Machine Learning-Based Route Optimization for Smart Urban Transportation Systems

With the popularization of machine learning (ML) techniques and the increased chipset’s performance, the application of ML to pedestrian localization systems has received significant attention in the last years. Several survey papers have attempted to provide a state-of-the-art overview, but they usually limit their scope to a particular type of positioning system or technology. In addition, they are written from the point of view of ML techniques and their practice, not from the point of view of the localization system and the specific problems that ML techniques can help to solve. This article is intended to offer a comprehensive state-of-the-art survey of the ML techniques that have been adopted over the last ten years to improve the performance of pedestrian localization systems, addressing the applicability of ML techniques in this domain, along with the main localization strategies. It concludes by indicating the underlying open issues and challenges associated with the existing systems, and possible future directions in which ML techniques could improve the performance of pedestrian localization systems. Among other open issues, most previous authors have focused their attention on position estimation accuracy, which wastes the potential of ML techniques to improve other performance parameters (e.g., response time, computational complexity, robustness, scalability or energy efficiency). This study shows that there is a strong trend towards the application of supervised learning. Consequently, there are many potential research opportunities in the use of other learning types, such as unsupervised and reinforcement learning, to improve the performance of pedestrian localization systems.

This research investigates methods to enhance multimodal route optimization in the maritime sector through the integration of real-time traffic data and professionalism standards. Conducted by researchers and lecturers at the Maritime Institute, the study involves 100 cadets predominantly studying multimodal transportation, logistics, and port management. The research utilises qualitative methods to explore cadets' perspectives on route optimization and professionalism in the industry. Findings reveal a recognition of the significance of real-time traffic data for informed routing decisions, along with an emphasis on compliance with international standards, training, and ethical considerations. Furthermore, cadets perceive machine learning algorithms as effective tools to address the complexities of route optimization. These insights contribute to advancing knowledge in transportation management and education, highlighting the importance of integrating real-time data and professionalism in enhancing route optimization practices.

With increasingly stringent environmental constraints and the rapid growth of urban logistics demand, electric vehicles (EVs) have become an important component of urban delivery systems due to their low-carbon, energy-efficient, and low-noise characteristics. However, limited driving range, charging requirements, and the uneven spatial distribution of charging infrastructure make the electric vehicle routing problem (EVRP) significantly more complex than conventional vehicle routing problems, posing new challenges to logistics operations and traffic management. In recent years, extensive research has been conducted on EV routing optimization, covering route planning, charging strategy coordination, mixed fleet operations, and charging infrastructure deployment. Meanwhile, the rapid development of intelligent transportation systems (ITS) has provided new technical support for EV routing optimization. By leveraging real-time traffic information, data sharing, and intelligent dispatching, ITS enhances the adaptability and responsiveness of routing decisions, thereby improving delivery efficiency and reducing energy consumption and emissions. This paper presents a comprehensive review of EV routing optimization oriented to ITS, systematically summarizing key research issues and application scenarios. Future development trends related to technological integration, infrastructure planning, and system-level coordination are also discussed, providing insights for the development of efficient, low-carbon, and sustainable urban logistics and transportation systems.

Bidirectional Human-Robot Learning: Imitation and Skill Improvement

In today’s rapidly evolving healthcare landscape, data-driven decision-making (DDDM) is revolutionizing the industry by enhancing operational efficiency, optimizing resource allocation, and improving patient outcomes. This research explores the role of DDDM in driving healthcare business success, emphasizing key independent variables such as technology infrastructure, organizational culture & leadership, and regulatory & policy framework. This study investigates the transformative impact of data-driven decision-making (DDDM) on business success in today's rapidly evolving landscape. By analyzing how organizations leverage data insights to optimize operations, enhance customer experiences, and drive innovation, this research highlights the critical role of DDDM in maintaining a competitive edge. The study employs a mixed-methods approach, combining quantitative analysis of performance metrics with qualitative insights from industry experts. Key findings reveal that DDDM not only improves accuracy and efficiency but also fosters a culture of innovation and enhances decision-making speed. However, the successful implementation of DDDM hinges on addressing challenges such as data quality, privacy concerns, and skill gaps. The study concludes by providing actionable strategies for building a data-driven culture, investing in advanced technologies, and ensuring data accessibility and privacy. Ultimately, this research underscores that DDDM is not just a strategic advantage but a necessity for businesses aiming to thrive in the data-centric future. The study utilizes the Resource-Based View (RBV), Triple Aim Framework, and Technology Acceptance Model (TAM) as theoretical underpinnings. By leveraging predictive analytics, real-time data processing, data integration, AI/ML utilization, and evidence-based decision-making, healthcare organizations can achieve financial stability, compliance with regulations, and innovation in service delivery. The findings highlight the significance of electronic health record (EHR) adoption, interoperability, cybersecurity, leadership support, ethical governance, and policy compliance in ensuring healthcare business success. This study provides actionable insights for policymakers, healthcare administrators, and technology developers in shaping data-driven healthcare environments.

In metropolitan areas, common traffic issues include traffic congestion, traffic accidents, air pollution, and energy consumption occur. To resolve this issues, Intelligent Transportation Systems (ITS) have been evolved by many researchers. One of the important sub-systems in the development of ITS is a Traffic Management System (TMS) which attempts to reduce a traffic congestion. In fact, TMS itself relies on the estimation of traffic flow, therefore providing such an accurate traffic flow prediction is needed. For this reason, we aim to provide an accurate traffic flow prediction to facilitate this system. In this works, a Supervised Deep Learning Based Traffic Flow Prediction (SDLTFP) was proposed which is a type of fully-connected deep neural network (FC-DNN). Timely prediction is also a major issue in guaranteeing reliable traffic flow prediction. However, training a deep network could be time-consuming, and overfitting is might be happening, especially when feeding small data into the deep architecture. The network is learned perfectly during the training, but in testing with the new data, it could fail to generalize the model. We adopt the Batch Normalization (BN) and Dropout techniques to help the network training. SGD and momentum are carried out to update the weight. We then take advantage of open data as historical traffic data which are then used to predict future traffic flow with the proposed method and model above. Experiments show that the Mean Absolute Percentage Error (MAPE) for our traffic flow prediction is within 5 % using sample data and between 15% to 20% using out of the sample data. Training a deep network faster with BN and Dropout reduces the overfitting.

Smart transportation in Vehicular Cyber Physical Systems (VCPS) are addressing a range of problems including reducing traffic accidents, congestion, fuel consumption, time spent on traffic jams, and to improve transportation safety. Smart transportation VCPS is expected to contribute an important role in the design and development of intelligent transportation systems. Intermittently Connected Vehicular Networks (ICVNs) are a kind of intelligent transportation systems, where due to mobility of vehicles there may be disconnections among the source and destination vehicles. A multi-hop scenario is used here, where a stationary road side unit exchanges data packets with a destination outside its communication range, using passing-by vehicles as information carriers. In order to deal with these ICVNs, an efficient routing scheme is necessary to withstand the maximum delay. We propose a routing scheme, which makes use of the movement history among the regions for routing a message. The proposed scheme ...

With the rapid development of intelligent transportation systems, vehicle detection and traffic flow statistics have become increasingly critical in traffic management and the construction of smart cities. However, complex weather conditions lead to challenges in vehicle detection algorithms, increasing false negatives and false positives. Additionally, the rapid growth of vehicle ownership makes traditional algorithms inadequate for meeting practical application needs. Therefore, this paper proposes a collaborative optimization-based method combining YOLOv11 for vehicle detection and traffic flow analysis under complex weather conditions. Vehicle information is accurately extracted through object detection and tracking methods, and further analyzed using Logistic Regression to assess traffic congestion. The main contributions of this study are: (1) Integration of the CBAM attention mechanism into YOLOv11, enhancing the vehicle feature extraction ability through collaborative channel and spatial attention, thereby improving interference resistance under complex weather conditions. (2) Adoption of the Shape-IoU loss function, with dynamic weight allocation to optimize the accuracy of detecting smaller vehicles and the precision of bounding box regression in images where vehicles are located at a greater distance. (3) Construction of a traffic congestion prediction model based on the detection results, integrated with Logistic Regression. The proposed method's effectiveness is validated on the public dataset UA-DETRAC. Through the synergistic effect of the CBAM attention mechanism and Shape-IoU loss function, the improved model's mAP50-95 shows a 0.3 percentage point increase over the YOLOv11 baseline, providing efficient and reliable technical support for intelligent transportation systems. This study enhances the prediction performance of traffic states under complex weather conditions by effectively calculating traffic flow parameters such as vehicle count and density, thus offering foundational data support for traffic management decision-making. The research conclusions are of practical significance for urban traffic improvement.

Understanding how congestion at one location can cause ripples throughout large-scale transportation network is vital for transportation researchers and practitioners to pinpoint traffic bottlenecks for congestion mitigation. Traditional studies rely on either mathematical equations or simulation techniques to model traffic congestion dynamics. However, most of the approaches have limitations, largely due to unrealistic assumptions and cumbersome parameter calibration process. With the development of Intelligent Transportation Systems (ITS) and Internet of Things (IoT), transportation data become more and more ubiquitous. This triggers a series of data-driven research to investigate transportation phenomena. Among them, deep learning theory is considered one of the most promising techniques to tackle tremendous high-dimensional data. This study attempts to extend deep learning theory into large-scale transportation network analysis. A deep Restricted Boltzmann Machine and Recurrent Neural Network architecture is utilized to model and predict traffic congestion evolution based on Global Positioning System (GPS) data from taxi. A numerical study in Ningbo, China is conducted to validate the effectiveness and efficiency of the proposed method. Results show that the prediction accuracy can achieve as high as 88% within less than 6 minutes when the model is implemented in a Graphic Processing Unit (GPU)-based parallel computing environment. The predicted congestion evolution patterns can be visualized temporally and spatially through a map-based platform to identify the vulnerable links for proactive congestion mitigation.

Traffic congestion is one of the major problems facing Yangon and is attributed to many factors including rapid population increase, poor road infrastructure, city structure, the rapid increase in the number of cars, and a lack of physical car parking plan. For this congestion problem, people can be lost their valuable time and cost. To avoid traffic congestion problems, the best choice of the urban transport system with multiple criteria such as Car Capacity (CC), Required Time (Time), Car Parking Place (PP), Required Cost (Cost), and Travelling Cost (Cost) are introduced in the proposed approach. Before applying the multicriteria analysis method, this paper analyzes the traffic congestion problem by using the Functional Resonance Analysis Method (FRAM). In this analysis, data collected from the Yangon Traffic Control Center (TCC) and show the traffic congestion status using Queuing Model. Based on the traffic congestion status, AHP is applied by identifying suitable alternative solutions of the urban transport system such as rail transport system, public bus system, taxi system, and private car system for the dedicated urban area in Yangon. As a result, the government can consider the urban transport system to avoid traffic congestion problem.

Evaluating semi-cooperative Nash/Stackelberg Q-learning for traffic routes plan in a single intersection

The process industry (PI) plays a vital role in the global economy and faces mounting pressure to enhance sustainability, operational agility, and resource efficiency amid tightening regulatory and market demands. Although artificial intelligence (AI) has been explored in this domain for decades, its adoption in industrial practice remains limited. Recently, machine learning (ML) has gained momentum, particularly when integrated with core PI systems such as process control, instrumentation, quality management, and enterprise platforms. Among ML techniques, reinforcement learning (RL) has emerged as a promising approach to tackle complex operational challenges. In contrast to conventional data-driven methods that focus on prediction or classification, RL directly addresses sequential decision making under uncertainty, a defining characteristic of dynamic process operations. Given RL’s growing relevance, this study conducts a systematic literature review to evaluate its current applications in the PI, assess methodological developments, and identify barriers to broader industrial adoption. The review follows the PRISMA methodology, a structured framework for identifying, screening, and selecting relevant publications. This approach ensures alignment with a clearly defined research question and minimizes bias, focusing on studies that demonstrate meaningful industrial applications of RL. The findings reveal that RL is transitioning from a theoretical construct to a practical tool, particularly in the chemical sector and for tasks such as process control and scheduling. Methodological maturity is improving, with algorithm selection increasingly tailored to problem-specific requirements and a trend toward hybrid models that integrate RL with established control strategies. However, most implementations remain confined to simulated environments, underscoring the need for real-world deployment, safety assurances, and improved interpretability. Overall, RL exhibits the potential to serve as a foundational component of next-generation smart manufacturing systems.

The transport sector significantly contributes to global greenhouse gas emissions, making electromobility crucial in the race toward the United Nations Sustainable Development Goals. In recent years, the increasing competition among manufacturers, the development of cheaper batteries, the ongoing policy support, and people’s greater environmental awareness have consistently increased electric vehicles (EVs) adoption. Nevertheless, EVs charging needs—highly influenced by EV drivers’ behavior uncertainty—challenge their integration into the power grid on a massive scale, leading to potential issues, such as overloading and grid instability. Smart charging strategies can mitigate these adverse effects by using information and communication technologies to optimize EV charging schedules in terms of power systems’ constraints, electricity prices, and users’ preferences, benefiting stakeholders by minimizing network losses, maximizing aggregators’ profit, and reducing users’ driving range anxiety. To this end, accurately forecasting EV charging demand is paramount. Traditionally used forecasting methods, such as model-driven and statistical ones, often rely on complex mathematical models, simulated data, or simplifying assumptions, failing to accurately represent current real-world EV charging profiles. Machine learning (ML) methods, which leverage real-life historical data to model complex, nonlinear, high-dimensional problems, have demonstrated superiority in this domain, becoming a hot research topic. In a scenario where EV technologies, charging infrastructure, data acquisition, and ML techniques constantly evolve, this paper conducts a systematized literature review (SLR) to understand the current landscape of ML-based EV charging demand forecasting, its emerging trends, and its future perspectives. The proposed SLR provides a well-structured synthesis of a large body of literature, categorizing approaches not only based on their ML-based approach, but also on the EV charging application. In addition, we focus on the most recent technological advances, exploring deep-learning architectures, spatial-temporal challenges, and cross-domain learning strategies. This offers an integrative perspective. On the one hand, it maps the state of the art, identifying a notable shift toward deep-learning approaches and an increasing interest in public EV charging stations. On the other hand, it uncovers underexplored methodological intersections that can be further exploited and research gaps that remain underaddressed, such as real-time data integration, long-term forecasting, and the development of adaptable models to different charging behaviors and locations. In this line, emerging trends combining recurrent and convolutional neural networks, and using relatively new ML techniques, especially transformers, and ML paradigms, such as transfer-, federated-, and meta-learning, have shown promising results for addressing spatial-temporality, time-scalability, and geographical-generalizability issues, paving the path for future research directions.

The rise in complexity of large scale IoT-enabled drone logistics networks would require intelligent computing systems that can autonomously make optimal scheduling and routing decisions. Since drones are highly important in real-time delivery and surveillance services, the planning of routes and flexible scheduling are critical to the improvement of the reliability and scalability of the operations. The current means have shortcomings in terms of lack of flexibility, routing algorithms that are fixed and lack the responsiveness to the dynamic aspects of the environment like weather, air traffic and the varying need to deliver goods. To eliminate these constraints, this paper proposes the Reinforcement Learning-Based Adaptive Route Optimization (RL-ARO) model, which incorporates Deep Reinforcement Learning into the IoT-based contextual information to optimize routes and schedule. The framework allows multi-agent drones to jointly discover the best flight paths because they constantly adapt to the current network conditions, resource limitations, and energy efficiency needs. The suggested RL-ARO algorithm is implemented in a smart healthcare delivery system for the real-time medical supply and vaccine delivery environment with minimal latency and energy usage. The results of the experiment show that the framework can dramatically increase the efficiency of the route, decrease the delivery time by more than 35%, and increase the resilience of the system in large-scale and dynamical domains. The proposed method achieves the average time gap after 150 missions, energy consumption reduction (850 wh), route optimality (> 90), adaptation response time (6 s), packet deliver ratio (96–99). The RL-ARO framework optimizes drone routes using reinforcement learning and IoT data for dynamic conditions. The system reduces delivery time by 35%, increases energy efficiency, and ensures high reliability in real-time logistics. RL-ARO provides scalable and resilient drone operations, adapting quickly to environmental and operational changes.

This paper introduces a deep reinforcement learning approach for optimizing network-on-chip layout verification and route optimization. The proposed method addresses the challenges of increasing design complexity and traditional verification limitations in modern VLSI circuits. A novel three-headed policy gradient network architecture is developed to handle layout verification and routing optimization tasks simultaneously. The framework integrates feature extraction networks for topology analysis, policy networks for decision-making, and value networks for performance evaluation. The system employs a complex-valued reinforcement learning model to capture both spatial and temporal dependencies in NoC designs. Experimental results demonstrate significant improvements across multiple performance metrics: a 23.4% reduction in average packet latency, a 23.6% increase in network throughput, and a 20.8% decrease in power consumption compared to conventional methods. The verification accuracy achieves 98.7% with a false positive rate below 0.5%. The framework maintains consistent performance across various network sizes and traffic patterns, demonstrating robust scalability and practical applicability in real-world chip designs. Implementation results on ISPD 2005 benchmarks validate the effectiveness of the proposed approach, showing superior performance in both verification accuracy and optimization efficiency compared to existing state-of-the-art methods.