Profile
Keywords: software engineering, software architecture, internet of things, mobile computing, service oriented architecture, smart buildings, smart cities, digital health
Dr. Eleni Stroulia is a Professor in the Department of Computing Science, at the University of Alberta. From 2011-2016, she held the NSERC/AITF Industrial Research Chair on Service Systems Management, with IBM. Her research focuses on addressing industry-driven problems and interdisciplinary challenges, using AI and machine-learning methods. She has played leadership roles in the GRAND and AGE-WELL Networks of Centres of Excellence. In 2018 she received a McCalla professorship, and in 2019 she was recognized with a Killam Award for Excellence in Mentoring. She has supervised more than 60 graduate students and PDFs, who have gone forward to stellar academic and industrial careers. From 2020 to 2023, she was the Director of the University of Alberta's AI4Society Signature Area, and since 2021 she is serving as the Vice Dean of the Faculty of Science. She is currently leading a CFI-funded project that will transform the UCommons building into a smart living lab .
Outputs Show only Author
Title
Category
Date
Authors
Projects
SociQL: A Query Language for the SocialWeb University of Alberta Publication 2013-01-01 Detecting Cognitive Ability Changes in Patients With Moderate Dementia Using a Modified 'Whack-a-Mole' Game B. Wallace, F. Knoefel, R. Goubran, P. Masson, A. Baker, V. Guana, E. Stroulia, “Detecting Cognitive Ability Changes in Patients With Moderate Dementia Using a Modified 'Whack-a-Mole' Game”, IEEE Transactions on Instrumentation and Measurement, vol. 67, no. 7, pp. 1521-1534, Jul. 2018. University of Alberta Publication 2018-07-01 Bruce Wallace, Frank Knoefel, Rafik Goubran, Amanda Baker, Victor Guana,
Stroulia, E. Detecting Cognitive Ability Changes in Patients with Moderate Dementia Using a Modified "Whack-a-Mole B. Wallace, F. Knoefel, R. Goubran, P. Masson, A. Baker, V. Guana, E. Stroulia, “Detecting Cognitive Ability Changes in Patients With Moderate Dementia Using a Modified 'Whack-a-Mole' Game”, IEEE Transactions on Instrumentation and Measurement, vol. 67, no. 7, pp. 1521-1534, Jul. 2018 This paper presents results from a 1-year study of 12 patients with moderate dementia in an adult-day program who played a novel whack-a-mole game-based measurement instrument for cognitive behavior and performance. The ongoing measurement of cognition and changes associated with dementia is a challenge for healthcare providers. Measurement methods based on a tablet-based instrument are proposed. Partnership with the adult day program greatly eased recruitment: all but 1 eligible participant joined our study, compared to 1 in 5, or lower, for previous studies with similar populations. There are three unique aspects to the design of our game: first, it has two distinct targets requiring different actions, which increases the cognitive processing for the users; second, each level is systematically more difficult; third, it records and analyzes player performance. The results show that the patients’ game performance improves over the first few weeks; this indicates that they are learning the game and retaining ability gains from week to week, suggesting some procedural learning is still intact. Over the year, 4 participants showed cognitive decline, 4 were stable and 3 improved based on their MMSE score. Two measures are proposed based on level progression within the sessions and mole-hit performance. The level-progression measure identifies declining participants with 1FN and 1FP error. The mole-hit performance measure identifies declining participants with 1FN error. These results demonstrate the potential for the proposed instrument to provide an ongoing measurement as an alternative for the repeated application of the MMSE. University of Alberta Publication 2018-07-01 Frank Knoefel, Rafik Goubran, Philippe Masson, Brianna Allard, Amanda Baker, Bruce Wallace, Victor Guana,
Stroulia, E. Detecting Cognitive Ability Changes in Patients With Moderate Dementia Using a Modified “Whack-a-Mole” Game Wallace, Bruce; Knoefel, Frank; Goubran, Rafik; Masson, Philippe; Baker, Amanda; Allard, Brianna; Guana Garces, Victor; Stroulia, Eleni (2017 Oct).Detecting Cognitive Ability Changes in Patients With Moderate Dementia Using a Modified “Whack-a-Mole” Game. IEEE TRANSACTIONS ONINSTRUMENTATION AND MEASUREMENT, 67(7):1521–1534. Institute of Electrical and Electronics Engineers (IEEE) University of Alberta Publication 2017-10-01 Bruce Wallace, Frank Knoefel, Rafik Goubran, Philippe Masson, Amanda Baker, Brianna Allard, Victor Guana,
Stroulia, E. VirtualGym: An Exergames Platform for Seniors University of Alberta Publication 2018-08-01 Victor Fernandez, Noelannah Neubauer, Benjamin Hunter,
Stroulia, E. , Lili Liu
VirtualGym : A kinect-based system for seniors exercising at home University of Alberta Publication 2018-08-01 Victor Fernandez-Cervantes, Noelannah Neubauer, Benjamin Hunter,
Stroulia, E. , Lili Liu
Recognizing Emotional States With Wearables While Playing a Serious Game Dillam Jossue Diaz Romero, Adriana Maria Rios Rincon, Antonio Miguel Cruz, Nicholas Yee, Eleni Stroulia: Recognizing Emotional States With Wearables While Playing a Serious Game. IEEE Trans. Instrum. Meas. 70: 1-12 (2021) University of Alberta Publication 2021-02-01 Dillam Romero, Adriana Rios-Rincon, Antonio Miguel-Cruz, Nicholas Yee,
Stroulia, E. Learning Language and Acoustic Models for Identifying Alzheimer’s Dementia From Speech Zehra Shah, Jeffrey Sawalha, Mashrura Tasnim, Shiang Qi, Eleni Stroulia, Russell Greiner: Learning Language and Acoustic Models for Identifying Alzheimer's Dementia From Speech. Frontiers Comput. Sci. 3: 624659 (2021) University of Alberta Publication 2021-02-01 Predicting engagement in older adults with and without dementia while playing mobile games University of Alberta Publication 2021-08-01 Antonio Miguel-Cruz, Adriana Rios-Rincon, Christine Daum, Daniel A Quiroga-Torrez, Ruby Dejesus, Lili Liu,
Stroulia, E. Implementation and evaluation of a pain assessment app and novel community platform for long-term care health professionals. Scientific publication in press in Aging & Mental Health University of Alberta Publication 2022-12-01 Vivian Tran, Emily Winters,
Stroulia, E. , Thomas Hadjistavropoulos
Behavioural pain assessment implementation using a tablet app: A case series and quasi experimental design University of Alberta Publication 2020-02-01 N Zahid, Natasha L Gallant, Thomas Hadjistavropoulos,
Stroulia, E. Behavioral Pain Assessment Implementation in Long-Term Care Using a Tablet App: Case Series and Quasi-Experimental Design University of Alberta Publication 2020-04-01 M Zahid, Natasha L Gallant, Thomas Hadjistavropoulos,
Stroulia, E. Effect of a serious mobile-game intervention on older adults’ engagement, affect, and cognitive function Submission of the manuscript to Physical & Occupational Therapy In Geriatrics University of Alberta Publication 2021-01-01 Adriana Rios-Rincon, Christine Daum, Antonio Miguel-Cruz, Lili Liu,
Stroulia, E. Feasibility and acceptability of a serious mobile-game intervention for older adults A Journal article- Feasibility and acceptability of a serious mobile-game intervention for older adults was submitted to the journal Physical & Occupational Therapy In Geriatrics in Oct 19, 2021 and it is currently under review. University of Alberta Publication 2021-10-01 Adriana Rios-Rincon, Christine Daum, Antonio Miguel-Cruz, Lili Liu,
Stroulia, E. PhyDSLK: a model-driven framework for generating exergames. Maria Teresa Baldassarre, Danilo Caivano, Simone Romano, Francesco Cagnetta, Víctor Fernández-Cervantes, Eleni Stroulia: PhyDSLK: a model-driven framework for generating exergames. Multim. Tools Appl. 80(18): 27947-27971 (2021) University of Alberta Publication 2021-05-01 Maria T Baldassarre, Danilo Caivano, Simone Romano, Francesco Cagnetta, Victor Fernandez-Cervantes,
Stroulia, E. Intersectionality in Developing a Virtual Community of Practice Platform on Abortion Abortion is an essential healthcare service in many countries including Canada. The number of people who seek abortion is disproportionately higher among equity-deserving populations. Yet the knowledge needed to provide evidence-based, culturally safe, and gender-affirming abortion services remain limited among healthcare professionals. Using an intersectional lens, we conducted focus group discussions with 14 healthcare professionals to understand how an abortion web-based platform, which is currently under development, can be adapted to meet the needs of equity deserving populations. The findings revealed the need for multi-lingual resources on abortion, information on funding coverage for undocumented migrants, educational resources on Indigenous cultural safety and gender-affirming practices, and a mapping tool to locate providers or pharmacists. Beyond presenting clinical guidelines on web platforms, this study revealed important considerations for the design of web platforms that can help advance access to abortion for equity-deserving populations. University of British Columbia, University of Alberta Publication 2024-07-24 A Health Professional Mentorship Platform to Improve Equitable Access to Abortion: Development, Usability, and Content Evaluation Access to safe abortion care is a reproductive right for all individuals across Canada. Underserved populations are overrepresented among those with unintended pregnancies and particularly those seeking abortion. Yet, few resources exist to help health care and allied helping professionals provide culturally competent and gender-affirming abortion care to such a population group. This project aimed to redesign and adapt an existing subscription-based medication abortion mentorship platform into a culturally appropriate and gender-affirming open-access website of curated health professional resources to promote equitable, accessible, high-quality abortion care, particularly for underserved populations. We drew on a user-centered design framework to redesign the web platform in 5 iterative phases. Health care and allied helping professionals were engaged in each stage of the development process including the initial design of the platform, curation of the resources, review of the content, and evaluation of the wireframes and the end product. This project resulted in an open-access bilingual (English and French) web-based platform containing comprehensive information and resources on abortion care for health care providers (physicians, nurse practitioners, and pharmacists) and allied helping professionals (midwives, medical officers, community workers, and social workers). The website incorporated information on clinical, logistical, and administrative guidance, including culturally competent and gender-affirming toolkits that could equip health care professionals with the requisite knowledge to provide abortion care for underserved populations. This platform contains resources that can increase the competencies of health care professionals to initiate and sustain culturally and contextually appropriate abortion care for underserved groups while clarifying myths and misconceptions that often militate against initiating abortion. Our resource also has the potential to support equitable access to high-quality abortion care, particularly for those among underserved populations who may have the greatest unmet need for abortion services yet face the greatest barriers to accessing care. University of British Columbia, University of Alberta Publication 2024-06-19 A software pipeline for systematizing machine learning of speech data The reproducibility and replicability of experimental findings is an essential element of the scientific process. The machine-learning community has a long-established practice of sharing data sets so that researchers can report the performance of their models on the same data. In the area of speech analysis, and more specifically speech of individuals with mental health and neurocognitive conditions, a number of such data sets exist and are the subject of organized "challenge tasks". However, as the complexity of the available relevant software libraries and their parameters increases, we argue that researchers should not only share their data but also their preprocessing and machine learning configurations so that their experiments may be fully reproduced. This is why we have designed and developed a suite of configurable software pipelines with Python Luigi for speech-data preprocessing, feature extraction, fold construction for cross-validation, machine learning training, and label prediction. These components rely on state-of-the-art software libraries, frequently used by researchers, and implement many typical tasks in this field, i.e., scikit-learn, openSMILE, LogMMSE, so that, given the configuration parameters of each task, any underlying experiments can be readily reproduced. We have evaluated our platform by replicating three different machine learning studies, with the aim of detecting depression, mild cognitive impairment, and aphasia from speech data. University of Alberta Publication 2025-07-29 Jimuel Celeste, Mashrura Tasnim, Amable J Valdés Cuervo, Enrique de la Cal,
Stroulia, E. Correction: Using Wearable Devices and Speech Data for Personalized Machine Learning in Early Detection of Mental Disorders: Protocol for a Participatory Research Study University of Alberta Publication 2025-07-28 Ramon E Diaz-Ramos, Isabella Noriega, Luis A Trejo,
Stroulia, E. , Bo Cao
Correction: Using Wearable Devices and Speech Data for Personalized Machine Learning in Early Detection of Mental Disorders: Protocol for a Participatory Research Study (Preprint) University of Alberta Publication 2025-05-29 Ramon E Diaz-Ramos, Isabella Noriega, Luis A Trejo,
Stroulia, E. , Bo Cao
Simulation as a decision-support tool in construction project management: Simphony-Dynamic-as-a-Service University of Alberta Publication 2025-05-01 Muhtasim Fuad Rafid, Stephen Hague, Simaan AbouRizk,
Stroulia, E. Machine Learning Analysis of Engagement Behaviors in Older Adults With Dementia Playing Mobile Games: Exploratory Study Abstract Background The prevalence of dementia is expected to rise with an aging population, necessitating accessible early detection methods. Serious games have emerged as potential cognitive screening tools. They provide not only an engaging platform for assessing cognitive function but also serve as valuable indicators of cognitive health through engagement levels observed during play. Objective This study aims to examine the differences in engagement-related behaviors between older adults with and without dementia during serious gaming sessions. Further, it seeks to identify the key contributors that enhance the effectiveness of machine learning for dementia classification based on engagement-related behaviors. Methods This was an exploratory proof-of-concept study. Over 8 weeks, 20 older adults, 6 of whom were living with dementia, were enrolled in a single-case design study. Participants played 1 of 4 “Vibrant Minds” serious games (Bejeweled, Whack-A-Mole, Mah-jong, and Word-Search) over 8 weeks (16 30-min sessions). Throughout the study, sessions were recorded to analyze engagement-related behaviors. This paper reports on the analysis of the engagement-related behaviors of 15 participants. The videos of these 15 participants (10 cognitively intact, 5 with dementia) were analyzed by 2 independent raters, individually annotating engagement-related behaviors at 15-second intervals using a coding system. This analysis resulted in 1774 data points categorized into 47 behavior codes, augmented by 54 additional features including personal characteristics, technical issues, and environmental factors. Each engagement-related behavior was compared between older adults living with dementia and older adults without dementia using the χ ² test with a 2×2 contingency table with a significance level of .05. Codes underwent one-hot encoding and were processed using random forest classifiers to distinguish between participant groups. Results Significant differences in 64% of engagement-related behaviors were found between groups, notably in torso movements, voice modulation, facial expressions, and concentration. Including engagement-related behaviors, environmental disturbances, technical issues, and personal characteristics resulted in the best model for classifying cases of dementia correctly, achieving an F 1 -score of 0.91 (95% CI 0.851‐0.963) and an area under the receiver operating curve of 0.99 (95% CI 0.984‐1.000). Conclusions Key features distinguishing between older adults with and without dementia during serious gameplay included torso, voice, facial, and concentration behaviors, as well as age. The best performing machine learning model identified included features of engagement-related behavios, environmental disturbances, technical challenges, and personal attributes. Engagement-related behaviors observed during serious gaming offer crucial markers for identifying dementia. Machine learning models that incorporate these unique behavioral markers present a promising, noninvasive approach for early dementia screening in a variety of settings. University of Alberta Publication 2025-03-03 Melika Torabgar, Mathieu Figeys, Shaniff Esmail,
Stroulia, E. , Adriana Ríos Rincón
Learning Interior Design Rules from Synthetic Rule-Compliant Example Bim Layouts Digitization and standardization of building components and their information allow for automated building evaluation letting designers iterate and improve their designs. Specifying model-checking rules in machine-readable, however, is still a challenge for non-experts. While Domain Specific Languages (DSLs) can help, it would be desirable to automate the rule-generation process. This paper describes a novel method that learns rules from interior layout examples, leveraging a rule DSL. Based on expert design rules, we used an automated layout generation method to construct a dataset of highly compliant interior layouts. This dataset was used as input to our rule-learning algorithm that produced a set of newly learnt rules whose evaluation scores were compared with original expert rules. Findings suggest that expert and learnt rules correlate highly when the learnt rules are produced based on high-quality layouts. University of Alberta Publication 2025-01-01 Between cultures and traditions: a qualitative investigation of sexual and reproductive health experiences of immigrant adolescents in Canada Immigrant adolescents in Canada face challenges accessing accurate sexual and reproductive health (SRH) information and services. Many challenges stem from taboos associated with SRH, cultural and religious restrictions, and social beliefs regarding the unnecessity of SRH education for adolescents. We explored the SRH experiences of immigrant adolescents in the context of their cultural and religious perspectives. We engaged adolescents as collaborators and active participants in the research process. With the support of an Adolescent Advisory Group (AAG) and community partners, we conducted qualitative interviews with immigrant adolescents in Edmonton, Toronto, and Vancouver (n = 58). Through thematic analysis, we identified three broad themes: (1) 'What's really happening?' Experiencing body changes from puberty to adulthood; (2) 'It's something that's shameful': Encountering myths, misperceptions, and norms about SRH; and (3) 'I'll be there for you': Navigating family and digital resources for support. Our findings highlight the specific SRH challenges faced by immigrant adolescents in Canada, such as differences between cultural values, and communication barriers within families. Dealing with SRH matters is dependent on education, family readiness, and personal values attached to these topics. Programmes must focus on engaging cultural and religious preferences and tailoring interventions to adolescents' needs. University of Alberta, Toronto Metropolitan University Publication 2024-12-08 Salima Meherali, Amyna Ismail Rehmani, Mariam Ahmad, Samar Kauser, Piper Scott Fiddler, Paula Pinzon-Hernandez, Zeba Khan, Sarah Flicker, Philomina Okeke‐Ihejirika, Bukola Salami,
Stroulia, E. , Ashley Vandermorris,
Wong, J. , Wendy V Norman, Shannon D Scott, Sarah Munro
Augmented Reality Indoor-Outdoor Navigation Through a Campus Digital Twin University of Alberta Publication 2024-11-11 Virtual-GymVR: A Virtual Reality Platform for Personalized Exergames University of Alberta Publication 2024-07-17 User-Centered Design of a Health Professional Mentorship Platform to Improve Equitable Access to Abortion (Preprint) BACKGROUND Access to safe abortion care is a reproductive right for all individuals across Canada. Underserved populations are over-represented among those with unintended pregnancies and particularly those seeking abortion. Yet, few resources exist to help healthcare and allied helping professionals provide culturally competent, and gender-affirming abortion care for underserved populations. OBJECTIVE This project aimed to redesign and adapt an existing subscription-based medication abortion mentorship platform into a culturally appropriate and gender-affirming open-access website of curated health professional resources to promote equitable, accessible, high-quality abortion care, particularly for underserved populations METHODS We drew on a user-centered design framework to redesign the web platform in five iterative phases. Healthcare and allied helping professionals were engaged in each stage of the development process including the initial design of the platform, curation of the resources, reviewing the content, and evaluation of the wireframes and the end product. RESULTS This project resulted in an open-access bilingual (English and French) online platform containing comprehensive information and resources on abortion care for healthcare providers (physicians, nurse practitioners, and pharmacists) and allied helping professionals (midwives, medical officers, community workers, and social workers). The website incorporated information on clinical, logistical, and administrative guidance, including culturally competent and gender-affirming toolkits that could equip healthcare professionals with the requisite knowledge to provide abortion care for underserved populations. CONCLUSIONS This platform contains resources that can increase the competencies of healthcare professionals to initiate and sustain culturally and contextually appropriate abortion care for underserved groups while clarifying myths and misconceptions that often militate against initiating abortion. Our resource also has the potential to support equitable access to high-quality abortion care, particularly for those among underserved populations who may have the greatest unmet need for abortion services yet face the greatest barriers to access to care University of AlbertaPublication 2024-06-19 Fatawu Abdulai, Cam Duong,
Stroulia, E. , Efrat Czerniak, Rachel Chiu, Aashay Mehta, K. Koike, Wendy V Norman
Patterns of multi-container composition for service orchestration with Docker Compose University of Alberta Publication 2024-05-01 A Machine-Learning Model for Detecting Depression, Anxiety, and Stress from Speech Predicting mental health conditions from speech has been widely explored in recent years. Most studies rely on a single sample from each subject to detect indicators of a particular disorder. These studies ignore two important facts: certain mental disorders tend to co-exist, and their severity tends to vary over time. This work introduces a longitudinal dataset labeled with depression, anxiety, and stress scores using the DASS-21 self-report questionnaire, and describes a machine-learning pipeline to determine the severity of the three mental disorders using acoustic features extracted from speech samples of this dataset. Our initial findings suggest that healthy participants adhere more to the study procedure than participants who exhibit indicators of depression, anxiety, and stress and demonstrate that a one-dimensional convolutional neural network, trained on VGG-19 features, predicts the severity of depression, anxiety, and stress with high accuracy. University of Alberta Publication 2024-03-18 Mashrura Tasnim, Ramon Diaz Ramos,
Stroulia, E. , Luis A Trejo
VR Rhythm Game Featuring Audience Participation This study presents a virtual reality (VR) game with a mechanic that enables audience participation. It has been previously shown that VR games offer better immersion, as well as improved enjoyment for the player. By introducing audience participation we aim to investigate the extent to which an audience becomes emotionally invested while observing and providing support to a VR game player. To achieve that, a preliminary experiment was conducted to measure the enjoyment of the player and the audiences, and to evaluate social interaction among the audience members. The results show the potential of the audience participation mechanic in a VR game for the enjoyment of the player and the audiences. In addition, the results show that the proposed mechanic effectively promotes the social interactivity among the audience members. University of Alberta Publication 2023-11-19 Van Khôi Lê, Adrien Villars, Febri Abdullah, Mustafa Can Gursesli, Xiao You, S Román Lara E de los M, Ruck Thawonmas, Víctor Fernández-Cervantes,
Stroulia, E.
YouTube
