Elena Di Lascio |

M2Sleep

Fri, 01 Apr 2022 00:00:00 +0000

Personal informatics systems can help people promote their health and well-being. Recent studies have shown that such systems can be used to infer relevant health indicators such as, e.g., stress, anxiety, and sleeping habits. While automatic detection of sleep has been studied extensively, there is a lack of studies exploring how population and personalized models influence the performance of sleep detection. In this article, we address this challenge by investigating the recognition of sleep/wake stages and high/low sleep quality with a focus on the impact of personalized models. To evaluate our approach, we collect a dataset of physiological signals and self-reports about sleep/wake times and sleep quality score. The dataset contains 6557 hours of sensor data collected using wristbands from 16 participants over one month. Our results show that personalized models perform significantly better than population models for sleep quality recognition, and are comparably good for sleep stage detection. The balanced accuracy for sleep/wake and high/low sleep quality are 92.2% and 61.51%, which are significantly higher than baseline classifiers.

Handling Missing Data For Sleep Monitoring Systems

Sat, 01 Jan 2022 00:00:00 +0000

Multi-task Learning for Stress Recognition

Sat, 01 Jan 2022 00:00:00 +0000

On the Impact of Lateralization in Physiological Signals from Wearable Sensors

Sat, 01 Jan 2022 00:00:00 +0000

The Role of Model Personalization for Sleep Stage and Sleep Quality Recognition Using Wearables

Sat, 01 Jan 2022 00:00:00 +0000

HAFAR

Mon, 18 Oct 2021 00:00:00 +0000

Head gestures and facial expressions – like, e.g., nodding or smiling – are important indicators of the quality of human interactions in physical meetings as well as in computer-mediated settings. Computer systems able to recognize such behavioral cues can support and improve human interactions. Several researchers have thus tackled the problem of automatically recognizing head gestures and facial expressions, mainly leveraging video data. In this paper, we instead consider inertial signals collected from unobtrusive, ear-mounted devices. We focus on typical activities performed during social interactions – head shaking, nodding, smiling, talking and yawning – and propose a hierarchical classification approach to discriminate them from each other. Further, we investigate whether the transfer of knowledge learned from publicly available datasets leads to further performance improvements. Our results show that the combined use of our hierarchical approach and transfer learning allows the classifier to discriminate head and mouth activities with an F1 score of 84.79, smile, talk and yawn with an F1 score of 45.42, and nodding and head shaking with an F1 score of 88.24, outperforming shallow classifiers by 2-9 percentage points.

Automatic Recognition of Flow During Work Activities Using Context and Physiological Signals

Fri, 01 Jan 2021 00:00:00 +0000

Biometric recognition using wearable devices in real-life settings

Fri, 01 Jan 2021 00:00:00 +0000

Hierarchical Classification and Transfer Learning to Recognize Head Gestures and Facial Expressions Using Earbuds

Fri, 01 Jan 2021 00:00:00 +0000

EDArtifact

Mon, 15 Jun 2020 00:00:00 +0000

Recent wearable devices enable continuous and unobtrusive monitoring of human’s physiological parameters, like e.g., electrodermal activity and heart rate, over long periods of time in everyday life settings. Continuous monitoring of these parameters enables the creation of systems able to predict affective states and stress with the goal of providing feedback to improve them. Deployment of such systems in everyday life settings is still complex and prone to errors due to the low quality of the collected data impacted by the presence of artifacts. In this paper we present an automatic approach to detect artifacts in electrodermal activity (EDA) signals collected in-the-wild over long periods of time. To this end we first perform a systematic literature review and compile a set of guidelines for human annotators to label artifacts manually and we use these labels as ground-truth to test our automatic approach. To evaluate our approach, we collect physiological data from 13 participants in-the-wild and two human annotators label 107.56 hours of this data set. We make the data set publicly available to other researchers upon request. Our model achieves a recall of 98% for clean and shape artifacts classification on data collected in-the-wild using leave-one-subject-out cross-validation, which is 42 percentage points higher than the baseline. We show that state of the art approaches do not generalize well when tested with completely in-the-wild data and identify only 17% of the artifacts present in our data set, even after manual adaption. We further test the robustness of our approach over time using leave-one-day-out and achieve very similar performance. We then introduce a new metric to evaluate the quality of EDA segments that considers the impact of not only artifacts in the shape of EDA but also artifacts generated by environmental temperature changes or user’s high intensity movement. Our results imply that we can eliminate the need for human annotators or significantly reduce the time they need to label data. Also, our approach can be used in an online manner to automatically detect artifacts in EDA signals.

A Multi-Sensor Approach to Automatically Recognize Breaks and Work Activities of Knowledge Workers in Academia

Wed, 01 Jan 2020 00:00:00 +0000

Detection of Artifacts in Ambulatory Electrodermal Activity Data

Wed, 01 Jan 2020 00:00:00 +0000

USILaughs

Mon, 20 May 2019 00:00:00 +0000

A growing number of pervasive systems integrate emotion recognition capabilities with the aim of fostering and promoting human health and wellbeing. In this paper, we argue that enhancing these systems with the ability to detect laughter episodes automatically would improve their effectiveness. This is because laughter is one of the most expressive behavioral cues for positive emotions. However, the existing approaches for laughter recognition rely on the use of obtrusive devices or of video and audio cues and have thus limited applicability in real-world settings. To overcome this limitation, we evaluate the feasibility of a novel, multi-modal approach to recognize laughter episodes using physiological and body movement data gathered with unobtrusive, wrist-worn devices. To assess the performance of our method, we collect an extensive data set of laughter episodes, which we also make publicly available. Our results show that laughter episodes can be distinguished from non-laughter episodes with an accuracy of 81%. Further, we demonstrate that the signatures left by laughter episodes on physiological and body-movement data differ significantly from those caused by slightly intense motions or cognitive load tasks.

Laughter Recognition Using Non-invasive Wearable Devices

Tue, 01 Jan 2019 00:00:00 +0000

Movie+: Towards Exploring Social Effects of Emotional Fingerprints for Video Clips and Movies

Tue, 01 Jan 2019 00:00:00 +0000

UPA'19: 4th international workshop on ubiquitous personal assistance

Tue, 01 Jan 2019 00:00:00 +0000

Using Unobtrusive Wearable Sensors to Measure the Physiological Synchrony Between Presenters and Audience Members

Tue, 01 Jan 2019 00:00:00 +0000

Calmify: Measuring the Effectiveness of Personalized Meditation Techniques Using Mobile Technologies