Tyndall National Institute - Journal Articles

Permanent URI for this collection

https://hdl.handle.net/10468/3238

Browse

Now showing 1 - 5 of 1549

Assessing trust in collaborative robotics with different human-robot interfaces
(Institute of Electrical and Electronics Engineers (IEEE), 2024) Menolotto, Matteo; Komaris, Dimitrios-Sokratis; O’Sullivan, Patricia; O’Flynn, Brendan; Enterprise Ireland; Science Foundation Ireland; European Regional Development Fund
Human-robot interfaces (HRIs) serve as the main communication tools for controlling and programming robots in industry 4.0 applications. To be effective, the design of these interfaces should consider not only functional and morphological characteristics, but also factors influencing human interactions, such as trust. A lack of trust is linked to the underutilization or misuse of collaborative robots, leading to ineffective automation implementation and compromised safety. The assessment of human factors is therefore gaining traction in robotics, with the emergence of both objective and subjective methodologies. Nevertheless, the absence of a holistic approach hinders the development of a unified assessment framework. This study introduces a novel assessment methodology that integrates self-reporting questionnaires with human-centric data collected through wearable sensing technologies. The approach aims to offer a comprehensive evaluation of HRIs, considering both perceptual and behavioral dimensions. Empirical testing on three different HRIs substantiates the effectiveness of this methodology. Preliminary results reveal variations in trust levels based on the combination of tasks performed and the specific HRI used for communication with a collaborative robot. These findings not only contribute to advancing our understanding of trust dynamics in human-robot interactions but also lay the groundwork for a more inclusive evaluation framework, enhancing our comprehension of the intricate interplay between humans and robots in the context of smart manufacturing.
Inter-rater reliability of hand motor function assessment in Parkinson’s disease: impact of clinician training
(Elsevier, 2024) Kenny, Lorna; Azizi, Zahra; Moore, Kevin; Alcock, Megan; Heywood, Sarah; Jonsson, Agnes; McGrath, Keith; Foley, Mary J.; Sweeney, Brian; O'Sullivan, Sean S.; Barton, John; Tedesco, Salvatore; Sica, Marco; Crowe, Colum; Timmons, Suzanne; Interreg
Medication adjustments in Parkinson’s disease (PD) are driven by patient subjective report and clinicians’ rating of motor feature severity (such as bradykinesia and tremor). Objective: As patients may be seen by different clinicians at different visits, this study aims to determine the interrater reliability of upper limb motor function assessment among clinicians treating people with PD (PwPD). Methods: PwPD performed six standardised hand movements from the Movement Disorder Society’s Unified Parkinson’s Disease Rating Scale (MDS-UPDRS), while two cameras simultaneously recorded. Eight clinicians independently rated tremor and bradykinesia severity using a visual analogue scale. We compared intraclass correlation coefficient (ICC) before and after a training/calibration session where high-variance participant videos were reviewed and MDS-UPDRS instructions discussed. Results: In the first round, poor agreement was observed for most hand movements, with best agreement for resting tremor (ICC 0.66 bilaterally; right hand 95 % CI 0.50–0.82; left hand: 0.50–0.81). Postural tremor (left hand) had poor agreement (ICC 0.14; 95 % CI 0.04–0.33), as did wrist pronation-supination (right hand ICC 0.34; 95 % CI 0.19–0.56). In post-training rating exercises, agreements improved, especially for the right hand. Best agreement was observed for hand open-close ratings in the left hand (ICC 0.82, 95 % CI 0.64–0.94) and resting tremor in the right hand (ICC 0.92, 95 % CI 0.83–0.98). Discrimination between right and left hand features by raters also improved, except in resting tremor (disimprovement) and wrist pronation-supination (no change). Conclusions: Clinicians vary in rating video-recorded PD upper limb motor features, especially bradykinesia, but this can be improved somewhat with training
Wearable-enabled algorithms for the estimation of parkinson’s symptoms evaluated in a continuous home monitoring setting using inertial sensors
(Institute of Electrical and Electronics Engineers (IEEE), 2024) Crowe, Colum; Sica, Marco; Kenny, Lorna; O'Flynn, Brendan; Scott Mueller, David; Timmons, Suzanne; Barton, John; Tedesco, Salvatore; Enterprise Ireland; AbbVie; Science Foundation Ireland; European Regional Development Fund
Motor symptoms such as tremor and bradykinesia can develop concurrently in Parkinson’s disease; thus, the ideal home monitoring system should be capable of tracking symptoms continuously despite background noise from daily activities. The goal of this study is to demonstrate the feasibility of detecting symptom episodes in a free-living scenario, providing a higher level of interpretability to aid AI-powered decision-making. Machine learning models trained on wearable sensor data from scripted activities performed by participants in the lab and clinician ratings of the video recordings of these tasks identified tremor, bradykinesia, and dyskinesia in the supervised lab environment with a balanced accuracy of 83%, 75%, and 81%, respectively, when compared to the clinician ratings. The performance of the same models when evaluated on data from subjects performing unscripted activities unsupervised in their own homes achieved a balanced accuracy of 63%, 63%, and 67%, respectively, in comparison to self-assessment patient diaries, further highlighting their limitations. The ankle-worn sensor was found to be advantageous for the detection of dyskinesias but did not show an added benefit for tremor and bradykinesia detection here.
Treatment effect analysis of the Frailty Care Bundle (FCB) in a cohort of patients in acute care settings
(Springer, 2024) Crowe, Colum; Naughton, Corina; de Foubert, Marguerite; Cummins, Helen; McCullagh, Ruth; Skelton, Dawn A.; Dahly, Darren L.; Palmer, Brendan A.; O'Flynn, Brendan; Tedesco, Salvatore; Health Research Board; South South-West Hospital; Science Foundation Ireland
Purpose: The aim of this study is to explore the feasibility of using machine learning approaches to objectively differentiate the mobilization patterns, measured via accelerometer sensors, of patients pre- and post-intervention. Methods: The intervention tested the implementation of a Frailty Care Bundle to improve mobilization, nutrition and cognition in older orthopedic patients. The study recruited 120 participants, a sub-group analysis was undertaken on 113 patients with accelerometer data (57 pre-intervention and 56 post-intervention), the median age was 78 years and the majority were female. Physical activity data from an ankle-worn accelerometer (StepWatch 4) was collected for each patient during their hospital stay. These data contained daily aggregated gait variables. Data preprocessing included the standardization of step counts and feature computation. Subsequently, a binary classification model was trained. A systematic hyperparameter optimization approach was applied, and feature selection was performed. Two classifier models, logistic regression and Random Forest, were investigated and Shapley values were used to explain model predictions. Results: The Random Forest classifier demonstrated an average balanced accuracy of 82.3% (± 1.7%) during training and 74.7% (± 8.2%) for the test set. In comparison, the logistic regression classifier achieved a training accuracy of 79.7% (± 1.9%) and a test accuracy of 77.6% (± 5.5%). The logistic regression model demonstrated less overfitting compared to the Random Forest model and better performance on the hold-out test set. Stride length was consistently chosen as a key feature in all iterations for both models, along with features related to stride velocity, gait speed, and Lyapunov exponent, indicating their significance in the classification. Conclusion: The best performing classifier was able to distinguish between patients pre- and post-intervention with greater than 75% accuracy. The intervention showed a correlation with higher gait speed and reduced stride length. However, the question of whether these alterations are part of an adaptive process that leads to improved outcomes over time remains.
Development of a personalized anomaly detection model to detect motion artifacts over ppg data using catch22 features
(Institute of Electrical and Electronics Engineers (IEEE), 2024) Valerio, Andrea; Demarchi, Danilo; O'Flynn, Brendan; Tedesco, Salvatore; Science Foundation Ireland
As remote health monitoring grows, it's crucial to distinguish high-quality biomedical signals from low-quality ones. Identifying and mitigating motion artifacts (MAs) is essential for accurate data from wearable devices. Methods: In this work, a high-performing subset of time-series features denoted as catch22 (22 CAnonical Time-series CHaracteristics) was used to detect the presence of MAs in photoplethysmogram (PPG) data acquired from the brachial and digital artery of 31 healthy subjects. Three unsupervised algorithms were employed along with catch22 to detect MAs within the dataset, these were: One-Class Support Vector Machine, Isolation Forest, and Local Outlier Factor. Results: Aggregated precision, recall, and F1-score were computed per each method to assess the detection performances according to a variety of features and anomalies' distribution. These metrics resulted respectively equal to 0.5, 0.64, and 0.55 for OC- SVM, 0.91, 0.94, and 0.92 for IF, and 0.74, 0.75, and 0.74 for LOF. Conclusion: Experimental findings illustrate that by employing the catch22 feature subset, it is viable to discern the presence of MAs in beat-to-beat pulse waveforms without recurring to prior knowledge or data-driven PPG features.

Browse

Recent Submissions