Zachary Patterson
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Zachary Patterson has a total of 60 co-authors. Here are the top co-authors by number of shared publications:
- Nizar Bouguila
Concordia University, Montreal, Canada
15 shared publications - Edward Owen Douglas Waygood
Polytechnique Montreal
8 shared publications - Bilal Farooq
Toronto Metropolitan University
5 shared publications - Bobin Wang
Université Laval
5 shared publications - Sneha Paul
Concordia University
4 shared publications - Xinyi Zhou
Concordia Institute for Information Systems Engineering, Concordia University, Montreal, QC, Canada
4 shared publications
Latest Publications
- Open Access
- 3 September 2026
- Published by Springer Nature in Theory and Society
- Vol. 55 (5) , 77
The diversity hypothesis: A rapid scoping review of diversity and scientific output and impact in the natural and social sciences
Recent years have witnessed many strong claims that ‘diversity’ leads to more original and impactful science, which is a science-focused form of what we call “The Diversity Hypothesis.” However, what evidence supports the claim that diversity enhances scientific output or impact? This pre-registered rapid scoping review seeks to collate and evaluate the scientific evidence for the Diversity Hypothesis as a foundation for future, methodologically rigorous studies that address the Diversity Hypothesis. Guided by the Joanna Briggs Institute approach and Preferred Reporting Items for Systematic Reviews and Meta-Analyses for Scoping Reviews (PRISMA-ScR), a systematic search of three electronic databases (Web of Science, Scopus, and Ovid PsycInfo) was performed. The Mixed Methods Assessment Tool was used for quality appraisal of included articles. Studies were included if they were peer-reviewed, empirical studies that satisfied the population (‘scientists or scientific teams/labs’), concept (‘diversity of scientists or scientific teams/labs’), context (‘scientific productivity or impact’) as well as other inclusion criteria. In total, 104 articles were included and their findings pertaining to the relationship between diversity and scientific productivity and impact analysed. We estimate that only between 15% and 28% of results reported in these articles are unambiguously consistent with the Diversity Hypothesis, with the balance not being so. Overall, the results indicate that there is little empirical evidence that diversity, as defined narrowly by demographic or identity diversity, improves scientific output and impact. Despite claims that evidence for the Diversity Hypothesis is unambiguous, the results of this scoping review suggest that, presently, this broad conclusion is unsubstantiated and that more nuanced propositions pertaining to the types and effects of diversity be advanced and enacted in the context of scientific claims, funding, and policy-making.
- 3 September 2026
- Published by Springer Nature in Theory and Society
- Vol. 55 (5) , 77
Open AccessThe diversity hypothesis: A rapid scoping review of diversity and scientific output and impact in the natural and social sciences
Recent years have witnessed many strong claims that ‘diversity’ leads to more original and impactful science, which is a science-focused form of what we call “The Diversity Hypothesis.” However, what evidence supports the claim that diversity enhances scientific output or impact? This pre-registered rapid scoping review seeks to collate and evaluate the scientific evidence for the Diversity Hypothesis as a foundation for future, methodologically rigorous studies that address the Diversity Hypothesis. Guided by the Joanna Briggs Institute approach and Preferred Reporting Items for Systematic Reviews and Meta-Analyses for Scoping Reviews (PRISMA-ScR), a systematic search of three electronic databases (Web of Science, Scopus, and Ovid PsycInfo) was performed. The Mixed Methods Assessment Tool was used for quality appraisal of included articles. Studies were included if they were peer-reviewed, empirical studies that satisfied the population (‘scientists or scientific teams/labs’), concept (‘diversity of scientists or scientific teams/labs’), context (‘scientific productivity or impact’) as well as other inclusion criteria. In total, 104 articles were included and their findings pertaining to the relationship between diversity and scientific productivity and impact analysed. We estimate that only between 15% and 28% of results reported in these articles are unambiguously consistent with the Diversity Hypothesis, with the balance not being so. Overall, the results indicate that there is little empirical evidence that diversity, as defined narrowly by demographic or identity diversity, improves scientific output and impact. Despite claims that evidence for the Diversity Hypothesis is unambiguous, the results of this scoping review suggest that, presently, this broad conclusion is unsubstantiated and that more nuanced propositions pertaining to the types and effects of diversity be advanced and enacted in the context of scientific claims, funding, and policy-making.
- 4 August 2026
- Published by Elsevier in Sustainable Cities and Society
- Vol. 149
Bus passenger flow prediction with a dynamic graph neural network and bidirectional gated recurrent unit
- 4 August 2026
- Published by Elsevier in Sustainable Cities and Society
- Vol. 149
Bus passenger flow prediction with a dynamic graph neural network and bidirectional gated recurrent unit
- 30 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. PP (15249050) , 1-15
A Graph-Based Transfer Learning Approach for Short-Term Bus Passenger Flow Prediction
Bus passenger flow prediction is a crucial task in bus transportation management and optimization, characterized by strong spatiotemporal dependencies and influenced by external factors such as weather and holidays. However, existing methods face challenges in responding to sudden events, modeling dynamic changes in bus network topology, and improving model generalization. To address these issues, this paper proposes a graph transfer learning-based approach for bus passenger flow prediction. First, a dynamic graph neural network is used to construct the passenger flow network, and Framelet Transform along with Self-Expressiveness Regularization is applied for denoising, enhancing data quality. Second, an adaptive neighborhood-aware dynamic graph convolutional network is introduced, integrating random mask enhancement, hop count perception fusion, and multi-channel spatiotemporal feature extraction for accurate passenger flow modeling. Furthermore, a combination of source data and source free transfer learning is leveraged to optimize feature distribution alignment through pseudo-label generation, graph diffusion, and consistency loss. Finally, a GRU is used for passenger flow prediction, and extensive experiments on real-world datasets test the proposed method. Results demonstrate superior accuracy and generalization performance compared to existing state of the art (SOTA) models.
- 30 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. PP (15249050) , 1-15
A Graph-Based Transfer Learning Approach for Short-Term Bus Passenger Flow Prediction
Bus passenger flow prediction is a crucial task in bus transportation management and optimization, characterized by strong spatiotemporal dependencies and influenced by external factors such as weather and holidays. However, existing methods face challenges in responding to sudden events, modeling dynamic changes in bus network topology, and improving model generalization. To address these issues, this paper proposes a graph transfer learning-based approach for bus passenger flow prediction. First, a dynamic graph neural network is used to construct the passenger flow network, and Framelet Transform along with Self-Expressiveness Regularization is applied for denoising, enhancing data quality. Second, an adaptive neighborhood-aware dynamic graph convolutional network is introduced, integrating random mask enhancement, hop count perception fusion, and multi-channel spatiotemporal feature extraction for accurate passenger flow modeling. Furthermore, a combination of source data and source free transfer learning is leveraged to optimize feature distribution alignment through pseudo-label generation, graph diffusion, and consistency loss. Finally, a GRU is used for passenger flow prediction, and extensive experiments on real-world datasets test the proposed method. Results demonstrate superior accuracy and generalization performance compared to existing state of the art (SOTA) models.
- 19 March 2026
- Published by Springer Nature in Theory and Society
- Vol. 55 (2) , 29
The post-critical social sciences
- 19 March 2026
- Published by Springer Nature in Theory and Society
- Vol. 55 (2) , 29
The post-critical social sciences
- Open Access
Enhancing Diversity and Feasibility: Joint Population Synthesis from Multi-source Data Using Generative Models
Generating realistic synthetic populations is essential for agent-based models (ABM) in transportation and urban planning. Current methods face two major limitations. First, many rely on a single dataset or follow a sequential data fusion and generation process, which means they fail to capture the complex interplay between features. Second, these approaches struggle with sampling zeros (valid but unobserved attribute combinations) and structural zeros (infeasible combinations due to logical constraints), which reduce the diversity and feasibility of the generated data. This study proposes a novel method to simultaneously integrate and synthesize multi-source datasets using a Wasserstein Generative Adversarial Network (WGAN) with gradient penalty. This joint learning method improves both the diversity and feasibility of synthetic data by defining a regularization term (inverse gradient penalty) for the generator loss function. For the evaluation, we implement a unified evaluation metric for similarity, and place special emphasis on measuring diversity and feasibility through recall, precision, and the F1 score. Results show that the proposed joint approach outperforms the sequential baseline, with recall increasing by 7\% and precision by 15\%. Additionally, the regularization term further improves diversity and feasibility, reflected in a 10\% increase in recall and 1\% in precision. We assess similarity distributions using a five-metric score. The joint approach performs better overall, and reaches a score of 88.1 compared to 84.6 for the sequential method. Since synthetic populations serve as a key input for ABM, this multi-source generative approach has the potential to significantly enhance the accuracy and reliability of ABM.
Open AccessEnhancing Diversity and Feasibility: Joint Population Synthesis from Multi-source Data Using Generative Models
Generating realistic synthetic populations is essential for agent-based models (ABM) in transportation and urban planning. Current methods face two major limitations. First, many rely on a single dataset or follow a sequential data fusion and generation process, which means they fail to capture the complex interplay between features. Second, these approaches struggle with sampling zeros (valid but unobserved attribute combinations) and structural zeros (infeasible combinations due to logical constraints), which reduce the diversity and feasibility of the generated data. This study proposes a novel method to simultaneously integrate and synthesize multi-source datasets using a Wasserstein Generative Adversarial Network (WGAN) with gradient penalty. This joint learning method improves both the diversity and feasibility of synthetic data by defining a regularization term (inverse gradient penalty) for the generator loss function. For the evaluation, we implement a unified evaluation metric for similarity, and place special emphasis on measuring diversity and feasibility through recall, precision, and the F1 score. Results show that the proposed joint approach outperforms the sequential baseline, with recall increasing by 7\% and precision by 15\%. Additionally, the regularization term further improves diversity and feasibility, reflected in a 10\% increase in recall and 1\% in precision. We assess similarity distributions using a five-metric score. The joint approach performs better overall, and reaches a score of 88.1 compared to 84.6 for the sequential method. Since synthetic populations serve as a key input for ABM, this multi-source generative approach has the potential to significantly enhance the accuracy and reliability of ABM.
- Open Access
- 24 January 2026
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2680 (10) , 1-18
Choice Set Generation in Work Destination Choice Modeling with Variational Autoencoders
Accurate destination choice modeling is vital for transportation and urban planning, influencing demand prediction, infrastructure development, and policy assessment. Conventional methods for choice set generation—both deterministic and stochastic—often face limitations such as failing to capture individual variability, requiring extensive data, and inadequately representing decision-making processes, thus compromising reliability. This study introduces a novel application of variational autoencoders (VAEs) for generating choice sets in destination choice modeling, focusing on home-based work trips in Montreal, Canada. Leveraging the deep generative capabilities of VAEs enhances the realism and diversity of choice sets, addressing implicit perception and availability of alternatives. Our methodology integrates VAE-generated choice sets with a multinomial logit model to predict destination choices. The results show significant improvements in model fit and predictive accuracy. The VAE-based model achieved a ρ 2 value of 0.5733 and an accuracy of 49.61%, outperforming other models. The importance-sampling-based model followed, with a ρ 2 of 0.3123 and an accuracy of 41.19%, while the simple random-sampling-based model achieved a ρ 2 of 0.2528 and an accuracy of 30.10%. The model considering all alternatives available performed worst, with a ρ 2 of 0.1532 and an accuracy of 10.82%. These results highlight the effectiveness of VAEs for choice set generation, leading to more reliable destination choice models. All models were evaluated using the same number of alternatives and observations, ensuring a fair comparison and demonstrating the superior performance of the VAE-based approach.
- 24 January 2026
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2680 (10) , 1-18
Open AccessChoice Set Generation in Work Destination Choice Modeling with Variational Autoencoders
Accurate destination choice modeling is vital for transportation and urban planning, influencing demand prediction, infrastructure development, and policy assessment. Conventional methods for choice set generation—both deterministic and stochastic—often face limitations such as failing to capture individual variability, requiring extensive data, and inadequately representing decision-making processes, thus compromising reliability. This study introduces a novel application of variational autoencoders (VAEs) for generating choice sets in destination choice modeling, focusing on home-based work trips in Montreal, Canada. Leveraging the deep generative capabilities of VAEs enhances the realism and diversity of choice sets, addressing implicit perception and availability of alternatives. Our methodology integrates VAE-generated choice sets with a multinomial logit model to predict destination choices. The results show significant improvements in model fit and predictive accuracy. The VAE-based model achieved a ρ 2 value of 0.5733 and an accuracy of 49.61%, outperforming other models. The importance-sampling-based model followed, with a ρ 2 of 0.3123 and an accuracy of 41.19%, while the simple random-sampling-based model achieved a ρ 2 of 0.2528 and an accuracy of 30.10%. The model considering all alternatives available performed worst, with a ρ 2 of 0.1532 and an accuracy of 10.82%. These results highlight the effectiveness of VAEs for choice set generation, leading to more reliable destination choice models. All models were evaluated using the same number of alternatives and observations, ensuring a fair comparison and demonstrating the superior performance of the VAE-based approach.
- 22 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (3) , 2970-2984
STAM-GED: Spatial–Temporal Attention Masked Graph Neural Networks for Passenger Flow Prediction
Accurate passenger flow prediction helps public transportation authorities optimize routes, reduce delays, and enhance travel experiences. Recently, Spatial-Temporal Graph Neural Networks (ST-GNNs) have emerged as powerful tools for predicting passenger flows in public transportation. While ST-GNNs can offer valuable insights, they usually assume a static network structure that may not fully consider the real-world dynamics of public transportation systems. With the increasing accessibility of real-time bus schedule data, passengers are adjusting their arrival times at stops according to the latest bus schedules, significantly impacting passenger flow patterns. To address these dynamics, it is critical to incorporate real-time data into ST-GNNs, making these models more dynamic and flexible in terms of both nodes and edges. This adjustment allows the models to better align with actual bus schedules. Current ST-GNN models primarily focus on the temporal evolution of edges, often overlooking the changing status of the nodes. This study introduces a novel dynamic spatial-temporal graph neural network framework, the first to account for the dynamic nature of nodes, providing a more comprehensive approach to predicting passenger flow in bus networks. In this framework, which is entitled Spatial-Temporal Attention Masked Graph Encoder-Decoder, through analysis of active stops - those where buses are scheduled to arrive based on the bus schedule - a more realistic representation of a network’s spatial and temporal dynamics will be captured. The proposed model was evaluated on two real-world transit networks—Laval, Canada, and Ames, USA—and consistently outperformed both classical and recent state-of-the-art baselines across multiple forecasting horizons.
- 22 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (3) , 2970-2984
STAM-GED: Spatial–Temporal Attention Masked Graph Neural Networks for Passenger Flow Prediction
Accurate passenger flow prediction helps public transportation authorities optimize routes, reduce delays, and enhance travel experiences. Recently, Spatial-Temporal Graph Neural Networks (ST-GNNs) have emerged as powerful tools for predicting passenger flows in public transportation. While ST-GNNs can offer valuable insights, they usually assume a static network structure that may not fully consider the real-world dynamics of public transportation systems. With the increasing accessibility of real-time bus schedule data, passengers are adjusting their arrival times at stops according to the latest bus schedules, significantly impacting passenger flow patterns. To address these dynamics, it is critical to incorporate real-time data into ST-GNNs, making these models more dynamic and flexible in terms of both nodes and edges. This adjustment allows the models to better align with actual bus schedules. Current ST-GNN models primarily focus on the temporal evolution of edges, often overlooking the changing status of the nodes. This study introduces a novel dynamic spatial-temporal graph neural network framework, the first to account for the dynamic nature of nodes, providing a more comprehensive approach to predicting passenger flow in bus networks. In this framework, which is entitled Spatial-Temporal Attention Masked Graph Encoder-Decoder, through analysis of active stops - those where buses are scheduled to arrive based on the bus schedule - a more realistic representation of a network’s spatial and temporal dynamics will be captured. The proposed model was evaluated on two real-world transit networks—Laval, Canada, and Ames, USA—and consistently outperformed both classical and recent state-of-the-art baselines across multiple forecasting horizons.
- 14 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (1) , 895-910
A Noise-Robust Approach Using Dynamic Graph Neural Networks for Bus Passenger Flow Prediction
Short-term passenger flow prediction is critical for intelligent scheduling and efficient operation of public transportation systems. However, existing methods often struggle to maintain robustness and generalizability when facing complex and heterogeneous noise sources, such as passenger flow noise including sensor-induced missing values and abrupt ridership fluctuations caused by unexpected events, and graph structural noise resulting from dynamic changes in the network topology due to route modifications or stop closures. To address these challenges, this paper proposes a novel deep learning framework: Robust Dynamic Graph Neural Networks (RDGNN), that integrates noise cleaning, dynamic graph modeling, and more efficient prediction. The proposed noise cleaning employs K-Nearest Neighbor imputation and Gaussian Mixture Models with a penalty function to mitigate data-level noise, while a graph structure denoising module is introduced to correct topological anomalies in the transit network and enhance the reliability of spatial representation. For feature modeling, the framework constructs a dynamic graph neural network from a subgraph perspective to capture both spatial dependencies and temporal dynamics, particularly suited to modeling interactions among transfer stations. A Liquid Neural Network is adopted as the prediction module, leveraging its strong adaptability and memory capacity to handle irregular and non-stationary time series, while remaining computationally efficient. The RDGNN model was trained and validated on real-world bus passenger flow data from Ames, Iowa, and further evaluated on the large-scale EXO dataset. Compared to state-of-the-art models, RDGNN consistently achieves better prediction accuracy, higher robustness to noise and missing data, and greater computational efficiency. Its strong and stable performance across both datasets, including in scenarios such as route disruptions and seasonal variation, demonstrates excellent generalization capability in diverse urban transit systems. The code is available at: https://github.com/XinyiZhou0318/A-Noise-Robust-Approach-Using-Dynamic-Graph-Neural-Networks-for-Bus-Passenger-Flow-Prediction
- 14 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (1) , 895-910
A Noise-Robust Approach Using Dynamic Graph Neural Networks for Bus Passenger Flow Prediction
Short-term passenger flow prediction is critical for intelligent scheduling and efficient operation of public transportation systems. However, existing methods often struggle to maintain robustness and generalizability when facing complex and heterogeneous noise sources, such as passenger flow noise including sensor-induced missing values and abrupt ridership fluctuations caused by unexpected events, and graph structural noise resulting from dynamic changes in the network topology due to route modifications or stop closures. To address these challenges, this paper proposes a novel deep learning framework: Robust Dynamic Graph Neural Networks (RDGNN), that integrates noise cleaning, dynamic graph modeling, and more efficient prediction. The proposed noise cleaning employs K-Nearest Neighbor imputation and Gaussian Mixture Models with a penalty function to mitigate data-level noise, while a graph structure denoising module is introduced to correct topological anomalies in the transit network and enhance the reliability of spatial representation. For feature modeling, the framework constructs a dynamic graph neural network from a subgraph perspective to capture both spatial dependencies and temporal dynamics, particularly suited to modeling interactions among transfer stations. A Liquid Neural Network is adopted as the prediction module, leveraging its strong adaptability and memory capacity to handle irregular and non-stationary time series, while remaining computationally efficient. The RDGNN model was trained and validated on real-world bus passenger flow data from Ames, Iowa, and further evaluated on the large-scale EXO dataset. Compared to state-of-the-art models, RDGNN consistently achieves better prediction accuracy, higher robustness to noise and missing data, and greater computational efficiency. Its strong and stable performance across both datasets, including in scenarios such as route disruptions and seasonal variation, demonstrates excellent generalization capability in diverse urban transit systems. The code is available at: https://github.com/XinyiZhou0318/A-Noise-Robust-Approach-Using-Dynamic-Graph-Neural-Networks-for-Bus-Passenger-Flow-Prediction
- Open Access
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1005-1011
LSTM vs. DistilBERT: A Comparative Study for 2025 SHL Recognition Challenge
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1005-1011
Open AccessLSTM vs. DistilBERT: A Comparative Study for 2025 SHL Recognition Challenge
- 21 January 2025
- Published by Elsevier in Case Studies on Transport Policy
- Vol. 19
Bus user itinerary choice: Can crowding information help shift riders?
- 21 January 2025
- Published by Elsevier in Case Studies on Transport Policy
- Vol. 19
Bus user itinerary choice: Can crowding information help shift riders?