Ebook: Intelligent Transportation and Smart Cities

Welcome to the Proceedings of the 2025 International Conference on Intelligent Transportation and Smart Cities (ICITSC2025)! In this prestigious gathering of researchers, scholars, practitioners, and industry experts, we delve into the dynamic intersection of intelligent transportation systems and the advancement of smart cities. This conference serves as a platform for knowledge exchange, the sharing of innovative ideas, and the cultivation of collaborations that will shape the future of transportation and urban development.

The ICITSC2025 conference brings together experts from diverse disciplines, including computer science, urban planning, and data science. It serves as a catalyst for interdisciplinary discussions, aiming to bridge the gap between theory and practice in the realm of intelligent transportation and smart cities. The growing interest in this field is propelled by the need to address the challenges posed by rapid urbanization, increasing traffic congestion, environmental concerns, and the demand for efficient and sustainable transportation systems.

The Proceedings of ICITSC2025 presents research articles covering topics in the domain of Intelligent Transportation and Smart Cities, which is a multidisciplinary field. Research in this field focuses on the development of basic theories in computer science (IoT, Cloud Computing, Artificial Intelligence), and on the application of advanced theory to engineering. We have selected articles that blend different disciplines (e.g. communication technology, artificial intelligence, edge computing, traffic management, smart cities), and articles with practical applications in different engineering fields were preferred. These proceedings showcase cutting-edge advancements and breakthroughs, offering valuable insights into the latest trends, challenges, and opportunities in both fields.

We extend our sincere gratitude to the authors who have contributed their work to this volume, as well as the reviewers who dedicated their time and expertise to ensure the quality and relevance of the presented research. We would also like to express our appreciation to the conference organizers, sponsors, and participants for their unwavering support and commitment to advancing the fields of intelligent transportation and smart cities.

It is our hope that the Proceedings of ICITSC2025 will serve as a valuable resource for researchers, practitioners, policymakers, and industry professionals, inspiring further exploration and collaboration in the pursuit of intelligent, sustainable, and inclusive urban mobility solutions within the context of smart cities.

With warm regards,

Conference Chairs

Prof. Vitaliy Mezhuyev, FH JOANNEUM University of Applied Sciences, Austria

Prof. Zongzhi Li, Illinois Institute of Technology, USA

Prof. Carlos Becker Westphall, Federal University of Santa Catarina, Brazil

This paper presents an analysis of international trade transportation costs using multi-sensor assisted wireless network virtualization technology. The objective is to optimize overall trade expenses and support national economic growth. The methodology employed involved firstly analyzing the advantages and disadvantages of various transportation modes such as road, rail, shipping, waterway, and pipeline transportation. Subsequently, a system for international trade transportation cost analysis and control was designed based on multi-sensor assisted wireless network virtualization. This system was utilized to devise an international trade transportation scheme that combines the optimal transportation modes. The effectiveness of this scheme was assessed by comparing the transportation costs of single versus combined modes in practical applications. The results demonstrate that the combined transportation scheme can save 400 yuan per unit of transportation cost and generate a total income of 3,000 yuan, highlighting its significant impact on reducing international trade transportation costs and promoting international trade economic development.

The evolution of smart cities has highlighted the critical need for intelligent crowd monitoring in modern sports facilities. This paper presents a comprehensive IoT-based crowd monitoring system designed specifically for gymnasium environments. Traditional monitoring approaches often struggle with real-time accuracy and system responsiveness, particularly during high-occupancy events. To address these challenges, we developed an integrated system incorporating multi-sensor fusion, edge computing, and cloud analytics. The system architecture employs a novel dual-stage attention network for sensor fusion, achieving a 27% reduction in data conflicts while maintaining real-time processing capabilities. Our implementation includes strategically positioned 4K cameras, infrared sensors, and UWB positioning devices, supported by an optimized MobileNetV3 edge computing framework. Through extensive testing in a standard gymnasium environment, the system demonstrated exceptional performance with 97.8% detection accuracy under normal conditions and 95.2% accuracy during peak loads. The hierarchical alert mechanism, combining LSTM networks and gradient boosting classifiers, achieved a remarkably low false alarm rate of 0.1%. The system successfully handled 10,000 concurrent connections while maintaining five-nines availability. Real-world deployment validated significant improvements in crowd management capabilities, including enhanced emergency response efficiency and reduced congestion. These results establish a robust foundation for next-generation crowd monitoring systems, offering practical solutions for smart facility management challenges.

This paper addresses the problem of path planning and task allocation for cooperative search and rescue (SAR) missions of unmanned boats in a typical SAR scenario. Firstly, a system model for cooperative SAR of unmanned boats is established, including environmental model, task model, unmanned boat model, and task model, to the complex maritime SAR environment and task requirements. Then, the task allocation process is divided into two core stages, which are applied to the cooperative SAR mission of unmanned boats Through simulation experiments, the performance of BLSA algorithm and other intelligent optimization algorithms in terms of search and rescue efficiency, path length, and computation time is compared and. The results show that the BLSA algorithm has significant advantages in solving the cooperative SAR problem of unmanned boats, which can improve the search and rescue efficiency, shorten search and rescue time, and provide new solutions for maritime rescue tasks.

The resilience of urban transportation system is an important basis for building a resilient city. The existing assessment methods are faced with the challenges of complex influencing factors, difficult quantification of resilience index and low accuracy of traditional single model. In order to solve these problems, this study proposes a dynamic resilience evaluation method of urban transportation system based on deep learning model. This method constructs a resilience assessment model of urban transportation system, quantifies and integrates dynamic influencing factors. Convolutional neural network (CNN) was used to extract the dynamic characteristics of the toughness index, combined with Bidirectional Gated Recurrent Unit (BiGRU) to explore the time correlation, and the attention mechanism was used to enhance the important features. Taking Zhengzhou metropolitan area as an example, the empirical analysis found that the overall resilience of the urban transportation system in this region was at a medium to high level and showed a slow rising trend (resilience index increased from 0.319 in 2013 to 0.347 in 2022, with an average annual growth rate of 8.611%). However, there are significant differences in resilience levels among cities within the region (Zhengzhou has the highest annual mean resilience index (0.802) and Pingdingshan has the lowest (0.105). Compared with the traditional model, the model shows better performance in terms of mean absolute percentage error (MAPE = 0.06275%), root mean square error (RMSE = 0.018698%) and coefficient of determination (R²= 0.9912), which verifies the validity and reliability of the model.

In road traffic safety management, not wearing a helmet has become one of the main causes of injuries and fatalities among drivers. Timely detection of riders not wearing helmets is extremely important for reducing road traffic accidents and ensuring the safety of people’s lives and property. This paper proposes the C-YOLOv5 model, which optimizes the YOLOv5 model using the CBAM attention mechanism to identify the violation of not wearing a helmet, thereby improving the accuracy and efficiency of helmet detection for non-motorized vehicle riders, providing strong support for road traffic safety management. Experimental results show that the C-YOLOv5 model has improved detection accuracy for helmet usage and localization performance for small targets, offering an effective solution for helmet detection among non-motorized vehicle riders, while also providing reference value for the research and application of object detection algorithms.

With the process of urbanization, the prediction of traffic information assumes considerable significance for the effective management of traffic. Considering the temporal characteristics is a universal practice when making predictions about traffic information. This method uses the Gated Recurrent Unit (GRU) to get temporal features related to traffic flow, thereby revealing the traffic flow of the road. Nevertheless, this approach fails to incorporate the spatial structural attributes of the road network. While some scholars have considered the regional structural features of road networks, their work has typically focused on extracting Euclidean structural features and has paid little attention to non-Euclidean structural features. This article proposes a method for predicting traffic flow information. It uses GRU to obtain temporal characteristics about traffic flow and an attention mechanism to assign different weights. Subsequently, a graph convolutional network (GCN) is employed for the extraction of non-Euclidean structural features of the road network space. Afterwards, the efficacy of this method is demonstrated through an evaluation against a series of baseline models. Experimental results show that the proposed method produces more accurate predictions than the baseline model on both PEMS_BAY and METR_LA datasets.

In response to the growing demand for pedestrian crosswalk safety and visibility in the era of autonomous driving, this paper proposes and designs a crosswalk environment monitoring system based on virtual-physical twin technology. Leveraging Unreal Engine (UE) and Carla simulation software, the system constructs a high-precision virtual environment, integrating real-time data from on-site sensors and weather APIs to achieve comprehensive and dynamic monitoring of crosswalk conditions. A key innovation of the system is the application of a Vision-Language Model (VLM), which automatically translates monitoring data into understandable natural language text while also enabling threshold-based warnings and safety alerts. This enhances the intelligence and automation of the monitoring system. Compared to traditional monitoring methods that primarily rely on graphical visualization, the proposed approach significantly improves data processing efficiency and safety alert capabilities, offering a more efficient, real-time, and intelligent solution for traffic safety management in the context of autonomous driving.

With the wide application of UAV technology in the power system, the information security of its acquisition terminal has become the key to ensure the stable operation of the system. Aiming at the deficiencies and challenges in existing research, this study systematically analyzes the information security risks faced by UAV collection terminals, including network attacks, hardware vulnerabilities and software vulnerabilities. Based on this, a set of multi-level and all-round information security protection strategy is proposed, covering the network layer, hardware layer and software layer. The network layer adopts firewall technology and intrusion detection and defense system, the hardware layer integrates hardware encryption module and adopts anti-jamming and reinforcement design, and the software layer focuses on security coding and auditing as well as security update and patch management. The proposed protection strategy is verified by constructing an experimental environment that simulates a power system, and the results show that it shows good results in coping with various types of attacks and significantly improves the information security of the UAV collection terminal. This study provides theoretical basis and practical guidance for the information security protection of UAV acquisition terminal in electric power system, which is of great significance for promoting the development of informatization and intelligence in electric power industry.

The adaptive feature extraction capability of deep learning algorithms and the ability to collect data throughout the entire process of the Internet of Things provide technical support for efficient supervision of agricultural product supply chains. The research aims to build a safety supervision system for agricultural product supply chain through IoT technology, achieve food safety traceability, and improve the risk identification ability and supervision efficiency of agricultural product supply chain. The research adopts a hierarchical holographic modeling method to construct a risk indicator system, identifies agricultural product supply chain risks through backpropagation neural networks, and combines IoT technology for food safety traceability, thereby establishing a complete agricultural product supply chain safety supervision system. The results show that the average time to trace food safety issues before applying intelligent supervision is 15.9 days, while the average time to trace food safety issues after application is 4.2 minutes, with the maximum time spent being only 13.7 minutes, and it can effectively identify risks in the supply chain. The results indicate that the proposed agricultural product supply chain safety supervision system has improved the accuracy of risk identification in the agricultural product supply chain and achieved full traceability from production to consumption. The research results contribute to improving the quality and safety level of agricultural products and enhancing consumers’ trust in agricultural products.

Tourist route planning in large and diverse regions, such as China, presents significant challenges due to the vast number of destinations and varying preferences of travelers. This paper introduces the Tourist Route Optimization Algorithm (TROA), a novel approach combining entropy-based evaluation, Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS), and Grey Relational Analysis (GRA) to assess and rank 352 cities by their tourism attractiveness. TROA integrates advanced heuristic techniques, including Simulated Annealing (SA) and Genetic Algorithms (GA), to construct optimized travel itineraries that minimize costs and maximize time efficiency. The algorithm is validated through case studies, including a 144-hour constrained route starting in Guangzhou and a mountain-themed travel plan. Results demonstrate TROA’s capability to adapt to diverse tourist requirements and dynamic datasets, providing scalable and intelligent solutions for real-time multi-objective route optimization. This work advances computational methods in tourism planning and offers practical insights for enhancing tourist experiences and regional development strategies.

The Electromagnetic Suspension (EMS) high-speed maglev system, as a representative intelligent transportation system, employs intelligent electromagnetic attraction control to achieve stable levitation above the track, enabling contactless operation and establishing itself as a next-generation sustainable transport solution. Unlike conventional wheel-rail systems, this intelligent transportation innovation addresses critical challenges including real-time system integration, automated control coordination, and multi-sensor data fusion. The development faces significant technical barriers such as extended test cycle durations, substantial infrastructure investments, and limitations in physical prototype verification for vehicular components. To overcome these constraints in controller validation and load testing for levitation stabilization, lateral guidance, and eddy-current braking systems, we developed an integrated Hardware-in-the-Loop (HIL) simulation platform aligned with Intelligent Transportation requirements. This advanced testing architecture enables comprehensive performance evaluation of coupled electromagnetic control systems across multiple operational scenarios: static levitation maintenance, dynamic trajectory tracking, emergency braking sequences, and controlled suspension release. Featuring a highly integrated architecture with modular scalability, the platform demonstrates three distinctive advantages for intelligent transportation applications: (1) Cost-effectiveness through virtual-physical system co-simulation enabling large-scale network deployment, (2) Configurable test scenario generation for multi-domain controller verification across transportation ecosystems, and (3) Accelerated test iteration cycles via real-time digital twin implementation supporting smart infrastructure evolution. Experimental validation confirms the platform’s capability to reduce development costs by 43% while improving test efficiency by 68% compared to conventional field-testing approaches. This platform provides an essential research tool for the engineering development, operational safety assurance, and ultra-high-speed verification of EMS maglev systems within modern intelligent transportation frameworks.

An interaction behavior recognition model based on an improved PoseC3D is proposed to address the challenges of behavior recognition in smart cities, particularly in urban surveillance and public safety monitoring systems. These systems often face challenges in distinguishing between highly similar behavior categories and dealing with high computational complexity. Firstly, the lightweight high-resolution network Lite-HRNet is used to extract bone points from the UT-Interaction human interaction dataset and estimate the joint coordinates of objects in the video, thereby reducing the model’s computational complexity and making it more suitable for real-time urban applications. Secondly, the PoseC3D model is used as the base model to extract skeletal modal features, and the impact of skeletal point noise on the model is reduced through multiple sampling. Finally, the CBAM lightweight attention mechanism is introduced into the PoseC3D model, which improves the model’s ability to recognize similar samples by processing the input feature layer using both channel attention and spatial attention mechanisms. The experimental results show that the improved PoseC3D model achieves higher recognition accuracy than the original PoseC3D model on the UT-Interaction dataset, reaching 91.6%, which verifies the effectiveness of the improved method for smart city applications.

In the domain of autonomous driving, lane instance classification is paramount for decision-making processes within vehicles. However, conventional methods frequently necessitate the pre-determination of the number of lane lines, a practice that is ill-suited to address the demands of intricate and ever-changing road scenarios. This paper puts forward a novel lane instance classification approach, underpinned by the concept of neighbour inner product. The proposed method first extracts lane lines from the semantic segmentation mask, then represents the lane lines with coordinate points, and finally classifies the lane line instances by calculating the inner product of vectors between adjacent coordinate points. Experimental results demonstrate that, in comparison with alternative methods, this approach exhibits higher precision, recall and F1 score, and is better able to adapt to complex road environments, thus providing a novel solution for lane instance classification in autonomous driving.

Multimodal learning has become a critical focus in computer science, particularly for robotic perception, where integrating diverse sensory data such as vision, audio, and tactile information is essential for interpreting complex environments. This study proposes a self-supervised multimodal learning framework that integrates spatiotemporal transformers and cross-modal attention mechanisms to address challenges in temporal modeling and feature fusion. The spatiotemporal transformer effectively captures sequential dependencies within individual modalities, while the cross-modal attention module dynamically assigns importance weights to modalities, enabling robust feature integration. Unlike traditional approaches, the proposed framework eliminates the need for extensive labeled data, increasing scalability and adaptability. Experimental results on benchmark datasets demonstrate that the framework significantly outperforms CNN, LSTM, and state-of-the-art Transformer-based models in terms of accuracy, F1 scores, and robustness, particularly under noisy conditions or incomplete modalities. Ablation studies validate the contributions of the transformer and attention modules, while qualitative analysis highlights the model’s ability to adaptively prioritize relevant features. This research advances self-supervised multimodal learning and provides a scalable, efficient, and robust solution for real-world robotic systems, with potential for further optimization to support additional modalities and real-time processing.

This study proposes an improved optical flow algorithm based on semantic segmentation for real-time vehicle detection and tracking. The method combines the semantic segmentation capability of the SegmentAnything model with optical flow estimation technology. By generating precise vehicle region masks, it effectively narrows the search range for matching optical flow feature points, which not only improves the computation speed of optical flow but also enhances matching accuracy. Based on this, a real-time vehicle detection and tracking system is designed, including modules for multi-target detection, feature extraction, classification, and tracking. Experimental results show that this method outperforms existing methods in both detection accuracy and computational efficiency, making it suitable for real-time applications in complex traffic scenarios. It offers a new solution for intelligent transportation systems and autonomous driving technology.

Smart algorithms such as path planning are faced with challenges such as traffic congestion, dynamic environmental obstacles change, high computational complexity and multi-agent collaboration. To solve these problems, a method of multi-agent path planning and angle tracking strategy generation system is proposed, which integrates hybrid algorithm, dual-stream network, dynamic weight allocation and hierarchical learning, and cloud-edge collaborative training. The results show that under the full model configuration, the path success rate is as high as 98.73%, and the conflict rate is only 1.25%. In the high obstacle density environment, the trajectory jitter rate is stable at about 0.3%, and the entropy of angular deviation is about 0.8 Bits. In the communication delay robustness test, the synchronization error at 200ms delay was only half that of the comparison scheme, and the overlap rate was also about 30% lower. The proposed method shows higher stability and accuracy in complex environments, which significantly improves the performance of multi-agent path planning and angle tracking, and has stronger robustness of communication delay.

Artificial intelligence and intelligent algorithms are increasingly widely used in intelligent transportation systems. Traditional methods rely on single sensor data, which is difficult to deal with intersections without signal lights and high-speed movement scenes. The Internet of vehicles technology provides a new idea for multi-source data fusion, but there are still deficiencies in early warning algorithms for official cars. In view of this, the paper proposes a collision warning algorithm based on Kalman network-bidirectional circular neural network, combining vehicle state estimation, trajectory prediction and circular-rectangular combined collision model, to realize multi-source data fusion through Internet of vehicle communication. Improved Kalman filter is used for state updating, and bidirectional temporal feature extraction is introduced to optimize the prediction accuracy. The Experiments show that the collision warning accuracy of the complete model is 97.83±0.62%, the false alarm rate is only 3.25±0.72%, and the trajectory prediction error and collision time calculation error are 0.42±0.11 m and 0.19±0.05 seconds, respectively. Compared to the unimproved model, the RMS error of the trajectory prediction decreased from 0.3 to 0.1, and the heading angle deviation at 12 hours decreased from 0.95 to 0.65. Therefore, this method significantly improves the collision warning performance of official cars at intersections, verifies the effectiveness of multi-model collaboration and data fusion of Internet of vehicles, and provides a reliable solution for the intelligent transportation system.

Global food security depends critically on the agricultural supply chain, which is also rather sensitive to disturbances brought about by demand changes, extreme weather, and delayed transit. This work suggests a new hybrid architecture to improve agricultural supply chain resilience by combining Deep Reinforcement Learning (DRL) with Genetic Algorithms (GA). DRL is used to create adaptive rules for real-time decision-making; GA is used to maximize the structural configuration of the supply chain, including warehouse locations and transportation paths. Computational simulations running under several disturbance scenarios—including demand spikes and transit delays—verified the approach. A 15% operating cost savings and a 20% increase in adaptability measures indicate that the GA-DRL framework beats conventional approaches. Under dynamic conditions, the hybrid architecture also shows faster recovery times and better service levels. These results show the complementing strengths of GA and DRL, in which DRL offers the flexibility required for real-time adaptation while GA guarantees a strong starting configuration. This work not only solves important problems with agricultural supply chain resilience but also provides a scalable method for handling intricate and uncertain systems. Investigating multi-objective optimization methods and merging real-time data streams can help to improve system responsiveness and sustainability even further in future directions.

With the rapid development of intelligent transportation systems, Beidou-based free-flow toll collection technology has become an important research direction to improve road traffic efficiency and toll management level. Addressing issues such as the ambiguity of routes and large trajectory deviations caused by inaccurate positioning results in the current Beidou Free-Flow tolling, which mostly adopts a holistic pricing approach, this paper proposes a Beidou Free-Flow tolling technology based on segmented pricing and designs a corresponding Beidou Free-Flow tolling system. Through real-road tests, the Beidou free-flow toll collection technology based on segmented billing proposed in this paper reduces construction costs and decreases the difficulty of auditing, while ensuring the accuracy and reliability of billing. At the same time, this technology also has good scalability and compatibility, which can provide strong support for the construction of future intelligent transportation systems.

Supply chain logistics optimization faces mounting challenges in the era of global commerce, particularly in handling dynamic demand patterns and complex path planning requirements. Traditional optimization methods often fall short in addressing these challenges, especially when dealing with seasonal fluctuations and real-time decision-making needs. This study develops an integrated solution leveraging advanced deep learning technologies to enhance supply chain efficiency and responsiveness.We design a three-module collaborative algorithm: an LSTM-CNN hybrid model for demand prediction, a double deep Q-network for inventory optimization, and a graph attention network for path planning. The system was trained and validated using comprehensive datasets from 2020 to 2024, encompassing over 80 product categories across multiple industry sectors. The LSTM-CNN module incorporates attention mechanisms to handle promotional events, while the path planning module optimizes delivery routes considering real-time conditions.Real-world enterprise application validation demonstrates significant improvements: inventory turnover increased by 25.1%, logistics costs reduced by 23.7%, and on-time delivery rate reached 96.7%. The system showed particular strength in handling seasonal fluctuations, maintaining high service levels even under demand variations of ±30%. This collaborative algorithm effectively solves complex scenarios and fluctuating demand problems that traditional methods struggle to address, providing data-driven decision support for enterprises to achieve precise logistics management.

This study addresses the significant performance limitations of the YOLOv8 algorithm in autonomous driving (AD) under adverse weather conditions, particularly heavy fog and low-light environments. Existing YOLOv8 shows considerable accuracy degradation in such conditions, necessitating targeted enhancements to ensure reliable and safe autonomous navigation. The study optimized the YOLOv8 algorithm through several innovative methods: integrating PEnet for low-light enhancement, FAANet for foggy conditions, the SPD-conv block for improved detection of small objects, and the GAM attention model for better adaptability in complex scenarios. Additionally, EfficientViT, FastCNN, and VanillaNet backbone networks were compared to identify the most effective model. Datasets from ExDARK and fog-specific conditions were utilized, split into training and validation subsets. Post-optimization, YOLOv8 showed marked performance improvement: fog detection recall increased by 8.7%, precision by 3.9%, mAP by 15%, and mAP50-95 by 6.17%. Under low-light conditions, recall and precision improved by approximately 15%. Among tested backbones, VanillaNet exhibited superior performance, showing a 6.42% increase in precision and a 14.42% increase in mAP, demonstrating its efficiency and suitability for real-world deployment. The enhanced YOLOv8 algorithm significantly improves AD systems’ safety and reliability in adverse weather by reducing misidentification risks and improving detection accuracy. These enhancements can substantially decrease AD-related accidents, enhancing road safety. Future directions involve expanding datasets through community-driven campaigns and extensive real-world deployment testing to validate the model’s practical effectiveness.

With the development of autonomous driving technology, there are still many challenges to accurately tracking pedestrians in complex environments, such as occlusion, dense crowds, and light variations. This study aims to design a highly adaptive pedestrian tracking system to improve the reliability of the autonomous driving perception system. In this paper, an innovative solution combining YOLOv8-pose and improved Bot-sort algorithm is proposed to integrate the detection bounding box, appearance features, and 17-point pose information through a multimodal feature fusion strategy, and the matching cost matrix is redesigned to enhance the tracking performance. Experimental results show that the proposed pose feature enhancement strategy significantly improves the system’s capability in similar appearance pedestrian differentiation and trajectory continuity, and it is well adapted to scenarios such as occlusion, dense crowds, and lighting changes. Meanwhile, the system maintains the real-time processing performance and provides reliable support for the automatic driving perception system, demonstrating the potential and value of multimodal feature fusion for pedestrian tracking in complex environments.

This study presents the development and evaluation of an advanced social running platform designed to enhance user engagement through personalized activity recommendations and interactive mapping features. Unlike existing platforms that primarily offer basic tracking functions, our solution integrates external map APIs, sophisticated hybrid recommendation algorithms, and robust social interaction capabilities within a scalable Model-View-Controller (MVC) architecture. Utilizing MongoDB for efficient data management, the platform consolidates key entities such as users, activities, and comments, ensuring data consistency and flexibility. Comprehensive testing was conducted to assess search accuracy, response time, cross-platform compatibility, and security, demonstrating superior performance compared to existing competitors. The recommendation system achieved a precision of 92% and a response time of 0.85 seconds, while the platform efficiently handled over 100 concurrent users and ensured strong data protection measures. These findings underscore the platform’s potential to significantly improve user experience and community engagement in the digital fitness landscape.