Milad Haghani

Human-centric traffic signal control in corridor networks must increasingly account for multimodal travelers, particularly high-occupancy public transportation, rather than focusing solely on vehicle-centric performance. This paper proposes STDSH-MARL (Spatio-Temporal Dual-Stage Hypergraph based Multi-Agent Reinforcement Learning), a scalable multi-agent deep reinforcement learning framework that follows a centralized training and decentralized execution paradigm. The proposed method captures spatio-temporal dependencies through a novel dual-stage hypergraph attention mechanism that models interactions across both spatial and temporal hyperedges. In addition, a hybrid discrete action space is introduced to jointly determine the next signal phase configuration and its corresponding green duration, enabling more adaptive signal timing decisions. Experiments conducted on a corridor network under five traffic scenarios demonstrate that STDSH-MARL consistently improves multimodal performance and provides clear benefits for public transportation priority. Compared with state-of-the-art baseline methods, the proposed approach achieves superior overall performance. Further ablation studies confirm the contribution of each component of STDSH-MARL, with temporal hyperedges identified as the most influential factor driving the observed performance gains.

Coordinating traffic signals along multimodal corridors is challenging because many multi-agent deep reinforcement learning (DRL) approaches remain vehicle-centric and struggle with high-dimensional discrete action spaces. We propose MA2B-DDQN, a human-centric multi-agent action-branching double Deep Q-Network (DQN) framework that explicitly optimizes traveler-level equity. Our key contribution is an action-branching discrete control formulation that decomposes corridor control into (i) local, per-intersection actions that allocate green time between the next two phases and (ii) a single global action that selects the total duration of those phases. This decomposition enables scalable coordination under discrete control while reducing the effective complexity of joint decision-making. We also design a human-centric reward that penalizes the number of delayed individuals in the corridor, accounting for pedestrians, vehicle occupants, and transit passengers. Extensive evaluations across seven realistic traffic scenarios in Melbourne, Australia, demonstrate that our approach significantly reduces the number of impacted travelers, outperforming existing DRL and baseline methods. Experiments confirm the robustness of our model, showing minimal variance across diverse settings. This framework not only advocates for a fairer traffic signal system but also provides a scalable solution adaptable to varied urban traffic conditions.

Sports and exercise medicine is important in the prevention, diagnosis, and management of a variety of musculoskeletal presentations and injuries as well as aiding athletes’ recovery and enhancing public health by promoting physical activity for all. It has evolved from a subspecialty into a distinct interdisciplinary domain. Using scientometric analysis, this study examines sports and exercise medicine’s scope, history, current landscape and future directions. Utilising data from the Web of Science, covering 150,380 publications up to November 2022, trends from the early 1970s to 2022 are analysed. There was gradual growth in the field between 1980 and 2000 and a significant surge post-2000. The study reveals global distribution, with the United States contributing over half of the field’s output. However, questions arise about international collaboration and resource allocation. Citespace analysis visualises 26 research streams in sports and exercise medicine, with many emerging around 2000, showcasing adaptability to trends. Document co-citation and citation burst analyses highlight pivotal moments in sports medicine’s intellectual history and foundational knowledge. Semantic analysis categorises sports medicine into four primary divisions: Exercise, Lower limb injuries, Physical activity, and Biomechanics in sport, emphasising its multidisciplinary nature. This scientometric analysis highlights sports medicine’s evolution into a diverse, interdisciplinary field, with significant growth since 2000. By identifying and mapping trends, global contributions, and key research themes (Exercise variables, Lower limb injuries, Sports dynamics, and Biomechanics) this study provides valuable insights for guiding collaboration, research, and resource allocation to advance athletes’ well-being and health at a population level.

The paper "Simulating dynamical features of escape panic" by Helbing, Farkas, and Vicsek, published over two decades ago in Nature, has left an indelible mark on the field of crowd dynamics.With nearly 3,000 citations to date, according to the Web of Science records, this influential work has significantly shaped the field. This analysis investigates the overall influence of this paper through various indicators, documenting its reach across multiple research areas. The intellectual foundation of the paper is traced, examining the references cited and uncovering some misalignments between certain assertions and the citations meant to support them. The terminological impact is also explored, showing how the paper invigorated the use of terms like "panic" and "herding". Moreover, the alignment of some key assumptions of the paper with empirical evidence that has emerged since its publication is investigated, revealing discrepancies in key assertions about panic behaviour. It is also determined that the numerical observations of the paper have significantly influenced the field by introducing concepts such as the "faster-is-slower" phenomenon, on which empirical research has since produced mixed evidence rather than irrefutable support.While the paper remains a key pillar in crowd dynamics, we advocate for a new course for the field that could facilitate a paradigm shift in conceptualising crowd behavior, particularly one that reconsiders some terminologies and key behavioral concepts adopted in the paper, rather than treating them as proven.

The paper "Simulating dynamical features of escape panic" by Helbing, Farkas, and Vicsek, published over two decades ago in Nature, has left an indelible mark on the field of crowd dynamics. With nearly 3,000 citations to date, according to the Web of Science records, and significant influence, it has shaped the crowd dynamics field. This analysis investigates the overall influence of this paper through a variety of indicators, mapping its reach across research areas. The intellectual foundation of the paper is traced, examining the references cited. The terminological impact is also explored, showing how the paper made use of terms like "panic" and "herding". Moreover, the alignment of the assumptions of the paper with empirical evidence is discussed, finding discrepancies in key assertions about panic behaviour. The numerical simulations of the paper and observations have significantly influenced the field, such as for the case of the "faster-is-slower" phenomenon. The paper remains a key pillar in crowd dynamics, nevertheless, we advocate for a new course of the field shifting away from the terminology adopted in the paper and focusing more on empirical evidence.

Crowds can be subject to intrinsic and extrinsic sources of risk, and previous records have shown that, in the absence of adequate safety measures, these sources of risk can jeopardise human lives. To mitigate these risks, we propose that implementation of multiple layers of safety measures for crowds—what we label The Swiss Cheese Model of Crowd Safety—should become the norm for crowd safety practice. Such system incorporates a multitude of safety protection layers including regulations and policymaking, planning and risk assessment, operational control, community preparedness, and incident response. The underlying premise of such model is that when one (or multiple) layer(s) of safety protection fail(s), the other layer(s) can still prevent an accident. In practice, such model requires a more effective implementation of technology, which can enable provision of real-time data, improved communication and coordination, and efficient incident response. Moreover, implementation of this model necessitates more attention to the overlooked role of public education, awareness raising, and promoting crowd safety culture at broad community levels, as one of last lines of defence against catastrophic outcomes for crowds. Widespread safety culture and awareness has the potential to empower individuals with the knowledge and skills that can prevent such outcomes or mitigate their impacts, when all other (exogenous) layers of protection (such as planning and operational control) fail. This requires safety campaigns and development of widespread educational programs. We conclude that, there is no panacea solution to the crowd safety problem, but a holistic multi-layered safety system that utilises active participation of all potential stakeholders can significantly reduce the likelihood of disastrous accidents. At a global level, we need to target a Vision Zero of Crowd Safety, i.e., set a global initiative of bringing deaths and severe injuries in crowded spaces to zero by a set year.