Foreseeing future falls with accelerometer features in active community-dwelling older persons with no recent history of falls.

BACKGROUND: Acceleration sensors are a viable option for monitoring gait patterns and its application on monitoring falls and risk of falling. However the literature still lacks prospective studies to investigate such risk before the occurrence of falls. OBJECTIVE: To investigate features extracted from accelerometer signals with the purpose of predicting future falls in individuals with no recent history of falls. METHODS: In this study we investigate the risk of fall in active and healthy community-dwelling living older persons with no recent history of falls, using a single accelerometer and variants of the Timed Up and Go (TUG) test. A prospective study was conducted with 74 healthy non-fallers older persons. After collecting acceleration data from the participants at the baseline, the occurrence of falls (outcome) was monitored quarterly during one year. A set of frequency features were extracted from the signal and their ability to predict falls was evaluated. RESULTS: The best individual feature result shows an accuracy of 0.75, sensitivity of 0.71 and specificity of 0.76. A fusion of the three best features increases the sensitivity to 0.86. On the other hand, the cut-off points of the TUG seconds, often used to assess fall risk, did not demonstrate adequate sensitivity. CONCLUSION: The results confirms previous evidence that accelerometer features can better estimate fall risk, and support potential applications that try to infer falls risk in less restricted scenarios, even in a sample stratified by age and gender composed of active and healthy community-dwelling living older persons.

Learning image features with fewer labels using a semi-supervised deep convolutional network.

Learning feature embeddings for pattern recognition is a relevant task for many applications. Deep learning methods such as convolutional neural networks can be employed for this assignment with different training strategies: leveraging pre-trained models as baselines; training from scratch with the target dataset; or fine-tuning from the pre-trained model. Although there are separate systems used for learning features from labelled and unlabelled data, there are few models combining all available information. Therefore, in this paper, we present a novel semi-supervised deep network training strategy that comprises a convolutional network and an autoencoder using a joint classification and reconstruction loss function. We show our network improves the learned feature embedding when including the unlabelled data in the training process. The results using the feature embedding obtained by our network achieve better classification accuracy when compared with competing methods, as well as offering good generalisation in the context of transfer learning. Furthermore, the proposed network ensemble and loss function is highly extensible and applicable in many recognition tasks.

Fall detection and fall risk assessment in older person using wearable sensors: A systematic review.

BACKGROUND: wearable sensors are often used to acquire data for gait analysis as a strategy to study fall events, due to greater availability of acquisition platforms, and advances in computational intelligence. However, there are no review papers addressing the three most common types of applications related to fall using sensors, namely: fall detection, fallers classification and fall risk screening. OBJECTIVE: To identify the state of art of fall-related events detection in older person using wearable sensors, as well as the main characteristics of the studies in the literature, pointing gaps for future studies. METHODS: A systematic review design was used to search peer-reviewed literature on fall detection and risk in elderly through inertial sensors, published in English, Portuguese, Spanish or French between August 2002 and June 2019. The following questions are investigated: the type of sensors and their sampling rate, the type of signal and data processing employed, the scales and tests used in the study and the type of application. RESULTS: We identified 608 studies, from which 29 were included. The accelerometer, with sampling rate 50 or 100 Hz, allocated in the waist or lumbar was the most used sensor setting. Methods comparing features or variables extracted from the accelerometry signal are the most common, and fall risk screening the most observed application. CONCLUSION: This review identifies the main elements to be addressed in studies on the detection of events related to falls in the elderly and may help in future studies on the subject. However, some aspects are still no reach consensus in the literature such as the size of the sample to be studied, the population under study and how to acquire data for each application.