Abstract Hand gestures serve as a powerful means of communication, capable conveying extensive information across various public health domains, including medicine and education. The process hand gesture recognition involves the use mathematical algorithms to identify human finds applications in areas such communication for deaf, human-computer interaction, intelligent driving, virtual reality. This study introduces robust method aimed at recognizing dynamic gestures, particularly...

This study presents a domain-specific automated machine learning (AutoML) for risk prediction and behaviour assessment, which can be used in the behavioural decision-making motion trajectory planning of autonomous vehicles (AVs). The AutoML enables end-to-end from vehicle movement sensing data to detailed levels corresponding characteristics, integrates three main components of: unsupervised identification by surrogate indicators big clustering, feature based on XGBoost, model auto-tuning...

In power energy distribution networks, switchgear is considered critical equipment. This because the act of monitoring operation and condition switchgear, as well performing required corrective maintenance on any potentially problematic equipment, critical. A single event may harm thousands customers over time pose a significant risk to operational staff. Many considerations must be put in place before using outages switch down system since they raise costs disrupt supply users. As result,...

Abstract At signalized intersections, the decision‐making process of each individual driver is a very complex that involves many factors. In this article, fuzzy cellular automata (FCA) model, which incorporates traditional (CA) and logic (FL), developed to simulate estimate effect driving behavior on traffic performance. Different from existing models applications, proposed FCA model utilizes interface systems (FISs) membership functions cognition system drivers. Four FISs are defined for...

The unsafe behaviors and great stress during the critical takeover process cause safety issues in conditionally automated driving. To compensate for limitations of existing performance improvement methods, current study aims to reduce by correcting driver cognitions. This proposed a behavioral inoculation approach against behaviors. intervention motivated drivers refute incorrect cognition then form safe Two rounds experiments were conducted. first round, with 40 participants, was analyze...

Multimodal pedestrian detection has garnered significant attention due to its potential applications in complex scenarios. The complementarity characteristics between infrared and visible modalities can enhance performance. However, the design of cross-modal fusion mechanisms in-depth exploration inter-modal still pose challenges. To address this, we propose TCCDNet, a novel network integrating complementarity. Specifically, efficient multi-scale C2f (EMAC) is designed for backbone, which...

This paper evaluates the safety effect of Responsibility-Sensitive Safety (RSS) model on autonomous carfollowing maneuvers. The RSS is embedded into Model Predictive Control (MPC) based Adaptive Cruise (ACC) algorithm. Car-following scenarios with sudden deceleration lead vehicle at various front gap and velocity conditions are simulated. Vehicle movements characteristics surrogate measurements analyzed to evaluate performance simulation before after embedded. Results show that ACC can be...

SUMMARY Shared lanes at signalized intersections are designed for use by vehicles of different movement directions. lane usage increases the flexibility assigning grouping to accommodate variable traffic volume direction. However, a shared is not always beneficial as it can time result in blockage that leads both capacity and safety constraints. This paper establishes cellular automata model simulate movements with lanes. Several simulation experiments carried out single an approach lane....

A study is conducted to compare two simulation methods for estimating conflicts between road users. An improved cellular automata (CA) model proposed estimate the occurrences and severity of traffic (both vehicle–vehicle vehicle–pedestrian) at signalized intersections. The CA compared with a calibrated method surrogate safety assessment (SSAM) based on Vissim. Simulated from both are observed vehicle automated tracking severity. Simulation results show that approach able replicate realistic...

Safety is an important challenge in the development of autonomous vehicles (AVs). To ensure safety AVs, Intel and Mobileye have proposed a model called Responsibility-Sensitive (RSS). Previous studies shown that RSS has potential to improve performance especially for partial driving algorithms. However, it been leads considerable car-following distance, which negative effect on traffic efficiency. efficiency when applied adaptive cruise control (ACC) systems, this paper proposes improved...

Purpose The presentation of in-vehicle warnings information at risky driving scenarios is aimed to improve the collision avoidance ability drivers. Existing studies have found that driver’s performance affected by both warning and workload. However, whether moderation mediation effects exist among information, cognition, behavior unclear. Design/methodology/approach This purpose this study examine type modifies relationship between forward risk behavior. A simulator experiment was conducted...

Crowd movement dynamics at a signalized pedestrian crossing constitutes complex system affected by many factors. Existing crowd simulation models seldom consider cognition and decision making of individual pedestrians. In this study, fuzzy cellular automata (FCA) model was developed to simulate movements crowded crossings that incorporated decision-making processes. The proposed FCA logic into conventional (CA) model. contrast existing applications, the used sets membership functions...

The reliability of environmental perception is the key to ensuring stability and safety autonomous vehicles. Complex road environments pose attentional challenges automated driving, especially for vehicle systems. Therefore, evaluating performance driving algorithms in complex great significance. However, as geometry complex, with many factors, including curvature, slope, lane marking conditions, so on, existing approach assessing an algorithm through detection tests low efficiency. this...

The movement process of debris flow in the complex roads system is important for risk evaluation and emergency rescue. This paper presents an in-depth study diversion effect cross channels, a common branching structure both natural engineered environments, especially field urban prevention. A mathematical model established based on conservation mass, momentum, energy, solid–liquid two-phase motion equation derived from theory. numerical solution method, combining finite difference method...

Objective This study aims to investigate the causes of take-over failures in conditional automated driving with spatial-temporal analysis brain zone activation. Background Take-over requires a human driver resume control vehicle when its automation system disengages. Existing studies have found that occur frequently on some drivers, but not been thoroughly studied. Method In simulator experiment, 40 drivers took over critical freeway cut-in situations. Functional near-infrared spectroscopy...