Wearable Fall Detection System Research Articles

Fall Detection Based on Data-Adaptive Gaussian Average Filtering Decomposition and Machine Learning

Falls are a significant health concern leading to increased morbidity and healthcare costs, especially for the elderly. Early and accurate detection of fall events is critical for timely intervention and preventing severe complications. This study presents a novel approach to triaxial accelerometer signals by employing data-adaptive Gaussian average filtering (DAGAF) decomposition in conjunction with machine learning techniques for fall detection. The triaxial accelerometer signals from the FallAllD dataset were decomposed into intrinsic mode functions (IMFs) and a residual component, from which feature vectors were extracted to train support vector machine (SVM) and k-nearest neighbor (kNN) classifiers. Experimental results demonstrate that the combination of the first and the third IMFs with the residual component yields the highest classification accuracy of 96.34%, with SVM outperforming kNN across all performance metrics. This approach significantly improves fall detection accuracy compared to using raw accelerometer signals, highlighting its potential in enhancing wearable fall detection systems. The proposed DAGAF decomposition method not only enhances feature extraction but also provides a promising advancement in the field, suggesting its potential to increase the reliability and accuracy of fall detection in practical applications.

Cross-dataset evaluation of wearable fall detection systems using data from real falls and long-term monitoring of daily life

The evaluation of fall detection systems based on wearables is controversial as most studies in the literature benchmark their proposals against falls that are simulated by experimental subjects under unrealistic laboratory conditions. In order to systematically investigate the suitability of this procedure, this paper evaluates a wide set of artificial intelligence algorithms used for fall detection, when trained with a large number of datasets containing acceleration samples captured during the emulation of falls and ordinary movements and then tested with the signals of both actual falls and long-term traces collected from the constant monitoring of users during their daily routines. The results, based on a large number of repositories, show a remarkable degradation in all performance metrics (sensitivity, specificity and false alarm hourly rate) with respect to the typical case in which the detectors are tested with the same types of laboratory movements for which they were trained.

Interactive design of intelligent wearable products based on network communication technology

At this stage, network communication technology is increasingly mature, and intelligent wearable products are also widely used in human daily life. Wearable products are popular with users because of their numerous types, complete functions and convenient services. Wearable products integrate interaction technology, and users can interact with products. However, how to improve the user’s interaction experience and reduce the user’s cognitive burden on the interaction interface is an urgent problem in the current product interaction design. Therefore, based on the analysis of the types and related technologies of wearable products, this paper made a specific analysis of the interaction design of wearable products, and established an interaction design model. At the same time, the wearable fall detection system was also tested by machine learning algorithm. The experimental results showed that the average test result of the algorithm in this paper was 87.39%, while the average test result of the traditional algorithm was 83.79%. In terms of the missed alarm rate of fall detection, the average test result of this algorithm was 6.4%, while the average test result of the traditional algorithm was 12.33%. In terms of fall detection sensitivity, the average test result of this algorithm was 92.50%, while the average test result of the traditional algorithm was 88.24%. Compared with traditional algorithms, this method performs better, with lower missed detection rate and higher sensitivity. Innovative combination of machine learning algorithm, through three-dimensional coordinate system, differentiation and vector sum formula, improves the accuracy and reliability of fall detection. In conclusion, the algorithm in this paper can effectively optimize the relevant performance of the system, thus improving the accuracy of the system’s fall detection.

Convolutional neural network for wearable fall detection systems

Fall accidents are a common cause of critical injuries among older adults. Therefore, fall detection systems have garnered considerable attention in research and industry. Feature extraction is the key for detecting falls, but it is time-consuming and tedious process. Deep learning can autonomously extract features from raw sensor data. In this study, we proposed a fall detection algorithm for wearable devices using a convolutional neural network (CNN) to differentiate falls from activities of daily living. The proposed model achieved over 99% metrics (sensitivity, specificity, precision, accuracy, and F1 score) by evaluating two different public datasets and provided better classification performance compared to other fall detection models in the same dataset. The higher CNN performance was recognized without requiring complex data preparation and manual feature extraction. Results from this study could induce CNN through the application of classification problems in technological environments.

A practical wearable fall detection system based on tiny convolutional neural networks

Falls are a major public health problem in a rapidly aging society due to their high prevalence and severe consequences among the older population. Therefore, automatic fall detection is of primary importance to enable timely medical intervention for older fall victims. The existing fall detection methods suffer from either poor robustness or high computational cost, limiting their practical applications in wearable fall detection systems. In this study, a tiny convolutional neural network (TinyCNN) with two-stage efficient feature extraction was proposed and evaluated on two large-scale public fall datasets (KFall and SisFall) collected from wearable inertial sensors. Cross-validation results showed that TinyCNN achieved both mean sensitivities and specificities over 99 % on the KFall, and over 98 % on the SisFall. While benefiting from the effectiveness of TinyCNN, we also addressed its black-box effect using class activation map (CAM). Furthermore, by employing quantization techniques, TinyCNN achieved a low latency of 0.037 s on an ultra-low-power microcontroller (Arduino Nano BLE 33 Sense), enabling real-time performance without sacrificing the accuracy. Compared with existing state-of-the-art fall detection algorithms, the newly proposed TinyCNN yielded a more balanced performance in terms of accuracy and practicality. Inspired by these promising results, we further developed a practical wearable prototype system based on this embeddable TinyCNN and an accompanying mobile App for automatic fall detection and immediate alarm. This AI-enabled wearable system has great potential for real-life fall detection applications among older individuals.

Colombian Stakeholder Perceptions and Recommendations Regarding Fall Detection Systems for Older Adults.

This study aimed to analyze perceptions and recommendations from stakeholders on the effectiveness of fall detection systems for older adults, aside from any additional technological solutions they may use within their activities of daily living (ADLs). This study performed a mixed-method approach to explore the views and recommendations of stakeholders concerning the implementation of wearable fall detection systems. Semi-structured online interviews and surveys were conducted on 25 Colombian adults classified into four stakeholder groups: older adults, informal caregivers, healthcare professionals, and researchers. A total of 25 individuals were interviewed or surveyed, comprising 12 females (48%) and 13 males (52%). The four groups cited the importance of wearable fall detection systems in ADLs monitoring of older adults. They did not consider them stigmatizing nor discriminatory but some raised potential privacy issues. The groups also communicated that the apparatus could be small, lightweight, and easy to handle with a help message sent to a relative or caregiver. All stakeholders interviewed perceived assistive technology as potentially useful for opportune healthcare, as well as for promoting independent living for the end user and their family members. For this reason, this study assessed the perceptions and recommendations received concerning fall detectors depending on the needs of stakeholders and the settings in which they are used.

A Wearable Micro-Electromechanical System Inertial Sensor System for Fall Behaviour Detection Based on a Multi-Level Threshold Algorithm

Falling is an important health issue that occurs in elderly people, which becomes a major problem that needs to be addressed urgently. To address this problem, a wearable fall detection system based on a Micro-Electromechanical System (MEMS) inertial sensor is proposed. The identification of four falling behaviours (Forward, Backward, Left, and Right Falls (FF, BF, LF, and RF)) and six normal behaviours (walking, running, hopping, up-and-down (U/D), stooping, and sitting) was successfully performed using this detection system. Quaternion complementary filtering attitude analysis and multi-level threshold algorithm are applied to determine the thresholds of the combined acceleration, angular velocity, and attitude angle of the fall behaviours, which are 4.8 g, 180 deg s−1, and 100 deg, respectively. The proposed system can effectively distinguish falling behaviour from normal behaviour and give early warning before falling. The sensitivity, specificity, and accuracy for predicting the falling are calculated to be 91.0%, 93.3%, and 92.3%, respectively.

Development of a Real-Time Wearable Fall Detection System in the Context of Internet of Things

Fall detection is of increasing significance in terms of the health monitoring of the elderly and disabled people, as falls may lead to physical injuries or even mental trauma. The existing fall detection methods have achieved impressive performance, but limitations present in operability, interface with public healthcare systems, and other technical issues such as high-power consumption, cost, and reliability. In this article, we present a wearable fall detection system, which is based on a novel multilevel threshold algorithm. The algorithm combines micro-electro-mechanical-systems (MEMS) with narrow band Internet of Things (NB-IoT). The system also includes a user interface for healthcare professionals, developed based on the cloud technology and server-client architecture. For the verification of the algorithm, we recruited 20 volunteers to perform the activities of daily living and falls. The experimental result showed that the proposed algorithm can achieve an accuracy of 94.88%, a sensitivity of 95.25%, and a specificity of 94.5%, suggesting the effectiveness of our system.

A study of the influence of the sensor sampling frequency on the performance of wearable fall detectors

Last decade has witnessed a major research interest on wearable fall detection systems. Sampling rate in these detectors strongly affects the power consumption and required complexity of the employed wearables. This study investigates the effect of the sampling frequency on the efficacy of the detection process. For this purpose, we train a convolutional neural network to directly discriminate falls from conventional activities based on the raw acceleration signals captured by a transportable sensor. Then, we analyze the changes in the performance of this classifier when the sampling rate is progressively reduced. In contrast with previous studies, the detector is tested against a wide set of public repositories of benchmarking traces. The quality metrics achieved for the different frequencies and the analysis of the spectrum of the signals reveal that a sampling rate of 20 Hz can be enough to maximize the effectiveness of a fall detector.

A study on the impact of the users\u2019 characteristics on the performance of wearable fall detection systems

Wearable Fall Detection Systems (FDSs) have gained much research interest during last decade. In this regard, Machine Learning (ML) classifiers have shown great efficiency in discriminating falls and conventional movements or Activities of Daily Living (ADLs) based on the analysis of the signals captured by transportable inertial sensors. Due to the intrinsic difficulties of training and testing this type of detectors in realistic scenarios and with their target audience (older adults), FDSs are normally benchmarked against a predefined set of ADLs and emulated falls executed by volunteers in a controlled environment. In most studies, however, samples from the same experimental subjects are used to both train and evaluate the FDSs. In this work, we investigate the performance of ML-based FDS systems when the test subjects have physical characteristics (weight, height, body mass index, age, gender) different from those of the users considered for the test phase. The results seem to point out that certain divergences (weight, height) of the users of both subsets (training ad test) may hamper the effectiveness of the classifiers (a reduction of up 20% in sensitivity and of up to 5% in specificity is reported). However, it is shown that the typology of the activities included in these subgroups has much greater relevance for the discrimination capability of the classifiers (with specificity losses of up to 95% if the activity types for training and testing strongly diverge).

An argumentation enabled decision making approach for Fall Activity Recognition in Social IoT based Ambient Assisted Living systems

With the advancement in Information and Communication Technologies (ICTs), smart devices are becoming even more smart and intelligent with every passing day. Further, the evolution of speaking and hearing enabled devices in an IoT network is transforming the face of research in the Social IoT domain. However, the integration of argumentation enabled devices in Social IoT network has not been fully explored by researchers in the past. Therefore, this research work focuses on development of argument enabled Social IoT networks. In this paper, a fuzzy argument based classification scheme termed as Classification Enhanced with Fuzzy Argumentation (CleFAR) is proposed. The proposed scheme is deployed for classification of fall activities in fall prevention applications. A novel framework for fall prevention system using Fall Activity Recognition (FAR) is presented. The proposed system is designed for the purpose of fall activity recognition in smart home Ambient Assisted Living (AAL) systems. To experimentally evaluate the system’s performance, a smart home AAL environment is simulated and the inhabitant’s routine activity dataset is generated. The fall activities are simulated using wearable fall detection systems. The proposed scheme is trained and tested on generated datasets and its performance is compared with traditional classification algorithms such as Random Forest (RF), Support Vector Machines (SVM), Naive Bayes (NB), Decision Tree (DT) and Artificial Neural Networks (ANN) as well as existing argumentation based game theoretic Weighted Voting Scheme (WVS). Experimental results indicate that the proposed scheme outperforms the traditional classification schemes and WVS approach with prediction accuracy up to 91%. It turns out that the proposed approach achieves significant improvement over the existing schemes.

A Feasibility Study of the Use of Smartwatches in Wearable Fall Detection Systems

Over the last few years, the use of smartwatches in automatic Fall Detection Systems (FDSs) has aroused great interest in the research of new wearable telemonitoring systems for the elderly. In contrast with other approaches to the problem of fall detection, smartwatch-based FDSs can benefit from the widespread acceptance, ergonomics, low cost, networking interfaces, and sensors that these devices provide. However, the scientific literature has shown that, due to the freedom of movement of the arms, the wrist is usually not the most appropriate position to unambiguously characterize the dynamics of the human body during falls, as many conventional activities of daily living that involve a vigorous motion of the hands may be easily misinterpreted as falls. As also stated by the literature, sensor-fusion and multi-point measurements are required to define a robust and reliable method for a wearable FDS. Thus, to avoid false alarms, it may be necessary to combine the analysis of the signals captured by the smartwatch with those collected by some other low-power sensor placed at a point closer to the body’s center of gravity (e.g., on the waist). Under this architecture of Body Area Network (BAN), these external sensing nodes must be wirelessly connected to the smartwatch to transmit their measurements. Nonetheless, the deployment of this networking solution, in which the smartwatch is in charge of processing the sensed data and generating the alarm in case of detecting a fall, may severely impact on the performance of the wearable. Unlike many other works (which often neglect the operational aspects of real fall detectors), this paper analyzes the actual feasibility of putting into effect a BAN intended for fall detection on present commercial smartwatches. In particular, the study is focused on evaluating the reduction of the battery life may cause in the watch that works as the core of the BAN. To this end, we thoroughly assess the energy drain in a prototype of an FDS consisting of a smartwatch and several external Bluetooth-enabled sensing units. In order to identify those scenarios in which the use of the smartwatch could be viable from a practical point of view, the testbed is studied with diverse commercial devices and under different configurations of those elements that may significantly hamper the battery lifetime.

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.

A Simulator to Support Machine Learning-Based Wearable Fall Detection Systems

People’s life expectancy is increasing, resulting in a growing elderly population. That population is subject to dependency issues, falls being a problematic one due to the associated health complications. Some projects are trying to enhance the independence of elderly people by monitoring their status, typically by means of wearable devices. These devices often feature Machine Learning (ML) algorithms for fall detection using accelerometers. However, the software deployed often lacks reliable data for the models’ training. To overcome such an issue, we have developed a publicly available fall simulator capable of recreating accelerometer fall samples of two of the most common types of falls: syncope and forward. Those simulated samples are like real falls recorded using real accelerometers in order to use them later as input for ML applications. To validate our approach, we have used different classifiers over both simulated falls and data from two public datasets based on real data. Our tests show that the fall simulator achieves a high accuracy for generating accelerometer data from a fall, allowing to create larger datasets for training fall detection software in wearable devices.

A Wearable Fall Detection System based on LoRa LPWAN Technology

The fall problem affects approximately one third of people aged over 65 years. Falls and fall-related injuries are one of the major causes of morbidity and mortality in the elderly population. Since many years, research activities have been targeted towards the development of technological solutions for the automatic detection and notification of falls. Among them, wearable based systems offer the advantage of being available ideally everywhere and cost-effective in terms of economy and computational burden. However, their use poses different challenges, from acceptability to battery usage. The choice of the communication technology, in particular, plays a fundamental role in the realization of a suitable solution, able to meet the target users’ needs. In this paper, we present a fall detection system, based on a pair of instrumented shoes. They communicate the alarming events to a supervising system through the LoRa LPWAN technology, without the need of a portable gateway. Experimental results demonstrate the effectiveness of the chosen communication technology and fall detection reliability.

FallAllD: An Open Dataset of Human Falls and Activities of Daily Living for Classical and Deep Learning Applications

In the last two decades, a wide variety of wearable fall detection systems have been proposed. Most of them were based on machine learning. While the reported results give the impression that the problem is almost solved, crucial questions raise about the representation capacity of the considered datasets and accordingly the reliability of performance evaluation. In this article, the limitations of a multitude of state-of-the-art fall detection datasets are discussed. Particularly, limitations related to the sensors that are used to capture the motion signals, the positions of these wearable sensors, the sampling frequency and the measurement range are discussed. Moreover, limitations concerning the simulation protocol e.g. the considered types of falls are discussed. A comprehensive data acquisition system and simulation protocol are proposed to overcome these limitations. Consequently, a large dataset, namely FallAllD, is proposed. It consists of 26 420 files collected using three data-loggers worn on the waist, wrist and neck of the subjects. Motion signals are captured using an accelerometer, gyroscope, magnetometer and barometer with efficient configurations that suit the potential applications. The performance of deep learning and classical learning-based algorithms is evaluated on the proposed dataset as well as some reference datasets. The results show significant performance differences when considering different datasets. The reasons underlying these differences are discussed and the advantages of FallAllD are highlighted. Moreover, challenges of acceleration-based fall detection are deeply analyzed. This analysis reveals the main reasons underlying false positives and false negatives. FallAllD could be used in fall detection, fall prevention and human activity recognition contexts.

A Study of the Use of Gyroscope Measurements in Wearable Fall Detection Systems

Due to the serious impact of falls on the quality of life of the elderly and on the economical sustainability of health systems, the study of new monitoring systems capable of automatically alerting about falls has gained much research interest during the last decade. In the field of Human Activity Recognition, Fall Detection Systems (FDSs) can be contemplated as pattern recognition architectures able to discriminate falls from ordinary Activities of Daily Living (ADLs). In this regard, the combined application of cellular communications and wearable devices that integrate inertial sensors offers a cost-efficient solution to track the user mobility almost ubiquitously. Inertial Measurement Units (IMUs) typically utilized for these architectures, embed an accelerometer and a gyroscope. This paper investigates if the use of the angular velocity (captured by the gyroscope) as an input feature of the movement classifier introduces any benefit with respect to the most common case in which the classification decision is uniquely based on the accelerometry signals. For this purpose, the work assesses the performance of a deep learning architecture (a convolutional neural network) which is optimized to differentiate falls from ADLs as a function of the raw data measured by the two inertial sensors (gyroscope and accelerometer). The system is evaluated against on a well-known public dataset with a high number of mobility traces (falls and ADL) measured from the movements of a wide group of experimental users.

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.

Accurate fall detection for patients with Parkinson's disease based on a data event algorithm and wireless sensor nodes

Elderly fall detection in Parkinson’s disease (PD) and epilepsy can cause broken bones or other injuries, decreasing the quality of life and possibly resulting in death. However, such fall-detection systems suffer from certain limitations and challenges such as fall-detection accuracy. This work aims to design and implement a wearable fall-detection system (WFDS) for PD patients based on the low-power ZigBee wireless sensor network (WSN). Patient falls were accurately detected based on the data event algorithm (DEA) results of two wireless sensor nodes an accelerometer and Myoware mounted on the patient’s body. The fall direction of the PD was accurately determined based on a direction fall event (DFE) algorithm in the receiver node. The experimental results show that the WFDS achieved 100% accuracy, sensitivity, and specificity in detecting the patient’s fall. The experimental WFDS appears to outperform existing modalities in terms of fall detection sensitivity, accuracy, and specificity.

A Survey on Recent Advances in Wearable Fall Detection Systems.

With advances in medicine and healthcare systems, the average life expectancy of human beings has increased to more than 80 yrs. As a result, the demographic old-age dependency ratio (people aged 65 or above relative to those aged 15–64) is expected to increase, by 2060, from ∼28% to ∼50% in the European Union and from ∼33% to ∼45% in Asia (Ageing Report European Economy, 2015). Therefore, the percentage of people who need additional care is also expected to increase. For instance, per studies conducted by the National Program for Health Care of the Elderly (NPHCE), elderly population in India will increase to 12% of the national population by 2025 with 8%–10% requiring utmost care. Geriatric healthcare has gained a lot of prominence in recent years, with specific focus on fall detection systems (FDSs) because of their impact on public lives. According to a World Health Organization report, the frequency of falls increases with increase in age and frailty. Older people living in nursing homes fall more often than those living in the community and 40% of them experience recurrent falls (World Health Organization, 2007). Machine learning (ML) has found its application in geriatric healthcare systems, especially in FDSs. In this paper, we examine the requirements of a typical FDS. Then we present a survey of the recent work in the area of fall detection systems, with focus on the application of machine learning. We also analyze the challenges in FDS systems based on the literature survey.