Shkurta Gashi

Last Name

Gashi

First Name

Shkurta

ORCID

0000-0001-6650-3784

Show all metadata

Search Results

Publications1 - 10 of 10

Systematic Evaluation of Self-Supervised Learning Approaches for Wearable-Based Fatigue Recognition
Visy, Tamás; Kuznetsova, Rita; Holz, Christian; et al. (2024)
Proceedings of Machine Learning Research ~ Proceedings of the fifth Conference on Health, Inference, and Learning
Fatigue is one of the most prevalent symptoms of chronic diseases, such as Multiple Sclerosis, Alzheimer’s, and Parkinson’s. Recently researchers have explored unobtrusive and continuous ways of fatigue monitoring using mobile and wearable devices. However, data quality and limited labeled data availability in the wearable health domain pose significant challenges to progress in the field. In this work, we perform a systematic evaluation of self-supervised learning (SSL) tasks for fatigue recognition using wearable sensor data. To establish our benchmark, we use Homekit2020, which is a large-scale dataset collected using Fitbit devices in everyday life settings. Our results show that the majority of the SSL tasks outperform fully supervised baselines for fatigue recognition, even in limited labeled data scenarios. In particular, the domain features and multi-task learning achieve 0.7371 and 0.7323 AUROC, which are higher than the other SSL tasks and supervised learning baselines. In most of the pre-training tasks, the performance is higher when using at least one data augmentation that reflects the potentially low quality of wearable data (e.g., missing data). Our findings open up promising opportunities for continuous assessment of fatigue in real settings and can be used to guide the design and development of health monitoring systems.
Representation Learning for Wearable-Based Applications in the Case of Missing Data
Jungo, Janosch; Xiang, Yutong; Gashi, Shkurta; et al. (2024)
arXiv
Wearable devices continuously collect sensor data and use it to infer an individual's behavior, such as sleep, physical activity, and emotions. Despite the significant interest and advancements in this field, modeling multimodal sensor data in real-world environments is still challenging due to low data quality and limited data annotations. In this work, we investigate representation learning for imputing missing wearable data and compare it with state-of-the-art statistical approaches. We investigate the performance of the transformer model on 10 physiological and behavioral signals with different masking ratios. Our results show that transformers outperform baselines for missing data imputation of signals that change more frequently, but not for monotonic signals. We further investigate the impact of imputation strategies and masking rations on downstream classification tasks. Our study provides insights for the design and development of masking-based self-supervised learning tasks and advocates the adoption of hybrid-based imputation strategies to address the challenge of missing data in wearable devices.
Meaningful digital biomarkers derived from wearable sensors to predict daily fatigue in multiple sclerosis patients and healthy controls
Moebus, Max; Gashi, Shkurta; Hilty, Marc; et al. (2024)
iScience
Fatigue is the most common symptom among multiple sclerosis (MS) patients and severely affects the quality of life. We investigate how perceived fatigue can be predicted using biomarkers collected from an arm-worn wearable sensor for MS patients (n = 51) and a healthy control group (n = 23) at an unprecedented time resolution of more than five times per day. On average, during our two-week study, participants reported their level of fatigue 51 times totaling more than 3,700 data points. Using interpretable generalized additive models, we find that increased physical activity, heart rate, sympathetic activity, and parasympathetic activity while awake and asleep relate to perceived fatigue throughout the day—partly affected by dysfunction of the ANS. We believe our analysis opens up new research opportunities for fine-grained modeling of perceived fatigue based on passively collected physiological signals using wearables—for MS patients and healthy controls alike.
WellComp 2023: Sixth International Workshop on Computing for Well-Being
Gashi, Shkurta; Spathis, Dimitris; Dang, Ting; et al. (2023)
UbiComp/ISWC '23 Adjunct: Adjunct Proceedings of the 2023 ACM International Joint Conference on Pervasive and Ubiquitous Computing & the 2023 ACM International Symposium on Wearable Computing
With the advancements in ubiquitous computing, ubicomp technology has deeply spread into our daily lives, including office work, home and house-keeping, health management, transportation, or even urban living environments. Furthermore, beyond the initial metrics commonly applied in computing, such as “efficiency” and “productivity”, the benefits that people (users) get from well-being-aware ubiquitous technology have been greatly emphasized in the recent years. Through the sixth “WellComp” (Computing for Well-being) workshop, we will discuss and debate the contribution of ubiquitous computing towards users’ well-being covering physical, mental, and social wellness (and the combinations thereof), from the viewpoints of various different layers of computing. Organized by a diverse international team of ubicomp researchers, WellComp 2023 will bring together researchers and practitioners from both academia and industry to explore versatile topics related to well-being and ubiquitous computing.
Multi-Frequency Federated Learning for Human Activity Recognition Using Head-Worn Sensors
Fenoglio, Dario; Li, Mohan; Casnici, Davide; et al. (2024)
2024 International Conference on Intelligent Environments (IE)
Human Activity Recognition (HAR) benefits various application domains, including health and elderly care. Traditional HAR involves constructing pipelines reliant on centralized user data, which can pose privacy concerns as they necessitate the uploading of user data to a centralized server. This work proposes multi-frequency Federated Learning (FL) to enable: (1) privacy-aware ML; (2) joint ML model learning across devices with varying sampling frequency. We focus on head-worn devices (e.g., earbuds and smart glasses), a relatively unexplored domain compared to traditional smartwatch- or smartphone-based HAR. Results have shown improvements on two datasets against frequency-specific approaches, indicating a promising future in the multi-frequency FL-HAR task. The proposed network's implementation is publicly available for further research and development.
Large Language Models for Wearable Data Analysis and Interpretation
Böhi, Simon; Gashi, Shkurta (2024)
The Second Tiny Papers Track at ICLR 2024
In this paper, we investigate the application of large language models (LLMs) to zero-shot and few-shot prediction and classification of multimodal wearable sensor data. Using data from the large-scale HomeKit2020 dataset, we explore health tasks including cardiac activity monitoring, metabolic health prediction, and sleep detection. We demonstrate that LLMs perform feature extraction, prediction, and classification with comparable or higher performance than classical machine learning approaches even in the zero-shot scenario. Our findings show promising results in using LLMs for wearable data analysis and interpretation.
Modeling multiple sclerosis using mobile and wearable sensor data
Gashi, Shkurta; Oldrati, Pietro; Moebus, Max; et al. (2024)
npj Digital Medicine
Multiple sclerosis (MS) is a neurological disease of the central nervous system that is the leading cause of non-traumatic disability in young adults. Clinical laboratory tests and neuroimaging studies are the standard methods to diagnose and monitor MS. However, due to infrequent clinic visits, it is fundamental to identify remote and frequent approaches for monitoring MS, which enable timely diagnosis, early access to treatment, and slowing down disease progression. In this work, we investigate the most reliable, clinically useful, and available features derived from mobile and wearable devices as well as their ability to distinguish people with MS (PwMS) from healthy controls, recognize MS disability and fatigue levels. To this end, we formalize clinical knowledge and derive behavioral markers to characterize MS. We evaluate our approach on a dataset we collected from 55 PwMS and 24 healthy controls for a total of 489 days conducted in free-living conditions. The dataset contains wearable sensor data - e.g., heart rate - collected using an arm-worn device, smartphone data - e.g., phone locks - collected through a mobile application, patient health records - e.g., MS type - obtained from the hospital, and self-reports - e.g., fatigue level - collected using validated questionnaires administered via the mobile application. Our results demonstrate the feasibility of using features derived from mobile and wearable sensors to monitor MS. Our findings open up opportunities for continuous monitoring of MS in free-living conditions and can be used to evaluate and guide the effectiveness of treatments, manage the disease, and identify participants for clinical trials.
WellComp 2024: Seventh International Workshop on Computing for Well-Being
Dang, Ting; Gashi, Shkurta; Spathis, Dimitris; et al. (2024)
UbiComp '24: Companion of the 2024 on ACM International Joint Conference on Pervasive and Ubiquitous Computing
With the advancements in ubiquitous computing, ubicomp technology has deeply spread into our daily lives, including office work, home and housekeeping, health management, transportation, and even urban living environments. Furthermore, beyond the initial metric of computing, such as “efficiency” and “productivity”, the benefits that people (users) benefit on a well-being perspective based on such ubiquitous technology have been greatly paid attention to in recent years. In our seventh “WellComp” (Computing for Well-being) workshop, we intensively discuss the contribution of ubiquitous computing towards users' well-being that covers physical, mental, and social wellness (and their combinations), from the viewpoints of various different layers of computing. After big success of the six previous workshops, with strong international organization members in various ubicomp research domains, WellComp 2024 will bring together researchers and practitioners from the academia and industry to explore versatile topics related to well-being and ubiquitous computing.
Heart Rate During Sleep Measured Using Finger-, Wrist-and Chest-Worn Devices: A Comparison Study
Abdalazim, Nouran; Arbilla Larraza, Joseba Aitzol; Alchieri, Leonardo; et al. (2023)
Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering ~ Pervasive Computing Technologies for Healthcare
Wearable heart rate (HR) sensing devices are increasingly used to monitor human health. The availability and the quality of the HR measurements may however be affected by the body location at which the device is worn. The goal of this paper is to compare HR data collected from different devices and body locations and to investigate their interchangeability at different stages of the data analysis pipeline. To this goal, we conduct a data collection campaign and collect HR data from three devices worn at different body positions (finger, wrist, chest): The Oura ring, the Empatica E4 wristband and the Polar chestbelt. We recruit five participants for 30 nights and gather HR data along with self-reports about sleep behavior. We compare the raw data, the features extracted from this data over different window sizes, and the performance of models that use these features in recognizing sleep quality. Raw HR data from the three devices show a high positive correlation. When features are extracted from the raw data, though, both small and significant differences can be observed. Ultimately, the accuracy of a sleep quality recognition classifier does not show significant differences when the input data is derived from the Oura ring or the E4 wristband. Taken together, our results indicate that the HR measurements collected from the considered devices and body locations are interchangeable. These findings open up new opportunities for sleep monitoring systems to leverage multiple devices for continuous sleep tracking.
Lateralization Effects in Electrodermal Activity Data Collected Using Wearable Devices
Alchieri, Leonardo; Abdalazim, Nouran; Alecci, Lidia; et al. (2024)
Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
Electrodermal activity (EDA) is a physiological signal that can be used to infer humans' affective states and stress levels. EDA can nowadays be monitored using unobtrusive wearable devices, such as smartwatches, and leveraged in personal informatics systems. A still largely uncharted issue concerning EDA is the impact on real applications of potential differences observable on signals measured concurrently on the left and right side of the human body. This phenomenon, called lateralization, originates from the distinct functions that the brain's left and right hemispheres exert on EDA. In this work, we address this issue by examining the impact of EDA lateralization in two classification tasks: a cognitive load recognition task executed in the lab and a sleep monitoring task in a real-world setting. We implement a machine learning pipeline to compare the performance obtained on both classification tasks using EDA data collected from the left and right sides of the body. Our results show that using EDA from the side that is not associated with the specific hemisphere activation leads to a significant decline in performance for the considered classification tasks. This finding highlights that researchers and practitioners relying on EDA data should consider possible EDA lateralization effects when deciding on sensor placement.

Publications1 - 10 of 10

Shkurta Gashi

Last Name

First Name

ORCID

Organisational unit

Filters

Search Results