A5101462695- Traffic and Road Safety
- Human-Automation Interaction and Safety
- Autonomous Vehicle Technology and Safety
- Sleep and Work-Related Fatigue
- Traffic control and management
- Safety Warnings and Signage
- Ergonomics and Musculoskeletal Disorders
- COVID-19 Clinical Research Studies
- Transportation Planning and Optimization
- Railway Engineering and Dynamics
- Traffic Prediction and Management Techniques
- Legal principles and applications
- Gaze Tracking and Assistive Technology
- Microbial Inactivation Methods
- Effects of Vibration on Health
- Railway Systems and Energy Efficiency
- Fire Detection and Safety Systems
- Radiomics and Machine Learning in Medical Imaging
- Engineering Applied Research
- Heart Rate Variability and Autonomic Control
- Law, logistics, and international trade
- EEG and Brain-Computer Interfaces
- COVID-19 diagnosis using AI
- Freezing and Crystallization Processes
- Competitive and Knowledge Intelligence
Tsinghua University
2015-2024
Jinan University
2024
University of Arkansas at Little Rock
2024
Zhejiang University
2018-2024
Chinese PLA General Hospital
2020-2021
Guangxi Veterinary Research Institute
2021
Ministry of Industry and Information Technology
2020
Affiliated Zhongshan Hospital of Dalian University
2019
Ministry of Agriculture and Rural Affairs
2018
University of Illinois Urbana-Champaign
2018
Accurate trajectory prediction of surrounding road users is critical to autonomous driving systems. In mixed traffic flows, with different kinds behaviors and styles bring complexity the environment, which requires considering interactions among when anticipating their future trajectories. This paper presents a long-term interactive method for vehicles using hierarchical multi-sequence learning network. contrast non-interactive assumes that are independent each other, this can automatically...
Driver distraction has been identified as one major cause of unsafe driving. The existing studies on cognitive detection mainly focused high-speed driving situations, but less low-speed traffic in urban This paper presents a method for the driver at stop-controlled intersections and compares its feature subsets classification accuracy with that speed-limited highway. In simulator study, 27 subjects were recruited to participate. is induced by clock task taxes visuospatial working memory....
Predicting driver rear-end risk-avoidance maneuvers in cut-in scenarios, especially dangerous precrash benefits the customization of automatic driving, particularly steering. This paper studies behaviors scenarios on a straight three-lane highway. Data from 24 participants 1326 valid trials were collected using motion-based driving simulator. An Eysenck Personality Questionnaire (revised for Chinese participants) was used to obtain personality traits participants. Based statistical analysis,...
Cooperative driving of human driver and automated system can effectively reduce the necessity extremely accurate environment perception highly vehicles, enhance robustness decision-making motion control. However, due to two players' different intentions, severe conflicts may exist during cooperation, which often result in negative consequences on safety maneuverability. This paper presents an indirect shared control method model situation improve performance, focus affine input nonlinear...
For highly automated vehicles, effective take-over performance measures are essential for establishing quantitative models and exploring approaches to improve performance. However, there is a lack of comprehensive that suitably combine multiple objective metrics based on an average evaluation from human drivers. In this study, we proposed human-centered measure (HCMTP). There four main building blocks the HCMTP. First, adopted sparse principal component analysis identify aspects original...
Abstract Background Patients with Alzheimer’s disease or dementia are at increased risk for COVID-19 hospitalization and mortality. However, no study has examined whether memory function is associated outcomes in general older adults. Methods Data were obtained from SHARE (the Survey of Health, Ageing Retirement Europe), HRS Health Study), ELSA English Longitudinal Study Ageing), three prospective representative cohorts non-institutionalized adults aged 50 years 25 European countries plus...
Traffic accidents due to fatigue account for a large proportion of road fatalities. Based on simulated driving experiments with drivers recruited from college students, this paper investigates the use heart rate variability (HRV) features detect driver while considering sex differences. Sex-independent and sex-specific differences in HRV between alert fatigued states derived 2 min electrocardiogram (ECG) signals were determined. Then, decision trees used detection using either all subjects...
Three experiments were conducted to examine the effectiveness of two forward crash warning systems, a flashing brake system and hazard system, using an advanced driving simulator. In Experiment 1, 20 subjects followed lead vehicle with desired time gap braked when necessary. Results showed that gap, velocity, deceleration all significantly affected drivers’ response times. 2, six times sudden (0.6 g at 80 km/h) measured for gaps. reduced drivers' by 0.14~0.62 s 0.03~0.95 s, respectively, in...
Lane change maneuver recognition is critical in driver characteristics analysis and behavior modeling for active safety systems. This paper presents an enhanced classification method to recognize lane by using optimized features exclusively extracted from vehicle state operation signals. The sequential forward floating selection (SFFS) algorithm was adopted select the feature set maximize k-nearest-neighbor classifier performance. hidden Markov models (HMMs), based on set, were developed...
Purpose Decision-making is one of the key technologies for self-driving cars. The high dependency previously existing methods on human driving data or rules makes it difficult to model policies different situations. Design/methodology/approach In this research, a probabilistic decision-making method based Markov decision process (MDP) proposed deduce optimal maneuver automatically in two-lane highway scenario without using any data. issues traffic environment are formulated as MDP by...
Abstract The pandemic of Coronavirus Disease 2019 (COVID-19) is causing enormous loss life globally. Prompt case identification critical. reference method the real-time reverse transcription PCR (RT-PCR) assay, whose limitations may curb its prompt large-scale application. COVID-19 manifests with chest computed tomography (CT) abnormalities, some even before onset symptoms. We tested hypothesis that application deep learning (DL) to 3D CT images could help identify infections. Using data...
Detection of driver cognitive distraction is critical for active safety systems road vehicles. Compared with visual distraction, more challenging detection due to the lack apparent exterior features. This paper presents a novel real-time algorithm by using support vector machine (SVM). Data are collected from 26 subjects, driving in typical urban and highway scenarios simulator. The chosen scenario stop-controlled intersection speed-limited highway. Driver while induced clock tasks which...
Although latent hazard notification for highly automated driving is expected to enhance traffic safety, its practical effects have yet be verified. This study systemically investigated the safety benefits and driver behavioral adaptation based on structural equation modeling. First, we developed a system inform drivers of hazards with auditory alerts conducted simulation experiment involving eyes-off-road situations. To test system, adopted two types events (i.e., collision avoidance...
For better small-radius curve negotiation performance, the independently rotating wheelset has potential to be equipped in urban rail transit. As a crucial part of running gear, its dynamic characteristics directly affect railway vehicle’s stability and ability. This study follows model–simulation–experiment method delve into process steady convergent wheelset. An improved mathematical model is established, considering gravitational restoring forces different creepages between left right...
Stropharia rugosoannulata is a valuable medicinal and food fungus with high nutritive value. Freeze-drying addresses the storage transportation challenges of fresh rugosoannulata, expanding its market while preserving flavor quality more effectively than other drying methods. This study optimizes vacuum freeze-drying process for using an orthogonal experiment method. The parameters were optimized to determine their effects on freeze-dried product, including pre-freezing temperature, time,...
The effects of fatigue on a driver’s autonomic nervous system (ANS) were investigated through heart rate variability (HRV) measures considering the difference sex. Electrocardiogram (ECG) data from 18 drivers recorded during simulator-based driving experiment. Thirteen short-term HRV extracted time-domain and frequency-domain methods. First, differences in related to mental state (alert or fatigued) analyzed all subjects. Then, sex-specific changes between alert fatigued states investigated....
Bicycling is one of the popular modes transportation, but bicyclists are easily involved in injuries or fatalities vehicle-bicycle (V-B) accidents. The AEB (Autonomous Emergency Braking) systems have been developed to avoid collisions, their adaptiveness needs be further improved under different motion patterns V-B conflicts. This paper analyzes drivers’ braking behaviors conflicts improve performance Bicyclist-AEB systems. For safety and data reliability, a driving simulator was used...
As human-machine collaborative driving systems, highly automated vehicles require human drivers to take over when take-over requests are triggered. Extensive studies have shown that drivers' performance is affected by their fatigue state, traffic conditions, and the time budget (TB). However, there still a paucity of systematic understanding how these factors affect performance, which prevents implementation adaptive systems. This study establishes accurate prediction model systematically...
Accounting about 70% of vehicle miles on roadways, highway driving is a critical issue in traffic safety deployment. Of the various maneuvers that comprise highly complex task, each one requires understanding connections between states, performance and drivers' actions. This paper attempts to flesh out complete picture highways. Eighteen drivers participated this study. They drove an instrumented highways accumulate 2,600 km naturalistic data. The data were segmented classified into 11...
Accurate detection of driver's eye state by computer vision is critical to driver drowsiness monitoring. The histogram oriented gradients (HOG) commonly used as descriptive feature image for classification. However, HOG often suffers from the limit local gradient information. This paper proposes a new HOG-like image, called cooccurrence matrix (CMOG), purpose more effectively classifying state. By introducing matrix, CMOG enhances ability describing global information images. ZJU blink...
Abstract Different processing sequences of ultrasound and heat were applied for the inactivation Staphylococcus aureus Escherichia coli in milk. The changes whey protein content, particle size, zeta potential, pH, viscosity, color values studied to evaluate effects on quality Results indicated treatment (600 W, 5 min) with postheating (63 °C reduced S. E. by 1.58 2.02 log cfu/ml, respectively, but yielded 0.26 0.19 cfu/ml sublethal . Milk preheated 63 (5 followed showed 1.17 1.68 reductions...