial and temporal dimension. A movement tube detection network integrating 3D CNN and object detection framework such as SSD is proposed to detect human fall with constrained movement tubes. The constrained movement tube, which encapsulates the person with a sequence of bounding boxes, has the merits of encapsulating the person closely and avoiding peripheral interference. A 3D convolutional neural network is used to encode the motion and appearance features of a video clip, which are fed into the tube anchors generation layer, softmax classification, and movement tube regression layer. The movement tube regression layer fine tunes the tube anchors to the constrained movement tubes. A large-scale spatio-temporal (LSST) fall dataset is constructed using self-collected data to evaluate the fall detection in both spatial and temporal dimensions. LSST has three characteristics of large scale, annotation, and posture and viewpoint diversities. Furthermore, the comparative experiments on a public dataset demonstrate that the proposed algorithm achieved sensitivity, specificity an accuracy of 100%, 97.04%, and 97.23%, respectively, outperforms the existing methods.

The Association of Falls with Instability: An Analysis of Perceptions and Expectations toward the Use of Fall Detection Devices Among Older Adults in Malaysia

Background: Falls are a significant incident among older adults affecting one in every three individuals aged 65 and over. Fall risk increases with age and other factors, namely instability. Recent studies on the use of fall detection devices in the Malaysian community are scarce, despite the necessity to use them. Therefore, this study aimed to investigate the association between the prevalence of falls with instability. This study also presents a survey that explores older adults' perceptions and expectations toward fall detection devices.

Methods: A cross-sectional survey was conducted involving 336 community-dwelling older adults aged 50 years and older; based on randomly selected participants. Data were analyzed using quantitative descriptive analysis. Chi-square test was conducted to investigate the associations between self-reported falls with instability, demographic and walking characteristics. Additionally, older adults' perceptions and expectations concerning the use of fall detection devices in their daily lives were explored.

Results: The prevalence of falls was 28.9%, where one-quarter of older adults fell at least once in the past 6 months. Participants aged 70 years and older have a higher fall percentage than other groups. The prevalence of falls was significantly associated with instability, age, and walking characteristics. Around 70% of the participants reported having instability issues, of which over half of them fell at least once within 6 months. Almost 65% of the participants have a definite interest in using a fall detection device. Survey results revealed that the most expected features for a fall detection device include: user-friendly, followed by affordably priced, and accurate.

Conclusions: The prevalence of falls in community-dwelling older adults is significantly associated with instability. Positive perceptions and informative expectations will be used to develop an enhanced fall detection incorporating balance monitoring system. Our findings demonstrate the need to extend the fall detection device features aiming for fall prevention intervention.

Fall Detection from Electrocardiogram (ECG) Signals and Classification by Deep Transfer Learning

Fall is a prominent issue due to its severe consequences both physically and mentally. Fall detection and prevention is a critical area of research because it can help elderly people to depend less on caregivers and allow them to live and move more independently. Using electrocardiograms (ECG) signals independently for fall detection and activity classification is a novel approach used in this paper. An algorithm has been proposed which uses pre-trained convolutional neural networks AlexNet and GoogLeNet as a classifier between the fall and no fall scenarios using electrocardiogram signals. The ECGs for both falling and no falling cases were obtained as part of the study using eight volunteers. The signals are pre-processed using an elliptical filter for signal noises such as baseline wander and power-line interface. As feature extractors, frequency-time representations (scalograms) were obtained by applying a continuous wavelet transform on the filtered ECG signals. These scalograms were used as inputs to the neural network and a significant validation accuracy of 98.08% was achieved in the first model. The trained model is able to distinguish ECGs with a fall activity from an ECG with a no fall activity with an accuracy of 98.02%. For the verification of the robustness of the proposed algorithm, our experimental dataset was augmented by adding two different publicly available datasets to it. The second model can classify fall, daily activities and no activities with an accuracy of 98.44%. These models were developed by transfer learning from the domain of real images to the medical images. In comparison to traditional deep learning approaches, the transfer learning not only avoids “reinventing the wheel,” but also presents a lightweight solution to otherwise computationally heavy problems.

Privacy-Preserved Fall Detection Method with Three-Dimensional Convolutional Neural Network Using Low-Resolution Infrared Array Sensor

Due to the rapid aging of the population in recent years, the number of elderly people in hospitals and nursing homes is increasing, which results in a shortage of staff. Therefore, the situation of elderly citizens requires real-time attention, especially when dangerous situations such as falls occur. If staff cannot find and deal with them promptly, it might become a serious problem. For such a situation, many kinds of human motion detection systems have been in development, many of which are based on portable devices attached to a user’s body or external sensing devices such as cameras. However, portable devices can be inconvenient for users, while optical cameras are affected by lighting conditions and face privacy issues. In this study, a human motion detection system using a low-resolution infrared array sensor was developed to protect the safety and privacy of people who need to be cared for in hospitals and nursing homes. The proposed system can overcome the above limitations and have a wide range of application. The system can detect eight kinds of motions, of which falling is the most dangerous, by using a three-dimensional convolutional neural network. As a result of experiments of 16 participants and cross-validations of fall detection, the proposed method could achieve 98.8% and 94.9% of accuracy and F1-measure, respectively. They were 1% and 3.6% higher than those of a long short-term memory network, and show feasibility of real-time practical application.