Random Parameters Research Articles

Effect of vault on predicting postoperative refractive error for posterior chamber phakic intraocular lens based on a machine learning model

Purpose: To investigate how vault and other biometric variations affect postoperative refractive error of implantable collamer lenses (ICLs) by integrating artificial intelligence and modified vergence formula. Setting: Eye and ENT Hospital of Fudan University, Shanghai, China. Design: Artificial intelligence and big data-based prediction model. Methods: 2845 eyes that underwent uneventful spherical ICL or toric ICL implantation and with manifest refraction results 1 month postoperatively were included. 1 eye of each patient was randomly included. Random forest was used to calculate the postoperative sphere, cylinder, and spherical equivalent by inputting variable ocular parameters. The influence of predicted vault and modified Holladay formula on predicting postoperative refractive error was analyzed. Subgroup analysis of ideal vault (0.25 to 0.75 mm) and extreme vault (<0.25 mm or >0.75 mm) was performed. Results: In the test set of both ICLs, all the random forest-based models significantly improved the accuracy of predicting postoperative sphere compared with the Online Calculation & Ordering System calculator (P < .001). For ideal vault, the combination of modified Holladay formula in spherical ICL exhibited highest accuracy (R = 0.606). For extreme vault, the combination of predicted vault in spherical ICL enhanced R values (R = 0.864). The combination of predicted vault and modified Holladay formula was most optimal for toric ICL in all ranges of vault (ideal vault: R = 0.516, extreme vault: R = 0.334). Conclusions: The random forest-based calculator, considering vault and variable ocular parameters, illustrated superiority over the existing calculator on the study datasets. Choosing an appropriate lens size to control the vault within the ideal range was helpful to avoid refractive surprises.

Analysis of Factors Affecting the Severity of Injuries in Electric Two-Wheeled Vehicle Crashes with or without Violation: A Random Parametric Logit Model considering Heterogeneity of Means and Variances

Electric two-wheeled vehicle is one of the main commuting tools in China, but they are also more likely to have violations of the road group. In order to study the effect of the presence of violation on the severity of road traffic crashes among electric two-wheeler riders, in this study, the effects of rider characteristics, road characteristics, collision characteristics, and environmental characteristics on the severity of injuries of electric two-wheeled vehicle riders were considered separately analyzed based on the data of 6403 two-wheeled electric vehicle traffic crashes in a region of Shandong Province from 2015 to 2021, and a random parametric logit model considering the heterogeneity of the mean and the variance (RP-HMV logit) was established based on the presence or absence of violation behaviors of riders, respectively, in order to explore unobserved heterogeneity. In order to test the validity of the model for modeling the injury severity of pedestrians riding electric two-wheelers, multinomial logit (MN-logit model), and random parameter logit model (RP-logit) were estimated, and the results showed that the RP-HMV logit model was significantly superior in terms of goodness of fit. The study showed that some of the factors differed somewhat between the two scenarios, such as gender, while the factors that were significant in both scenarios were >60, broken pavement, street lights at night, no street lights at night, mixed motorized and nonmotorized lanes, sidewalks, other angles, no control, severe weather, and visibility <200 m, where the severe weather and visibility <200 m were random parameters obeying normal distributions, there is a significant difference between having street lights and no control at night in both scenarios, and the difference is significant. The results of the study can provide a reference for the development of targeted countermeasures to improve the traffic safety of electric two-wheeled vehicles in China.

An error components mixed logit with heterogeneity in means and variance for fixed object occupant severity outcomes

This paper presents an error components mixed logit with heterogeneity in means and variance to capture the heterogeneous effects of contributing factors on fixed object occupant severity. One year (2021) of crash data on fixed object related crashes in Lubbock County, Texas was analyzed with fixed object details extracted from crash narratives and classified into 11 groupings. Crash data included any fixed object collision occurring at any point in the sequence of crash events (not exclusive to the first harmful event). The random parameters were identified as indicators for occupant involvement in the first harmful crash sequence event, with that event being collision with a fixed object, for possible injury and injury severity outcomes. Heterogeneity in the means of these random parameters was found with respect to six different indicator variables. Additionally, heterogeneity in the variance of the injury random parameter was found with respect to two different indicator variables. Inclusion of two error component nests improved prediction accuracy at the observation level for higher severity outcomes. The findings in this study suggest that fixed object classification types should be explored further in relation to heterogeneous effects on occupant severity outcomes. Furthermore, the findings also highlight the applicability of an error components mixed logit model for severity analysis.

Understanding Clinician Preferences for Treatment Attributes in Oncology: A Discrete Choice Experiment of Oncologists' and Urologists' Preferences for First-Line Treatment of Locally Advanced/Unresectable Metastatic Urothelial Carcinoma in Five European Countries.

Prior discrete choice experiments (DCE) in oncology found that, on average, clinicians rank survival as the most important treatment attribute. We investigate heterogeneity in clinician preferences within the context of first-line treatment for advanced urothelial carcinoma in Spain, France, Italy, Germany, and the UK. The online DCE included 12 treatment choice tasks, each comparing two hypothetical therapy profiles defined by treatment attributes: grade 3/4 treatment-related adverse events (TRAEs), induction and maintenance administration schedules, progression-free survival, and overall survival (OS). We used a random parameters logit model to estimate attribute relative importance (RI) (0-100%) and generate preference shares for four treatment profiles. Results were stratified by country. Preference heterogeneity was evaluated by latent class analysis. In August and September 2022, 498 clinicians (343 oncologists and 155 urologists) completed the DCE. OS had the strongest influence on clinicians' preferences [RI = 62%; range, 51.6% (Germany) to 63.7% (Spain)] followed by frequency of grade 3/4 TRAEs (RI = 27%). Among treatment profiles, the chemotherapy plus immune checkpoint inhibitor maintenance therapy profile had the largest preference share [51%; range, 38% (Italy) to 56% (UK)]. Four latent classes of clinicians were identified (N = 469), with different treatment profile preferences: survival class (30.1%), trade-off class (22.4%), no strong preference class (40.9%), and aggressive treatment class (6.6%). OS was not the most important attribute for 30.0% of clinicians. While average sample results were consistent with those of prior DCEs, this study found heterogeneity in clinician preferences within and across countries, highlighting the diversity in clinician decision making in oncology.

Load Forecasting and Operation Optimization of Ice-Storage Air Conditioners Based on Improved Deep-Belief Network

The prediction of cold load in ice-storage air conditioning systems plays a pivotal role in optimizing air conditioning operations, significantly contributing to the equilibrium of regional electricity supply and demand, mitigating power grid stress, and curtailing energy consumption in power grids. Addressing the issues of minimal correlation between input and output data and the suboptimal prediction accuracy inherent in traditional deep-belief neural-network models, this study introduces an enhanced deep-belief neural-network combination prediction model. This model is refined through an advanced genetic algorithm in conjunction with the “Statistical Products and Services Solution” version 25.0 software, aiming to augment the precision of ice-storage air conditioning load predictions. Initially, the input data undergo processing via the “Statistical Products and Services Solution” software, which facilitates the exclusion of samples exhibiting low coupling. Subsequently, the improved genetic algorithm implements adaptive adjustments to surmount the challenge of random weight parameter initialization prevalent in traditional deep-belief networks. Consequently, an optimized deep-belief neural-network load prediction model, predicated on the enhanced genetic algorithm, is established and subjected to training. Ultimately, the model undergoes simulation validation across three critical dimensions: operational performance, prediction evaluation indices, and operating costs of ice-storage air conditioners. The results indicate that, compared to existing methods for predicting the cooling load of ice-storage air conditioning, the proposed model achieves a prediction accuracy of 96.52%. It also shows an average improvement of 14.12% in computational performance and a 14.32% reduction in model energy consumption. The prediction outcomes align with the actual cooling-load variation patterns. Furthermore, the daily operational cost of ice-storage air conditioning, derived from the predicted cooling-load data, has an error margin of only 2.36%. This contributes to the optimization of ice-storage air conditioning operations.

Stochastic Electromagnetic Scattering From Stratified Media of Inhomogeneous Layers With Random Constitutive Parameters

Stochastic Electromagnetic Scattering From Stratified Media of Inhomogeneous Layers With Random Constitutive Parameters

Canopy Randomness, Scale, and Stem Size Effects on the Interfacial Transfer Process in Vegetated Flows

AbstractAquatic vegetation plays an important role in natural water environments by interacting with the flow and generating turbulence that affects the air‐water and sediment‐water interfacial transfer. Regular and staggered arrays are often set as simplified layouts for vegetation canopy to study both mean flow and turbulence statistics in vegetated flows, which creates uniform spacing between vegetation elements, resulting in preferential flow paths within the array. Such preferential paths can produce local high velocity and strong turbulence, which do not necessarily happen in natural environments where vegetation is randomly distributed. How the randomness of the canopy affects interfacial processes by altering spatial turbulence distribution, which can potentially lead to different turbulence feedback on the interfacial transfer process, remains an open question. This study conducted a series of laboratory experiments in a race‐track flume using rigid cylinders as plant surrogates. Mean and turbulent flow statistics were characterized by horizontal‐ and vertical‐sliced PIV. Based on the measured flow characteristics under different stem diameters and array configurations, we propose a method to quantify the randomness of the vegetation array and update a sediment‐water‐air interfacial gas transfer model with the randomness parameter to improve its accuracy. The updated model agrees well with the dissolved oxygen experimental data from our study and data from existing literature at various scales. The study provides critical insight into water quality management in vegetated channels with improved dissolved oxygen predictions considering vegetation layout as part of the interfacial transfer model.

Stochastic simulation of magnetically controlled convection in porous media with random porosity via Karhunen-Loève expansion and intrusive polynomial chaos expansion

Understanding and quantifying uncertainty factors are crucial for accurately predicting thermomagnetic convection phenomena. This study presented a mathematical model and algorithm framework for uncertainty analysis of thermomagnetic convection in porous media with random porosity. The proposed method combined Karhunen-Loève expansion and intrusive polynomial chaos expansion to represent the input random parameters and output response, respectively. The Galerkin projection method was employed to decouple the stochastic governing equations of thermomagnetic convection into deterministic governing equations that can be efficiently solved using the finite volume method. By solving the polynomial chaos expansion of the output response and employing the stochastic projection method to solve the associated decoupled governing equations, the temporal evolution and statistical characteristics of the output response were obtained. The study revealed that porosity uncertainty in the porous medium affects the thermomagnetic convection of paramagnetic fluid, exhibiting significant chaos effects. Monte Carlo simulations were performed to validate the accuracy of the proposed approach and demonstrate its computational efficiency compared to traditional Monte Carlo methods. This research provides valuable insights into the uncertainty analysis of thermomagnetic convection and offers a promising methodology for analyzing heat transfer in various porous media applications.

Robust visual tracking via modified Harris hawks optimization

Due to its outstanding efficiency and high precision, Harris hawks optimization (HHO for short) is suitable for solving the problem of visual target tracking under conditions of occlusion, deformation, rotation and in other complicated tracking scenes. A visual target tracker based on HHO is proposed in this study. To further promote the efficiency and stability of the standard HHO method and reduce the probability of the iteration falling into local optima and algorithm prematurity, in this study we propose an improved method called Super-HHO and apply it to visual target tracking. Compared with standard HHO, Super-HHO is superior due to its parameter optimization and updating strategy. We first optimize the random parameters of HHO via chaos theory to avoid frequent repeated exploration of the feasible region. Next, we design a nonlinear renewal strategy for the escape energy, which solves the problem in traditional HHO in which the fixed escape energy cannot accurately reflect the real hunting process of Harris hawks. Mutation strategies are also designed for the locations of the prey and the hunters to improve the optimization ability and eliminate the risk of falling into local extremes. In addition, a frame scale adjustment method model is developed to address the the issue in which the use of a size-fixed tracking frame makes it easy to include too many invalid features, which reduces the efficiency. Finally, we use the OTB2015, and VOT2018 tracking evaluation datasets, which contain hundreds of visual sequences and more than 10 complex interference scenes to conduct a qualitative analysis, a quantitative analysis and a statistical analysis of ours and other classic trackers, and to effectively test and compare the success ratio, precision and stability of each tracker. The proposed method was also compared with other classic trackers using classic large-scale benchmarks such as LaSOT and TrackingNet. Experimental data prove that ours performs well in terms of robustness, precision and efficiency.

Policy gradient methods for discrete time linear quadratic regulator with random parameters

This paper studies an infinite horizon optimal control problem for discrete-time linear system and quadratic criteria, both with random parameters which are independent and identically distributed with respect to time. In this general setting, we apply the policy gradient method, a reinforcement learning technique, to search for the optimal control without requiring knowledge of statistical information of the parameters. We investigate the sub-Gaussianity of the state process and establish global linear convergence guarantee for this approach based on assumptions that are weaker and easier to verify compared to existing results. Numerical experiments are presented to illustrate our result.

Effects of speed difference on injury severity of freeway rear-end crashes: Insights from correlated joint random parameters bivariate probit models and temporal instability

Rear-end crashes particularly on freeways are the most frequent type of collisions causing many injuries, damage and congestion. This paper investigates the impact of varying speed differences between following and leading vehicles on injury severity in two-vehicle rear-end crashes. It develops three groups of correlated joint random parameters bivariate probit models with heterogeneity in means. The rear-end crash data from 2019 to 2021 on Interstate freeways in Florida are utilized, and categorized into periods before, during, and after the COVID-19 pandemic. The study considers two potential injury severity outcomes: no injury and injury/fatality, for both drivers involved in these crashes. The findings indicate that a range of variables, including driver, vehicle, roadway, environmental, crash, and temporal attributes, significantly influence the injury severity outcomes for drivers in both following and leading vehicles. Demonstrating superior goodness-of-fit, the proposed approach sheds light on interactive unobserved heterogeneity, captured through heterogeneity in means and significant correlations among random parameters. The study observes critical influences on the injury severity outcomes of both drivers, with significant factors such as gender, age, vehicle type, weather conditions, lighting, and time of day. Furthermore, the results substantiate the heightened risk outcomes associated with greater speed differences and the period of the COVID-19 pandemic. These findings yield further insights into the risk mechanisms of two-vehicle rear-end crashes and offer guidance for the development of effective safety countermeasures.

Probability of stability calculation of MIMOn cascade non-linear systems with random parameters

Abstract The stability problem of Multiple n Inputs and Multiple n Outputs (MIMOn) cascade non-linear systems with random parameters is considered in this paper using the probability of stability estimation method. MIMOn cascade non-linear systems, particularly when the number of inputs and outputs exceeds three (n > 3), exhibit a unique property: the appearance of spatial hyperchaos that can lead to system instability. To achieve desired spatial dynamics and prevent the occurrence of spatial hyperchaos, it is necessary to select the appropriate parameter values for these systems. Moreover, the optimal parameter values enable the attainment of the highest probability of stability for stochastic MIMOn systems. The research presents the results of stability analysis using tools such as bifurcation diagram, Lyapunov diagram and spatial phase portraits, generated through MATLAB M-files, with a specific focus on a stochastic MIMO5 system (five inputs and five outputs).

Uncertainty quantification of the flexural strengthening of RC beams with UHPC using improved metaheuristic algorithm

This study presents an artificial intelligence-based model to predict the flexural strengthening of RC beam/slab strengthened with UHPC (RC-UHPC) and perform uncertainty quantification of such values. Improved eliminate particle swamp optimization hybridized artificial neural network (IEPANN) was a model developed on artificial neural network (ANN) optimized by improved-eliminate-particle-swamp optimization (IEPSO). Experimental datasets were used to establish the hybrid ML model. The efficiency of IEPANN was compared against support vector regression (SVR) and multiple linear regression (MLR). The IEPANN demonstrates outstanding performance over MLR and SVR. The flexural strengthening of RC-UHPC depends on materials and geometrical configurations, which have stochastic characteristics. Convergence studies, sensitivity, and probabilistic analyses were conducted on each random parameter. Simulation results indicated that strengthening configuration is the most sensitive to flexural strengthening. Systematic assessment of uncertainties in flexural strengthening may lead to a higher confidence level in model outcomes, and RC-UHPC is examined and designed. It enhances construction reliability.

Monitoring internal heat fluxes on Pulsating Heat Pipes using Kalman filter – Numerical and experimental results

The present study proposes an approach to monitor the wall-to-fluid internal heat flux on Pulsating Heat Pipes (PHP), which provides meaningful information about the efficiency and limiting operation conditions of such devices. In this sense, the current work adopts the Kalman Filter (KF) to estimate the heat flux between the working fluid and the internal tube wall along the adiabatic section of a PHP device by solving an inverse heat conduction problem. The KF is a well-known tracking technique, and therefore the current study is attractive due to the possibility of real-time evaluation of internal heat fluxes, a prospect that is extremely difficult to realize by standard whole domain inverse problem techniques. A high-speed and high-resolution infrared camera performs the temperature acquisition on the external wall of the PHP device. Two mathematical heat conduction models are considered: complete and thin-wall models. The complete model determines the temperature and heat flux evolution over time, and the thin-wall model is used to correct the random walk parameter on the KF formulation. Since the time step needed to the KF evolution model is smaller than the measurements acquisition interval, a matrix manipulation is used during the prediction step, reducing the number of mathematical operations. Hence, instead of predicting the states until reaching the measurement times, a proper mathematical manipulation reduces several mathematical operations to a single one. Then, the KF estimation capability is evaluated by considering synthetic data with different noise levels and different heat flux values. Subsequently, real experimental data are employed, and the results are compared with the ones obtained via a standard whole domain technique. The results obtained with the KF presented good visual agreement with the exact solution. Once the KF presents a delayed response, which is a characteristic of some filtering techniques, the errors with synthetic data were calculated offsetting the delay of the estimation in time in order to make a fair comparison, showing a maximum estimation error lower than 36 % considering the highest noise level. The synthetic data considered 20 s of time experiment, and the KF was able to estimate the PHP internal heat flux in less than 12 s, including the smoothing temperature step, showing fast and accurate results. For the real experimental data, the agreement between the KF and a whole domain technique is highly commendable, demonstrating a deviation of 25.5 % between both techniques. Moreover, the KF required significantly less computational time. The proposed methodology for heat flux estimation on PHPs is promising to evaluate their thermal behavior in real-time due to a low CPU time and computational memory required, as well as its simplicity to be implemented, possibly on embarked devices. Such information may therefore provide a thermal indicator of the correct functioning of PHPs in real time applications.

Injury-severity analysis of crashes involving defective vehicles and accounting for the underlying socioeconomic mediators

Crashes occur from a combination of factors related to the driver, roadway, and vehicle factors. The impact of vehicles on road crashes is a critical consideration within road safety analysis, even though not much studies have been conducted in this area. This study assessed how various vehicle and other crash factors are significantly associated with crash outcomes. To do this, historical vehicle defect-related crashes were obtained for the state of Alabama from 2016 to 2020. After data cleaning, a crash injury severity model was developed using the random parameters multinomial logit with heterogeneity in means approach to account for possible unobserved heterogeneity in the data. A spatial analysis was further conducted to better understand vehicle defect crashes as a broader societal issue and potentially explore their connection with the socio-demographic characteristics of the drivers of these vehicles. The preliminary data analysis showed that brake and tire defects accounted for about 65% of the vehicle defects associated with the crashes. The model estimation results revealed that improper tread depth and headlight defects were associated with major injury outcomes, while brake defects were more associated with minor injuries. Also, crashes associated with speeding, drunk driving, failure to use seatbelts, and those that occurred on curved roads left with downgrades were likely to result in major injuries. Findings from the spatial analysis showed that postal codes with higher median incomes are more likely to record lower vehicle defect-related crashes, unlike those that have higher proportions of females and African Americans. The study's findings provide data-driven evidence for sustained safety campaigns, workshops, and training on basic vehicle maintenance practices in the low-income communities in the state.

Predicting mechanical properties of 3D printed nanocomposites using multi-scale modeling

The main objective of this research is to predict the Young’s modulus of 3D-printed specimens made of nanocomposites. Printable nanocomposites filaments reinforced with various portions of carbon nanotubes (CNTs) are produced at the first stage. At the second stage, extruded nanocomposite filaments are fed into a 3D desktop printer and tensile specimens are printed with two different infill patterns. A multi-scale modeling is developed as a hierarchical computational procedure covering involved scales of micro, meso and macro. Treating CNT length, orientation and agglomeration as random parameters, stochastic modeling is performed. CNT length is considered at microscale, while CNT agglomeration and orientation are taken into account at the scale of meso. The infill patterns and printing parameters are captured at the uppermost scale of macro. The Young’s modulus of both nanocomposite filaments and 3D printed samples are predicted and compared with the results of experimental characterization.

Extensive hypothesis testing for estimation of crash frequency models

Estimating crash data count models poses a significant challenge which requires extensive knowledge, experience, and meticulous hypothesis testing to capture underlying trends. Simultaneous consideration of multiple modelling aspects is required including, among others, functional forms, likely contributing factors, and unobserved heterogeneity. However, model development, frequently affected by time and knowledge, can easily overlook crucial modelling aspects such as identification of likely contributing factors, necessary transformations, and distributional assumptions. To facilitate model development and an estimation that can extract as many insights as possible, an optimization framework is proposed to generate and simultaneously test a diverse array of hypothesis. The framework comprises a mathematical programming formulation and three alternative solution algorithms. The objective function involves minimizing the Bayesian Information Criterion (BIC) to avoid overfitting. The solution algorithms include metaheuristics to deal with an NP-hard problem and search through a complex and nonconvex space. The metaheuristics also enable to handle unique datasets through varying search strategies. The effectiveness of the proposed framework was ascertained using three distinct datasets, and published models used as benchmarks. The results highlighted the ability of the proposed framework to estimate crash data count models, surpassing benchmark models in terms of insights and goodness-of-fit. The framework provides several advantages, such as robust hypothesis testing, uncovering unique specifications and vital insights in the data, and leveraging existing knowledge to enhance search efficiency. The framework also exposes the vulnerability of traditional analyst efforts to fall into local optima, bias, and limitations in creating more efficient models. In a compelling example using crash data from Washington, the proposed framework unveiled insights overlooked by a benchmark published model, identifying speed, interchanges, and grade breaks as likely crash contributors, and revealing the potential danger of excessively wide shoulders. Conversely, the benchmark model identified fewer contributing factors and missed a crucial non-linear relationship between crash safety and shoulder widths. While wider shoulders are typically associated with improved safety, the proposed models suggest a safety threshold beyond which further widening could decrease safety. The introduction of random parameters in the analysis revealed a more nuanced relationship with crash frequency, thereby underlining the limitations of models incapable of capturing heterogeneity.

Assessing the effects of geometry and non-geometry related factors in work-zone crashes

Objective Work zones are unique in geometry and traffic management, utilizing special traffic signs, standard channelizing devices, appropriate barriers, and pavement markings. These configurations can introduce unexpected driving conditions, potentially posing risks to drivers. This analysis aims to explore potential differences in contributing factors between work-zone crashes where geometry was identified as a factor and those where it was non-geometry factor. To gain insights into driver injury severities in single-vehicle work-zone crashes, this study analyzed work zone crash data from Florida. Method This study employed random parameters logit models, accommodating potential variations in parameter estimates’ means and variances. The dataset encompassed a wide array of factors known to influence driver injury severity, encompassing crash characteristics, vehicle attributes, roadway features, prevailing traffic volume, driver profiles, and spatial and temporal considerations. Results This analysis yielded significantly distinct parameters for work-zone crashes, distinguishing between geometry-related and non-geometry-related factors (primarily the human factors). This distinction suggests a complex interplay between these factors. Notably, the marginal effects of individual parameter estimates exhibited marked differences between these two categories – geometry and non-geometry factors. Conclusion These findings contribute to the growing body of research indicating that geometric restrictions within work zones introduce a distinct set of risk factors compared to non-geometry-related factors. Recognizing the significance of geometric restrictions, beyond typical driving conditions, holds the implications for enhancing safety within various work zone configurations and offers valuable insights for crash scene investigators to pinpoint contributing factors accurately.

Determinants of zero-car and car-owning apartment households

AbstractWhile much research has explored the determinants of car ownership, there is little understanding of these factors in the context of apartment households, where off-street car parking provision is frequently stipulated by planning requirements and zero-car households are more evident. Drawing on a survey of apartment residents (n = 1316) in three Australian cities, this study aimed to understand the determinants of zero-car and car-owning apartment households. The data was analysed using binary and multinominal logistic regression, including random parameter modelling. A joint model of car ownership and off-street car parking supply was also developed to account for potential endogeneity between these two variables. The results highlight the significant association between car ownership and off-street car parking supply, alongside a range of socio-demographics, attitudes, perceptions, built environment and transport characteristics. An additional off-street car parking space, on average, was found to increase the odds of having 2+ cars, compared with zero cars, by around 10 times. The findings imply that reducing off-street residential car parking requirements can play a significant role in supporting lower car ownership levels among apartment households.

Assessing the Impact of Different Population Density Scenarios on Two-Wheeler Accident Characteristics at Intersections

Examining 1192 intersection car and two-wheeled vehicle collision accidents from the China In-Depth Accident Study (CIDAS) database, this study employs population density heat maps for precise assessment of surrounding population densities at accident sites. The K-Medoid clustering algorithm and silhouette coefficient were used to classify accidents into two distinct groups based on population density. Subsequent application of the random parameter logit model revealed key contributing factors to these accidents in varying population densities. The results show notable differences in factors such as collision direction of two-wheeled vehicles, types of accident conflict, road conditions, and traffic flow, depending on the population density. Based on these conclusions, the research can inform differentiated risk prediction for two-wheeled vehicle accidents at intersections and provide insights for intersection design in various population density scenarios.