Towards a social and context-aware multi-sensor fall detection and risk assessment platform

Wrist-Based Fall Detection: Towards Generalization across Datasets

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

Deep Learning-Based Near-Fall Detection Algorithm for Fall Risk Monitoring System Using a Single Inertial Measurement Unit

Proactively detecting falls and preventing injuries are among the primary keys to a healthy life for the elderly. Near-fall remote monitoring in daily life could provide key information to prevent future falls and obtain quantitative rehabilitation status for patients with weak balance ability. In this study, we developed a deep learning-based novel classification algorithm to precisely categorize three classes (falls, near-falls, and activities of daily living (ADLs)) using a single inertial measurement unit (IMU) device attached to the waist. A total of 34 young participants were included in this study. An IMU containing accelerometer and gyroscope sensors was fabricated to acquire acceleration and angular velocity signals. A comprehensive experiment including thirty-six types of activities (10 types of falls, 10 types of near-falls, and 16 types of ADLs) was designed based on previous studies. A modified directed acyclic graph-convolution neural network (DAG-CNN) architecture with hyperparameter optimization was proposed to predict fall, near-fall, and ADLs. Prediction results of the modified DAG-CNN structure were found to be approximately 7% more accurate than the traditional CNN structure. For the case of near-falls, the modified DAG-CNN demonstrated excellent prediction performance with accuracy of over 98% by combining gyroscope and accelerometer features. Additionally, by combining acceleration and angular velocity the trained model showed better performance than each model of acceleration and angular velocity. It is believed that information to preemptively handle the risk of falls and quantitatively evaluate the rehabilitation status of the elderly with weak balance will be provided by monitoring near-falls.

Device-Free Human Activity Recognition with Low-Resolution Infrared Array Sensor Using Long Short-Term Memory Neural Network

Sensor-based human activity recognition (HAR) has attracted enormous interests due to its wide applications in the Internet of Things (IoT), smart homes and healthcare. In this paper, a low-resolution infrared array sensor-based HAR approach is proposed using the deep learning framework. The device-free sensing system leverages the infrared array sensor of 8×8 pixels to collect the infrared signals, which can ensure users' privacy and effectively reduce the deployment cost of the network. To reduce the influence of temperature variations, a combination of the J-filter noise reduction method and the Butterworth filter is performed to preprocess the infrared signals. Long short-term memory (LSTM), a representative recurrent neural network, is utilized to automatically extract characteristics from the infrared signal and build the recognition model. In addition, the real-time HAR interface is designed by embedding the LSTM model. Experimental results show that the typical daily activities can be classified with the recognition accuracy of 98.287%. The proposed approach yields a better result compared to the existing machine learning methods, and it provides a low-cost yet promising solution for privacy-preserving scenarios.

Acceleration Magnitude at Impact Following Loss of Balance Can Be Estimated Using Deep Learning Model

Pre-impact fall detection can detect a fall before a body segment hits the ground. When it is integrated with a protective system, it can directly prevent an injury due to hitting the ground. An impact acceleration peak magnitude is one of key measurement factors that can affect the severity of an injury. It can be used as a design parameter for wearable protective devices to prevent injuries. In our study, a novel method is proposed to predict an impact acceleration magnitude after loss of balance using a single inertial measurement unit (IMU) sensor and a sequential-based deep learning model. Twenty-four healthy participants participated in this study for fall experiments. Each participant worn a single IMU sensor on the waist to collect tri-axial accelerometer and angular velocity data. A deep learning method, bi-directional long short-term memory (LSTM) regression, is applied to predict a fall's impact acceleration magnitude prior to fall impact (a fall in five directions). To improve prediction performance, a data augmentation technique with increment of dataset is applied. Our proposed model showed a mean absolute percentage error (MAPE) of 6.69 ± 0.33% with r value of 0.93 when all three different types of data augmentation techniques are applied. Additionally, there was a significant reduction of MAPE by 45.2% when the number of training datasets was increased by 4-fold. These results show that impact acceleration magnitude can be used as an activation parameter for fall prevention such as in a wearable airbag system by optimizing deployment process to minimize fall injury in real time.

Falls management framework for supporting an independent lifestyle for older adults: a systematic review

Falls are one of the common health and well-being issues among the older adults. Internet of things (IoT)-based health monitoring systems have been developed over the past two decades for improving healthcare services for older adults to support an independent lifestyle. This research systematically reviews technological applications related to falls detection and falls management. The systematic review was conducted in accordance to the preferred reporting items for systematic reviews and meta-analysis statement (PRISMA). Twenty-four studies out of 806 articles published between 2015 and 2017 were identified and included in this review. Selected studies were related to pre-fall and post-fall applications using motion sensors (10; 41.67%), environment sensors (10; 41.67%) and few studies used the combination of these types of sensors (4; 16.67%). As an outcome of this review, we postulated a falls management framework (FMF). FMF considered pre- and post-fall strategies to support older adults live independently. A part of this approach involved active analysis of sensor data with the aim of helping the older adults manage their risk of fall and stay safe in their home. FMF aimed to serve the researchers, developers, clinicians and policy makers with pre- and post-falls management strategies to enhance the older adults' independent living and well-being.

Social-aware Event Handling within the FallRisk Project

Objectives: With the uprise of the Internet of Things, wearables and smartphones are moving to the foreground. Ambient Assisted Living solutions are, for example, created to facilitate ageing in place. One example of such systems are fall detection systems. Currently, there exists a wide variety of fall detection systems using different methodologies and technologies. However, these systems often do not take into account the fall handling process, which starts after a fall is identified or this process only consists of sending a notification. The FallRisk system delivers an accurate analysis of incidents occurring in the home of the older adults using several sensors and smart devices. Moreover, the input from these devices can be used to create a social-aware event handling process, which leads to assisting the older adult as soon as possible and in the best possible way.

Methods: The FallRisk system consists of several components, located in different places. When an incident is identified by the FallRisk system, the event handling process will be followed to assess the fall incident and select the most appropriate caregiver, based on the input of the smartphones of the caregivers. In this process, availability and location are automatically taken into account.

Results: The event handling process was evaluated during a decision tree workshop to verify if the current day practices reflect the requirements of all the stakeholders. Other knowledge, which is uncovered during this workshop can be taken into account to further improve the process.

Conclusions: The FallRisk offers a way to detect fall incidents in an accurate way and uses context information to assign the incident to the most appropriate caregiver. This way, the consequences of the fall are minimized and help is at location as fast as possible. It could be concluded that the current guidelines on fall handling reflect the needs of the stakeholders. However, current technology evolutions, such as the uptake of wearables and smartphones, enables the improvement of these guidelines, such as the automatic ordering of the caregivers based on their location and availability.

The OCarePlatform: A context-aware system to support independent living

BACKGROUND

Currently, healthcare services, such as institutional care facilities, are burdened with an increasing number of elderly people and individuals with chronic illnesses and a decreasing number of competent caregivers.

OBJECTIVES

To relieve the burden on healthcare services, independent living at home could be facilitated, by offering individuals and their (in)formal caregivers support in their daily care and needs. With the rise of pervasive healthcare, new information technology solutions can assist elderly people ("residents") and their caregivers to allow residents to live independently for as long as possible.

METHODS

To this end, the OCarePlatform system was designed. This semantic, data-driven and cloud-based back-end system facilitates independent living by offering information and knowledge-based services to the resident and his/her (in)formal caregivers. Data and context information are gathered to realize context-aware and personalized services and to support residents in meeting their daily needs. This body of data, originating from heterogeneous data and information sources, is sent to personalized services, where is fused, thus creating an overview of the resident's current situation.

RESULTS

The architecture of the OCarePlatform is proposed, which is based on a service-oriented approach, together with its different components and their interactions. The implementation details are presented, together with a running example. A scalability and performance study of the OCarePlatform was performed. The results indicate that the OCarePlatform is able to support a realistic working environment and respond to a trigger in less than 5 seconds. The system is highly dependent on the allocated memory.

CONCLUSION

The data-driven character of the OCarePlatform facilitates easy plug-in of new functionality, enabling the design of personalized, context-aware services. The OCarePlatform leads to better support for elderly people and individuals with chronic illnesses, who live independently.

An Analysis on Sensor Locations of the Human Body for Wearable Fall Detection Devices: Principles and Practice

Wearable devices for fall detection have received attention in academia and industry, because falls are very dangerous, especially for elderly people, and if immediate aid is not provided, it may result in death. However, some predictive devices are not easily worn by elderly people. In this work, a huge dataset, including 2520 tests, is employed to determine the best sensor placement location on the body and to reduce the number of sensor nodes for device ergonomics. During the tests, the volunteer’s movements are recorded with six groups of sensors each with a triaxial (accelerometer, gyroscope and magnetometer) sensor, which is placed tightly on different parts of the body with special straps: head, chest, waist, right-wrist, right-thigh and right-ankle. The accuracy of individual sensor groups with their location is investigated with six machine learning techniques, namely the k-nearest neighbor (k-NN) classifier, Bayesian decision making (BDM), support vector machines (SVM), least squares method (LSM), dynamic time warping (DTW) and artificial neural networks (ANNs). Each technique is applied to single, double, triple, quadruple, quintuple and sextuple sensor configurations. These configurations create 63 different combinations, and for six machine learning techniques, a total of 63 × 6 = 378 combinations is investigated. As a result, the waist region is found to be the most suitable location for sensor placement on the body with 99.96% fall detection sensitivity by using the k-NN classifier, whereas the best sensitivity achieved by the wrist sensor is 97.37%, despite this location being highly preferred for today’s wearable applications.

SmartFABER: Recognizing fine-grained abnormal behaviors for early detection of mild cognitive impairment

OBJECTIVE

In an ageing world population more citizens are at risk of cognitive impairment, with negative consequences on their ability of independent living, quality of life and sustainability of healthcare systems. Cognitive neuroscience researchers have identified behavioral anomalies that are significant indicators of cognitive decline. A general goal is the design of innovative methods and tools for continuously monitoring the functional abilities of the seniors at risk and reporting the behavioral anomalies to the clinicians. SmartFABER is a pervasive system targeting this objective.

METHODS

A non-intrusive sensor network continuously acquires data about the interaction of the senior with the home environment during daily activities. A novel hybrid statistical and knowledge-based technique is used to analyses this data and detect the behavioral anomalies, whose history is presented through a dashboard to the clinicians. Differently from related works, SmartFABER can detect abnormal behaviors at a fine-grained level.

RESULTS

We have fully implemented the system and evaluated it using real datasets, partly generated by performing activities in a smart home laboratory, and partly acquired during several months of monitoring of the instrumented home of a senior diagnosed with MCI. Experimental results, including comparisons with other activity recognition techniques, show the effectiveness of SmartFABER in terms of recognition rates.