Laura Barnes's research while affiliated with University of Virginia and other places

Publications (37)

Article
Introduction: The current studies examined how smartphone-assessed contextual features (i.e., location, time-of-day, social situation, and affect) contribute to the relative likelihood of emotion regulation strategy endorsement in daily life. Methods: Emotion regulation strategy endorsement and concurrent contextual features were assessed either pa...
Article
During pandemics, effective interventions require monitoring the problem at different scales and understanding the various trade-offs between efficacy, privacy, and economic burden. To address these challenges, we propose a framework where we perform Bayesian change-point analysis on aggregate behavior markers extracted from mobile sensing data col...
Preprint
BACKGROUND Neuromuscular diseases, such as Spinal Muscular Atrophy (SMA) and Duchenne Muscular Dystrophy (DMD), may lead to loss of motor movements, respiratory failure, and early mortality in young children and adulthood. With novel treatments now available, new evaluation methods are needed to assess progress not currently captured with existing...
Preprint
This study evaluated the effectiveness of different recruitment messages for encouraging enrollment in a digital mental health intervention (DMHI) for anxiety among 1,600 anxious patients in a large healthcare system. Patients were randomly assigned to receive a standard message, or one of five messages designed to encourage enrollment: Three messa...
Conference Paper
Ubiquitous sensing from smartphones and wearable devices has proven to be useful for applications ranging from sports to modern medicine. The aim of this paper is to propose a visualization framework to illustrate the points in time when a query trajectory is deviating the most from a reference trajectory. Validation is performed through the use of...
Article
Full-text available
Clinical research involving participants with mild cognitive impairment (MCI) presents challenges to recruitment that may be further compounded by concerns when delivering a behavioral intervention via the Internet. The purpose of this talk is to describe recruitment adaptations for an Internet-delivered behavioral intervention study with older adu...
Article
Background: Insomnia is present in up to 50% of older adults with cognitive impairment. When insomnia is left untreated, pre-existing cognitive problems may be exacerbated and potentially contribute to further cognitive decline. One promising approach to improve cognitive health in individuals with cognitive impairment is to improve quantity and q...
Article
Technology-delivered interventions have the potential to help address the treatment gap in mental healthcare but are plagued by high attrition. Adding coaching, or minimal contact with a non-specialist provider, may encourage engagement and decrease dropout, while remaining scalable. Coaching has been studied in interventions for various mental hea...
Article
Background: Approximately 50%of older adults with cognitive impairment suffer from insomnia. When untreated, pre-existing cognitive problems may be exacerbated and potentially contribute to further cognitive decline. One promising approach to maintain cognitive health is to improve sleep quantity and quality. Objective: To determine feasibility,...
Chapter
American football is a leading sport for contact-related injuries such as cervical spine injuries, some of which result from an unforeseen hit. The use of a feedback mechanism to alert an athlete of a potential hit may mitigate the risk for sport-related concussion and catastrophic injury by allowing athletes to effectively brace for an otherwise u...
Preprint
Full-text available
Mobile Sensing Apps have been widely used as a practical approach to collect behavioral and health-related information from individuals and provide timely intervention to promote health and well-beings, such as mental health and chronic cares. As the objectives of mobile sensing could be either (a) personalized medicine for individuals or (b) publi...
Preprint
Full-text available
Mental health problems are highly prevalent and appear to be increasing in frequency and severity among the college student population. The upsurge in mobile and wearable wireless technologies capable of intense, longitudinal tracking of individuals, provide valuable opportunities to examine temporal patterns and dynamic interactions of key variabl...
Preprint
The burden of entry into mobile crowdsensing (MCS) is prohibitively high for human-subject researchers who lack a technical orientation. As a result, the benefits of MCS remain beyond the reach of research communities (e.g., psychologists) whose expertise in the study of human behavior might advance applications and understanding of MCS systems. Th...
Article
Full-text available
The present study assessed target engagement, preliminary efficacy, and feasibility as primary outcomes of a free multi-session online cognitive bias modification of interpretation (CBM-I) intervention for anxiety in a large community sample. High trait anxious participants (N = 807) were randomly assigned to a CBM-I condition: 1) Positive training...
Chapter
Activity recognition using built-in sensors in smart and wearable devices provides great opportunities to understand and detect human behavior in the wild and gives a more holistic view of individuals’ health and well being. Numerous computational methods have been applied to sensor streams to recognize different daily activities. However, most met...
Preprint
Full-text available
American football is a leading sport for contact-related injuries such as cervical spine injuries, some of which result from an unforeseen hit. The use of a feedback mechanism to alert an athlete of a potential hit may mitigate the risk for sport-related concussion and catastrophic injury by allowing athletes to effectively brace for an otherwise u...
Preprint
The present study assessed target engagement, preliminary efficacy, and feasibility as primary outcomes of a free multi-session online cognitive bias modification of interpretation (CBM-I) intervention for anxiety in a large community sample. High trait anxious participants (N = 807) were randomly assigned to a CBM-I condition: 1) Positive training...
Article
Full-text available
Internet-based interventions using technology can promote access to treatment and reduce participant burden for sleep disorders. However, preliminary studies examining technology use and compliance in older adults with mild cognitive impairment (MCI) are needed prior to undertaking large-scale interventions. Older adults with MCI were recruited fro...
Article
Full-text available
Chronic kidney disease (CKD) is a gradual loss of renal function over time, and it increases the risk of mortality, decreased quality of life, as well as serious complications. The prevalence of CKD has been increasing in the last couple of decades, which is partly due to the increased prevalence of diabetes and hypertension. To accurately detect C...
Article
Individuals with mild cognitive impairment (MCI) experience more sleep disturbances than individuals without MCI, and improving sleep in this at‐risk group may delay progression to Alzheimer’s disease. Internet‐based interventions may promote access to treatments for sleep disorders, such as insomnia. However, preliminary studies examining technolo...
Preprint
Full-text available
Chronic kidney disease (CKD) is a gradual loss of renal function over time, and it increases the risk of mortality, decreased quality of life, as well as serious complications. The prevalence of CKD has been increasing in the last couple of decades, which is partly due to the increased prevalence of diabetes and hypertension. To accurately detect C...
Preprint
Full-text available
Activity recognition using built-in sensors in smart and wearable devices provides great opportunities to understand and detect human behavior in the wild and gives a more holistic view of individuals' health and well being. Numerous computational methods have been applied to sensor streams to recognize different daily activities. However, most met...
Conference Paper
Full-text available
Activity recognition using built-in sensors in smart and wearable devices provides great opportunities to understand and detect human behavior in the wild and gives a more holistic view of individuals' health and well being. Numerous computational methods have been applied to sensor streams to recognize different daily activities. However, most met...
Preprint
Full-text available
Machine learning techniques applied to the Natural Language Processing (NLP) component of conversational agent development show promising results for improved accuracy and quality of feedback that a conversational agent can provide. The effort required to develop an educational scenario specific conversational agent is time consuming as it requires...
Preprint
A growing body of recent evidence has highlighted the limitations of natural language processing (NLP) datasets and classifiers. These include the presence of annotation artifacts in datasets, classifiers relying on shallow features like a single word (e.g., if a movie review has the word "romantic", the review tends to be positive), or unnecessary...
Preprint
Full-text available
Virtual coaching has rapidly evolved into a foundational component of modern clinical practice. At a time when healthcare professionals are in short supply and the demand for low-cost treatments is ever-increasing, virtual health coaches (VHCs) offer intervention-on-demand for those limited by finances or geographic access to care. More recently, A...
Preprint
Objectives: Poor emotion regulation (ER) has been implicated in many mental illnesses, including social anxiety disorder. To work towards a scalable, low-cost intervention for improving ER, we developed a novel contextual recommender algorithm for ER strategies. Design: N=114 socially anxious participants were prompted via a mobile app up to six ti...
Conference Paper
Full-text available
Over 35% of the world's population uses social media. Platforms like Facebook, Twitter, and Instagram have radically influenced the way individuals interact and communicate. These platforms facilitate both public and private communication with strangers and friends alike, providing rich insight into an individual's personality, health, and wellbein...
Article
Full-text available
The rise of pervasive and mobile technologies has led to the development of the "quantified self" (QS) movement as a social and cultural phenomenon. Fitness, sleep-tracking, and meditation apps are just a few examples of the rapidly-growing body of QS technology. A large body of literature has outlined methodological approaches to designing and imp...
Article
Full-text available
In recent years, there has been an exponential growth in the number of complex documents and texts that require a deeper understanding of machine learning methods to be able to accurately classify texts in many applications. Many machine learning approaches have achieved surpassing results in natural language processing. The success of these learni...
Conference Paper
This paper describes the development of a deep learning methodology for semantic utterance classification (SUC) for use in domain-specific dialogue systems. Semantic classifiers need to account for a variety of instances where the utterance for the semantic domain class varies. In order to capture the candidate relationships between the semantic cl...

Citations

... Psychophysiology refers to psychological states such as emotional responses (e.g., anger, frustration, and happiness), cognitive load, and distraction, which can be measured through changes in human physiological responses (e.g., HR, skin temperature, and skin conductance) (Lohani et al., 2019;Lee et al., 2020). In human-centered research, psychophysiological measures such as driver's HR (Sugie et al., 2016;Tavakoli et al., 2019Tavakoli et al., , 2021Alrefaie et al., 2019;Melnicuk et al., 2021), gaze patterns (Baee et al., 2019;Tavakoli et al., 2021a;Tavakoli et al., 2021b), skin conductance (Pakdamanian et al., 2020a;Pakdamanian et al., 2020b), and brain signals (Pakdamanian et al., 2020a;Pakdamanian et al., 2020b;Ergan et al., 2019) were all used for retrieving driver's stress level, cognitive load and behavioral metrics. ...
... After that, the system receiving antenna receives the carrier signals sent from the tags and then transmits them to the reader through the antenna regulator. Next, the reader demodulates and decodes the signals it receives and then transmits them to the Computational Intelligence and Neuroscience background main system for relevant processing [25]. Figure 4 presents its internal structure below. ...
... The DL techniques used in HAR can be divided into three parts such as deep neural networks (DNN), hybrid deep learning (HDL) models, and transfer learning (TL) based models . (Shown in Figure S.5 of Supporting document) The DNN includes the models like convolutional neural networks (CNN) (Deep and Zheng 2019;Liu et al. 2020;Zeng et al. 2014), recurrent neural networks (RNN) (Murad and Pyun 2017) and RNN variants which include long short-term memory (LSTM) and gated recurrent unit (GRU) (Zhu et al. 2019;Du et al. 2019;Fazli et al. 2021). In hybrid HAR models, the combination of CNN and RNN models is trained on spatio-temporal data. ...
... Participants completed the six-part CBT-I intervention over nine weeks with two-week pre-and post-assessments using self-report sleep diaries and wrist-worn actigraphs to obtain sleep measures over time. Participants with MCI demonstrated feasibility of Internet-delivered CBT-I and online sleep diary entry across baseline and postintervention assessment periods [65]. Details and outcomes will be presented in a forthcoming publication that provides merit to conduct a Phase 2 trial with a larger sample size. ...
... There are usually no public comments sections in academic journals, unlike the highly active and engaged Twitter or Facebook threads. Unfortunately, many of these SCI-COMM PERILS & PEARLS 5 threads will be dominated by trolls (as the focal articled noted), and even non-troll readers tend to be harsher in online public criticisms (Kruse et al., 2017;Mendu et al., 2020). I had a particularly difficult experience where I published a public piece in a widely read business magazine criticizing the use of popular personality tests (e.g., Myers-Briggs, use of traditional Likert-type scales, lack of consideration for within-person personality variance). ...
... Du et al. [13] proposed a representation learning method for dynamic multivariate time series data, which can jointly learn the long-term temporal dependencies pattern and non-linear correlation features of multivariate temporal data. A novel framework to learn sparse longitudinal representations of patient's medical records was presented in [39]. The proposed model achieved higher predictive performance and the learned representation is interpreted and visualized to bring clinical insights. ...
... However, such hierarchical classification methods have the disadvantage of increasing the number of models when dealing with a large number of classification classes or classes with complex hierarchical relationships. Especially, in some hierarchical classification methods with DL [5,6], the increase in the number of models leads to a significant increase in computational costs. On the other hand, in computer vision, Zhu et al. [7] proposed the branch CNN (B-CNN), which incorporates the hierarchical relationship among classes into the CNN model structure. ...
... Wearers can use various mood tracking applications, such as MyTherapy, Breathe2Relax, MoodKit, MoodTracker or Daylio as part of QS [125]. Studies [126,127] show that those who use QS applications feel more in control over their mood, which helps them control their mood and show more confidence, a positive attitude and a better outlook towards their emotional wellbeing. Users can understand their emotional cycles by using moodtracking applications. ...
... Another limitation of DL is that it usually requires a lot more data than traditional machine learning algorithms. Additionally, the large amount of data required for DL classification algorithms further increases the computational complexity during training phase (Kowsari et al. 2019). Whereas the proposed optimizers are easy to interpret, works well for small to large data, and selects optimal features from high-dimensional data in less time, which in turn speed up the classification process of traditional machine learning algorithms. ...
... One of the main ongoing challenges of chatbots is the natural interaction with the user, and their ability to understand what the user is saying. Therefore, several studies have focused more on the overall accuracy of the system, both related to the accuracy of the NLU components and understanding the user input [10,13,14,17,18], but also the dialogue management component that selects the correct responses to the users [18,21,25]. ...