Browsing by Author "Duffett-Leger, Linda"
Now showing 1 - 8 of 8
Results Per Page
Sort Options
- ItemOpen AccessAn AI-Based Human-Centered Approach to Support Multidisciplinary Requirements Engineering(2023-01-30) Salmani, Ali; Moshirpour, Mohammad; Duffett-Leger, Linda; Far, Behrouz; Deshpande, GouriMultidisciplinary teams are often a necessity for software projects as they provide the required expertise to effectively solve complex problems. However, efficient collaboration between teams with different disciplines is challenging due to several factors including gaps of knowledge areas, establishing a process, and different requirements from various groups of stakeholders. Agile methodologies such as scrum provide a powerful approach to effectively manage software projects through tools and approaches to properly address change which is often more common in multidisciplinary teams. In this study, we will leverage process evaluation tools and techniques to analyze the efficiency of our software development process. We have evaluated this approach based on the project data recorded in Jira and GitHub. This approach is applied to a case study of a virtual healthcare intervention system to measure the team's productivity. Several deficiencies have been identified and discussed based on the results. We conclude that the enumerated deficiencies are related to the requirements engineering (RE) process. To improve the RE process, a set of solutions have been analyzed to determine their feasibility. Automating the requirements engineering process can be an efficient approach to address the aforementioned issues. The main objectives of this thesis is to devise an automated approach to 1) identify the system requirements including the new features and bugs from the users' speech and break them down into tasks, 2) find similar Jira tickets that are already implemented, and 3) estimate the amount of effort needed for the new task. By providing smart and automated support for requirements analysis and elicitation, this solution seamlessly integrates with scrum and is expected to considerably improve the efficiency of the software development process for the virtual intervention system that is used as the case study of this thesis. As part of this thesis, we aim to implement a model to determine whether tasks are similar and a model to estimate the effort required to complete each new task, which is the second and third objectives. For finding the similarities between tasks that relate to objectives 2 and 3 of the thesis, S-BERT, one of the most powerful transformer-based machine learning techniques, was utilized and trained with a dataset that was collected, pre-processed, and normalized. For estimating the required effort of the tasks, we have used an approach that converts original commit instances into a high-dimensional feature space using Kernel-based Principal Component Analysis (KPCA) along with Adversarial Learning (AL). Based on the results, the trained model has improved its ability for topic segmentation and finding similarities between requirements. As well, our model has an accuracy of 86\% when it comes to estimating the required effort.
- ItemOpen AccessAn AI-based Framework For Parent-child Interaction Analysis(2023-07) Nikbakhtbideh, Behnam; Moshirpour, Mohammad; Duffett-Leger, Linda; Far, Behrouz; Drew, SteveThe quality of parent-child interactions is foundational to children's social-emotional and cognitive development, as well as their lifelong mental health. The Parent-Child Interaction Teaching Scale (PCITS) is a well-established and effective tool used to measure parent-child interaction quality. It is utilized in both public health settings and basic and applied research studies to identify problem areas within parent-child interactions. However, like other observational measures of parent-child interaction quality, the PCITS can be time-consuming to administer and score, which limits its wider implementation. Therefore, the main objective of this research is to organize a framework for the recognition of behavioural symptoms of the child and parent during interventions. Based on the literature on interactive parent-child behaviour analysis, we categorized PCITS labels into three modalities: language, audio, and video. Some labels have dyadic actors, while others have a single actor (either the parent or child). In addition, within each modality, there are technical issues, considerations, and limitations in terms of artificial intelligence. Hence, we divided the problem into three modalities, proposed models for each modality, and a solution to combine them. Firstly, we proposed a model for recognizing action-related labels (video). These labels are interactive and involve two actors: the parent and the child. We conducted a feature extraction algorithm to produce semantic features passed through a feature selection algorithm to extract the most meaningful semantic features from the video. We chose this method due to its lower data requirement compared to other modalities. Also, because of using 2D video files, the proposed feature extraction and selection algorithms are to handle the occlusion and natural conditions like camera movement, Secondly, we proposed a model for recognizing language- and audio-related labels. These labels represent a single-actor role for the parent, as children are not yet capable of producing meaningful text in the intervention videos. To develop this model, we conducted research on a similar dataset to utilize transfer learning between two problems. Therefore, the second part of this research is associated with working on this text dataset. Third, we focused on multi-modal aspects of the work. We conducted experiments to determine how to integrate the prior work into our model. We also provided an ensemble model, which combined the modalities of language and audio based on the semantic and syntactic characteristics of the text. This ensemble model provides a baseline for developing further models with different aspects and modalities. Finally, we provided a roadmap to support more labels that were not covered in this research due to not reaching enough samples. Our proposed framework includes a labelling system that we developed in the primary stages of the research to gather labelled data. This system also plays a role to be integrated with AI modules to provide auto-recognition of the behavioural labels in parent-child interaction videos to the nurses.
- ItemEmbargoInterpretable Deep Learning Models for Wearable Data in Sleep and Stress Analysis: Bridging the Gap between Predictive Accuracy and Explainability in Personalized Health Monitoring(2024-01-26) Barati, Ronak; Moshirpour, Mohammad; Duffett-Leger, Linda; Moshirpour, Mohammad; Duffett-Leger, Linda; Barcomb, Ann; Sameet Deshpande, GouriThis study integrates wearable technology, machine learning, and personal health to analyze human sleep patterns and stress levels. It aims to understand the impact of daily activities and physiological metrics on individual well-being, utilizing a broad data set from various individuals. The research compiles three interrelated studies, offering a detailed view of personalized health monitoring and its potential for future applications. The first study utilizes LSTM networks, as well as RNN, complemented by Explainable AI, particularly LIME. This approach provides a deep dive into the rich, extensive data gathered from smartwatches, revealing how our daily routines—our steps, heart rates, stress, and physical activities—influence the sleep duration of our different levels of sleep Through this in-depth analysis, not only are we able to uncover the subtle but significant ways in which our lives influence our sleep, but the data allows us to develop tailored health interventions specific to everyone. The second study makes use of data from wearable devices to classify sleep levels using seven machine-learning models. Throughout this journey, stress plays a pivotal role in affecting sleep quality. The comparison of models with and without stress data suggests a compelling case for holistic health monitoring. An important finding of models that incorporate stress data is that psychological factors play a significant role in understanding and improving sleep health. The implications of this insight have a significant supporting on the development of wearable technologies and health monitoring systems, advancing our understanding of sleep disorders and treating them. In our final study, smartwatch data from first responders and their families were analyzed over three years using machine learning classifiers like SVM, Logistic Regression, KNN, Decision Trees, Random Forests, Naive Bayes, and XGBoost. The comparison between datasets with and without sleep data showed that sleep inclusion significantly boosts stress prediction accuracy to 98%, underlining the relationship between sleep and stress. This research offers vital stress management insights, especially for first responders.
- ItemOpen AccessInvestigating the Design of an Immersive Smart Home System for Supporting Seniors Living with Neurocognitive Disorders(2022-09-16) Alabood, Lorans; Maurer, Frank; Neuhaus, Fabian; Levy, Richard; Duffett-Leger, LindaThe Internet of Things (IoT) technology allows for creating customized and accessible smart home systems for supporting aging in place. These systems are called Supportive Smart Home Systems (SSHS). Nonetheless, this approach comes with two main challenges. Firstly, customizing and interacting with IoT devices requires a certain level of technology literacy which many Seniors with Neurocognitive Disorders (SwNCDs) and caregivers may not have. Secondly, relying solely on smartphone applications is impractical for homecare purposes. Head-mounted Mixed Reality (MR) devices blend the physical and digital worlds to unlock natural and intuitive holographic interactions. This model makes designing tailored and seamless user experiences for SwNCDs more feasible. In addition, integrating a wearable MR device into an SSHS provides instant and effortless user interactions. However, considering MR is an emerging field of study, there is a major lack of design recommendations, especially for SwNCDs users. In this thesis, we applied a comprehensive User-Centered Design approach to introduce an immersive supportive smart home system for SwNCDs. During the investigation phase, we conducted a systematic literature review study to provide a taxonomy of the SSHS literature. Thereafter, we investigated the special requirements of SwNCDs by conducting a requirements elicitation study. Based on findings from these two studies, we introduced an initial system design. We leveraged video prototypes demonstrating all possible user-system interactions of the initial prototype to run an online Design Critique evaluation with 24 participants across Canada and the USA. After running all Design Critique sessions, a course of Thematic Analysis was conducted on the qualitative data to extract design recommendations for immersive smart home systems. Finally, we used the newly extracted design recommendations to reiterate our initial system design to produce a high-fidelity prototype and implemented it on a HoloLens2 device. We conducted usability evaluations using the Cognitive Walkthrough and Heuristic Evaluation methods. The evaluations did not identify any major usability issues in the prototype. These findings indicates that our design and evaluation process has the potential to introduce highly usable smart home system concepts.
- ItemOpen AccessMovement Biomechanics and Personalized Exercise Interventions in Individuals with Hip Osteoarthritis(2016) Leigh, Ryan; Ferber, Reed; Dukelow, Sean; Culos-Reed, Nicole; Duffett-Leger, LindaHip osteoarthritis (OA) is a prevalent musculoskeletal disorder that results in increased patient morbidity and dysfunction. While exercise is a common therapeutic modality employed in the management of this disorder, effect sizes remain small. Given this finding, the overarching aim of this thesis was to better understand the 3-dimensioanl (3D) gait biomechanics of this clinical population and subsequently test novel exercise interventions to improve clinical outcomes in individuals with mild-to-moderate hip OA. Following the Introduction, Chapter 2 explored whether tester experience influenced the reliability with which 3D gait data can be collected. This study was important since 3D gait collections would be a major part of the final two chapters. Using a coefficient of multiple correlation (CMC) statistic to estimate within-tester reliability, we found that within-tester CMC values exceeded 0.90 for both novice and experienced testers across all kinematic variables. Chapter 3 summarized the current hip OA and exercise literature and determined whether land-based exercise is an effective intervention in hip OA subjects not awaiting surgery. Pooled data from 7 studies demonstrated exercise had no effect on pain or self-reported function immediately post intervention and the overall effect sizes remained small. Chapter 4 characterized the 3D kinematic gait patterns of individuals with mild-to-moderate hip OA considering that to this point, the lower extremity kinematics of hip OA patients had not been fully described. We reported that hip OA subjects walked with greater peak hip abduction, reduced peak hip extension, and greater peak hip external rotation compared to age and body mass index (BMI) matched healthy controls. Whether these subtle biomechanical abnormalities could be used as treatment targets was explored in the capstone investigation. In Chapter 5, we targeted these 3D gait abnormalities with a novel tailored exercise intervention in mild-to-moderate hip OA subjects. This exercise protocol was compared to a tailored intervention that was based on a standard clinical assessment. No significant improvements in pain were found across either group at 8-weeks follow-up and a 3D gait derived exercise program did not result in improved clinical outcomes.
- ItemOpen AccessParental Technology Use and its Implications for Parent-Child Interactions and Children’s Health and Development(2023-06) Komanchuk, Jelena; Letourneau, Nicole; Cameron, Judy L.; Duffett-Leger, Linda; King-Shier, KathrynAdverse experiences (e.g., poverty, family violence, neglect in childhood) can lead to negative health and developmental consequences, yet impacts may be buffered by positive parent-child interactions. While families experiencing adversity (e.g., poverty) report barriers to attending in-person parenting programs, online parenting programs have potential to improve children’s health and development by increasing accessibility. In contrast, parental technoference (i.e., parental technology use that interrupts interactions with one’s child) can negatively affect parent-child relationships and children’s outcomes (e.g., behavior, mental health). Research is needed on digitally delivered parenting programs for families experiencing adversity and on the implications of parental technoference on parent-child relationships and children’s outcomes. The first manuscript in this dissertation is a realist review of research and theory on serve and return interactions (a metaphor utilized to convey the importance of sensitive and responsive caregiving) and a synthesis of research examining its impacts on children’s health (e.g., mental, physical) and development. The second manuscript presents findings from a randomized controlled trial evaluation of the First Pathways program with families experiencing adversity in Alberta. The First Pathways program is an online tool designed to improve parent-child interactions and children’s development by sharing brain development knowledge and activities for parents and children. Compared to the quartile of parent-child dyads who seldom accessed the website (n = 12), the quartile of parent-child dyads who accessed the website the most (n = 13) demonstrated significantly greater improvements in parent-child interaction quality. Further, daily reminders significantly increased website access. High retention (99%) was observed in the First Pathways study; thus, the third manuscript describes the effective recruitment and retention strategies employed. In the fourth manuscript, a realist review of literature on the psychometrics of digitally delivered child development tools is presented. The last manuscript is a scoping review on parental technoference and its effects on parent-child relationships, children’s health, and development. This dissertation concludes with a discussion of the positive and negative implications of parental technology use on children’s health and development and recommendations for nursing research, education, and practice.
- ItemOpen AccessThe role of education on Cancer amenable mortality among non-Hispanic blacks & non-Hispanic whites in the United States (1989–2018)(2021-09-07) Barcelo, Alberto; Duffett-Leger, Linda; Pastor-Valero, Maria; Pereira, Juliana; Colugnati, Fernando A. B.; Trapido, EdwardAbstract Background Cancer mortality in the U.S. has fallen in recent decades; however, individuals with lower levels of education experienced a smaller decline than more highly educated individuals. This analysis aimed to measure the influence of education lower than a high school diploma, on cancer amenable mortality among Non-Hispanic Whites (NHW) and Non-Hispanic Blacks (NHB) in the U.S. from 1989 to 2018. Methods We analyzed data from 8.2 million death certificates of men and women who died from cancer between 1989 and 2018. We examined 5-year and calendar period intervals, as well as annual percent changes (APC). APC was adjusted for each combination of sex, educational level, and race categories (8 models) to separate the general trend from the effects of age. Results Our study demonstrated an increasing mortality gap between the least and the most educated NHW and NHB males and females who died from all cancers combined and for most other cancer types included in this study. The gap between the least and the most educated was broader among NHW males and females than among NHB males and females, respectively, for most malignancies. Conclusions In summary, we reported an increasing gap in the age-adjusted cancer mortality among the most and the least educated NHW and NHB between 25 and 74 years of age. We demonstrated that although NHB exhibited the greatest age-adjusted mortality rates for most cancer locations, the gap between the most and the least educated was shown for NHW.
- ItemOpen AccessThe Use of Real-Time Feedback to Improve Kinematic Marker Placement Consistency Among Novice Examiners(2017) Macaulay, Charles Andrew John; Ferber, Reed; Jacob, Christian; Edwards, Brent; Duffett-Leger, LindaMarker placement deviation contributes the largest amount of error in gait kinematic data. The study purpose was to determine whether a novel, real-time marker-placement tool could improve consistency of gait kinematic data. Twelve novice examiners placed retroreflective markers on a single runner. For each examiner, a running trial was analyzed using two static trials: (1) PRE and (2) POST implementation of the feedback tool. The protocol was repeated a second time, one week later, resulting in PRE1, POST1, PRE2, and POST2 conditions. The 95% confidence interval (CI) of the mean joint angles for the entire stride, was compared between the PRE1/POST1, and PRE2/POST2 conditions. POST1 feedback trials showed a reduced 95%CI range for eight of nine joint angles compared to PRE1. POST2 trials reduced the 95%CI for five of nine joint angles compared to PRE2. The results indicate a real-time feedback tool improves kinematic marker placement consistency for novice examiners.