Department of Computer Science

Permanent link for this collection

https://hdl.handle.net/20.500.14078/7

Browse

Now showing 1 - 20 of 65

Analysis of hockey forward line Corsi: should the focus be on forward pairs?
(2024) Brownlee, Samuel; Khan, Ayesha; Vanderzyl, Barnaby; El-Hajj, Mohamad
Professional ice hockey is a popular sport in North America, with multiple previous analyses providing insights into teams. Most research has been done on analyzing pairs of players on the same team that work well together. The focus of this study was to analyze if trios on a forward line perform well together, as there has not been enough research in this field. Our goal was to determine if the third player changes the performance of a duo and identify key factors that explain this change. We have analyzed more than 14 years worth of data. This data started with more than 100 dimensions; from those 100, 35 dimensions were chosen for analysis. To reach our conclusion, we used three methods: K-Means, Random Forest, and Support vector machines. Single variate random forest was used to analyze which variables affected the Corsi Percentage. The results from K-Mean clustering, combined with the results from Single Variate Random Forest, were used to see if the substitution of a third player on a line of three makes a difference in the overall performance of the line. The Support Vector Machine algorithm was used to reinforce the cluster numbers obtained from K-means clustering. Our study found that adding a third player will have a positive effect when the third player consistently plays with the other two players and the three players participate more effectively in defence. These findings could help teams plan how they form their player lines when they want to achieve good game results.
An analysis of rock climbing sport regarding performance, sponsorship, and health
(2018) Huynh, Huy; Sobek, Elliott; El-Hajj, Mohamad; Atwal, Sunny
The basis of this work was to extract knowledge using data mining techniques over 2 million records from rock climbing competitions all over the world. The first phase of the project involved heavy data cleaning and preprocessing procedures to prepare the data for the mining models. After the first phase was completed, we explored three main questions: which factors can predict the performance of a competitor, which factors will likely lead to a sponsorship of a competitor and is it possible to predict healthiness of a competitor. This research will not only help rock climbers gain significant insights about their performance, it will also help sports sponsors choose the best candidates to assign their brand to.
Analyzing factors impacting COVID-19 vaccination rates
(2023) Cho, Dongseok; Driedger, Mitchell; Han, Sera; Khan, Noman; Elmorsy, Mohammed; El-Hajj, Mohamad
Since the approval of the COVID-19 vaccine in late 2020, vaccination rates have varied around the globe. Access to a vaccine supply, mandated vaccination policy, and vaccine hesitancy contribute to these rates. This study used COVID-19 vaccination data from Our World in Data and the Multilateral Leaders Task Force on COVID-19 to create two COVID-19 vaccination indices. The first index is the Vaccine Utilization Index (VUI), which measures how effectively each country has utilized its vaccine supply to doubly vaccinate its population. The second index is the Vaccination Acceleration Index (VAI), which evaluates how efficiently each country vaccinated their populations within their first 150 days. Pearson correlations were created between these indices and country indicators obtained from the World Bank. Results of these correlations identify countries with stronger Health indicators such as lower mortality rates, lower age-dependency ratios, and higher rates of immunization to other diseases display higher VUI and VAI scores than countries with lesser values. VAI scores are also positively correlated to Governance and Economic indicators, such as regulatory quality, control of corruption, and GDP per capita. As represented by the VUI, proper utilization of the COVID-19 vaccine supply by country is observed in countries that display excellence in health practices. A country’s motivation to accelerate its vaccination rates within the first 150 days of vaccinating, as represented by the VAI, was largely a product of the governing body’s effectiveness and economic status, as well as overall excellence in health practises.
Analyzing patterns of car speeding in an urban environment using multivariate functional data clustering
(2023) Smith, Iain; Dobosz, Dominic; El-Hajj, Mohamad
Traffic flow and speed differences between cars are important factors that indicate the likelihood and danger of collisions. A vital part of intelligent transportation systems is discovering important locations to monitor and ticket speeding vehicles. To find these locations, we study data from a low-density city. We identify three critical road groups that indicate risk levels based on car speed differences and weather conditions. We find that these groups have differing weekly trends, which allow traffic enforcement time to change locations to enforce them. We create an analysis that an intelligent transportation system could automate to reduce risk on these roads and save city resources on enforcement.
Artificial intelligence approaches to build ticket to ride maps
(2022) Smith, Iain; Anton, Calin
Fun, as a game trait, is challenging to evaluate. Previous research explores game arc and game refinement to improve the quality of games. Fun, for some players, is having an even chance to win while executing their strategy. To explore this, we build boards for the game Ticket to Ride while optimizing for a given win rate between four AI agents. These agents execute popular strategies human players use: one-step thinking, long route exploitation, route focus, and destination hungry strategies. We create the underlying graph of a map by connecting several planar bipartite graphs. To build the map, we use a multiple phase design, with each phase implementing several simplified Monte Carlo Tree Search components. Within a phase, the components communicate with each other passively. The experiments show that the proposed approach results in improvements over randomly generated graphs and maps.
Assessing learning in an immersive virtual reality: a curriculum-based experiment in chemistry education
(2024) Qorbani, Sam; Dalili, Shadi; Arya, Ali; Joslin, Christopher
Despite the recent advances in Virtual Reality technology and its use in education, the review of the literature shows several gaps in research on how immersive virtual environments impact the learning process. In particular, the lack of curriculum-specific experiments along with investigations of the effects of different content, activity, and interaction types in the current VR studies has been identified as a significant shortcoming. This has been more significant in STEM fields, where VR has the potential to offer engaging experiential learning opportunities. The study reported here was designed to address this gap by assessing the effect of authentic visualization and interaction types on learning a particular scientific concept. A use case scenario of “orbital hybridization” in chemistry education was selected to create this experiment and to collect data for analysis. We collected data on learning outcomes, task-completion efficiency, accuracy, and subjective usability. A combination of learning content and tasks designed based on the relevant educational theories was presented to three groups: 2D, VR interaction type 1 (hand gestures), and VR interaction type 2 (ray casting). The results showed that VR could improve learning and that interaction type could influence efficiency and accuracy depending on the task.
An association analysis of breast cancer with carotenoids
(2023) Neumann, Samuel; El-Hajj, Mohamad
The environment and the exposure individuals carry throughout their lifetime can gar- ner diverse effects on their health. This paper discusses the application of association analysis, to determine relationships between carcinogenesis and the human exposome. Human exposome data from the World Health Organization was analyzed to determine associations between human exposure and breast cancer. The discovered associations outline specific factors that may be associated with the prevention or causation of breast cancer. We discovered an association between biomarkers in specific biospecimens and breast cancer. Xanthophylls, measured in two different biospecimens, were determined to be associated with American breast cancer patients. The associations discovered may be of use in future cancer studies. This research is particularly interesting because of xanthophylls’ relationship to retinol, inhibiting oncogenesis. Providing support and data for such associations will encourage more research on the exposome’s effect on breast cancer and other conditions.
Automatic deep learning segmentation of the hippocampus on high resolution diffusion MRI and its application to the healthy lifespan
(2024) Efird, Cory; Neumann, Samuel; Solar, Kevin; Beaulieu, Christian; Cobzas, Dana; Miller, Dylan
Diffusion tensor imaging (DTI) can provide unique contrast and insight into microstructural changes with age or disease of the hippocampus, although it is difficult to measure the hippocampus because of its comparatively small size, location, and shape. This has been markedly improved by the advent of a clinically feasible 1-mm isotropic resolution 6-min DTI protocol at 3 T of the hippocampus with limited brain coverage of 20 axial-oblique slices aligned along its long axis. However, manual segmentation is too laborious for large population studies, and it cannot be automatically segmented directly on the diffusion images using traditional T1 or T2 image-based methods because of the limited brain coverage and different contrast. An automatic method is proposed here that segments the hippocampus directly on high-resolution diffusion images based on an extension of well-known deep learning architectures like UNet and UNet++ by including additional dense residual connections. The method was trained on 100 healthy participants with previously performed manual segmentation on the 1-mm DTI, then evaluated on typical healthy participants (n = 53), yielding an excellent voxel overlap with a Dice score of ~ 0.90 with manual segmentation; notably, this was comparable with the inter-rater reliability of manually delineating the hippocampus on diffusion magnetic resonance imaging (MRI) (Dice score of 0.86). This method also generalized to a different DTI protocol with 36% fewer acquisitions. It was further validated by showing similar age trajectories of volumes, fractional anisotropy, and mean diffusivity from manual segmentations in one cohort (n = 153, age 5–74 years) with automatic segmentations from a second cohort without manual segmentations (n = 354, age 5–90 years). Automated high-resolution diffusion MRI segmentation of the hippocampus will facilitate large cohort analyses and, in future research, needs to be evaluated on patient groups.
Breach path detection reliability in energy harvesting wireless sensor networks
(2021) Abougamila, Salwa; Elmorsy, Mohammed; Elmallah, Ehab S.
In this paper, we consider reliability assessment of energy harvesting wireless sensor networks (EH-WSNs) deployed to guard a geographic area against intruders that can enter and exit the network through a known set of entry-exit perimeter sides. To handle energy fluctuations during different time slots, a node may reduce its transmission power. Using a probabilistic graph model, we formalize a problem denoted EH-BPDREL (for breach path detection reliability). The problem calls for estimating the likelihood that any such intrusion can be detected and reported to a sink node. Due to the hardness of the problem, bounding algorithms are needed. We devise an efficient algorithm to solve a core problem that facilitates the design of various lower bounding algorithms. We obtain numerical results on the use of Monte Carlo simulation to estimate the probabilistic graph parameters, and illustrate the use of our devised algorithm to bound the solutions.
Comparisons between text-only and multimedia tweets on user engagement
(2020) Indratmo, Indratmo; Zhao, Michael; Buro, Karen
Having highly engaged followers on social media allows us to spread information, seek feedback, and promote a sense of community efficiently. Crafting engaging posts, however, requires careful thoughts, creativity, and communication skills. This research studied tweets and explored the effect of content types on user engagement. More specifically, we compared the number of likes and retweets between text-only and multimedia tweets. We analyzed four Twitter accounts relevant to the City of Edmonton, Canada, and performed negative binomial regressions to model the expected count of likes and retweets based on accounts, content types, and their interaction. The results showed that multimedia content increased engagement in two of the four accounts but did not change engagement significantly in the other two. In other words, multimedia content had a positive or neutral effect on user engagement, depending on accounts. Our analysis also showed the effectiveness of well-written texts in attracting the attention of users. Tweets, by design, are text-oriented, and posting multimedia content may help, but is not a necessary condition to engage with followers effectively on Twitter.
A deep level set method for image segmentation
(2017) Tang, Min; Valipour, Sepehr; Zhang, Zichen; Cobzas, Dana; Jagersand, Martin
This paper proposes a novel image segmentation approach that integrates fully convolutional networks (FCNs) with a level set model. Compared with a FCN, the integrated method can incorporate smoothing and prior information to achieve an accurate segmentation. Furthermore, different than using the level set model as a post-processing tool, we integrate it into the training phase to fine-tune the FCN. This allows the use of unlabeled data during training in a semi-supervised setting. Using two types of medical imaging data (liver CT and left ventricle MRI data), we show that the integrated method achieves good performance even when little training data is available, outperforming the FCN or the level set model alone.
Developing a simple and cost-effective markerless augmented reality tool for chemistry education
(2021) Qorbani, Sam; Abdinejad, Maryam; Ferrag, Celia; Dalili, Shadi
Traditional visualization methods have a limited capacity to enhance students’ understanding of 3D molecular structure and reactivity. Studies have shown that 3D visualization tools can play an essential role in improving students’ learning. Augmented reality (AR) is a technology that merges virtual objects with real-world images seamlessly. We have previously developed a “marker-based” AR app (ARchemy) for Android devices to help students visualize molecular structures in 3D. Using recent technological advancements, to avoid the limitation of using a printed marker, we have successfully developed a simple and low-cost “markerless” AR app, which can be used for both Android and iOS devices. Students who used the AR app saw a significant increase in understanding of the complexity of molecular structures compared to those who used traditional molecular modeling kits. This unique technology will not only help teachers create more interactive and engaging lessons but also benefit students by making it more accessible and cost-effective to access the resources from any place and at any time.
Developmental hip dysplasia diagnosis at three-dimensional US: a multicenter study
(2018) Zonoobi, Dornoosh; Hareendranathan, Abhilash; Mostofi, Emanuel; Mabee, Myles; Pasha, Saba; Cobzas, Dana; Rao, Padma; Dulai, Sukhdeep K.; Kapur, Jeevesh; Jaremko, Jacob L.
Purpose: To validate accuracy of diagnosis of developmental dysplasia of the hip (DDH) from geometric properties of acetabular shape extracted from three-dimensional (3D) ultrasonography (US).
Discriminative analysis of regional evolution of iron and myelin/calcium in deep gray matter of multiple sclerosis and healthy subjects
(2018) Elkady, Ahmed M.; Cobzas, Dana; Sun, Hongfu; Blevins, Gregg; Wilman, Alan H.
Combined R2* and quantitative susceptibility (QS) has been previously used in cross‐sectional multiple sclerosis (MS) studies to distinguish deep gray matter (DGM) iron accumulation and demyelination. We propose and apply discriminative analysis of regional evolution (DARE) to define specific changes in MS and healthy DGM. Longitudinal (baseline and 2‐year follow‐up) retrospective study. Twenty‐seven relapsing‐remitting MS (RRMS), 17 progressive MS (PMS), and corresponding age‐matched healthy subjects . Field Strength/Sequence: 4.7T 10‐echo gradient‐echo acquisition. Automatically segmented caudate nucleus (CN), thalamus (TH), putamen (PU), globus pallidus, red nucleus (RN), substantia nigra, and dentate nucleus were retrospectively analyzed to quantify regional volumes, bulk mean R2*, and bulk mean QS. DARE utilized combined R2* and QS localized changes to compute spatial extent, mean intensity, and total changes of DGM iron and myelin/calcium over 2 years. We used mixed factorial analysis for bulk analysis, nonparametric tests for DARE (α = 0.05), and multiple regression analysis using backward elimination of DGM structures (α = 0.05, P = 0.1) to regress bulk and DARE measures with the follow‐up Multiple Sclerosis Severity Score (MSSS). False detection rate correction was applied to all tests. Bulk analysis only detected significant (Q ≤ 0.05) interaction effects in RRMS CN QS (η = 0.45; Q = 0.004) and PU volume (η = 0.38; Q = 0.034). DARE demonstrated significant group differences in all RRMS structures, and in all PMS structures except the RN. The largest RRMS effect size was CN total R2* iron decrease (r = 0.74; Q = 0.00002), and TH mean QS myelin/calcium decrease for PMS (r = 0.70; Q = 0.002). DARE iron increase using total QS demonstrated the highest correlation with MSSS (r = 0.68; Q = 0.0005). DARE enabled discriminative assessment of specific DGM changes over 2 years, where iron and myelin/calcium changes were the primary drivers in RRMS and PMS compared to age‐matched controls, respectively. Specific DARE measures of MS DGM correlated with follow‐up MSSS, and may reflect complex disease pathology.
Discriminative analysis of regional evolution of iron and myelin/calcium in deep gray matter of multiple sclerosis and healthy subjects
(2018) Elkady, Ahmed M.; Cobzas, Dana; Sun, Hongfu; Blevins, Gregg; Wilman, Alan H.
Background: Combined R2* and quantitative susceptibility (QS) has been previously used in cross‐sectional multiple sclerosis (MS) studies to distinguish deep gray matter (DGM) iron accumulation and demyelination. Purpose: We propose and apply discriminative analysis of regional evolution (DARE) to define specific changes in MS and healthy DGM. Study Type: Longitudinal (baseline and 2‐year follow‐up) retrospective study. Subjects: Twenty‐seven relapsing‐remitting MS (RRMS), 17 progressive MS (PMS), and corresponding age‐matched healthy subjects. Field Strength/Sequence: 4.7T 10‐echo gradient‐echo acquisition. Assessment: Automatically segmented caudate nucleus (CN), thalamus (TH), putamen (PU), globus pallidus, red nucleus (RN), substantia nigra, and dentate nucleus were retrospectively analyzed to quantify regional volumes, bulk mean R2*, and bulk mean QS. DARE utilized combined R2* and QS localized changes to compute spatial extent, mean intensity, and total changes of DGM iron and myelin/calcium over 2 years. Statistical Tests: We used mixed factorial analysis for bulk analysis, nonparametric tests for DARE (α = 0.05), and multiple regression analysis using backward elimination of DGM structures (α = 0.05, P = 0.1) to regress bulk and DARE measures with the follow‐up Multiple Sclerosis Severity Score (MSSS). False detection rate correction was applied to all tests. Results: Bulk analysis only detected significant (Q ≤ 0.05) interaction effects in RRMS CN QS (η = 0.45; Q = 0.004) and PU volume (η = 0.38; Q = 0.034). DARE demonstrated significant group differences in all RRMS structures, and in all PMS structures except the RN. The largest RRMS effect size was CN total R2* iron decrease (r = 0.74; Q = 0.00002), and TH mean QS myelin/calcium decrease for PMS (r = 0.70; Q = 0.002). DARE iron increase using total QS demonstrated the highest correlation with MSSS (r = 0.68; Q = 0.0005).Data Conclusion: DARE enabled discriminative assessment of specific DGM changes over 2 years, where iron and myelin/calcium changes were the primary drivers in RRMS and PMS compared to age‐matched controls, respectively. Specific DARE measures of MS DGM correlated with follow‐up MSSS, and may reflect complex disease pathology.
The effects of neighbourhood characteristics on crime incidence
(2018) Letourneau, Steven; Ell, Nathan; Cheung, Peter; McCaskill, Jordan; El-Hajj, Mohamad
Using data from the City of Edmonton, Canada Open Data Portal, an exploration process is undergone using data mining techniques to help detect unseen relationships between tangible spatial characteristics and non-tangible crime incidences. These findings will help law enforcement and city planners make empirically based decisions and avoid the misappropriation of public resources. Using frequent pattern analysis to examine neighbourhood attributes that occur alongside crime provides insight into why crime occurs. These techniques include clustering, classification algorithms, and association algorithms. Results of the analysis on neighbourhood spatial characteristics indicate that dwelling structure type and tree density relate to incidence of neighbourhood crime, while other neighbourhood spatial characteristics bear no relationship. Results also show that intangible neighbourhood characteristics indicate that the distribution of yearly household income and employment and school enrollment levels relate to incidence of neighbourhood crime. The distribution of yearly household income bears a relationship to crime type, specifically violent vs non-violent types.
The efficacy of stacked bar charts in supporting single-attribute and overall-attribute comparisons
(2018) Indratmo, Indratmo; Howorko, Lee; Boedianto, Joyce Maria; Daniel, Ben
Stacked bar charts are a visualization method for presenting multiple attributes of data, and many visualization tools support these charts. To assess the efficacy of stacked bar charts in supporting attribute comparison tasks, we conducted a user study to compare three types of stacked bar charts: classical, inverting, and diverging. Each chart type was used to visualize six attributes of data where half of the attributes have the characteristics of ‘lower better’ whereas the other half ‘higher better.’ Thirty participants were asked to perform two types of comparison tasks: single-attribute and overall-attribute comparisons. We measured the completion time, error rate, and perceived difficulty of the comparison tasks. The results of the study suggest that, for overall-attribute comparisons, the inverting stacked bar chart was the most effective with regards to the completion time. The results also show that performing overall-attribute comparisons using the classical and diverging stacked bar charts required more time than performing single-attribute comparisons using these charts. Participants perceived the inverting and diverging stacked bar charts as easier-to-use than the classical stacked bar chart for overall-attribute comparisons. However, for single-attribute comparisons, all chart types delivered similar performance. We discuss how these findings can inform the better design of interactive stacked bar charts and visualization tools.
End-to-end detection-segmentation network with ROI convolution
(2018) Zhang, Zichen; Tang, Min; Cobzas, Dana; Zonoobi, Dornoosh; Jagersand, Martin; Jaremko, Jacob L.
We propose an end-to-end neural network that improves the segmentation accuracy of fully convolutional networks by incorporating a localization unit. This network performs object localization first, which is then used as a cue to guide the training of the segmentation network. We test the proposed method on a segmentation task of small objects on a clinical dataset of ultrasound images. We show that by jointly learning for detection and segmentation, the proposed network is able to improve the segmentation accuracy compared to only learning for segmentation.
Evaluation of automated computed tomography segmentation to assess body composition and mortality associations in cancer patients
(2020) Cespedes Feliciano, Elizabeth M.; Popuri, Karteek; Cobzas, Dana; Baracos, Vickie E.; Beg, Mirza Faisal; Khan, Arafat Dad; Ma, Cydney; Chow, Vincent; Chow, Vincent; Prado, Carla M.; Xiao, Jingjie; Liu, Vincent; Chen, Wendy Y.; Meyerhardt, Jeffrey; Albers, Kathleen B.; Caan, Bette J.
Background Body composition from computed tomography (CT) scans is associated with cancer outcomes including surgical complications, chemotoxicity, and survival. Most studies manually segment CT scans, but Automatic Body composition Analyser using Computed tomography image Segmentation (ABACS) software automatically segments muscle and adipose tissues to speed analysis. Here, we externally evaluate ABACS in an independent dataset. Methods Among patients with non‐metastatic colorectal (n = 3102) and breast (n = 2888) cancer diagnosed from 2005 to 2013 at Kaiser Permanente, expert raters annotated tissue areas at the third lumbar vertebra (L3). To compare ABACS segmentation results to manual analysis, we quantified the proportion of pixel‐level image overlap using Jaccard scores and agreement between methods using intra‐class correlation coefficients for continuous tissue areas. We examined performance overall and among subgroups defined by patient and imaging characteristics. To compare the strength of the mortality associations obtained from ABACS's segmentations to manual analysis, we computed Cox proportional hazards ratios (HRs) and 95% confidence intervals (95% CI) by tertile of tissue area. Results Mean ± SD age was 63 ± 11 years for colorectal cancer patients and 56 ± 12 for breast cancer patients. There was strong agreement between manual and automatic segmentations overall and within subgroups of age, sex, body mass index, and cancer stage: average Jaccard scores and intra‐class correlation coefficients exceeded 90% for all tissues. ABACS underestimated muscle and visceral and subcutaneous adipose tissue areas by 1–2% versus manual analysis: mean differences were small at −2.35, −1.97 and −2.38 cm2, respectively. ABACS's performance was lowest for the <2% of patients who were underweight or had anatomic abnormalities. ABACS and manual analysis produced similar associations with mortality; comparing the lowest to highest tertile of skeletal muscle from ABACS versus manual analysis, the HRs were 1.23 (95% CI: 1.00–1.52) versus 1.38 (95% CI: 1.11–1.70) for colorectal cancer patients and 1.30 (95% CI: 1.01–1.66) versus 1.29 (95% CI: 1.00–1.65) for breast cancer patients. Conclusions In the first study to externally evaluate a commercially available software to assess body composition, automated segmentation of muscle and adipose tissues using ABACS was similar to manual analysis and associated with mortality after non‐metastatic cancer. Automated methods will accelerate body composition research and, eventually, facilitate integration of body composition measures into clinical care.
Explaining anatomical shape variability: supervised disentangling with a variational graph autoencoder
(2023) Kiechle, Johannes; Miller, Dylan; Slessor, Jordan; Pietrosanu, Matthew; Kong, Linglong; Beaulieu, Christian; Cobzas, Dana
This work proposes a modular geometric deep learning framework that isolates shape variability associated with a given scalar factor (e.g., age) within a population (e.g., healthy individuals). Our approach leverages a novel graph convolution operator in a variational autoencoder to process 3D mesh data and learn a meaningful, low-dimensional shape descriptor. A supervised disentanglement strategy aligns a single component of this descriptor with the factor of interest during training. On a toy synthetic dataset and a high-resolution diffusion tensor imaging (DTI) dataset, the proposed model is better able to disentangle the learned latent space with a simulated factor and patient age, respectively, relative to other state-of-the-art methods. The relationship between age and shape estimated in the DTI analysis is consistent with existing neuroimaging literature.

Browse

Browsing Department of Computer Science by Title

Results Per Page

Sort Options