1,720,989 research outputs found
Real-time identification using gait pattern analysis on a standalone wearable accelerometer
Full text linkWearable devices can gather sensitive information about their users. For this reason, automated authentication and identification techniques are increasingly adopted to ensure security and privacy. Furthermore, identification can be used to automatically customize operations according to the needs of the current user. A gait-based identification method that can be executed in real time on devices with limited resources is here presented. The method exploits a wearable accelerometer to continuously analyze the user’s gait pattern and perform identification. Experiments were conducted with 10 volunteers, who carried the device in a trouser pocket and followed their daily routine without predefined constraints. In total, ~98 hours of acceleration traces were collected in uncontrolled environment, including 3073 gait segments. User identification results show a recognition rate ranging from 95% to 100%, depending on the mode of operation. It is demonstrated that the method can be executed on a standalone device with <8 KB of RAM. In addition, the energy consumption is evaluated and compared with an architecture that requires the presence of an external computing unit. Results show that the proposed solution significantly improves the lifetime of the device (approximately +70% for the considered platform), hence fostering user acceptance
Improving the Performance of Fall Detection Systems through Walk Recognition
Full text linkSocial problems associated with falls of elderly citizens are becoming increasingly important because of the continuous growth of aging population. Automatic fall detection systems represent a possible answer to some of these problems, as they are useful to obtain help in case of serious injuries and to reduce the long-lie problem. Nevertheless, widespread adoption of these systems is strongly influenced by their usability and trustworthiness, which are at the moment not excellent. In fact, the user is forced to wear the device according to placement and orientation restrictions that depend on the considered fall-recognition technique. Also, the number of false alarms generated is too high to be acceptable in real world scenarios. This paper presents a technique, based on walk recognition, that increases significantly both usability and trustworthiness of a smartphone-based fall detection system. In particular, the proposed technique automatically and dynamically determines the orientation of the device, thus relieving the user from the burden of wearing the device with predefined orientation. Orientation is then used to infer posture and eliminate a large fraction of false alarms (98 %)
Wearable systems for e-health and wellbeing
Full text linkWearable devices, such as smartwatches and fitness bands, are becoming a key element of our lives. They are used in an always increasing number of activities, for example during sport sessions for keeping track of energy expenditure, or when walking as unobtrusive pedestrian navigation systems. In general, these devices are worn continuously throughout the day and thus provide the opportunity to gather information about their users with unprecedented levels. In addition, many wearable devices are directly worn over the skin and they may include sensors not available on common smartphones (e.g., for monitoring the user’s heart rate). As a consequence, they are particularly suitable for those medical applications where continuous monitoring is fundamental. At the same time, the massive amount of information collected through these devices is enabling novel applications in the context of e-health and wellbeing. Finally, it is known that abundance of information promotes an effective management of patients’ condition, and a well-informed patient is more likely to conduct a healthy lifestyle.
This issue of Personal and Ubiquitous Computing collects recent, original research in the area of wearable systems for e-health and wellbeing. Fourteen papers were initially submitted to this issue. After two rounds of review, four of them were finally accepted for publication.
The first paper, “Sleep behavior assessment via smartwatch and stigmergic receptive fields”, presents a method for automatic assessment of sleep quality using a smartwatch. Heartbeat rate and wrist motion samples are processed using computational stigmergy, a bio-inspired technique that relies on digital pheromone marks.
The second paper, “Social Recommendations for Personalized Fitness Assistance”, presents a novel framework—PRO-Fit—aimed at engaging users in fitness activities. The proposed framework minimizes the need for user input and proactively generates personalized fitness schedules. Collaborative filtering and social network information are exploited to automatically provide activities and fitness buddy recommendations.
The third paper, “Robust Orientation Estimate via Inertial Guided Visual Sample Consensus”, presents a method for estimating the orientation of body joints using a wearable camera paired with an Inertial Measurement Unit (IMU). Visual information is used to correct the drift of the IMU, whereas information produced by the IMU enables more accurate and efficient image-based estimation.
The last paper, “SVM-based classification method to identify alcohol consumption using ECG and PPG monitoring”, presents a method for detecting alcohol intoxication that is compatible with the requirements of wearable devices. Cardiac activity, observed through simple sensor configurations, is given as input to a classification system in charge of estimating the status of the user.
Finally, as co-guest editors of this issue, we would like to thank all the authors for their contributions
Fall detection using ultra-wideband positioning
Full text linkFalls are a major health problem in our aging society. Fall detection systems
are aimed at automatically sending an alarm in case of falls. Unfortunately
most of the systems currently available, which use accelerometric sensors, are
characterized by a relatively large number of false alarms. In fact, many
activities of daily living may produce fall-like acceleration signals. We
propose a method that uses ultra-wideband positioning to track the movements of
the user and detect falls. Preliminary results show that the approach is
reliable in detecting falls and simple postures
Dispositivo e procedimento per il riconoscimento di falsi allarmi in un apparecchio personale di segnalazione di emergenze
No full textPosture Recognition Using the Interdistances Between Wearable Devices
Full text linkRecognition of user's postures and activities is particularly important, as it allows applications to customize their operations according to the current situation. The vast majority of available solutions are based on wearable devices equipped with accelerometers and gyroscopes. In this article, a different approach is explored: The posture of the user is inferred from the interdistances between the set of devices worn by the user. Interdistances are first measured by using ultra-wideband transceivers operating in two-way ranging mode and then provided as input to a classifier that estimates current posture. An experimental evaluation shows that the proposed method is effective (up to ∼98.2% accuracy), especially when using a personalized model. The method could be used to enhance the accuracy of activity recognition systems based on inertial sensors
Personalized gait detection using a wrist-worn accelerometer
Full text linkWrist-worn devices, such as smartwatches and smart bands, have brought about the unprecedented opportunity to continuously monitor gait during daily routines. However, the use of a single wrist-worn unit for gait analysis is challenging for a variety of reasons. Indeed, the signal collected at the user's wrist is subject to a significant “noise” with respect to other body positions (e.g. waist), mainly due to the arm swing while walking and other unpredictable hand movements. The aim of this paper is to investigate the design and evaluation of a lightweight and reliable gait detection technique for wrist-worn devices. To this end, the proposed method creates a personalized model of the user's gait patterns. The model is created through an automatic training phase, which requires the temporary use of an additional device (smartphone) to gather true gait segments. After, anomaly detection is used to distinguish gait from other activities. Gait data from 20 volunteers have been collected to test and evaluate the proposed technique. Volunteers were asked to walk at different pace, with their normal arm swing or placing the hand inside of a pocket. Results show that the proposed method can reliably distinguish gait from spurious hand movements
Fall detection using a head-worn barometer
Full text linkFalls are a significant health and social problem for older adults and their relatives. In this paper we study the use of a barometer placed at the user’s head (e.g., embedded in a pair of glasses) as a means to improve current wearable sensor-based fall detection methods. This approach proves useful to reliably detect falls even if the acceleration produced during the impact is relatively small. Prompt detection of a fall and/or an abnormal lying condition is key to minimize the negative effect on health
Gait-based authentication using a wrist-worn device
No full textEvery individual has a distinctive way of walking. For this reason gait can be a key element of biometric techniques aimed at authenticating and/or identifying the user of a wearable device. This paper presents a lightweight method that uses the acceleration collected at the user’s wrist for authentication purposes. The user’s typical gait pattern is learned during the first period of use, then detection of anomalies in a set of acceleration-based features is used to understand if a new user, a possible impostor or a thief, is wearing the device. The method has been successfully eval- uated with 15 volunteers, showing an Equal Error Rate of 2.9%. These results suggest that gait-based authentication with a wrist-worn device can be carried out with high accu- racy levels. A comparison with a similar method executed on a smartphone is also included
How effective are Large Language Models (LLMs) at inferring people’s personality based on texts they authored?
No full text- …
