Applying the multiphase optimization strategy to evaluate the feasibility and effectiveness of an online road safety education intervention for children and parents: a pilot study.

BACKGROUND: Reports of children's engagement in active transportation outline low participation rates in many countries despite many associated mental, physical, and social health benefits. One of the main contributors to this phenomenon is a cited lack of education and knowledge among children regarding active travel (AT), specifically road safety. To address this issue, the aim of this study was to evaluate the feasibility and effectiveness of an online road safety education intervention to promote AT among children and their parents. METHODS: Applying the Multiphase Optimization Strategy (MOST) for intervention development, implementation, and evaluation, we designed and assessed a four-module online road safety education intervention with a sample of 57 parent-child dyads using a 23 factorial design featuring both qualitative and quantitative analyses. RESULTS: Main intervention feasibility findings include positive and critical feedback on the program's content and design, and moderate participant engagement as reflected by program retention and completion rates. With respect to the preliminary intervention effectiveness on children, a significant improvement in road safety knowledge scores was observed for groups that feature the "wheeling safety and skills" module. Slight improvements in AT knowledge scores across all the intervention groups were observed, but were not of significance. Preliminary intervention effectiveness on select parental AT practices and perceptions saw significant improvements in some groups. Groups that featured the 'wheeling safety and skills' module exhibited significantly higher guided choice scores upon completion of the program than those who did not receive this component. CONCLUSION: The MOST framework allowed us to design and evaluate the feasibility and preliminary effectiveness of an online road safety education intervention. The developed intervention has demonstrated that it has the potential to improve children's road safety knowledge and some areas of parental AT practices and perceptions, to which improvements may be attributed to the inclusion of the "wheeling safety and skills" module, suggesting that the targeted focus on cycling skills is a prioritized area. AT programming and practice implications are discussed. Future research is encouraged to refine modules to better reflect the priorities of children and parents and to test these refined components among larger samples. WORD COUNT: 9,391 (excludes abstract, tables, figures, abbreviations, and references).

Decentralising the Self - Ethical Considerations in Utilizing Decentralised Web Technology for Direct Brain Interfaces.

The rapidly advancing field of brain-computer (BCI) and brain-to-brain interfaces (BBI) is stimulating interest across various sectors including medicine, entertainment, research, and military. The developers of large-scale brain-computer networks, sometimes dubbed 'Mindplexes' or 'Cloudminds', aim to enhance cognitive functions by distributing them across expansive networks. A key technical challenge is the efficient transmission and storage of information. One proposed solution is employing blockchain technology over Web 3.0 to create decentralised cognitive entities. This paper explores the potential of a decentralised web for coordinating large brain-computer constellations, and its associated benefits, focusing in particular on the conceptual and ethical challenges this innovation may pose pertaining to (1) Identity, (2) Sovereignty (encompassing Autonomy, Authenticity, and Ownership), (3) Responsibility and Accountability, and (4) Privacy, Safety, and Security. We suggest that while a decentralised web can address some concerns and mitigate certain risks, underlying ethical issues persist. Fundamental questions about entity definition within these networks, the distinctions between individuals and collectives, and responsibility distribution within and between networks, demand further exploration.

Perceptions of safety during everyday travel shaping older adults' mobility in Bengaluru, India.

BACKGROUND: In the context of socially sustainable urban development, comfortable, safe, and accessible public transport is crucial to motivating people to travel more sustainably. Using the framework given by Masoumi and Fastenmeier (2016) to examine the concepts of safety and security, we explore how perceptions of safety about different transport modes shaped the mobility of older adults in Bengaluru, India. METHODS: In-depth telephonic interviews were conducted with 60 adults, aged 50 years and over, residing in urban Bengaluru, using a semi-structured in-depth interview guide to explore the perceptions of safety in different transport modes. Observations were conducted prior to the COVID-19 pandemic. Applying thematic analysis, we present how the perceptions of safety during their everyday travel shaped their mobility. RESULTS: According to our research, older adults' perception of safety during their everyday travel is shaped by past negative experiences with accidents, pickpocketing, theft of mobile phones, and chain snatching. In addition, the Covid-19 pandemic exacerbated the already existing inequalities, further limiting older adults' mobility to carry out regular activities such as buying groceries, socialising, making a hospital visit, or going to work due to the fear of getting infected. CONCLUSION: Our findings indicate that the use of public transport needs to be encouraged among older adults by enhancing necessary safety features following the age-friendly cities framework. Furthermore, it can help policymakers develop transport polices, which suit the mobility needs of older adults.

Investigating the influence of streetscape environmental characteristics on pedestrian crashes at intersections using street view images and explainable machine learning.

Examining the relationship between streetscape features and road traffic accidents is pivotal for enhancing roadway safety. While previous studies have primarily focused on the influence of street design characteristics, sociodemographic features, and land use features on crash occurrence, the impact of streetscape features on pedestrian crashes has not been thoroughly investigated. Furthermore, while machine learning models demonstrate high accuracy in prediction and are increasingly utilized in traffic safety research, understanding the prediction results poses challenges. To address these gaps, this study extracts streetscape environment characteristics from street view images (SVIs) using a combination of semantic segmentation and object detection deep learning networks. These characteristics are then incorporated into the eXtreme Gradient Boosting (XGBoost) algorithm, along with a set of control variables, to model the occurrence of pedestrian crashes at intersections. Subsequently, the SHapley Additive exPlanations (SHAP) method is integrated with XGBoost to establish an interpretable framework for exploring the association between pedestrian crash occurrence and the surrounding streetscape built environment. The results are interpreted from global, local, and regional perspectives. The findings indicate that, from a global perspective, traffic volume and commercial land use are significant contributors to pedestrian-vehicle collisions at intersections, while road, person, and vehicle elements extracted from SVIs are associated with higher risks of pedestrian crash onset. At a local level, the XGBoost-SHAP framework enables quantification of features' local contributions for individual intersections, revealing spatial heterogeneity in factors influencing pedestrian crashes. From a regional perspective, similar intersections can be grouped to define geographical regions, facilitating the formulation of spatially responsive strategies for distinct regions to reduce traffic accidents. This approach can potentially enhance the quality and accuracy of local policy making. These findings underscore the underlying relationship between streetscape-level environmental characteristics and vehicle-pedestrian crashes. The integration of SVIs and deep learning techniques offers a visually descriptive portrayal of the streetscape environment at locations where traffic crashes occur at eye level. The proposed framework not only achieves excellent prediction performance but also enhances understanding of traffic crash occurrences, offering guidance for optimizing traffic accident prevention and treatment programs.

Enhancing highway transportation safety resilience during emergencies: A network-based analysis and assessment.

In order to evaluate the impact of emergencies on the resilience of highway transportation, a resilience network hierarchical model of the highway transportation system was constructed by analyzing the formation and emergence process of safety resilience in the highway transportation system. Four layers of networks were divided, including highway network, transport network, traffic network, and emergency network. Combined with the network hierarchical model, a resilience evaluation index system was designed, and an assessment method for highway transportation systems based on the fuzzy analytic hierarchy process(FAHP) was proposed. Finally, a case study of a public health emergency in a region of Hunan was carried out. The results show that the proposed method for evaluating the safety resilience of highway transportation systems can better reflect the overall resilience under public health emergencies, which is consistent with the quantitative analysis results through the system resilience curve. It helps to accurately evaluate the safety resilience of the system. At the same time, this method has the advantages of flexibility and simplicity in solving unstructured decision-making problems of the system, which helps to improve the safety production management and safety resilience level of highway transportation systems. In the future, the scope of research scenarios and regions can be expanded, and further analysis of the evolution of safety resilience and the ability of resilience development in different stages under external disturbances can be conducted in order to further explore and optimize the resilience of the system.

Exploring road safety using alignment perspective features in real driving images: A case study on mountain freeways.

INTRODUCTION: While driving, drivers frequently adapt their driving behaviors according to their perception of the road's alignment features. However, traditional two-dimensional alignment methods lack the ability to capture these features from the driver's perspective. METHOD: This study introduces a novel method for road alignment recognition, employing image recognition technology to extract alignment perspective features, namely alignment perspective skewness (APS) and alignment perspective kurtosis (APK), from in-real driving images. Subsequently, the K-means clustering algorithm is utilized for road segment classification based on APS and APK indicators. Various sliding step length for clustering are employed, with step length ranging from 100m to 400m. Furthermore, the accident rates for different segment clusters are analyzed to explore the relationship between alignment perspective features and traffic safety. A 150 km mountain road section of the Erlianhaote-Guangzhou freewway from Huaiji to Sihui is selected as a case study. RESULTS: The results demonstrate that using alignment perspective features as classification criteria produces favorable clustering outcomes, with superior clustering performance achieved using shorter segment lengths and fewer cluster centers. The road segment classification based on alignment perspective features reveals notable differences in accident rates across categories; while traditional two-dimensional parameters-based classification methods fail to capture these differences. The most significant differences in accident rates across categories are observed with segment length of 100m, with the significance gradually diminishing as segment length increases and disappearing entirely when the length exceeds 300m. IMPLICATION: These findings validate the reliability of using alignment perspective features (APS and APK) for road alignment classification and road safety analysis, providing valuable insights for road safety management.

Adjusting vehicle secondary safety ratings to account for crash-avoidance technology fitment using real-world crash and injury data.

OBJECTIVES: Publicizing safety ratings of vehicles can motivate manufacturers to prioritize safety and help consumers choose safer vehicles, leading to safer fleets. The benefits of primary safety technologies that prevent crash occurrence are not currently incorporated in current ratings in a way that values their safety benefits consistently. We aimed to propose a method for assigning weights for each safety technology to account for established safety benefits using published effectiveness and prevalence from real-life data. METHODS: To illustrate this method, we present a worked example calculated using crash and injury data from Australia and New Zealand. The method proposed attenuates the weights for given safety technologies where two or more safety technologies fitted to the same vehicle are effective for the same types of crashes. RESULTS: In the worked example using Australasian data, large SUVs were estimated to have the largest safety increment from the fitment of all the technologies considered compared to vehicles without these primary safety technologies, with an almost 17% reduction in crash occurrence. Cars with all the technologies fitted had estimated average crash reduction of between 11% and 12%. CONCLUSIONS: Different market groups have different crash patterns, so the safety attributable to safety technology fitment differs at the market group level. This study presents an approach for providing a summary measure of crash avoidance according to the fitment of safety technologies. If this measure is combined with an estimate of secondary safety (whether derived from existing crash and injury data or from new car crash assessment programs), the combined estimate then represents the important elements of safety provided by the vehicle. The methods presented here form a rational basis for assigning safety ratings to represent the benefits of swiftly developing safety technologies.

The sense of security of Ukrainians and Belarusians studying in Poland.

INTRODUCTION AND OBJECTIVE: Due to educational migration to Poland, students from Ukraine and Belarus may experience security to varying degrees. The aim of the study was to check the extent to which people from Ukraine and Belarus studying in Lublin feel safe, taking into account their own life and health. An attempt was also made to establish the relationship between the sense of security and selected features of the surveyed students. MATERIAL AND METHODS: The research was conducted using a survey method among 403 students from Ukraine, Belarus and Poland. Eight independent variables were introduced into the analysis of relationships: gender, age, self-assessment of the financial situation, country of origin, place of origin, place of residence during studies, and year of study. The dependency analysis used Wilcoxon and Kruskal-Wallisau tests and CATREG optimal scaling analysis. RESULTS: The study showed that both Polish and foreign students assessed the level of safety in Poland and during their studies in Lublin as high. They feel safer during the day than after dark. Polish students are more afraid of theft, rape and being hit by a car than students from Belarus and Ukraine, and students from Ukraine are more afraid of verbal abuse. The predictors influencing students' sense of insecurity are, among others, their financial situation and gender. CONCLUSIONS: The conducted research and analysis of the obtained results suggest that the situation of students from Ukraine and Belarus studying in Lublin, Poland, in terms of safety, is similar to that of Polish students, and even better in some aspects. This result suggests that Lublin is a friendly academic centre for students from across the eastern border of Poland.

Firearm Storage Behaviors - Behavioral Risk Factor Surveillance System, Eight States, 2021-2022.

Secure firearm storage might help reduce access by children and other unauthorized users and the related risk for injury or death. Information about state-specific prevalence of firearm storage practices can be used to develop secure storage messages and programs; however, such information is often unavailable. Data from the Behavioral Risk Factor Surveillance System, by respondent characteristics, were used to estimate prevalence of keeping firearms in or around the home and related storage practices for eight states that administered the firearm safety module in 2021 or 2022. Overall, 18.4% (California) to 50.6% (Alaska) of respondents reported that a firearm was kept in or around their home. Among those with a firearm in or around the home, 19.5% (Minnesota) to 43.8% (North Carolina) reported that a firearm was stored loaded. Across all eight states, approximately one half of those with a loaded firearm stored at least one loaded firearm unlocked. Among respondents with a child and a loaded firearm in the home, 25.2% (Ohio) to 41.4% (Alaska) reported that a loaded firearm was stored unlocked. Variability in firearm storage practices highlights the importance of local data and suggests opportunities to tailor prevention efforts to specific population groups to reduce risk for firearm handling by children without adult supervision, and other unauthorized persons.

A matched case-control analysis of autonomous vs human-driven vehicle accidents.

Despite the recent advancements that Autonomous Vehicles have shown in their potential to improve safety and operation, considering differences between Autonomous Vehicles and Human-Driven Vehicles in accidents remain unidentified due to the scarcity of real-world Autonomous Vehicles accident data. We investigated the difference in accident occurrence between Autonomous Vehicles' levels and Human-Driven Vehicles by utilizing 2100 Advanced Driving Systems and Advanced Driver Assistance Systems and 35,113 Human-Driven Vehicles accident data. A matched case-control design was conducted to investigate the differential characteristics involving Autonomous' versus Human-Driven Vehicles' accidents. The analysis suggests that accidents of vehicles equipped with Advanced Driving Systems generally have a lower chance of occurring than Human-Driven Vehicles in most of the similar accident scenarios. However, accidents involving Advanced Driving Systems occur more frequently than Human-Driven Vehicle accidents under dawn/dusk or turning conditions, which is 5.25 and 1.98 times higher, respectively. Our research reveals the accident risk disparities between Autonomous Vehicles and Human-Driven Vehicles, informing future development in Autonomous technology and safety enhancements.

Child pedestrian safety training in virtual reality: How quickly do children achieve adult functioning and what individual differences impact learning efficiency?

INTRODUCTION: Pedestrian injuries represent a leading cause of child death globally. One prevention strategy is teaching children street-crossing skills. Virtual reality (VR) has emerged as a strategy to offer repeated street-crossing practice and overcome ethical barriers of training children in live traffic. This study addressed two questions pertinent to implementation of child pedestrian safety training within VR: (a) how much training do children require to achieve adult street-crossing competency, and (b) what individual differences might facilitate children to acquire that competency more efficiently? METHODS: Five hundred 7- and 8-year-olds were recruited. Children completed pedestrian safety training within VR for up to 25 thirty-minute training sessions until they achieved adult levels of mastery. At baseline, four cognitive-perceptual skills (visual memory, visual perception, processing speed, working memory) and parent-reported externalizing symptomatology were assessed. RESULTS: On average, children achieved adult pedestrian safety competency after 10.0 training sessions (SD = 4.8). Just one child (<1%) failed to achieve adult pedestrian functioning after 25 training sessions. In univariate analyses, boys took slightly longer than girls to achieve adult functioning, and visual memory, visual perception, processing speed, working memory, and fewer externalizing symptoms were all positively associated with shorter time to mastery. In a multivariable model, only child age was a statistically significant predictor. CONCLUSION: Almost all participants achieved adult street-crossing skills competency through VR training, although they required about 10 sessions on average. Analysis of predictor variables confirmed that nearly all 7- and 8-year-olds are trainable. PRACTICAL APPLICATION: Implementation of VR pedestrian safety training is recommended, but must be conducted cautiously to ensure children are not permitted to engage independently in traffic until they are assessed and demonstrate sufficient skills.

Beyond 1D and oversimplified kinematics: A generic analytical framework for surrogate safety measures.

This paper presents a generic analytical framework tailored for surrogate safety measures (SSMs) that is versatile across various highway geometries, capable of encompassing vehicle dynamics of differing dimensionality and fidelity, and suitable for dynamic, real-world environments. The framework incorporates a generic vehicle movement model, accommodating a spectrum of scenarios with varying degrees of complexity and dimensionality, facilitating the estimation of future vehicle trajectory evolution. It establishes a generic mathematical criterion to denote potential collisions, characterized by the spatial overlap between a vehicle and any other entity. A collision risk is present if the collision criterion is met at any non-negative estimated future time point, with the minimum threshold representing the remaining time to collision. The framework's proficiency spans from conventional one-dimensional (1D) SSMs to extended multi-dimensional, high-fidelity SSMs. Its validity is corroborated through simulation experiments that assess the precision of the framework when linearization is performed on the vehicle movement model. The outcomes showcase remarkable accuracy in estimating vehicle trajectory evolution and the time remaining before potential collisions occur, comparing to high-accuracy numerical integration solutions. The necessity of higher-dimensional and higher-fidelity SSMs is highlighted through a comparison of conventional 1D SSMs and extended three-dimensional (3D) SSMs. The results showed that using 1D SSMs over 3D SSMs could be off by 300% for Time-to-Collision (TTC) values larger than 1.5 s and about 20% for TTC values below 1.5 s. In other words, conventional 1D SSMs can yield highly inaccurate and unreliable results when assessing collision proximity and substantially misjudge the count of conflicts with predefined threshold (e.g., below 1.5s). Furthermore, the framework's practical application is demonstrated through a case study that actively evaluates all potential conflicts, underscoring its effectiveness in dynamic, real-world traffic situations.

Accustomed or Regulated: Influencing factors of two-wheeler riders' illegal Lane-Transgressing behavior when overtaking.

Illegal lane-transgressing is a typical aberrant riding behavior of riders of two-wheelers, i.e., motorcycles, bicycles, and e-bikes, which is highly frequent in accident reports. However, there is insufficient attention to this behavior at present. This study aims to explore the socio-psychologic factors that influence the illegal lane-transgressing behavior of two-wheeler riders when overtaking. For this purpose, a questionnaire was first composed. The questionnaire included the behavioral intention of two-wheeler riders towards illegal overtaking behavior and five influencing factors: safety knowledge, descriptive norms, injunctive norms, perceived behavior control, and risk perception. Second, a survey was conducted on different two-wheeler riders in Xi'an. Third, various types of two-wheelers were analyzed jointly and separately by structural equation models and analyses of variance. Results show that e-bike riders were more similar to motorcycle riders in behavioral intentions, with their risk perception weaker than other riders. Descriptive norms and perceived behavior control played the most significant roles in the structural equation model. It was also found that two-wheeler riders with a car license had better traffic safety performance. Based on the above results, it is recommended that attention be paid to illegal lane-transgression in the process of law enforcement and education, and a higher level of safety training should be provided for two-wheeler riders.

The generalization of threat beliefs to novel safety stimuli induced by safety behaviors.

Safety behaviors are responses that can reduce or even prevent an expected threat. Moreover, empirical studies have shown that using safety behaviors to a learnt safety stimulus can induce threat beliefs to it. No research so far has examined whether threat beliefs induced this way generalize to other novel stimuli related to the safety stimulus. Using a fear and avoidance conditioning model, the current study (n=116) examined whether threat beliefs induced by safety behaviors generalize to other novel generalization stimuli (GSs). Participants first acquired safety behaviors to a threat predicting conditioned stimulus (CSthreat). Safety behaviors could then be performed in response to one safe stimulus (CSsafeShift) but not to another (CSsafe). In a following generalization test, participants showed a significant but small increase in threat expectancies to GSs related to CSsafeShift compared to GSs related to CSsafe. Interestingly, the degree of safety behaviors used to the CSsafeShift predicted the subsequent increase in generalized threat expectancies, and this link was elevated in trait anxious individuals. The findings suggest that threat beliefs induced by unnecessary safety behaviors generalize to other related stimuli. This study provides a potential explanation for the root of threat belief acquisition to a wide range of stimuli or situations.

Vehicle Lane-Changing scenario generation using time-series generative adversarial networks with an Adaptative parameter optimization strategy.

Connected and automated vehicles (CAVs) hold promise for enhancing transportation safety and efficiency. However, their large-scale deployment necessitates rigorous testing across diverse driving scenarios to ensure safety performance. In order to address two challenges of test scenario diversity and comprehensive evaluation, this study proposes a vehicle lane-changing scenario generation method based on a time-series generative adversarial network (TimeGAN) with an adaptive parameter optimization strategy (APOS). With just 13.3% of parameter combinations tested, we successfully trained a satisfactory TimeGAN and generate a substantial number of lane-changing scenarios. Then, the generated scenarios were evaluated for diversity, fidelity, and utility, demonstrating their effectiveness in capturing a wide range of driving situations. Furthermore, we employed a Lane-Changing Risk Index (LCRI) to identify the rare adversarial cases in scenarios. Compared to real scenarios, our approach generates 27 times more adversarial cases with 1.8 times higher average risk, highlighting its potential for uncovering critical safety vulnerabilities. This study paves the way for more comprehensive and effective CAV testing, ultimately contributing to safer and more reliable autonomous driving technologies.

Cyclist safety around trams: A market survey.

Tram systems present safety risks to cyclists, however only limited research has explored this topic, of which most has focused on crash and hospital data, and severe crash events. This paper presents the first known cyclist market survey focused specifically on the experience of cyclists related to safety around trams, including unreported incidents and those that did not result in hospital attendance. Findings suggest that track-skid incidents are more common than track-wedge incidents, in contrast to previous research that emphasizes track-wedging as a larger issue than skidding. This is may be explained by the differing outcomes, with track-wedging more likely to result in injury. This research is thus significant in identifying track skidding as a major risk concern, causing a majority of crashes, while also confirming that track wedging is the major severity concern. In the last five years, 21% of respondents were involved in at least one tram-track-related crash. This was less than the share of respondents involved in falls (50%), crashes relating to road defects (36%) or collisions with motor vehicles (29%). However, half of survey respondents (52%) reported cycling on roads with tram tracks for 0-20% of their cycling, which might suggest that tram track-related crash rates are high given that most inner-city cycling occurs on roads without tracks. Track-skidding was found to be associated with wet conditions. Those involved in at least one track-skid in the last five years where more likely to have been cycling more than 3 years, but involvement in track-wedging was more likely amongst those cycling > 10 years and aged < 45 years. Implications for research and practice are suggested.

Study on the risk assessment of Pedestrian-Vehicle conflicts in channelized Right-Turn lanes based on the Hierarchical-Grey Entropy-Cloud model.

Channelized right-turn lanes (CRTLs) in urban areas have been effective in improving the efficiency of right-turning vehicles but have also presented negative impacts on pedestrian movement. Pedestrians experience confusion regarding the allocation of road space when crossing crosswalks within these areas, leading to frequent conflicts between pedestrians and motor vehicles. In this paper, considering the characteristics of pedestrian-vehicle conflicts at channelized right-turn lanes as well as the ambiguity and uncertainty of the causes, a comprehensive assignment combined with a cloud model is proposed as a risk evaluation model for pedestrian-vehicle conflicts. The study established a risk indicator system based on three aspects of the transportation system: pedestrians, motor vehicles, and the road environment. Combining the analytic hierarchy process (AHP), grey relational analysis (GRA), and entropy weighting method (EWM) to get the weights of indicator combinations, and then using the cloud model to realize quantitative and qualitative language transformation to complete the risk evaluation. This study employs specific road segments in Qingdao as a validation case for model analysis. The results indicate that the model's evaluation outcomes exhibited a significant level of agreement with the findings from field investigations during both peak and off-peak periods. It is demonstrated that the model has good performance for the safety assessment of pedestrian-vehicle conflicts at CRTL, and it also reflects the ability of the model to assess fuzzy randomness problems. It provides participation value for urban pedestrian-vehicle safety problems as well as applications in other fields.

A modeling method for two-dimensional two-wheeler driving behavior during severe conflict interaction at intersections.

The safety of two-wheelers is a serious public safety issue nowadays. Two-wheelers usually have severe conflict interaction with vehicles at intersections, such as running red lights, which is very likely to cause traffic accidents. Therefore, a model of two-wheeler driving behavior in conflicting interactions can provide guidance for traffic safety management on one hand, and can be used for the development and testing of autonomous vehicles on the other. However, the existing models perform poorly when interacting with vehicles. To address the problems, this paper proposes a modeling method (an improved social force model, ISFM) for two-dimensional two-wheeler driving simulation for conflict interaction at intersections. Based on analysis of naturalistic driving study data, when two-wheelers encounter with vehicles, their driving intentions and trajectories can be categorized into two groups, which are yielding and overtaking. Therefore, the vehicle-related social forces are designed to be a set of two forces rather than a repulsion force in original SFM, which is a yielding force based on the relative distance between the two-wheeler and the vehicle, and an overtaking force based on the velocity of the two-wheeler itself. This opens up the possibilities for modeling the multi-modal driving intention of two-wheelers encountering with cross traffic. Based on ISFM, a bicycle model, a powered two-wheeler (PTW) model and a model of a group of PTWs, are then constructed. Compared to the original SFM, ISFM increases the precision of driving intention prediction by 19.7 % (yielding situation) and 25.0 % (overtaking situation), and reduces the root mean square error between simulated and actual trajectories by 7.8 % and 14.8 % on the bicycle model and the PTW model, respectively. Meanwhile, the model of a group of PTWs also performs well. Finally, the results of ablation experiments also validate the effectiveness of the social force designed based on velocity.