Comprehensive Decision Research Articles

Synergizing GIS and genetic algorithms to enhance road management and fund allocation with a comprehensive case study approach

This study identifies a critical knowledge gap, revealing how the deterioration of roads, compounded by extensive usage and additional factors, poses significant risks to the road networks’ functionality. Without a robust fund allocation and prioritization strategy, the extent of this risk may be overlooked, adversely affecting the performance of essential infrastructure elements. Our research introduces an integrated decision-making model for existing road infrastructures to address this gap. This innovative approach combines a Geographic Information System (GIS)-based road management model with a fund allocation prioritization strategy, enhanced by an optimization engine via a genetic algorithm. The primary aim is to precisely determine Maintenance and Repair (M&R) interventions tailored to the condition states, thereby improving the Pavement Condition Index (PCI) of the road segments. The research is structured around three key objectives: (1) develop a detailed GIS-based road management database incorporating inspection data and attributes of road infrastructure for proactive M&R decision-making; (2) efficiently allocate funds to maintain service delivery on deteriorated roads; and (3) pinpoint the optimal type and timing of M&R interventions to boost the condition and performance of the road segments. Anticipated results will provide asset managers with a comprehensive decision support system for executing effective M&R practices.

Post-transplant cyclophosphamide versus anti-thymocyte globulin in haploidentical stem cell transplantation: a systematic review and meta-analysis.

Post-transplant cyclophosphamide (PTCy) and anti-thymocyte globulin (ATG) are mainstay prophylactic treatment options for graft-versus-host disease (GVHD), widely used in haploidentical stem cell transplantation. Due to a lack of prospective studies, a number of retrospective comparisons have yielded different conclusions as to which prophylaxis regimen is superior. We performed a meta-analysis of these studies to get more informed and comprehensive decisions from clinicians. Nine studies were eligible, and a total of 1674 patients were included. The combined hazard ratio (HR), relative risk (RR), and weighted mean difference (WMD) results demonstrated that, compared with ATG, PTCy demonstrated better overall survival (OS) (HR 0.7, 95% CI 0.51-0.97), leukemia-free survival (LFS) (HR 0.66, 95% CI 0.53-0.81), and GVHD-free/relapse-free survival (GRFS) (HR 0.79, 95% CI 0.65-0.97); faster lymphocyte reconstitution, lower risk of relapse (HR 0.69, 95% CI 0.53-0.9) and fungal infection (RR 0.23, 95% CI 0.07-0.79). However, neutrophil engraftment was delayed in the PTCy regimen group (WMD 3.29, 95% CI 2.49-4.10). No statistically significant differences were observed in the time to platelet engraftment, bacterial infection, or viral infection, including cytomegalovirus, polyomaviruses BK/JC and Epstein-Barr virus. Nor was any statistically significant difference observed in the incidences of II-IV acute-GVHD (aGVHD) (HR 0.81, 95% CI 0.62-1.05), III-IV aGVHD (HR 0.67, 95% CI 0.22-2.19) or severe chronic-GVHD (cGVHD) (RR 1.22, 95% CI 0.51-2.88), or non-relapse mortality (NRM) outcomes (HR 0.67, 95% CI 0.4-1.11). Therefore, in haploidentical transplantation, PTCy accelerates lymphocyte reconstitution, significantly reduces the risk of recurrence and fungal infection, and improves the OS, LFS and GRFS, compared with ATG, with no significant difference in the efficacy of preventing acute or severe cGVHD, or the risk of bacterial or viral infection.

Thematic analysis of perceptions from both patients and dental students on a digital clinical decision aid in prosthodontics: A qualitative study.

The present study aimed to investigate the impact of utilizing an innovative and comprehensive patient-centered digital clinical decision aid designed to facilitate shared decision-making in missing tooth replacement between dental students and their patients. A qualitative study using interview approach was conducted in Hong Kong SAR and Malaysia. Thirty dental undergraduate students, each with one patient from the Faculty of Dentistry at The University of Hong Kong (n = 15) and Universiti Teknologi MARA (n = 15), were introduced to a digitally designed decision aid in missing tooth replacement prior to their treatment appointments. Semi-structured interviews were conducted with each student and patient, adhering to the interview protocol. Each interview was audio-recorded, transcribed, and subsequently coded to investigate the perceptions and potential advantages of this decision aid. Thematic analysis identified three key themes from the dental students' perspective: communication, utilization, and satisfaction. From patients' perceptions, four central themes emerged: communication, treatment information, uncertainty, and utilization. Detailed examination of the data highlighted an enhancement in patients' confidence and trust in their dental care providers, as well as a marked increase in both student and patient satisfaction levels upon implementing this novel approach. The average satisfaction rates for students were 83 % for Hong Kong SAR and 82 % for Malaysia. This patient-centered clinical decision aid helped to enhance communication between dental students and patients in both regions, ultimately leading to heightened patient satisfaction levels. Nonetheless, to address the present study's limitations, future studies should consider diversifying participant backgrounds, including patients without prior treatment discussions with students. Clinical decision aids are valuable tools in clinical teaching due to their enhancement of communication between clinicians and patients. They promote shared decision-making, leading to more personalized and evidence-driven treatment plans, ultimately improving patient care.

Analysis of the Correlation Between Factors Affecting Green Mining in Open-Pit Mines

Green mining is of great significance for the sustainable development of mines. However, the current green mine evaluation index system proposed in China is complex, and the intrinsic logical relationships between the indicators are not yet clear. To address this issue, this article conducts an in-depth analysis and study of the green mine evaluation index system. First, 16 indicators directly related to mining activities were selected. Then, using data mining technology based on the Apriori algorithm, the actual data of 30 open-pit mines were analyzed, and 7 effective association rules among the green mining indicators of open-pit mines were extracted. The results show that the association rule composed of ecological function requirements, mining technology, and advanced technology and equipment has the highest confidence level, with a confidence of 100% and a support of 68%. Advanced technology and equipment are identified as a key indicator for achieving green mining, playing a role in all 7 association rules. The remaining six effective association rules further emphasize the importance of the compatibility between different mining processes in achieving green mining goals, indicating that green mining is a complex system engineering requiring comprehensive decision making. The effective association rules proposed in this article provide a theoretical basis for mining enterprises to formulate more scientific work plans and thereby achieve green development goals.

The integration of optimizing train timetables with EMU route plans

Generally, to address the resource management issues in high-speed railway operations, particularly in the context of large-scale networked high-speed train transportation organizations, a phased optimization approach is introduced. This approach divides the problem into two stages: the high-speed train timetabling and the planning of Electric Multiple Unit (EMU) route. The lack of direct integration between these stages has hindered the flexible and efficient utilization of line capacity and EMU resources based on large-scale network, limiting the potential for mutual compensation and coordination among different types of resources across different regions. Furthermore, the coupling between interconnected resources has been overlooked. Compared to the aforementioned phased research areas, this study proposes an integrated optimization of train timetables and EMU routing plans in the context of networking. This study is capable of handling a large number of comprehensive optimization decision variables, which increase exponentially as the number of trains and EMUs considered grows. It thoroughly examines the importance of the linkage and coupling relationships between train timetables and EMUs, providing a new feasible method as the theoretical foundation. Adopting a resource linkage perspective, this paper employs complex system modeling, combined with empirical data from actual high-speed rail cases. This approach can significantly shorten the preparation period for high-speed train timetables and EMU routing plans, accelerating the frequency of updates and upgrades to high-speed rail passenger transportation services. To verify the feasibility and effectiveness of the proposed model and method, a case study was conducted on the EMU circulation plan and draft train timetable for the Beijing-Shanghai high-speed railway, with the results analyzed accordingly.

Perceived challenges in treatment decision-making for endometriosis: healthcare professional perspectives

ABSTRACT Background: Endometriosis, a systemic chronic inflammatory condition which has no cure, has a high symptom burden that can negatively impact every facet of life. Given the absence of a gold-standard treatment, the best symptom management regimen in endometriosis is heavily reliant on a patient's values and preferences, making shared decision-making (SDM) vital. However, a comprehensive patient decision aid (PtDA) intervention that could facilitate patient decision-making and promote SDM is lacking in endometriosis, and there is little research on the decisional support needs of individuals with this condition. This qualitative study aimed to explore healthcare professional (HP) perspectives of their clients’ decisional support needs when choosing treatments to manage endometriosis symptoms, with a view to evaluating the need for a PtDA. Methods: Australian HPs identified as specialising in endometriosis care (N = 13) were invited to participate in a short interview over the Internet by phone. Questions focussed on perceived facilitators and challenges of decision-making when choosing treatments for endometriosis. Transcribed qualitative data were thematically analysed and verified by multiple coders, using the template approach. Results: Four themes were identified: (1) Identifying and setting priorities; (2) HPs’ lack of time and perceived lack of knowledge; (3) Patient-centred care and SDM, including patient capacity; and (4) Decision-making blinded by hope. This is the first known study to explore HPs’ perspectives on patient decision-making challenges in endometriosis. Discussion: Findings draw attention to the difficulties people with endometriosis experience when assessing and choosing treatments, highlighting the need for a comprehensive PtDA intervention to support this decision-making.

An efficient method for identifying surface damage in hydraulic concrete buildings

Traditional hydraulic structures rely on manual visual inspection for apparent integrity, which is not only time-consuming and labour-intensive but also inefficient. The efficacy of deep learning models is frequently constrained by the size of available data, resulting in limited scalability and flexibility. Furthermore, the paucity of data diversity leads to a singular function of the model that cannot provide comprehensive decision support for improving maintenance measures. This paper proposes an efficacious methodology for identifying diverse apparent damages in hydraulic structures to address the limitations of existing technologies. The advanced features of apparent damage in hydraulic structures were elucidated by fine-tuning the top-level parameters of the lightweight pre-trained model, thereby mitigating the data dependency issue inherent in the model. Ensemble learning algorithms are employed to classify high-dimensional samples to enhance the accuracy and stability of the classification. However, ensemble learning algorithms are subject to time consuming issues when applied to high-dimensional datasets. To this end, we propose a robust discriminative feature selection model to identify the most salient features, thereby enhancing the performance of apparent damage recognition in hydraulic structures while concurrently reducing the inference time. The results demonstrated that the accuracies of this method in identifying crack, fracture, hole and normal structures were 87.65%, 87.82%, 96.99%, and 95.25%, respectively. This methodology exhibits significant applicability and practical value for the intelligent inspection of hydraulic structures.

Research on Production Process Decision Making Based on Dynamic Programming and Simulated Annealing Algorithm

In this paper, a comprehensive decision model based on dynamic programming and simulated annealing algorithm is constructed to solve the decision optimization problem of an enterprise in the production of popular electronic products. By analyzing each stage of the production process in detail, including parts purchase, inspection, assembly and finished product inspection, and combining the defective rate, inspection cost, market price and return loss and other key parameters of each stage, a scheme for optimizing production decision is formed. In this paper, the dynamic programming method is used to optimize the production path, and the simulated annealing algorithm is introduced to solve the larger scale production planning problem, and the detection and treatment strategy in the production process of enterprises is optimized. Finally, it provides an effective decision-making basis for enterprises to obtain the maximum production profit under uncertain conditions.

Algorithmization of combat operations to extinguish fires in infectious diseases departments of medical institutions

Purpose of research. An analysis of the problems and tasks in conducting combat operations in infectious diseases departments of medical institutions of the country allows us to talk about serious challenges facing the personnel of fire and rescue units. To develop approaches to solving these challenges, it is necessary to determine time periods for disinfection, as well as to formalize a regulatory algorithm for determining the parameters of personal respiratory protection equipment for integration into a decision support system when managing units of the gas and smoke protection service (GDSS) when extinguishing fires.Methods. Analysis of descriptions of fires in medical institutions, numerical methods of mathematical modeling, as well as experimental studies made it possible to establish the average time pressure values in the cylinders of the breathing apparatus of gas and smoke protectors carrying out combat operations to extinguish fires in conditions of possible infection with infectious diseases, as well as the amount of time required for personnel to carrying out appropriate disinfection measures.Results. In the course of the study, the authors found that: the average pressure values in the cylinders of breathing apparatus, which gas and smoke protection service members can use as much as possible when traveling to the fire and working on site, are 170 MPa; the lowest pressure in the cylinders of breathing apparatus when included in the unit is 2600 MPa; the time required to implement disinfection measures ranges from 81 seconds to 429 seconds.Conclusion. Algorithmization of the calculation of air reserves in personal respiratory and vision protection equipment (RPE), a harmonious combination of artificial intelligence and computer vision technologies creates additional prerequisites for the creation of new forms and opportunities for integration into a comprehensive management decision support system for the decision maker at the fire site.

Fostering team adaptivity under uncertain environment: comprehensive decision-making under paradoxical leadership

Fostering team adaptivity under uncertain environment: comprehensive decision-making under paradoxical leadership

Risk prediction of computer investment database information management system based on machine learning algorithms

In recent years, with the continuous development of the financial market, the risk prediction of computer investment database information management systems (IMS) has high practical value. At present, there are risk issues in the information management system, which may cause drawbacks to investment data processing. To address these issues, this article used Machine Learning (ML) algorithms to analyze the risk prediction of computer investment database IMS. This article introduced and utilized typical Self-Organizing Map (SOM) and Artificial Neural Network (ANN) combination algorithms, regression algorithms, and Gradient Boosting Decision Tree (GBDT) algorithms to compare and analyze the prediction accuracy of these three algorithms. This article found that the GBDT algorithm has the highest prediction accuracy. Through a large amount of experimental data, it has been proven that the average testing accuracy using regression algorithms was 3.5% higher than that using neural network algorithms. It was found that the average test accuracy using the GBDT algorithm was 7.2% higher than the average test accuracy using the regression algorithm. The study also explores the combination of physiological and behavioral data collected by wearable devices to provide more comprehensive risk assessment and decision support, which provides an important reference for the optimization of enterprise risk management. Through this innovative data source integration, this paper provides a new perspective for the application and development of machine learning algorithms in computer investment database IMS.

Unsupervised Image Classification Based on Fully Fuzzy Voronoi Tessellation

High noise resistance and high boundary fitting accuracy have always been the goals of image classification. However, the two mutually constrain each other, making it extremely difficult to reach equilibrium. To deal with this problem, the unsupervised image classification algorithm based on fully fuzzy Voronoi tessellation is proposed. It extends Voronoi tessellation from hard to fuzzy, and proposes a hierarchical fuzzy membership model, i.e., pixels fuzzily belong to Voronoi polygons and polygons fuzzily belong to clusters. The objective function is established based on the hierarchical fuzzy membership model by fully considering the transitivity of fuzziness between different levels. Then, the optimal classification result can be obtained by the fuzzy comprehensive decision theory under the best parameter solution. The first level retains the flexibility of pixels while modeling spatial constraints. The second level determines which class the polygon belongs to under the constraint of the first level. It provides an effective way of balancing noise resistance and boundary fitting. In addition, the Voronoi tessellation is explicitly expressed in the objective function in the form of the mathematical model, which allows it to obtain the optimal value through analytical solutions instead of the previous random sampling method. It greatly increases the convergence speed of the algorithm. Experiments have been performed on simulated and several remote sensing images with seven comparing algorithms to demonstrate the effectiveness of the proposed algorithm.

New world of big data - new challenges for evidence synthesis: Impact of data duplication on estimates generated by meta-analyses, and the development of a framework for its identification and management.

The aim of this study was to highlight the effects of entering duplicated or overlapping data from published studies using the same data registries into a meta-analysis, including its identification and management using a novel structured framework. Secondary analysis of data from a proportional meta-analysis of 30-day cumulative incidence of venous thromboembolic events (VTE) after metabolic and bariatric surgery was performed. Sensitivity analysis was conducted a) including all studies regardless of duplication (uncorrected sample) and b) comparing it to a corrected sample of studies. We developed a decision tree framework to identify duplicated data from prospective studies and data registries. We demonstrated that biasing from duplicated data, primarily from data registries, underestimated the incidence of VTE in the literature by 0.15% of the patient population (an erroneous difference equivalent to 22.06% of total VTE). This error persisted at 8.16% of total VTE when limiting to studies using a primarily laparoscopic approach. The decision tree framework used a comparison of the data source (country and hospital or registry), sampling timeframe (dates/years of included data) and inclusion characteristics (included procedures/diagnoses or inclusion criteria) to identify potentially duplicated data. Inter-rater reliability was excellent (κ=1.00, p<0.001), although only 17.86% of studies coded as containing data duplication were be verified by the authors while the remaining studies could not be verified. Lastly, we identified a strong lack of diversity in the geographical origins of the data from the included studies. We demonstrated that including duplicated data in a meta-analysis can result in substantially inaccurate pooled estimates. We outlined a comprehensive decision tree framework that future researchers can apply to assist with decision making when identifying and managing duplicated data, including that from data registries or other publicly accessible datasets.

Economic dispatch of microgrid generation-load-storage based on dynamic bi-level game of multiple stakeholders

During the participation of microgrid operators(MGO) and shared energy storage investors(SEI) in electricity market operations, unclear positioning of shared energy storage(SES) in the trading mechanism leads to decision-making limitations and mutual pricing constraints among stakeholders. Therefore, a dynamic bi-level game model based on multiple stakeholders is established in the paper. Considering the full life cycle investment costs, leasing costs, and load peak-shaving ancillary service revenue, establish a net revenue model for SEI. In the upper level, with SEI as leaders and MGO as followers, establishing a master-slave game model for optimizing SES leasing prices, and formulate leasing strategies. In the lower level, with MGO as leaders and cluster users as followers, establishing a master-slave game model for optimizing electricity prices and formulate scheduling strategies. A hybrid multi-strategy improved whale optimization algorithm based on simulated annealing(HSWMO) is proposed, combined with the theory of fixed points to solve the optimization problem of the upper and lower levels until obtaining the optimal solution that converges to a fixed point. Through case analysis, it is verified that the operational mode of SES as a market entity can bring higher economic benefits to multiple stakeholders such as MGO and cluster users. Meanwhile, the analysis from the perspective of SEI examines the optimal capacity investment and payback period for SES, providing effective reference for the comprehensive decision-making of SEI and MGO.

Photovoltaic DC series arc fault detection method based on two-stage feature comprehensive decision

To address the issue of strong randomness and the difficulty in accurately describing fault features of photovoltaic power generation system series arc, a photovoltaic DC series arc fault detection method based on two-stage feature comprehensive decision is proposed. Firstly, to solve the difficulty in selecting fault detection window size due to the non-periodicity and high randomness of DC signals, a signal windowing strategy based on autocorrelation function is proposed. Based on the transient characteristics of arc initiation stage and the steady-state characteristics of arc burning stage, the whole arc stage is divided into transient stage and steady-state stage. Then, in the arc initiation stage, a transient feature description method based on adjacent windows difference (AWD) is designed on the basis of signal windowing, effectively capturing the waveform mutation caused by arc, achieving the fault occurrence window positioning and the effective expression of transient feature. In the arc burning stage, a steady-state feature description method based on energy difference (ED) is designed on the basis of signal windowing and fault occurrence window positioning, effectively capturing the energy difference caused by arc, achieving a significant expression of steady-state feature, and overcoming the misjudgment issues caused by transient feature. Finally, SVMs are used to classify the proposed features, and voting decision is combined to obtain the arc fault detection results. Experimental results show that the proposed method is feasible and effective in the feature extraction and detection of arc fault, providing a valuable approach for photovoltaic DC series arc fault detection.

ACROPath Oligometastases: The American College of Radiation Oncology Clinical Pathway.

Radiation oncology is among the most data-driven specialties in medicine. Recently, a wealth of peer-reviewed data has been published supporting the treatment of oligometastatic malignancies, demonstrating improved survival with metastasis-directed therapy, such as stereotactic body radiation therapy (SBRT), when combined with appropriate patient selection and treatment. However, there are currently few, if any, established guidelines that synthesize the abundance of data specific to radiotherapy into a single, easily accessed resource for clinicians. ACROPath®is a major initiative of the American College of Radiation Oncology (ACRO) that aims to present aggregated clinical pathway data in a highly usable format that is readily accessible to clinicians at the point of care in real time. The oligometastases pathway is the first published algorithm in this collection, with additional pathways anticipated in future publications.Clinical radiation oncologists with expertise in the treatment and management of oligometastatic disease were recruited from across ACRO's diverse membership, including both academic and private practice physicians, to ensure a broad-based experience and insight. Individual participants were assigned subsections of the pathway for guideline development, and then, each subsection was presented to the full group for evaluation and consensus development based on published data. Rather than presenting an unstructured set of treatment options, as is common in other treatment guidelines, this initiative aimed to categorize appropriate treatments based on published clinical evidence in a hierarchy further ranked by efficacy, toxicity, and cost. Based on these strata, treatment recommendations were collated and grouped into three rank categories (gold, silver, or bronze) to denote the degree of applicability.The team assembled an interactive document that will eventually be available online, and it is summarized in detail here. Recommendations are grouped both by the anatomic site of metastasis and by the primary tumor type, recognizing that original histology might impact the treatment differently in different anatomic locations. After a review of available published clinical evidence, the committee reached a consensus on all recommendations presented, categorizing each option as gold, silver, or bronze to guide clinicians appropriately. This first iteration of ACROPath®Oligometastases represents one of the few comprehensive clinical decision support tools available for managing patients with limited metastatic disease. It presents available data in a highly accessible, easily used reference, which will be formally reviewed and updated by the committee as frequently as emerging data requires, likely at six- to 12-month intervals.

How to make land use policy decisions: Integrating science and economics to deliver connected climate, biodiversity, and food objectives

Land use change is crucial to addressing the existential threats of climate change and biodiversity loss while enhancing food security [M. Zurek et al., Science 376, 1416-1421 (2022)]. The interconnected and spatially varying nature of the impacts of land use change means that these challenges must be addressed simultaneously [H.-O. Pörtner et al., Science 380, eabl4881 (2023)]. However, governments commonly focus on single issues, incentivizing land use change via "Flat-Rate" subsidies offering constant per hectare payments, uptake of which is determined by the economic circumstances of landowners rather than the integrated environmental outcomes that will be delivered [G. Q. Bull et al., Forest Policy Econ. 9, 13-31 (2006)]. Here, we compare Flat-Rate subsidies to two alternatives: "Land Use Scenario" allocation of subsidies through consultation across stakeholders and interested parties; and a "Natural Capital" approach which targets subsidies according to expected ecosystem service response. This comparison is achieved by developing a comprehensive decision support system, integrating new and existing natural, physical, and economic science models to quantify environmental, agricultural, and economic outcomes. Applying this system to the United Kingdom's net zero commitment to increase carbon storage via afforestation, we show that the three approaches result in significantly different outcomes in terms of where planting occurs, their environmental consequences, and economic costs and benefits. The Flat-Rate approach actually increases net carbon emissions while Land Use Scenario allocation yields poor economic outcomes. The Natural Capital targeted approach outperforms both alternatives, providing the highest possible social values while satisfying net zero commitments.

Domain generalization through latent distribution exploration for motor imagery EEG classification

Electroencephalography (EEG)-based Motor Imagery (MI) brain-computer interface (BCI) systems play essential roles in motor function rehabilitation for patients with post-stroke. Existing neural networks for decoding MI EEG face challenges due to nonstationary characteristics and subject-specific variations of EEG data. To address these challenges and improve generalization performance, this study proposes a domain generalization (DG) model that eliminates the need for user-specific calibration in real-life applications. Specifically, the proposed model comprises two branches: the first branch applies several independent decision-making networks to decode and classify subjects’ motor intentions, while the second branch adaptively assigns weights to classification results and fuses them into a comprehensive decision. Both branches utilize EEGNet and ShallowConvNet to extract time-frequency-spatial features. By implementing multiple classification networks, the model can learn a broad range of data distributions from source subjects, which contributes to improved generalization performance on target subjects. The proposed EEG-DG framework was evaluated on BCI Competition IV Dataset 2a, 2b and PhysioNet. Results show that the proposed framework significantly enhances the classification performance of MI EEG, outperforming several state-of-the-art models on all three datasets, underlining its superior efficacy in real-world scenarios and exceptional generalization performance. The source code can be accessed at https://github.com/DrugLover/Multibranch-DG-EEG.

Predicting Electric Vehicle Charging Demand in Residential Areas Using POI Data and Decision‐Making Model

Transport electrification is a crucial element of the ongoing energy transition, essential for achieving carbon peaking and carbon neutrality goals. The proliferation of electric vehicles (EVs) introduces significant challenges to power distribution network stability due to their aggregated charging load in residential areas, particularly during peak electricity consumption periods. This paper proposes a method to predict the spatiotemporal distribution of EV charging demand in residential areas using geographic information points of interest (POI) data features and a decision‐making model. Utilizing real historical data, probability distribution models for EV users' arrival times and charging characteristics were constructed using Gaussian Mixture Models (GMM). The spatiotemporal characteristics of EV travel and charging behaviors were analyzed, and a comprehensive charging decision model incorporating both emergency and stochastic scenarios was developed. The model's efficacy in capturing the probability distributions of characteristic variables was validated through a case study. The results demonstrate the model's potential for accurately predicting EV charging demand, providing valuable insights for infrastructure planning and resource allocation. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

Human-like Decision Making for autonomous lane change driving: a hybrid inverse reinforcement learning with game-theoretical vehicle interaction model

The development of automated driving vehicles aims to provide safer, comfortable, and more efficient mobility options. However, the decision-making control of autonomous vehicles still embraces limitations on human performance mimicry. These limitations become particularly evident in complex and unfamiliar driving scenarios, where weak decisionmaking abilities and poor adaptation of vehicle behaviour are prominent issues. This paper proposes a game-theoretic decisionmaking algorithm for human-like driving in the vehicle lane change scenario. Firstly, an inverse reinforcement learning (IRL) model is used to quantitatively analyse the lane change trajectories of the natural driving dataset, establishing the human-like human cost function. Subsequently, joint safety, comfort to build the comprehensive decision cost function. Use the combined decision cost function to conduct a non-cooperative game of vehicle lane changing decision to solve the optimal decision of host vehicle lane changing. The host vehicle lane-changing decision problem is formulated as a Stackelberg game optimization problem. To verify the feasibility and effectiveness of the algorithm proposed in this study, a lane change test scenario has been established. Firstly, we analyse the human-like decision-making model derived by the maximum entropy inverse reinforcement learning algorithm to verify the effectiveness and robustness of the IRL algorithm. Secondly, the human-like game decisionmaking algorithm in this paper is validated by conducting an interactive lane-changing experiment with obstacle vehicles of different driving styles. The experimental results prove that the human-like driving decision-making model proposed in this study can make lane-changing behaviours in line with human driving patterns in lane-changing scenarios of expressway.