Distinguishing fall activities from normal activities by velocity characteristics

Enhancing elderly care: Efficient and reliable real-time fall detection algorithm

Background and Objective

Falls pose a significant risk to public health, especially for the elderly population, and could potentially result in severe injuries or even death. A reliable fall detection system is urgently needed to recognise and promptly alert to falls effectively. A vision-based fall detection system has the advantage of being non-invasive and affordable compared with another popular approach using wearable sensors. Nevertheless, the present challenge lies in the algorithm's limited on-device operating speed due to extremely high computational demands, and the high computational demands are usually essential to improve the performance for the complex scene. Therefore, it is crucial to address the above challenge in computational power and complex scenes.

Methods

This article presents the implementation of a real-time fall detection algorithm with low computational costs using a single webcam. The suggested method optimises precision and efficiency by synthesising the strengths of background subtraction and the human pose estimation model BlazePose. The biomechanical features, derived from body key points identified by BlazePose, are utilised in a random forest model for classifying fall events.

Results

The proposed algorithm achieves 89.99% accuracy and 29.7 FPS with a laptop CPU on the UR Fall Detection dataset and the Le2i Fall Detection dataset. The algorithm shows great generalisation and robustness in different scenarios.

Conclusion

Due to the low computational power of the system, the findings also suggest the potential for implementing the system in small-scale medical monitoring equipment, which maximises its practical value in digital health.

Mobile Robotic Balance Assistant (MRBA): a gait assistive and fall intervention robot for daily living

BACKGROUND

Aging degrades the balance and locomotion ability due to frailty and pathological conditions. This demands balance rehabilitation and assistive technologies that help the affected population to regain mobility, independence, and improve their quality of life. While many overground gait rehabilitation and assistive robots exist in the market, none are designed to be used at home or in community settings.

METHODS

A device named Mobile Robotic Balance Assistant (MRBA) is developed to address this problem. MRBA is a hybrid of a gait assistive robot and a powered wheelchair. When the user is walking around performing activities of daily living, the robot follows the person and provides support at the pelvic area in case of loss of balance. It can also be transformed into a wheelchair if the user wants to sit down or commute. To achieve instability detection, sensory data from the robot are compared with a predefined threshold; a fall is identified if the value exceeds the threshold. The experiments involve both healthy young subjects and an individual with spinal cord injury (SCI). Spatial Parametric Mapping is used to assess the effect of the robot on lower limb joint kinematics during walking. The instability detection algorithm is evaluated by calculating the sensitivity and specificity in identifying normal walking and simulated falls.

RESULTS

When walking with MRBA, the healthy subjects have a lower speed, smaller step length and longer step time. The SCI subject experiences similar changes as well as a decrease in step width that indicates better stability. Both groups of subjects have reduced joint range of motion. By comparing the force sensor measurement with a calibrated threshold, the instability detection algorithm can identify more than 93% of self-induced falls with a false alarm rate of 0%.

CONCLUSIONS

While there is still room for improvement in the robot compliance and the instability identification, the study demonstrates the first step in bringing gait assistive technologies into homes. We hope that the robot can encourage the balance-impaired population to engage in more activities of daily living to improve their quality of life. Future research includes recruiting more subjects with balance difficulty to further refine the device functionalities.

Automatic detection of falling of the elderly subject among his daily activities

Most elderly patients after falling, being not able to rise up or call for help, are particularly at risk of complication. This urges for the development of autonomous devices for earliest detection of falls. This paper is an overview of the current design approaches to autonomous fall detectors - sensors and algorithms- and a methodology to assess their efficiency. We then propose our fall sensor, which features high sensitivity (95%) and specificity (99%) on simulated falls in lab settings, and lower sensitivity (62.5%) in real settings in a group of 10 patients, with 8 falls detected over a period of 28 days.

Pre-Impact Detection Algorithm to Identify Tripping Events Using Wearable Sensors

This study aimed to investigate the performance of an updated version of our pre-impact detection algorithm parsing out the output of a set of Inertial Measurement Units (IMUs) placed on lower limbs and designed to recognize signs of lack of balance due to tripping. Eight young subjects were asked to manage tripping events while walking on a treadmill. An adaptive threshold-based algorithm, relying on a pool of adaptive oscillators, was tuned to identify abrupt kinematics modifications during tripping. Inputs of the algorithm were the elevation angles of lower limb segments, as estimated by IMUs located on thighs, shanks and feet. The results showed that the proposed algorithm can identify a lack of balance in about 0.37 ± 0.11 s after the onset of the perturbation, with a low percentage of false alarms (<10%), by using only data related to the perturbed shank. The proposed algorithm can hence be considered a multi-purpose tool to identify different perturbations (i.e., slippage and tripping). In this respect, it can be implemented for different wearable applications (e.g., smart garments or wearable robots) and adopted during daily life activities to enable on-demand injury prevention systems prior to fall impacts.

Machine learning-based pre-impact fall detection model to discriminate various types of fall

Preimpact fall detection can send alarm service faster to reduce long-lie conditions and decrease the risk of hospitalization. Detecting various types of fall to determine the impact site or direction prior to impact is important because it increases the chance of decreasing the incidence or severity of fall-related injuries. In this study, a robust preimpact fall detection model was developed to classify various activities and falls as multi-class and its performance was compared with the performance of previous developed models. Twelve healthy subjects participated in this study. All subjects were asked to place an inertial measuring unit module by fixing on a belt near the left iliac crest to collect accelerometer data for each activity. Our novel proposed model consists of feature calculation and infinite latent feature selection algorithm, auto labeling of activities, application of machine learning classifiers for discrete and continuous time series data. Nine machine-learning classifiers were applied to detect falls prior to impact and derive final detection results by sorting the classifier. Our model showed the highest classification accuracy. Results for the proposed model that could classify as multi-class showed significantly higher average classification accuracy of 99.57 ± 0.01% for discrete data-based classifiers and 99.84 ± 0.02% for continuous time series-based classifiers than previous models (p < 0.01). In the future, multi-class preimpact fall detection models can be applied to fall protector devices by detecting various activities for sending alerts or immediate feedback reactions to prevent falls.

Automated remote fall detection using impact features from video and audio

Elderly people and people with epilepsy may need assistance after falling, but may be unable to summon help due to injuries or impairment of consciousness. Several wearable fall detection devices have been developed, but these are not used by all people at risk. We present an automated analysis algorithm for remote detection of high impact falls, based on a physical model of a fall, aiming at universality and robustness. Candidate events are automatically detected and event features are used as classifier input. The algorithm uses vertical velocity and acceleration features from optical flow outputs, corrected for distance from the camera using moving object size estimation. A sound amplitude feature is used to increase detector specificity. We tested the performance and robustness of our trained algorithm using acted data from a public database and real life data with falls resulting from epilepsy and with daily life activities. Applying the trained algorithm to the acted dataset resulted in 90% sensitivity for detection of falls, with 92% specificity. In the real life data, six/nine falls were detected with a specificity of 99.7%; there is a plausible explanation for not detecting each of the falls missed. These results reflect the algorithm's robustness and confirms the feasibility of detecting falls using this algorithm.

Evaluation of Inertial Sensor-Based Pre-Impact Fall Detection Algorithms Using Public Dataset

In this study, pre-impact fall detection algorithms were developed based on data gathered by a custom-made inertial measurement unit (IMU). Four types of simulated falls were performed by 40 healthy subjects (age: 23.4 ± 4.4 years). The IMU recorded acceleration and angular velocity during all activities. Acceleration, angular velocity, and trunk inclination thresholds were set to 0.9 g, 47.3°/s, and 24.7°, respectively, for a pre-impact fall detection algorithm using vertical angles (VA algorithm); and 0.9 g, 47.3°/s, and 0.19, respectively, for an algorithm using the triangle feature (TF algorithm). The algorithms were validated by the results of a blind test using four types of simulated falls and six types of activities of daily living (ADL). VA and TF algorithms resulted in lead times of 401 ± 46.9 ms and 427 ± 45.9 ms, respectively. Both algorithms were able to detect falls with 100% accuracy. The performance of the algorithms was evaluated using a public dataset. Both algorithms detected every fall in the SisFall dataset with 100% sensitivity). The VA algorithm had a specificity of 78.3%, and TF algorithm had a specificity of 83.9%. The algorithms had higher specificity when interpreting data from elderly subjects. This study showed that algorithms using angles could more accurately detect falls. Public datasets are needed to improve the accuracy of the algorithms.

Fall detection algorithms for real-world falls harvested from lumbar sensors in the elderly population: a machine learning approach

Automatic fall detection will promote independent living and reduce the consequences of falls in the elderly by ensuring people can confidently live safely at home for linger. In laboratory studies inertial sensor technology has been shown capable of distinguishing falls from normal activities. However less than 7% of fall-detection algorithm studies have used fall data recorded from elderly people in real life. The FARSEEING project has compiled a database of real life falls from elderly people, to gain new knowledge about fall events and to develop fall detection algorithms to combat the problems associated with falls. We have extracted 12 different kinematic, temporal and kinetic related features from a data-set of 89 real-world falls and 368 activities of daily living. Using the extracted features we applied machine learning techniques and produced a selection of algorithms based on different feature combinations. The best algorithm employs 10 different features and produced a sensitivity of 0.88 and a specificity of 0.87 in classifying falls correctly. This algorithm can be used distinguish real-world falls from normal activities of daily living in a sensor consisting of a tri-axial accelerometer and tri-axial gyroscope located at L5.

An Energy-Efficient Multi-Tier Architecture for Fall Detection Using Smartphones

Automatic detection of fall events is vital to providing fast medical assistance to the causality, particularly when the injury causes loss of consciousness. Optimization of the energy consumption of mobile applications, especially those which run 24/7 in the background, is essential for longer use of smartphones. In order to improve energy-efficiency without compromising on the fall detection performance, we propose a novel 3-tier architecture that combines simple thresholding methods with machine learning algorithms. The proposed method is implemented on a mobile application, called uSurvive, for Android smartphones. It runs as a background service and monitors the activities of a person in daily life and automatically sends a notification to the appropriate authorities and/or user defined contacts when it detects a fall. The performance of the proposed method was evaluated in terms of fall detection performance and energy consumption. Real life performance tests conducted on two different models of smartphone demonstrate that our 3-tier architecture with feature reduction could save up to 62% of energy compared to machine learning only solutions. In addition to this energy saving, the hybrid method has a 93% of accuracy, which is superior to thresholding methods and better than machine learning only solutions.

Optimal fall indicators for slip induced falls on a cross-slope

Slip-induced falls are among the most common cause of major occupational injuries in the UK as well as being a major public health concern in the elderly population. This study aimed to determine the optimal fall indicators for fall detection models which could be used to reduce the detrimental consequences of falls. A total of 264 kinematic variables covering three-dimensional full body model translation and rotational measures were analysed during normal walking, successful recovery from slips and falls on a cross-slope. Large effect sizes were found for three kinematic variables which were able to distinguish falls from normal walking and successful recovery. Further work should consider other types of daily living activities as results show that the optimal kinematic fall indicators can vary considerably between movement types. Practitioner Summary: Fall detection models are used to minimise the adverse consequences of slip-induced falls, a major public health concern. Optimal fall indicators were derived from a comprehensive set of kinematic variables for slips on a cross-slope. Results suggest robust detection of falls is possible on a cross-slope but may be more difficult than level walking.

Pre-impact fall detection

Pre-impact fall detection has been proposed to be an effective fall prevention strategy. In particular, it can help activate on-demand fall injury prevention systems (e.g. inflatable hip protectors) prior to fall impacts, and thus directly prevent the fall-related physical injuries. This paper gave a systematical review on pre-impact fall detection, and focused on the following aspects of the existing pre-impact fall detection research: fall detection apparatus, fall detection indicators, fall detection algorithms, and types of falls for fall detection evaluation. In addition, the performance of the existing pre-impact fall detection solutions were also reviewed and reported in terms of their sensitivity, specificity, and detection/lead time. This review also summarized the limitations in the existing pre-impact fall detection research, and proposed future research directions in this field.

Prior-to- and Post-Impact Fall Detection Using Inertial and Barometric Altimeter Measurements

This paper investigates a fall detection system based on the integration of an inertial measurement unit with a barometric altimeter (BIMU). The vertical motion of the body part the BIMU was attached to was monitored on-line using a method that delivered drift-free estimates of the vertical velocity and estimates of the height change from the floor. The experimental study included activities of daily living of seven types and falls of five types, simulated by a cohort of 25 young healthy adults. The downward vertical velocity was thresholded at 1.38 m/s, yielding 80% sensitivity (SE), 100% specificity (SP) and a mean prior-to-impact time of 157 ms (range 40-300 ms). The soft falls, i.e., those with downward vertical velocity above 0.55 m/s and below 1.38 m/s were analyzed post-impact. Six fall detection methods, tuned to achieve 100% SE, were considered to include features of impact, change of posture and height, singularly or in association with one another. No single feature allowed for 100% SP. The detection accuracy marginally improved when the height change was considered in association with either the impact or the change of posture; the post-impact fall detection method that analyzed the impact and the change of posture together achieved 100% SP.

Human activities recognition with RGB-Depth camera using HMM

Fall detection remains today an open issue for improving elderly people security. It is all the more pertinent today when more and more elderly people stay longer and longer at home. In this paper, we propose a method to detect fall using a system made up of RGB-Depth cameras. The major benefit of our approach is its low cost and the fact that the system is easy to distribute and install. In few words, the method is based on the detection in real time of the center of mass of any mobile object or person accurately determining its position in the 3D space and its velocity. We demonstrate in this paper that this information is adequate and robust enough for labeling the activity of a person among 8 possible situations. An evaluation has been conducted within a real smart environment with 26 subjects which were performing any of the eight activities (sitting, walking, going up, squatting, lying on a couch, falling, bending and lying down). Seven out of these eight activities were correctly detected among which falling which was detected without false positives.

A distributed multiagent system architecture for body area networks applied to healthcare monitoring

In the last years the area of health monitoring has grown significantly, attracting the attention of both academia and commercial sectors. At the same time, the availability of new biomedical sensors and suitable network protocols has led to the appearance of a new generation of wireless sensor networks, the so-called wireless body area networks. Nowadays, these networks are routinely used for continuous monitoring of vital parameters, movement, and the surrounding environment of people, but the large volume of data generated in different locations represents a major obstacle for the appropriate design, development, and deployment of more elaborated intelligent systems. In this context, we present an open and distributed architecture based on a multiagent system for recognizing human movements, identifying human postures, and detecting harmful activities. The proposed system evolved from a single node for fall detection to a multisensor hardware solution capable of identifying unhampered falls and analyzing the users' movement. The experiments carried out contemplate two different scenarios and demonstrate the accuracy of our proposal as a real distributed movement monitoring and accident detection system. Moreover, we also characterize its performance, enabling future analyses and comparisons with similar approaches.

A procedure for a mechanical evaluation of an undefined osteo-protective material

Falls represent a major care and cost problem to health and social services world-widely, since 50% of falls result in an injury. In this work, is proposed a methodology to evaluate protective pads materials and geometry performance, in order to reduce impact results in a fall event. Since the material properties and the pad geometry are the key factors to make the protection possible when a fall event occurs, our approach relies on the use of mechanical tests to evaluate the properties of the material and in the study of the pad response during a fall. For this, were used compression, tensile and instrumented falling weight tests, that allow a fully characterization of the materials that can be employed in the protective pads. Likewise, to gather precise information on falls events, in order to study the pad response during a fall, a set of laboratory fall trials were created using a camera-less inertial motion capture (mocap) system. This allow the acquisition of dynamic information of falls, namely acceleration and velocity that can be used to create a finite element analysis (FEA) model, where different segments from the human body can be evaluated when the protective pad is associated to it. Through the proposed methodology, different materials and pad geometries can be studied towards maximizing the performance of protection pads for falls. The mocap system allows the acquisition of fall data, and also the creation of a human body geometrical model, representative of the fall. From the mechanical trials, was showed that the spacer fabric embedded with silicone has the higher ability to reduce the peak force in case of impact when compared with all the other specimens. The compression and the tensile tests allow the mechanical definition of the material, and with this the material definition on the FEA model.

Fall detection devices and their use with older adults: a systematic review

BACKGROUND

Falls represent a significant threat to the health and independence of adults aged 65 years and older. As a wide variety and large number of passive monitoring systems are currently and increasingly available to detect when individuals have fallen, there is a need to analyze and synthesize the evidence regarding their ability to accurately detect falls to determine which systems are most effective.

OBJECTIVES

The purpose of this literature review is to systematically assess the current state of design and implementation of fall-detection devices. This review also examines to what extent these devices have been tested in the real world as well as the acceptability of these devices to older adults.

DATA SOURCES

A systematic literature review was conducted in PubMed, CINAHL, EMBASE, and PsycINFO from their respective inception dates to June 25, 2013.

STUDY ELIGIBILITY CRITERIA AND INTERVENTIONS

Articles were included if they discussed a project or multiple projects involving a system with the purpose of detecting a fall in adults. It was not a requirement for inclusion in this review that the system targets persons older than 65 years. Articles were excluded if they were not written in English or if they looked at fall risk, fall detection in children, fall prevention, or a personal emergency response device.

STUDY APPRAISAL AND SYNTHESIS METHODS

Studies were initially divided into those using sensitivity, specificity, or accuracy in their evaluation methods and those using other methods to evaluate their devices. Studies were further classified into wearable devices and nonwearable devices. Studies were appraised for inclusion of older adults in sample and if evaluation included real-world settings.

RESULTS

This review identified 57 projects that used wearable systems and 35 projects using nonwearable systems, regardless of evaluation technique. Nonwearable systems included cameras, motion sensors, microphones, and floor sensors. Of the projects examining wearable systems, only 7.1% reported monitoring older adults in a real-world setting. There were no studies of nonwearable devices that used older adults as subjects in either a laboratory or a real-world setting. In general, older adults appear to be interested in using such devices although they express concerns over privacy and understanding exactly what the device is doing at specific times.

LIMITATIONS

This systematic review was limited to articles written in English and did not include gray literature. Manual paper screening and review processes may have been subject to interpretive bias.

CONCLUSIONS AND IMPLICATIONS OF KEY FINDINGS

There exists a large body of work describing various fall-detection devices. The challenge in this area is to create highly accurate unobtrusive devices. From this review it appears that the technology is becoming more able to accomplish such a task. There is a need now for more real-world tests as well as standardization of the evaluation of these devices.

Trunk angular kinematics during slip-induced backward falls and activities of daily living

Prior to developing any specific fall detection algorithm, it is critical to distinguish the unique motion features associated with fall accidents. The current study aimed to investigate the upper trunk angular kinematics during slip-induced backward falls and activities of daily living (ADLs). Ten healthy older adults (age = 75 ± 6 yr (mean ± SD)) were involved in a laboratory study. Sagittal trunk angular kinematics were measured using optical motion analysis system during normal walking, slip-induced backward falls, lying down, bending over, and various types of sitting down (SN). Trunk angular phase-plane plots were generated to reveal the motion features of falls. It was found that backward falls were characterized by a simultaneous occurrence of a slight trunk extension and an extremely high trunk extension velocity (peak average = 139.7 deg/s), as compared to ADLs (peak average = 84.1 deg/s). It was concluded that the trunk extension angular kinematics of falls were clearly distinguishable from those of ADLs from the perspective of angular phase-plane plot. Such motion features can be utilized in future studies to develop a new prior-to-impact fall detection algorithm.

Automatic fall monitoring: a review

Falls and fall-related injuries are major incidents, especially for elderly people, which often mark the onset of major deterioration of health. More than one-third of home-dwelling people aged 65 or above and two-thirds of those in residential care fall once or more each year. Reliable fall detection, as well as prevention, is an important research topic for monitoring elderly living alone in residential or hospital units. The aim of this study is to review the existing fall detection systems and some of the key research challenges faced by the research community in this field. We categorize the existing platforms into two groups: wearable and ambient devices; the classification methods are divided into rule-based and machine learning techniques. The relative merit and potential drawbacks are discussed, and we also outline some of the outstanding research challenges that emerging new platforms need to address.

"SmartMonitor"--an intelligent security system for the protection of individuals and small properties with the possibility of home automation

“SmartMonitor” is an intelligent security system based on image analysis that combines the advantages of alarm, video surveillance and home automation systems. The system is a complete solution that automatically reacts to every learned situation in a pre-specified way and has various applications, e.g., home and surrounding protection against unauthorized intrusion, crime detection or supervision over ill persons. The software is based on well-known and proven methods and algorithms for visual content analysis (VCA) that were appropriately modified and adopted to fit specific needs and create a video processing model which consists of foreground region detection and localization, candidate object extraction, object classification and tracking. In this paper, the “SmartMonitor” system is presented along with its architecture, employed methods and algorithms, and object analysis approach. Some experimental results on system operation are also provided. In the paper, focus is put on one of the aforementioned functionalities of the system, namely supervision over ill persons.

Development and evaluation of a prior-to-impact fall event detection algorithm

Automatic fall event detection has attracted research attention recently for its potential application in fall alarming system and wearable fall injury prevention system. Nevertheless, existing fall detection research is facing various limitations. The current study aimed to develop and validate a new fall detection algorithm using 2-D information (i.e., trunk angular velocity and trunk angle). Ten healthy elderly were involved in a laboratory study. Sagittal trunk angular kinematics was measured using inertial measurement unit during slip-induced backward falls and a variety of daily activities. The new algorithm was, on average, able to detect backward falls prior to impact, with 100% sensitivity, 95.65% specificity, and 255 ms response time. Therefore, it was concluded that the new fall detection algorithm was able to effectively detect falls during motion for the elderly population.

Pre-impact fall detection: optimal sensor positioning based on a machine learning paradigm

The aim of this study was to identify the best subset of body segments that provides for a rapid and reliable detection of the transition from steady walking to a slipping event. Fifteen healthy young subjects managed unexpected perturbations during walking. Whole-body 3D kinematics was recorded and a machine learning algorithm was developed to detect perturbation events. In particular, the linear acceleration of all the body segments was parsed by Independent Component Analysis and a Neural Network was used to classify walking from unexpected perturbations. The Mean Detection Time (MDT) was 351±123 ms with an Accuracy of 95.4%. The procedure was repeated with data related to different subsets of all body segments whose variability appeared strongly influenced by the perturbation-induced dynamic modifications. Accordingly, feet and hands accounted for most data information and the performance of the algorithm were slightly reduced using their combination. Results support the hypothesis that, in the framework of the proposed approach, the information conveyed by all the body segments is redundant to achieve effective fall detection, and suitable performance can be obtained by simply observing the kinematics of upper and lower distal extremities. Future studies are required to assess the extent to which such results can be reproduced in older adults and in different experimental conditions.

A Multi-Agent Care System to Support Independent Living

This paper presents a context-aware, multi-agent system called “Confidence” that helps elderly people remain independent longer by detecting falls and unusual movement, which may indicate a health problem. The system combines state-of-the-art sensor technologies and four groups of agents providing a reliable, robust, flexible monitoring system. It can call for help in case of an emergency, and issue warnings if unusual behavior is detected. The first group gathers data from the location and inertial sensors and suppresses noise. The second group reconstructs the position and activity of a person and detects the context. The third group assesses the person's condition in the environment and reacts to critical situations such as falls. The fourth group detects unusual behavior as an indicator of a potential health problem. The system was successfully tested on a scenario consisting of events that were difficult to recognize as falls, as well as in a scenario consisting of normal days and days when the person was ill. It was also demonstrated live several times, with excellent performance in complex situations.

Distinguishing the causes of falls in humans using an array of wearable tri-axial accelerometers

Falls are the number one cause of injury in older adults. Lack of objective evidence on the cause and circumstances of falls is often a barrier to effective prevention strategies. Previous studies have established the ability of wearable miniature inertial sensors (accelerometers and gyroscopes) to automatically detect falls, for the purpose of delivering medical assistance. In the current study, we extend the applications of this technology, by developing and evaluating the accuracy of wearable sensor systems for determining the cause of falls. Twelve young adults participated in experimental trials involving falls due to seven causes: slips, trips, fainting, and incorrect shifting/transfer of body weight while sitting down, standing up from sitting, reaching and turning. Features (means and variances) of acceleration data acquired from four tri-axial accelerometers during the falling trials were input to a linear discriminant analysis technique. Data from an array of three sensors (left ankle+right ankle+sternum) provided at least 83% sensitivity and 89% specificity in classifying falls due to slips, trips, and incorrect shift of body weight during sitting, reaching and turning. Classification of falls due to fainting and incorrect shift during rising was less successful across all sensor combinations. Furthermore, similar classification accuracy was observed with data from wearable sensors and a video-based motion analysis system. These results establish a basis for the development of sensor-based fall monitoring systems that provide information on the cause and circumstances of falls, to direct fall prevention strategies at a patient or population level.

Sudden event recognition: a survey

Event recognition is one of the most active research areas in video surveillance fields. Advancement in event recognition systems mainly aims to provide convenience, safety and an efficient lifestyle for humanity. A precise, accurate and robust approach is necessary to enable event recognition systems to respond to sudden changes in various uncontrolled environments, such as the case of an emergency, physical threat and a fire or bomb alert. The performance of sudden event recognition systems depends heavily on the accuracy of low level processing, like detection, recognition, tracking and machine learning algorithms. This survey aims to detect and characterize a sudden event, which is a subset of an abnormal event in several video surveillance applications. This paper discusses the following in detail: (1) the importance of a sudden event over a general anomalous event; (2) frameworks used in sudden event recognition; (3) the requirements and comparative studies of a sudden event recognition system and (4) various decision-making approaches for sudden event recognition. The advantages and drawbacks of using 3D images from multiple cameras for real-time application are also discussed. The paper concludes with suggestions for future research directions in sudden event recognition.

Differentiating slip-induced falls from normal walking and successful recovery after slips using kinematic measures

Slip-induced falls are prevalent and serious in occupational settings. Fall detection can minimise the adverse consequences caused by falls. However, a limitation in the existing fall detection research is that the fall indicators were predetermined without any theoretical and experimental basis. This study aimed to determine the optimal fall indicators for fall detection research by experimentally examining a comprehensive set of kinematic measures. The body kinematic measures were compared among normal walking, successful recovery after slips and slip-induced falls. We identified the kinematic measures that differ between falls and the selected non-fall activities (i.e. successful recovery and normal walking), especially at the early stage of loss-of-balance due to slips. Findings obtained from this study can enhance the understanding of kinematic differences between slip-induced falls and non-fall activities, and such knowledge is particularly useful for developing fall detection models.

PRACTITIONER SUMMARY

Slips have been reported to be a major cause of accidental falls. Findings from this study can help determine the kinematic measures that can effectively and efficiently differentiate slip-induced falls from successful recovery and normal walking. Such knowledge can help develop effective strategies to prevent slip-induced falls.

Exploration and implementation of a pre-impact fall recognition method based on an inertial body sensor network

The unintentional injuries due to falls in elderly people give rise to a multitude of health and economic problems due to the growing aging population. The use of early pre-impact fall alarm and self-protective control could greatly reduce fall injuries. This paper aimed to explore and implement a pre-impact fall recognition/alarm method for free-direction fall activities based on understanding of the pre-impact lead time of falls and the angle of body postural stability using an inertial body sensor network. Eight healthy Asian adult subjects were arranged to perform three kinds of daily living activities and three kinds of fall activities. Nine MTx sensor modules were used to measure the body segmental kinematic characteristics of each subject for pre-impact fall recognition/alarm. Our analysis of the kinematic features of human body segments showed that the chest was the optimal sensor placement for an early pre-impact recognition/alarm (i.e., prediction/alarm of a fall event before it happens) and post-fall detection (i.e., detection of a fall event after it already happened). Furthermore, by comparative analysis of threshold levels for acceleration and angular rate, two acceleration thresholds were determined for early pre-impact alarm (7 m/s/s) and post-fall detection (20 m/s/s) under experimental conditions. The critical angles of postural stability of torso segment in three kinds of fall activities (forward, sideway and backward fall) were determined as 23.9 ± 3.3, 49.9 ± 4.1 and 9.9 ± 2.5 degrees, respectively, and the relative average pre-impact lead times were 329 ± 21, 265 ± 35 and 257 ± 36 ms. The results implied that among the three fall activities the sideway fall was associated with the largest postural stability angle and the forward fall was associated with the longest time to adjust body angle to avoid the fall; the backward fall was the most difficult to avoid among the three kinds of fall events due to the toughest combination of shortest lead time and smallest angle of postural stability which made it difficult for the self-protective control mechanism to adjust the body in time to avoid falling down.

Classification of daily physical activities from a single kinematic sensor

This work was conducted in TIMC laboratory to develop methods able to monitor physical activities. In the framework of Health Smart Home, the purpose is to maintain and supervise elderly or fragile people at home. Activity and autonomy levels are important criteria to evaluate the health of the patient. The time spent in each postural state (lying, sitting, standing), the periods of walking and the number of postural transitions: sit-to-stand (StS), back-to-sit (BtS) give information about the patient's activity. The purpose of the current study is to detect these activities using an unique sensor made of three accelerometers, attached to the chest. First, this paper describes how each algorithm (posture, walk, postural transitions) works. Secondly, the results on real data are shown. An experiment with elderly subjects was carried out. Each subject performed daily activities (walking, sitting, lying down, ...) while wearing the sensor.

Detecting falls by analyzing angular momentum

The aim of the present pilot study is to investigate the hypothesis that fall detection systems based on sensors placed on the distal segments of the body are more effective than solution based on placing sensors on the trunk. To test this hypothesis, we observed the contribution of all body segments to the 3D angular momentum. Five healthy adults were enrolled for the experimental sessions. A set of 39 spherical markers was located on body landmarks and subjects underwent perturbed walking while a Motion Analysis System recorded 3D kinematics. From a biomechanical model, the angular momentum pattern related to each body segment was estimated. Data were post-processed with a threshold-based algorithm used to detect which among body segments allows detect as soon as possible and with limited false alarms the perturbation. Results showed that hands-forearms and chest-head are the most sensitive to external moments orientated along respectively the anterior-posterior and medio-lateral directions.

Evaluation of accelerometer-based fall detection algorithms on real-world falls

Despite extensive preventive efforts, falls continue to be a major source of morbidity and mortality among elderly. Real-time detection of falls and their urgent communication to a telecare center may enable rapid medical assistance, thus increasing the sense of security of the elderly and reducing some of the negative consequences of falls. Many different approaches have been explored to automatically detect a fall using inertial sensors. Although previously published algorithms report high sensitivity (SE) and high specificity (SP), they have usually been tested on simulated falls performed by healthy volunteers. We recently collected acceleration data during a number of real-world falls among a patient population with a high-fall-risk as part of the SensAction-AAL European project. The aim of the present study is to benchmark the performance of thirteen published fall-detection algorithms when they are applied to the database of 29 real-world falls. To the best of our knowledge, this is the first systematic comparison of fall detection algorithms tested on real-world falls. We found that the SP average of the thirteen algorithms, was (mean±std) 83.0%±30.3% (maximum value = 98%). The SE was considerably lower (SE = 57.0%±27.3%, maximum value = 82.8%), much lower than the values obtained on simulated falls. The number of false alarms generated by the algorithms during 1-day monitoring of three representative fallers ranged from 3 to 85. The factors that affect the performance of the published algorithms, when they are applied to the real-world falls, are also discussed. These findings indicate the importance of testing fall-detection algorithms in real-life conditions in order to produce more effective automated alarm systems with higher acceptance. Further, the present results support the idea that a large, shared real-world fall database could, potentially, provide an enhanced understanding of the fall process and the information needed to design and evaluate a high-performance fall detector.

Comparison of real-life accidental falls in older people with experimental falls in middle-aged test subjects

Falling is a common accident among older people. Automatic fall detectors are one method of improving security. However, in most cases, fall detectors are designed and tested with data from experimental falls in younger people. This study is one of the first to provide fall-related acceleration data obtained from real-life falls. Wireless sensors were used to collect acceleration data during a six-month test period in older people. Data from five events representing forward falls, a sideways fall, a backwards fall, and a fall out of bed were collected and compared with experimental falls performed by middle-aged test subjects. The signals from real-life falls had similar features to those from intentional falls. Real-life forward, sideways and backward falls all showed a pre impact phase and an impact phase that were in keeping with the model that was based on experimental falls. In addition, the fall out of bed had a similar acceleration profile as the experimental falls of the same type. However, there were differences in the parameters that were used for the detection of the fall phases. The beginning of the fall was detected in all of the real-life falls starting from a standing posture, whereas the high pre impact velocity was not. In some real-life falls, multiple impacts suggested protective actions. In conclusion, this study demonstrated similarities between real-life falls of older people and experimental falls of middle-aged subjects. However, some fall characteristics detected from experimental falls were not detectable in acceleration signals from corresponding heterogeneous real-life falls.

Reliability of Impact Forces, Hip Angles and Velocities during Simulated Forward Falls Using a Novel Propelled Upper Limb Fall ARrest Impact System (PULARIS)

Previous forward fall simulation methods have provided good kinematic and kinetic data, but are limited in that they have started the falls from a stationary position and have primarily simulated uni-directional motion. Therefore, a novel Propelled Upper Limb fall ARest Impact System (PULARIS) was designed to address these issues during assessments of a variety of fall scenarios. The purpose of this study was to present PULARIS and evaluate its ability to impact the upper extremities of participants with repeatable velocities, hand forces and hip angles in postures and with vertical and horizontal motion consistent with forward fall arrest. PULARIS consists of four steel tubing crossbars in a scissor-like arrangement that ride on metal trolleys within c-channel tracks in the ceiling. Participants are suspended beneath PULARIS by the legs and torso in a prone position and propelled horizontally via a motor and chain drive until they are quick released, and then impact floor-mounted force platforms with both hands. PULARIS velocity, hip angles and velocities and impact hand forces of ten participants (five male, five female) were collected during three fall types (straight-arm, self-selected and bent-arm) and two fall heights (0.05 m and 0.10 m) to assess the reliability of the impact conditions provided by the system. PULARIS and participant hip velocities were found to be quite repeatable (mean ICC = 0.81) with small between trial errors (mean = 0.03 m/s). The ratio of horizontal to vertical hip velocity components (∼0.75) agreed well with previously reported data (0.70-0.80). Peak vertical hand impact forces were also found to be relatively consistent between trials with a mean ICC of 0.73 and mean between trial error of 13.4 N. Up to 83% of the horizontal hand impact forces displayed good to excellent reliability (ICC > 0.6) with small between trial differences. Finally, the ICCs for between trial hip angles were all classified as good to excellent. Overall, PULARIS is a reliable method and is appropriate for studying the response of the distal upper extremity to impact loading during non-stationary, multi-directional movements indicative of a forward fall. This system performed well at different fall heights, and allows for a variety of upper and lower extremity, and hip postures to be tested successfully in different landing scenarios consistent with elderly and sport-related falls.

Evaluation under real-life conditions of a stand-alone fall detector for the elderly subjects

BACKGROUND AND OBJECTIVES

Elderly patients unable to get up after a fall or to activate an alarm mechanism are particularly at risk of complications and need to be monitored with extreme care. The different risk factors have fostered the development of stand-alone devices facilitating early detection of falls. We aimed at assessing performance of the Vigi'Fall(®) system, a cutting edge fall detector associating a "passive release" mechanism attached to the patient and including external sensors; in the event of a fall, the system automatically triggers an alarm, and it also incorporates embedded confirmation software. We have put it to the test under real-life conditions so as to evaluate not only its efficacy, but also and more particularly its acceptability and tolerability in elderly subjects.

METHOD

The study ran from March 2007 through December 2008 in a geriatric ward with 10 subjects over 75 years of age, all of whom presented with a risk of falling.

RESULTS

For eight patients wearing an accelerometric sensor, eight "falling" events and 30 "alarm release" events were recorded. Sensitivity and specificity of the device came to 62.5 and 99.5% respectively. For the two patients wearing the complete device, no events were detected. Not a single adverse occurrence was noted. Local tolerance was excellent in all but one of the subjects.

CONCLUSION

Our results clearly show that the device may be worn by patients without discomfort over prolonged periods of time, and also demonstrate that the verification component will help to increase sensitivity in real-life conditions to a level comparable to the level attained in our laboratory studies.

Innovations in health care services: the CAALYX system

PURPOSE

This paper describes proposed health care services innovations, provided by a system called CAALYX (Complete Ambient Assisted Living eXperiment). CAALYX aimed to provide healthcare innovation by extending the state-of-the-art in tele-healthcare, by focusing on increasing the confidence of elderly people living autonomously, by building on the knowledge base of the most common disorders and respective characteristic vital sign changes for this age group.

METHODS

A review of the state-of-the-art on health care services was carried out. Then, extensive research was conducted on the particular needs of the elderly in relation to home health services that, if offered to them, could improve their day life by giving them greater confidence and autonomy. To achieve this, we addressed issues associated with the gathering of clinical data and interpretation of these data, as well as possibilities of automatically triggering appropriate clinical measures. Considering this initial work we started the identification of initiatives, ongoing works and technologies that could be used for the development of the system. After that, the implementation of CAALYX was done.

FINDINGS

The innovation in CAALYX system considers three main areas of contribution: (i) The Roaming Monitoring System that is used to collect information on the well-being of the elderly users; (ii) The Home Monitoring System that is aimed at helping the elders independently living at home being implemented by a device (a personal computer or a set top box) that supports the connection of sensors and video cameras that may be used for monitoring and for interaction with the elder; (iii) The Central Care Service and Monitoring System that is implemented by a Caretaker System where attention and care services are provided to elders, where actors as Caretakers, Doctors and Relatives are logically linked to elders. Innovations in each of these areas are presented here.

CONCLUSIONS

The ageing European society is placing an added burden on future generations, as the 'elderly-to-working-age-people' ratio is set to steadily increase in the future. Nowadays, quality of life and fitness allows for most older persons to have an active life well into their eighties. Furthermore, many older persons prefer to live in their own house and choose their own lifestyle. The CAALYX system can have a clear impact in increasing older persons' autonomy, by ensuring that they do not need to leave their preferred environment in order to be properly monitored and taken care of.

Load on osseointegrated fixation of a transfemoral amputee during a fall: Determination of the time and duration of descent

Mitigation of fall-related injuries for populations of transfemoral amputees fitted with a socket or an osseointegrated fixation is challenging. Wearing a protective device fitted within the prosthesis might be a possible solution, provided that issues with automated fall detection and time of deployment of the protective mechanism are solved. The first objective of this study was to give some examples of the times and durations of descent during a real forward fall of a transfemoral amputee that occurred inadvertently while attending a gait measurement session to assess the load applied on the residuum. The second objective was to present five semi-automated methods of detection of the time of descent using the load data. The load was measured directly at 200 Hz using a six-channel transducer. The average time and duration of descent were 242 ± 42 ms (145-310 ms) and 619 ± 42 ms (550-715 ms), respectively. This study demonstrated that the transition between walking and falling was characterized by times of descent that occurred sequentially. The sensitivity and specificity of an automated algorithm might be improved by combining several methods of detection based on the deviation of the loads measured from their own trends and from a template previously established.

Prediction of foot clearance parameters as a precursor to forecasting the risk of tripping and falling

Tripping and falling is a serious health problem for older citizens due to the high medical costs incurred and the high mortality rates precipitated mostly by hip fractures that do not heal well. Current falls prevention technology encompasses a broad range of interventions; both passive (e.g., safer environments, hip protectors) and active (e.g., sensor-based fall detectors) which attempt to reduce the effects of tripping and falling. However the majority of these interventions minimizes the impact of falls and do not directly reduce the risk of falling. This paper investigates the prediction of gait parameters related to foot-to-ground clearance height during the leg swing phase which have been physically associated with tripping and falling risk in the elderly. The objective is to predict parameters of foot trajectory several walking cycles in advance so that anticipated low foot clearance could be addressed early with more volitional countermeasures, e.g., slowing down or stopping. In this primer study, foot kinematics was recorded with a highly accurate motion capture system for 10 healthy adults (25-32 years) and 11 older adults (65-82 years) with a history of falls who each performed treadmill walking for at least 10 min. Vertical foot displacement during the swing phase has three characteristic inflection points and we used these peak values and their normalized time as the target prediction values. These target variables were paired with features extracted from the corresponding foot acceleration signal (obtained through double differentiation). A generalized regression neural network (GRNN) was used to independently predict the gait variables over a prediction horizon (number of gait cycles ahead) of 1-10 gait cycles. It was found that the GRNN attained 0.32-1.10 cm prediction errors in the peak variables and 2-8% errors in the prediction of normalized peak times, with slightly better accuracies in the healthy group compared to elderly fallers. Prediction accuracy decreased linearly (best fit) at a slow rate with increasing prediction horizon ranging from 0.03 to 0.11 cm per step for peak displacement variables and 0.34 × 10(-3) - 1.81 × 10(-3)% per step for normalized peak time variables. Further time series analysis of the target gait variable revealed high autocorrelations in the faller group indicating the presence of cyclic patterns in elderly walking strategies compared to almost random walking patterns in the healthy group. The results are promising because the technique can be extended to portable sensor-based devices which measure foot accelerations to predict the onset of risky foot clearance, thus leading to a more effective falls prevention technology.

Fall detection with multiple cameras: an occlusion-resistant method based on 3-D silhouette vertical distribution

According to the demographic evolution in industrialized countries, more and more elderly people will experience falls at home and will require emergency services. The main problem comes from fall-prone elderly living alone at home. To resolve this lack of safety, we propose a new method to detect falls at home, based on a multiple-cameras network for reconstructing the 3-D shape of people. Fall events are detected by analyzing the volume distribution along the vertical axis, and an alarm is triggered when the major part of this distribution is abnormally near the floor during a predefined period of time, which implies that a person has fallen on the floor. This method was validated with videos of a healthy subject who performed 24 realistic scenarios showing 22 fall events and 24 cofounding events (11 crouching position, 9 sitting position, and 4 lying on a sofa position) under several camera configurations, and achieved 99.7% sensitivity and specificity or better with four cameras or more. A real-time implementation using a graphic processing unit (GPU) reached 10 frames per second (fps) with 8 cameras, and 16 fps with 3 cameras.

A method for automatic fall detection of elderly people using floor vibrations and sound--proof of concept on human mimicking doll falls

Falls are a major risk for the elderly people living independently. Rapid detection of fall events can reduce the rate of mortality and raise the chances to survive the event and return to independent living. In the last two decades, several technological solutions for detection of falls were published, but most of them suffer from critical limitations. In this paper, we present a proof of concept to an automatic fall detection system for elderly people. The system is based on floor vibration and sound sensing, and uses signal processing and pattern recognition algorithm to discriminate between fall events and other events. The classification is based on special features like shock response spectrum and mel frequency ceptral coefficients. For the simulation of human falls, we have used a human mimicking doll: "Rescue Randy." The proposed solution is unique, reliable, and does not require the person to wear anything. It is designed to detect fall events in critical cases in which the person is unconscious or in a stress condition. From the preliminary research, the proposed system can detect human mimicking dolls falls with a sensitivity of 97.5% and specificity of 98.6%.

Fall detection using multiple cameras

Today, different ways are suggested to help elderly people in case of emergency. Our aim here is to propose a novel method, without any wearable device, to detect falls on the floor with a multiple cameras system. This proposal uses image analysis to localise people and reconstruct their 3D shape and position. The particularity of this contribution is the use of cameras sharing a large common field of view. Experimental results obtained with 14 different fall scenarios and 14 normal daily activities showed a 100% fall detection efficiency.

Fall-detection through vertical velocity thresholding using a tri-axial accelerometer characterized using an optical motion-capture system

Falls in the elderly population are a major problem for today's society. The immediate automatic detection of such events would help reduce the associated consequences of falls. This paper describes the development of an accurate, accelerometer-based fall detection system to distinguish between Activities of Daily Living (ADL) and falls. It has previously been shown that falls can be distinguished from normal ADL through vertical velocity thresholding using an optical motion capture system. In this study however accurate vertical velocity profiles of the trunk were generated by simple signal processing of the signals from a tri-axial accelerometer (TA). By recording simulated falls onto crash mats and ADL performed by 5 young healthy subjects, using both a single chest mounted TA and using an optical motion capture system, the accuracy of the vertical velocity profiles was assessed. Data analysis was performed using MATLAB to determine the peak velocities recorded and RMS error during four different fall and six ADL types. Results show high correlations and low percentage errors between the vertical velocity profiles generated by the TA to those recorded using the optical motion capture system. In addition, through thresholding of the vertical velocity profiles generated using the TA at -1.3m/s, falls can be distinguished from normal ADL with 100% sensitivity and specificity.

Activity identification using body-mounted sensors--a review of classification techniques

With the advent of miniaturized sensing technology, which can be body-worn, it is now possible to collect and store data on different aspects of human movement under the conditions of free living. This technology has the potential to be used in automated activity profiling systems which produce a continuous record of activity patterns over extended periods of time. Such activity profiling systems are dependent on classification algorithms which can effectively interpret body-worn sensor data and identify different activities. This article reviews the different techniques which have been used to classify normal activities and/or identify falls from body-worn sensor data. The review is structured according to the different analytical techniques and illustrates the variety of approaches which have previously been applied in this field. Although significant progress has been made in this important area, there is still significant scope for further work, particularly in the application of advanced classification techniques to problems involving many different activities.

A wearable system for pre-impact fall detection

Unique features of body segment kinematics in falls and activities of daily living (ADL) are applied to make automatic detection of a fall in its descending phase, prior to impact, possible. Fall-related injuries can thus be prevented or reduced by deploying fall impact reduction systems, such as an inflatable airbag for hip protection, before the impact. In this application, the authors propose the following hypothesis: "Thigh segments normally do not exceed a certain threshold angle to the side and forward directions in ADL, whereas this abnormal behavior occurs during a fall activity". Torso and thigh wearable inertial sensors (3D accelerometer and 2D gyroscope) are used and the whole system is based on a body area network (BAN) for the comfort of the wearer during a long term application. The hypothesis was validated in an experiment with 21 young healthy volunteers performing both normal ADL and fall activities. Results show that falls could be detected with an average lead-time of 700 ms before the impact occurs, with no false alarms (100% specificity), a sensitivity of 95.2%. This is the longest lead-time achieved so far in pre-impact fall detection.

Distinguishing falls from normal ADL using vertical velocity profiles

This paper describes a technique for distinguishing falls from activities of daily living (ADL) through vertical velocity thresholding (VVT). To verify that VVT can be used to distinguish falls from ADL and to detect falls prior to impact, simulated fall and ADL testing was carried out on five young healthy subjects. Results show that the VVT method can distinguish falls from ADL with 100% accuracy and with an average lead-time of 323ms prior to trunk impact and 140ms prior to knee impact.

Fall detection--principles and methods

Fall detection of the elderly is a major public health problem. Thus it has generated a wide range of applied research and prompted the development of telemonitoring systems to enable the early diagnosis of fall conditions. This article is a survey of systems, algorithms and sensors, for the automatic early detection of the fall of elderly persons. It points out the difficulty to compare the performances of the different systems due to the lack of a common framework. It then proposes a procedure for this evaluation.