The FARSEEING real-world fall repository: a large-scale collaborative database to collect and share sensor signals from real-world falls

StresSense: Real-Time detection of stress-displaying behaviors

BACKGROUND

Wrist-worn gadgets like smartphones are ideal for unobtrusively gathering user data, in various fields such as health and fitness monitoring, communication, and productivity enhancement. They seamlessly integrate into users' daily lives, providing valuable insights and features without the need for constant attention or disruption. In sensitive domains like mental health, these devices provide user-friendly, privacy-protected means of diagnosis and treatment, offering a secure and cost-effective avenue for seeking help.

OBJECTIVES

This study addresses the limitations of traditional mental health assessment techniques, such as intrusive sensing and subjective self-reporting, by harnessing the unobtrusive data collection capabilities of smartphones. Equipped with accelerometers and other sensors, these devices offer a novel approach to mental health research. Our objective was to develop methods for real-time detection of stress and boredom behavior markers using smart devices and machine learning algorithms.

METHODOLOGY

By leveraging data from accelerometers (A), gyroscopes (G), and magnetometers (M), we compiled a dataset indicative of stress-related behaviors and trained various machine-learning models for predictive accuracy. The methodology involved collecting data from motion sensors (A, G, and M) on the dominant arm's wrist-worn smartphone, followed by data preprocessing, transformation from time series format, and training a Deep Neural Network (DNN) model for activity recognition.

FINDINGS

Remarkably, the DNN achieved an accuracy of 93.50% on test data, outperforming traditional and ensemble machine learning methods across different window sizes, and demonstrated real-time accuracy of 77.78%, validating its practical application.

CONCLUSION

In conclusion, this research presents a novel dataset for detecting stress and boredom behaviors using smartphones, reducing reliance on costly devices and offering a more objective assessment. It also proposes a DNN-based method for wrist-worn devices to accurately identify complex activities associated with stress and boredom, with benefits in terms of privacy and user convenience. This advancement represents a significant contribution to the field of mental health research, providing a less intrusive and more user-friendly approach to monitoring mental well-being.

Wrist-Based Fall Detection: Towards Generalization across Datasets

Increasing age is related to a decrease in independence of movement and with this decrease comes falls, millions of falls occur every year and the most affected people are the older adults. These falls usually have a big impact on health and independence of the older adults, as well as financial impact on the health systems. Thus, many studies have developed fall detectors from several types of sensors. Previous studies related to the creation of fall detection systems models use only one dataset that usually has a small number of samples. Training and testing machine learning models in this small scope: (i) yield overoptimistic classification rates, (ii) do not generalize to real-life situations and (iii) have very high rate of false positives. Given this, the proposal of this research work is the creation of a new dataset that encompasses data from three different datasets, with more than 1300 fall samples and 28 K negative samples. Our new dataset includes a standard way of adding samples, which allow the future addition of other data sources. We evaluate our dataset by using classic cost-sensitive Machine Leaning methods that deal with class imbalance. For the training and validation of this model, a set of temporal and frequency features were extracted from the raw data of an accelerometer and a gyroscope using a sliding window of 2 s with an overlap of 50%. We study the generalization properties of each dataset, by testing on the other datasets and also the performance of our new dataset. The model showed a good ability to distinguish between activities of daily living and falls, achieving a recall of 90.57%, a specificity of 96.91% and an Area Under the Receiver Operating Characteristic curve (AUC-ROC) value of 98.85% against the combination of three datasets.

TinyFallNet: A Lightweight Pre-Impact Fall Detection Model

Falls represent a significant health concern for the elderly. While studies on deep learning-based preimpact fall detection have been conducted to mitigate fall-related injuries, additional efforts are needed for embedding in microcomputer units (MCUs). In this study, ConvLSTM, the state-of-the-art model, was benchmarked, and we attempted to lightweight it by leveraging features from image-classification models VGGNet and ResNet while maintaining performance for wearable airbags. The models were developed and evaluated using data from young subjects in the KFall public dataset based on an inertial measurement unit (IMU), leading to the proposal of TinyFallNet based on ResNet. Despite exhibiting higher accuracy (97.37% < 98.00%) than the benchmarked ConvLSTM, the proposed model requires lower memory (1.58 MB > 0.70 MB). Additionally, data on the elderly from the fall data of the FARSEEING dataset and activities of daily living (ADLs) data of the KFall dataset were analyzed for algorithm validation. This study demonstrated the applicability of image-classification models to preimpact fall detection using IMU and showed that additional tuning for lightweighting is possible due to the different data types. This research is expected to contribute to the lightweighting of deep learning models based on IMU and the development of applications based on IMU data.

Inertial Data-Based AI Approaches for ADL and Fall Recognition

The recognition of Activities of Daily Living (ADL) has been a widely debated topic, with applications in a vast range of fields. ADL recognition can be accomplished by processing data from wearable sensors, specially located at the lower trunk, which appears to be a suitable option in uncontrolled environments. Several authors have addressed ADL recognition using Artificial Intelligence (AI)-based algorithms, obtaining encouraging results. However, the number of ADL recognized by these algorithms is still limited, rarely focusing on transitional activities, and without addressing falls. Furthermore, the small amount of data used and the lack of information regarding validation processes are other drawbacks found in the literature. To overcome these drawbacks, a total of nine public and private datasets were merged in order to gather a large amount of data to improve the robustness of several ADL recognition algorithms. Furthermore, an AI-based framework was developed in this manuscript to perform a comparative analysis of several ADL Machine Learning (ML)-based classifiers. Feature selection algorithms were used to extract only the relevant features from the dataset’s lower trunk inertial data. For the recognition of 20 different ADL and falls, results have shown that the best performance was obtained with the K-NN classifier with the first 85 features ranked by Relief-F (98.22% accuracy). However, Ensemble Learning classifier with the first 65 features ranked by Principal Component Analysis (PCA) presented 96.53% overall accuracy while maintaining a lower classification time per window (0.039 ms), showing a higher potential for its usage in real-time scenarios in the future. Deep Learning algorithms were also tested. Despite its outcomes not being as good as in the prior procedure, their potential was also demonstrated (overall accuracy of 92.55% for Bidirectional Long Short-Term Memory (LSTM) Neural Network), indicating that they could be a valid option in the future.

Fall Risk Assessment Using Wearable Sensors: A Narrative Review

Recently, fall risk assessment has been a main focus in fall-related research. Wearable sensors have been used to increase the objectivity of this assessment, building on the traditional use of oversimplified questionnaires. However, it is necessary to define standard procedures that will us enable to acknowledge the multifactorial causes behind fall events while tackling the heterogeneity of the currently developed systems. Thus, it is necessary to identify the different specifications and demands of each fall risk assessment method. Hence, this manuscript provides a narrative review on the fall risk assessment methods performed in the scientific literature using wearable sensors. For each identified method, a comprehensive analysis has been carried out in order to find trends regarding the most used sensors and its characteristics, activities performed in the experimental protocol, and algorithms used to classify the fall risk. We also verified how studies performed the validation process of the developed fall risk assessment systems. The identification of trends for each fall risk assessment method would help researchers in the design of standard innovative solutions and enhance the reliability of this assessment towards a homogeneous benchmark solution.

A Reliable Fall Detection System Based on Analyzing the Physical Activities of Older Adults Living in Long-Term Care Facilities

Fall detection systems are designed in view to reduce the serious consequences of falls thanks to the early automatic detection that enables a timely medical intervention. The majority of the state-of-the-art fall detection systems are based on machine learning (ML). For training and performance evaluation, they use some datasets that are collected following predefined simulation protocols i.e. subjects are asked to perform different types of activities and to repeat them several times. Apart from the quality of simulating the activities, protocol-based data collection results in big differences between the distribution of the activities of daily living (ADLs) in these datasets in comparison with the actual distribution in real life. In this work, we first show the effects of this problem on the sensitivity of the ML algorithms and on the interpretability of the reported specificity. Then, we propose a reliable design of an ML-based fall detection system that aims at discriminating falls from the ambiguous ADLs. The latter are extracted from 400 days of recorded activities of older adults experiencing their daily life. The proposed system can be used in neck- and wrist-worn fall detectors. In addition, it is invariant to the rotation of the wearable device. The proposed system shows 100% of sensitivity while it generates an average of one false positive every 25 days for the neck-worn device and an average of one false positive every 3 days for the wrist-worn device.

Support Vector Machine Classifiers Show High Generalizability in Automatic Fall Detection in Older Adults

Falls are a major cause of morbidity and mortality in neurological disorders. Technical means of detecting falls are of high interest as they enable rapid notification of caregivers and emergency services. Such approaches must reliably differentiate between normal daily activities and fall events. A promising technique might be based on the classification of movements based on accelerometer signals by machine-learning algorithms, but the generalizability of classifiers trained on laboratory data to real-world datasets is a common issue. Here, three machine-learning algorithms including Support Vector Machine (SVM), k-Nearest Neighbors (kNN), and Random Forest (RF) were trained to detect fall events. We used a dataset containing intentional falls (SisFall) to train the classifier and validated the approach on a different dataset which included real-world accidental fall events of elderly people (FARSEEING). The results suggested that the linear SVM was the most suitable classifier in this cross-dataset validation approach and reliably distinguished a fall event from normal everyday activity at an accuracy of 93% and similarly high sensitivity and specificity. Thus, classifiers based on linear SVM might be useful for automatic fall detection in real-world applications.

Wearable inertial sensors for human movement analysis: a five-year update

INTRODUCTION

The aim of the present review is to track the evolution of wearable IMUs from their use in supervised laboratory- and ambulatory-based settings to their application for long-term monitoring of human movement in unsupervised naturalistic settings.

AREAS COVERED

Four main emerging areas of application were identified and synthesized, namely, mobile health solutions (specifically, for the assessment of frailty, risk of falls, chronic neurological diseases, and for the monitoring and promotion of active living), occupational ergonomics, rehabilitation and telerehabilitation, and cognitive assessment. Findings from recent scientific literature in each of these areas was synthesized from an applied and/or clinical perspective with the purpose of providing clinical researchers and practitioners with practical guidance on contemporary uses of inertial sensors in applied clinical settings.

EXPERT OPINION

IMU-based wearable devices have undergone a rapid transition from use in laboratory-based clinical practice to unsupervised, applied settings. Successful use of wearable inertial sensing for assessing mobility, motor performance and movement disorders in applied settings will rely also on machine learning algorithms for managing the vast amounts of data generated by these sensors for extracting information that is both clinically relevant and interpretable by practitioners.

Comparing fall detection methods in people with multiple sclerosis: A prospective observational cohort study

Background Falls occur across the population but are more common, and have more negative sequelae, in people with multiple sclerosis (MS). Given the prevalence and impact of falls, accurate measures of fall frequency are needed. This study compares the sensitivity and false discovery rates of three methods of fall detection: the current gold standard, prospective paper fall calendars, real-time self-reporting and automated detection, the latter two from a novel body-worn device. Methods Falls in twenty-five people with MS were recorded for eight weeks with prospective fall calendars, real-time body-worn self-report, and an automated body-worn detector concurrently. Eligible individuals were adults with MS enrolled in a randomized controlled trial of a fall prevention intervention. Entry criteria were at least two falls or near-falls in the previous two months, Expanded Disability Status Scale ≤ 6.0, community dwelling, and no MS relapse in the previous month. The sensitivity (proportion of true falls detected) and false discovery rates (proportion of false reports generated) of the fall detection methods were compared. A true fall was a fall reported by at least two methods. A false report was a fall reported by only one method. The trial is registered on ClinicalTrials.gov (NCT02583386) and is closed. Results In the 1,276 person-days of fall counting with all three methods in use simultaneously there were 1344 unique fall events. Of these, 8.5% (114) were true falls and 91.5% (1230) were false reports. Fall calendars had the lowest sensitivity (0.614) and the lowest false discovery rate (0.067). The automated detector had the highest sensitivity (0.921) and the highest false discovery rate (0.919). All methods generated under one false report per day. There were no fall detection-related adverse events. Conclusion Fall calendars likely underestimate fall frequency by around 40%. The automated detector evaluated here misses very few falls but likely overestimates the number of falls by around one fall per day. Additional research is needed to produce an ideal fall detection and counting method for use in clinical and research applications. Funding United States Department of Veterans Affairs, Rehabilitations Research and Development Service.

A smartphone-based online system for fall detection with alert notifications and contextual information of real-life falls

BACKGROUND

Falls are a leading cause of accidental deaths and injuries worldwide. The risk of falling is especially high for individuals suffering from balance impairments. Retrospective surveys and studies of simulated falling in lab conditions are frequently used and are informative, but prospective information about real-life falls remains sparse. Such data are essential to address fall risks and develop fall detection and alert systems. Here we present the results of a prospective study investigating a proof-of-concept, smartphone-based, online system for fall detection and notification.

METHODS

The system uses the smartphone's accelerometer and gyroscope to monitor the participants' motion, and falls are detected using a regularized logistic regression. Data on falls and near-fall events (i.e., stumbles) is stored in a cloud server and fall-related variables are logged onto a web portal developed for data exploration, including the event time and weather, fall probability, and the faller's location and activity before the fall.

RESULTS

In total, 23 individuals with an elevated risk of falling carried the phones for 2070 days in which the model classified 14,904,000 events. The system detected 27 of the 37 falls that occurred (sensitivity = 73.0 %) and resulted in one false alarm every 46 days (specificity > 99.9 %, precision = 37.5 %). 42.2 % of the events falsely classified as falls were validated as stumbles.

CONCLUSIONS

The system's performance shows the potential of using smartphones for fall detection and notification in real-life. Apart from functioning as a practical fall monitoring instrument, this system may serve as a valuable research tool, enable future studies to scale their ability to capture fall-related data, and help researchers and clinicians to investigate real-falls.

A Large-Scale Open Motion Dataset (KFall) and Benchmark Algorithms for Detecting Pre-impact Fall of the Elderly Using Wearable Inertial Sensors

Research on pre-impact fall detection with wearable inertial sensors (detecting fall accidents prior to body-ground impacts) has grown rapidly in the past decade due to its great potential for developing an on-demand fall-related injury prevention system. However, most researchers use their own datasets to develop fall detection algorithms and rarely make these datasets publicly available, which poses a challenge to fairly evaluate the performance of different algorithms on a common basis. Even though some open datasets have been established recently, most of them are impractical for pre-impact fall detection due to the lack of temporal labels for fall time and limited types of motions. In order to overcome these limitations, in this study, we proposed and publicly provided a large-scale motion dataset called “KFall,” which was developed from 32 Korean participants while wearing an inertial sensor on the low back and performing 21 types of activities of daily living and 15 types of simulated falls. In addition, ready-to-use temporal labels of the fall time based on synchronized motion videos were published along with the dataset. Those enhancements make KFall the first public dataset suitable for pre-impact fall detection, not just for post-fall detection. Importantly, we have also developed three different types of latest algorithms (threshold based, support-vector machine, and deep learning), using the KFall dataset for pre-impact fall detection so that researchers and practitioners can flexibly choose the corresponding algorithm. Deep learning algorithm achieved both high overall accuracy and balanced sensitivity (99.32%) and specificity (99.01%) for pre-impact fall detection. Support vector machine also demonstrated a good performance with a sensitivity of 99.77% and specificity of 94.87%. However, the threshold-based algorithm showed relatively poor results, especially the specificity (83.43%) was much lower than the sensitivity (95.50%). The performance of these algorithms could be regarded as a benchmark for further development of better algorithms with this new dataset. This large-scale motion dataset and benchmark algorithms could provide researchers and practitioners with valuable data and references to develop new technologies and strategies for pre-impact fall detection and proactive injury prevention for the elderly.

Event-Centered Data Segmentation in Accelerometer-Based Fall Detection Algorithms

Automatic fall detection systems ensure that elderly people get prompt assistance after experiencing a fall. Fall detection systems based on accelerometer measurements are widely used because of their portability and low cost. However, the ability of these systems to differentiate falls from Activities of Daily Living (ADL) is still not acceptable for everyday usage at a large scale. More work is still needed to raise the performance of these systems. In our research, we explored an essential but often neglected part of accelerometer-based fall detection systems-data segmentation. The aim of our work was to explore how different configurations of windows for data segmentation affect detection accuracy of a fall detection system and to find the best-performing configuration. For this purpose, we designed a testing environment for fall detection based on a Support Vector Machine (SVM) classifier and evaluated the influence of the number and duration of segmentation windows on the overall detection accuracy. Thereby, an event-centered approach for data segmentation was used, where windows are set relative to a potential fall event detected in the input data. Fall and ADL data records from three publicly available datasets were utilized for the test. We found that a configuration of three sequential windows (pre-impact, impact, and post-impact) provided the highest detection accuracy on all three datasets. The best results were obtained when either a 0.5 s or a 1 s long impact window was used, combined with pre- and post-impact windows of 3.5 s or 3.75 s.

Domain-Adaptive Fall Detection Using Deep Adversarial Training

Fall detection (FD) systems are important assistive technologies for healthcare that can detect emergency fall events and alert caregivers. However, it is not easy to obtain large-scale annotated fall events with various specifications of sensors or sensor positions during the implementation of accurate FD systems. Moreover, the knowledge obtained through machine learning has been restricted to tasks in the same domain. The mismatch between different domains might hinder the performance of FD systems. Cross-domain knowledge transfer is very beneficial for machine-learning based FD systems to train a reliable FD model with well-labeled data in new environments. In this study, we propose domain-adaptive fall detection (DAFD) using deep adversarial training (DAT) to tackle cross-domain problems, such as cross-position and cross-configuration. The proposed DAFD can transfer knowledge from the source domain to the target domain by minimizing the domain discrepancy to avoid mismatch problems. The experimental results show that the average F1-score improvement when using DAFD ranges from 1.5% to 7% in the cross-position scenario, and from 3.5% to 12% in the cross-configuration scenario, compared to using the conventional FD model without domain adaptation training. The results demonstrate that the proposed DAFD successfully helps to deal with cross-domain problems and to achieve better detection performance.

NT-FDS-A Noise Tolerant Fall Detection System Using Deep Learning on Wearable Devices

Given the high prevalence and detrimental effects of unintentional falls in the elderly, fall detection has become a pertinent public concern. A Fall Detection System (FDS) gathers information from sensors to distinguish falls from routine activities in order to provide immediate medical assistance. Hence, the integrity of collected data becomes imperative. Presence of missing values in data, caused by unreliable data delivery, lossy sensors, local interference and synchronization disturbances and so forth, greatly hamper the credibility and usefulness of data making it unfit for reliable fall detection. This paper presents a noise tolerant FDS performing in presence of missing values in data. The work focuses on Deep Learning (DL) particularly Recurrent Neural Networks (RNNs) with an underlying Bidirectional Long Short-Term Memory (BiLSTM) stack to implement FDS based on wearable sensors. The proposed technique is evaluated on two publicly available datasets—SisFall and UP-Fall Detection. Our system produces an accuracy of 97.21% and 97.41%, sensitivity of 96.97% and 99.77% and specificity of 93.18% and 91.45% on SisFall and UP-Fall Detection respectively, thus outperforming the existing state of the art on these benchmark datasets. The resultant outcomes suggest that the ability of BiLSTM to retain long term dependencies from past and future make it an appropriate model choice to handle missing values for wearable fall detection systems.

U-turn speed is a valid and reliable smartphone-based measure of multiple sclerosis-related gait and balance impairment

BACKGROUND

People living with multiple sclerosis (MS) experience impairments in gait and mobility, that are not fully captured with manually timed walking tests or rating scales administered during periodic clinical visits. We have developed a smartphone-based assessment of ambulation performance, the 5 U-Turn Test (5UTT), a quantitative self-administered test of U-turn ability while walking, for people with MS (PwMS).

RESEARCH QUESTION

What is the test-retest reliability and concurrent validity of U-turn speed, an unsupervised self-assessment of gait and balance impairment, measured using a body-worn smartphone during the 5UTT?

METHODS

76 PwMS and 25 healthy controls (HCs) participated in a cross-sectional non-randomised interventional feasibility study. The 5UTT was self-administered daily and the median U-turn speed, measured during a 14-day session, was compared against existing validated in-clinic measures of MS-related disability.

RESULTS

U-turn speed, measured during a 14-day session from the 5UTT, demonstrated good-to-excellent test-retest reliability in PwMS alone and combined with HCs (intraclass correlation coefficient [ICC] = 0.87 [95 % CI: 0.80-0.92]) and moderate-to-excellent reliability in HCs alone (ICC = 0.88 [95 % CI: 0.69-0.96]). U-turn speed was significantly correlated with in-clinic measures of walking speed, physical fatigue, ambulation impairment, overall MS-related disability and patients' self-perception of quality of life, at baseline, Week 12 and Week 24. The minimal detectable change of the U-turn speed from the 5UTT was low (19.42 %) in PwMS and indicates a good precision of this measurement tool when compared with conventional in-clinic measures of walking performance.

SIGNIFICANCE

The frequent self-assessment of turn speed, as an outcome measure from a smartphone-based U-turn test, may represent an ecologically valid digital solution to remotely and reliably monitor gait and balance impairment in a home environment during MS clinical trials and practice.

Body-Worn Sensors for Remote Monitoring of Parkinson's Disease Motor Symptoms: Vision, State of the Art, and Challenges Ahead

The increasing prevalence of neurodegenerative conditions such as Parkinson's disease (PD) and related mobility issues places a serious burden on healthcare systems. The COVID-19 pandemic has reinforced the urgent need for better tools to manage chronic conditions remotely, as regular access to clinics may be problematic. Digital health technology in the form of remote monitoring with body-worn sensors offers significant opportunities for transforming research and revolutionizing the clinical management of PD. Significant efforts are being invested in the development and validation of digital outcomes to support diagnosis and track motor and mobility impairments "off-line". Imagine being able to remotely assess your patient, understand how well they are functioning, evaluate the impact of any recent medication/intervention, and identify the need for urgent follow-up before overt, irreparable change takes place? This could offer new pragmatic solutions for personalized care and clinical research. So the question remains: how close are we to achieving this? Here, we describe the state-of-the-art based on representative papers published between 2017 and 2020. We focus on remote (i.e., real-world, daily-living) monitoring of PD using body-worn sensors (e.g., accelerometers, inertial measurement units) for assessing motor symptoms and their complications. Despite the tremendous potential, existing challenges exist (e.g., validity, regulatory) that are preventing the widespread clinical adoption of body-worn sensors as a digital outcome. We propose a roadmap with clear recommendations for addressing these challenges and future directions to bring us closer to the implementation and widespread adoption of this important way of improving the clinical care, evaluation, and monitoring of PD.

On the Heterogeneity of Existing Repositories of Movements Intended for the Evaluation of Fall Detection Systems

Due to the serious impact of falls on the autonomy and health of older people, the investigation of wearable alerting systems for the automatic detection of falls has gained considerable scientific interest in the field of body telemonitoring with wireless sensors. Because of the difficulties of systematically validating these systems in a real application scenario, Fall Detection Systems (FDSs) are typically evaluated by studying their response to datasets containing inertial sensor measurements captured during the execution of labelled nonfall and fall movements. In this context, during the last decade, numerous publicly accessible databases have been released aiming at offering a common benchmarking tool for the validation of the new proposals on FDSs. This work offers a comparative and updated analysis of these existing repositories. For this purpose, the samples contained in the datasets are characterized by different statistics that model diverse aspects of the mobility of the human body in the time interval where the greatest change in the acceleration module is identified. By using one-way analysis of variance (ANOVA) on the series of these features, the comparison shows the significant differences detected between the datasets, even when comparing activities that require a similar degree of physical effort. This heterogeneity, which may result from the great variability of the sensors, experimental users, and testbeds employed to generate the datasets, is relevant because it casts doubt on the validity of the conclusions of many studies on FDSs, since most of the proposals in the literature are only evaluated using a single database.

Accelerometer-Based Fall Detection Using Machine Learning: Training and Testing on Real-World Falls

Falling is a significant health problem. Fall detection, to alert for medical attention, has been gaining increasing attention. Still, most of the existing studies use falls simulated in a laboratory environment to test the obtained performance. We analyzed the acceleration signals recorded by an inertial sensor on the lower back during 143 real-world falls (the most extensive collection to date) from the FARSEEING repository. Such data were obtained from continuous real-world monitoring of subjects with a moderate-to-high risk of falling. We designed and tested fall detection algorithms using features inspired by a multiphase fall model and a machine learning approach. The obtained results suggest that algorithms can learn effectively from features extracted from a multiphase fall model, consistently overperforming more conventional features. The most promising method (support vector machines and features from the multiphase fall model) obtained a sensitivity higher than 80%, a false alarm rate per hour of 0.56, and an F-measure of 64.6%. The reported results and methodologies represent an advancement of knowledge on real-world fall detection and suggest useful metrics for characterizing fall detection systems for real-world use.

Elderly Fall Detection Systems: A Literature Survey

Falling is among the most damaging event elderly people may experience. With the ever-growing aging population, there is an urgent need for the development of fall detection systems. Thanks to the rapid development of sensor networks and the Internet of Things (IoT), human-computer interaction using sensor fusion has been regarded as an effective method to address the problem of fall detection. In this paper, we provide a literature survey of work conducted on elderly fall detection using sensor networks and IoT. Although there are various existing studies which focus on the fall detection with individual sensors, such as wearable ones and depth cameras, the performance of these systems are still not satisfying as they suffer mostly from high false alarms. Literature shows that fusing the signals of different sensors could result in higher accuracy and lower false alarms, while improving the robustness of such systems. We approach this survey from different perspectives, including data collection, data transmission, sensor fusion, data analysis, security, and privacy. We also review the benchmark data sets available that have been used to quantify the performance of the proposed methods. The survey is meant to provide researchers in the field of elderly fall detection using sensor networks with a summary of progress achieved up to date and to identify areas where further effort would be beneficial.

Re-Enactment as a Method to Reproduce Real-World Fall Events Using Inertial Sensor Data: Development and Usability Study

BACKGROUND

Falls are a common health problem, which in the worst cases can lead to death. To develop reliable fall detection algorithms as well as suitable prevention interventions, it is important to understand circumstances and characteristics of real-world fall events. Although falls are common, they are seldom observed, and reports are often biased. Wearable inertial sensors provide an objective approach to capture real-world fall signals. However, it is difficult to directly derive visualization and interpretation of body movements from the fall signals, and corresponding video data is rarely available.

OBJECTIVE

The re-enactment method uses available information from inertial sensors to simulate fall events, replicate the data, validate the simulation, and thereby enable a more precise description of the fall event. The aim of this paper is to describe this method and demonstrate the validity of the re-enactment approach.

METHODS

Real-world fall data, measured by inertial sensors attached to the lower back, were selected from the Fall Repository for the Design of Smart and Self-Adaptive Environments Prolonging Independent Living (FARSEEING) database. We focused on well-described fall events such as stumbling to be re-enacted under safe conditions in a laboratory setting. For the purposes of exemplification, we selected the acceleration signal of one fall event to establish a detailed simulation protocol based on identified postures and trunk movement sequences. The subsequent re-enactment experiments were recorded with comparable inertial sensor configurations as well as synchronized video cameras to analyze the movement behavior in detail. The re-enacted sensor signals were then compared with the real-world signals to adapt the protocol and repeat the re-enactment method if necessary. The similarity between the simulated and the real-world fall signals was analyzed with a dynamic time warping algorithm, which enables the comparison of two temporal sequences varying in speed and timing.

RESULTS

A fall example from the FARSEEING database was used to show the feasibility of producing a similar sensor signal with the re-enactment method. Although fall events were heterogeneous concerning chronological sequence and curve progression, it was possible to reproduce a good approximation of the motion of a person's center of mass during fall events based on the available sensor information.

CONCLUSIONS

Re-enactment is a promising method to understand and visualize the biomechanics of inertial sensor-recorded real-world falls when performed in a suitable setup, especially if video data is not available.

A Study on the Application of Convolutional Neural Networks to Fall Detection Evaluated with Multiple Public Datasets

Due to the repercussion of falls on both the health and self-sufficiency of older people and on the financial sustainability of healthcare systems, the study of wearable fall detection systems (FDSs) has gained much attention during the last years. The core of a FDS is the algorithm that discriminates falls from conventional Activities of Daily Life (ADLs). This work presents and evaluates a convolutional deep neural network when it is applied to identify fall patterns based on the measurements collected by a transportable tri-axial accelerometer. In contrast with most works in the related literature, the evaluation is performed against a wide set of public data repositories containing the traces obtained from diverse groups of volunteers during the execution of ADLs and mimicked falls. Although the method can yield very good results when it is hyper-parameterized for a certain dataset, the global evaluation with the other repositories highlights the difficulty of extrapolating to other testbeds the network architecture that was configured and optimized for a particular dataset.

Home-based monitoring of falls using wearable sensors in Parkinson's disease

INTRODUCTION

Falling is among the most serious clinical problems in Parkinson's disease (PD). We used body-worn sensors (falls detector worn as a necklace) to quantify the hazard ratio of falls in PD patients in real life.

METHODS

We matched all 2063 elderly individuals with self-reported PD to 2063 elderly individuals without PD based on age, gender, comorbidity, and living conditions. We analyzed fall events collected at home via a wearable sensor. Fall events were collected either automatically using the wearable falls detector or were registered by a button push on the same device. We extracted fall events from a 2.5-year window, with an average follow-up of 1.1 years. All falls included were confirmed immediately by a subsequent telephone call. The outcomes evaluated were (1) incidence rate of any fall, (2) incidence rate of a new fall after enrollment (ie, hazard ratio), and (3) 1-year cumulative incidence of falling.

RESULTS

The incidence rate of any fall was higher among self-reported PD patients than controls (2.1 vs. 0.7 falls/person, respectively; P < .0001). The incidence rate of a new fall after enrollment (ie, hazard ratio) was 1.8 times higher for self-reported PD patients than controls (95% confidence interval, 1.6-2.0).

CONCLUSION

Having PD nearly doubles the incidence of falling in real life. These findings highlight PD as a prime "falling disease." The results also point to the feasibility of using body-worn sensors to monitor falls in daily life. © 2019 The Authors. Movement Disorders published by Wiley Periodicals, Inc. on behalf of International Parkinson and Movement Disorder Society.

Wearable Embedded Intelligence for Detection of Falls Independently of on-Body Location

Falls are one of the most common problems in the elderly population. Therefore, each year more solutions for automatic fall detection are emerging. This paper proposes a single accelerometer algorithm for wearable devices that works for three different body locations: chest, waist and pocket, without a calibration step being required. This algorithm is able to be fully executed on a wearable device and no external devices are necessary for data processing. Additionally, a study of the accelerometer sampling rate, that allows the algorithm to achieve a better performance, was performed. The algorithm was validated with a continuous dataset with daily living activities and 272 simulated falls. Considering the trade-off between sensitivity and the number of false alarms the most suitable sampling rate found was 50 Hz. The proposed algorithm was able to achieve a trade-off of no false alarms and 89.5% of fall detection rate when wearing the sensor on the user's waist with a medium sensitivity level of the algorithm. In conclusion, this paper presents a reliable solution for automatic fall detection that can be adapted to different usages and conditions, since it can be used in different body locations and its sensitivity can be adapted to different subjects according to their physical activity level.

UP-Fall Detection Dataset: A Multimodal Approach

Falls, especially in elderly persons, are an important health problem worldwide. Reliable fall detection systems can mitigate negative consequences of falls. Among the important challenges and issues reported in literature is the difficulty of fair comparison between fall detection systems and machine learning techniques for detection. In this paper, we present UP-Fall Detection Dataset. The dataset comprises raw and feature sets retrieved from 17 healthy young individuals without any impairment that performed 11 activities and falls, with three attempts each. The dataset also summarizes more than 850 GB of information from wearable sensors, ambient sensors and vision devices. Two experimental use cases were shown. The aim of our dataset is to help human activity recognition and machine learning research communities to fairly compare their fall detection solutions. It also provides many experimental possibilities for the signal recognition, vision, and machine learning community.

Transfer learning approach for fall detection with the FARSEEING real-world dataset and simulated falls

Falls are very rare and extremely difficult to acquire in free living conditions. Due to this, most of prior work on fall detection has focused on simulated datasets acquired in scenarios that mimic the real-world context, however, the validation of systems trained with simulated falls remains unclear. This work presents a transfer learning approach for combining a dataset of simulated falls and non-falls, obtained from young volunteers, with the real-world FARSEEING dataset, in order to train a set of supervised classifiers for discriminating between falls and non-falls events. The objective is to analyze if a combination of simulated and real falls could enrich the model. In the real-world, falls are a sporadic event, which results in imbalanced datasets. In this work, several methods for imbalance learning were employed: SMOTE, Balance Cascade and Ranking models. The Balance Cascade obtained less misclassifications in the validation set.There was an improvement when mixing the real falls and simulated non-falls compared to the case when only simulated falls were used for training. When testing with a mixed set with real falls and simulated non-falls, it is even more important to train with a mixed set. Moreover, it was possible to onclude that a model trained with simulated falls generalize better when tested with real falls, than the opposite. The overall accuracy obtained for the combination of different datasets were above 95 %.

SmartFall: A Smartwatch-Based Fall Detection System Using Deep Learning

This paper presents SmartFall, an Android app that uses accelerometer data collected from a commodity-based smartwatch Internet of Things (IoT) device to detect falls. The smartwatch is paired with a smartphone that runs the SmartFall application, which performs the computation necessary for the prediction of falls in real time without incurring latency in communicating with a cloud server, while also preserving data privacy. We experimented with both traditional (Support Vector Machine and Naive Bayes) and non-traditional (Deep Learning) machine learning algorithms for the creation of fall detection models using three different fall datasets (Smartwatch, Notch, Farseeing). Our results show that a Deep Learning model for fall detection generally outperforms more traditional models across the three datasets. This is attributed to the Deep Learning model’s ability to automatically learn subtle features from the raw accelerometer data that are not available to Naive Bayes and Support Vector Machine, which are restricted to learning from a small set of extracted features manually specified. Furthermore, the Deep Learning model exhibits a better ability to generalize to new users when predicting falls, an important quality of any model that is to be successful in the real world. We also present a three-layer open IoT system architecture used in SmartFall, which can be easily adapted for the collection and analysis of other sensor data modalities (e.g., heart rate, skin temperature, walking patterns) that enables remote monitoring of a subject’s wellbeing.

Methods for the Real-World Evaluation of Fall Detection Technology: A Scoping Review

Falls in older adults present a major growing healthcare challenge and reliable detection of falls is crucial to minimise their consequences. The majority of development and testing has used laboratory simulations. As simulations do not cover the wide range of real-world scenarios performance is poor when retested using real-world data. There has been a move from the use of simulated falls towards the use of real-world data. This review aims to assess the current methods for real-world evaluation of fall detection systems, identify their limitations and propose improved robust methods of evaluation. Twenty-two articles met the inclusion criteria and were assessed with regard to the composition of the datasets, data processing methods and the measures of performance. Real-world tests of fall detection technology are inherently challenging and it is clear the field is in its infancy. Most studies used small datasets and studies differed on how to quantify the ability to avoid false alarms and how to identify non-falls, a concept which is virtually impossible to define and standardise. To increase robustness and make results comparable, larger standardised datasets are needed containing data from a range of participant groups. Measures that depend on the definition and identification of non-falls should be avoided. Sensitivity, precision and F-measure emerged as the most suitable robust measures for evaluating the real-world performance of fall detection systems.

Satisfying Product Features of a Fall Prevention Smartphone App and Potential Users' Willingness to Pay: Web-Based Survey Among Older Adults

Background

Prohibiting falls and fall-related injuries is a major challenge for health care systems worldwide, as a substantial proportion of falls occur in older adults who are previously known to be either frail or at high risk for falls. Hence, preventive measures are needed to educate and minimize the risk for falls rather than just minimize older adults’ fall risk. Health apps have the potential to address this problem, as they enable users to self-assess their individual fall risk.

Objective

The objective of this study was to identify product features of a fall prevention smartphone app, which increase or decrease users’ satisfaction. In addition, willingness to pay (WTP) was assessed to explore how much revenue such an app could generate.

Methods

A total of 96 participants completed an open self-selected Web-based survey. Participants answered various questions regarding health status, subjective and objective fall risk, and technical readiness. Seventeen predefined product features of a fall prevention smartphone app were evaluated twice: first, according to a functional (product feature is implemented in the app), and subsequently by a dysfunctional (product feature is not implemented in the app) question. On the basis of the combination of answers from these 2 questions, the product feature was assigned to a certain category (must-be, attractive, one-dimensional, indifferent, or questionable product feature). This method is widely used in user-oriented product development and captures users’ expectations of a product and how their satisfaction is influenced by the availability of individual product features.

Results

Five product features were identified to increase users’ acceptance, including (1) a checklist of typical tripping hazards, (2) an emergency guideline in case of a fall, (3) description of exercises and integrated workout plans that decrease the risk of falling, (4) inclusion of a continuous workout program, and (5) cost coverage by health insurer. Participants’ WTP was assessed after all 17 product features were rated and revealed a median monthly payment WTP rate of €5.00 (interquartile range 10.00).

Conclusions

The results show various motivating product features that should be incorporated into a fall prevention smartphone app. Results reveal aspects that fall prevention and intervention designers should keep in mind to encourage individuals to start joining their program and facilitate long-term user engagement, resulting in a greater interest in fall risk prevention.

Estimation of Foot Plantar Center of Pressure Trajectories with Low-Cost Instrumented Insoles Using an Individual-Specific Nonlinear Model

Postural control is a complex skill based on the interaction of dynamic sensorimotor processes, and can be challenging for people with deficits in sensory functions. The foot plantar center of pressure (COP) has often been used for quantitative assessment of postural control. Previously, the foot plantar COP was mainly measured by force plates or complicated and expensive insole-based measurement systems. Although some low-cost instrumented insoles have been developed, their ability to accurately estimate the foot plantar COP trajectory was not robust. In this study, a novel individual-specific nonlinear model was proposed to estimate the foot plantar COP trajectories with an instrumented insole based on low-cost force sensitive resistors (FSRs). The model coefficients were determined by a least square error approximation algorithm. Model validation was carried out by comparing the estimated COP data with the reference data in a variety of postural control assessment tasks. We also compared our data with the COP trajectories estimated by the previously well accepted weighted mean approach. Comparing with the reference measurements, the average root mean square errors of the COP trajectories of both feet were 2.23 mm (±0.64) (left foot) and 2.72 mm (±0.83) (right foot) along the medial–lateral direction, and 9.17 mm (±1.98) (left foot) and 11.19 mm (±2.98) (right foot) along the anterior–posterior direction. The results are superior to those reported in previous relevant studies, and demonstrate that our proposed approach can be used for accurate foot plantar COP trajectory estimation. This study could provide an inexpensive solution to fall risk assessment in home settings or community healthcare center for the elderly. It has the potential to help prevent future falls in the elderly.

Differences Between Gait on Stairs and Flat Surfaces in Relation to Fall Risk and Future Falls

We used body-worn inertial sensors to quantify differences in semi-free-living gait between stairs and on normal flat ground in older adults, and investigated the utility of assessing gait on these terrains for predicting the occurrence of multiple falls. Eighty-two community-dwelling older adults wore two inertial sensors, on the lower back and the right ankle, during several bouts of walking on flat surfaces and up and down stairs, in between rests and activities of daily living. Derived from the vertical acceleration at the lower back, step rate was calculated from the signal's fundamental frequency. Step rate variability was the width of this fundamental frequency peak from the signal's power spectral density. Movement vigor was calculated at both body locations from the signal variance. Partial Spearman correlations between gait parameters and physiological fall risk factors (components from the Physiological Profile Assessment) were calculated while controlling for age and gender. Overall, anteroposterior vigor at the lower back in stair descent was lower in subjects with longer reaction times. Older adults walked more slowly on stairs, but they were not significantly slower on flat surfaces. Using logistic regression, faster step rate in stair descent was associated with multiple prospective falls over 12 months. No significant associations were shown from gait parameters derived during walking upstairs or on flat surfaces. These results suggest that stair descent gait may provide more insight into fall risk than regular walking and stair ascent, and that further sensor-based investigation into unsupervised gait on different terrains would be valuable.