Distractions by Work-related Activities: The Impact of Ride-hailing App and Radio System on Male Taxi Drivers

Tiantian (Nicole) Chen,Oscar Oviedo-Trespalacios,N.N. Sze,Sikai Chen 대한교통학회 2023 대한교통학회 학술대회지 Vol.88 No.-

Use of ride-hailing mobile apps has surged and reshaped the taxi industry. These apps allow real-time taxi-customer matching of taxi dispatch system. However, there are also increasing concerns for driver distractions as a result of these ride-hailing systems. This study aims to investigate the effects of distractions by different ride-hailing systems on the driving performance of taxi drivers using the driving simulator experiment. In this investigation, fifty-one male taxi drivers were recruited. During the experiment, the road environment (urban street versus motorway), driving task (free-flow driving versus car-following), and distraction type (no distraction, auditory distraction by radio system, and visual-manual distraction by mobile app) were varied. Repeated measures ANOVA and random parameter generalized linear models were adopted to evaluate the distracted driving performance accounting for correlations among different observations of a same driver. Results indicate that distraction by mobile app impairs driving performance to a larger extent than traditional radio systems, in terms of the lateral control in the free-flow motorway condition and the speed control in the free-flow urban condition. In addition, for car-following task on urban street, compensatory behaviour (speed reduction) is more prevalent when distracted by mobile app while driving, compared to that of radio system. Additionally, no significant difference in subjective workload between distractions by mobile app and radio system were found. Several driver characteristics such as experience, driving records, and perception variables also influence driving performances. The findings are expected to facilitate the development of safer ride-hailing systems, as well as driver training and road safety policy.

A Hazard-Based Duration Model to Quantify the Impact of Work-Related Distraction on Taxi Drivers’ Safety Performance: A Driving Simulator Study

Tiantian Chen,Shi Ye,Oscar Oviedo-Trespalacios,N.N. Sze 대한교통학회 2023 대한교통학회 학술대회지 Vol.89 No.-

A Hazard-Based Duration Model to Quantify the Impact of Work-Related Distraction on Taxi Drivers’ Safety Performance: A Driving Simulator Study

Tiantian Chen,Shi Ye,Oscar Oviedo-Trespalacios,N.N. Sze 대한교통학회 2023 대한교통학회 학술대회지 Vol.89 No.-

Rough tool path generation for NC machining of Loop subdivision surfaces

Tiantian Chen,Gang Zhao (사)한국CDE학회 2013 한국CAD/CAM학회 국제학술발표 논문집 Vol.2010 No.8

Subdivision surface modeling plays an important role in the field of surface modeling. As the gradual progress of subdivision is discrete, both a smooth design model and a discrete machining model can be represented by subdivision surface. Particularly, due to the unique multiresolution property, different multiresolution models can be obtained by utilizing subdivision wavelets analysis filters. Therefore, different multiresolution models can be applied to generate tool paths at different NC machining stages. Firstly, the paper is mainly focused on the key technologies of Loop subdivision surface multiresolution analysis. The biorthogonal Loop subdivision wavelets decomposition and reconstruction based on the reverse subdivision are realized and verified experimentally. Both the error control and boundary treatment are discussed. Secondly, special attention is paid to the tool path generation of rough machining based on reverse Loop subdivision surface. By making use of reverse Loop subdivision wavelets and adjustment algorithms of local control points, the smooth rough machining model with minimum energy is generated. Finally, machining simulation tests are implemented for the verification.

Analysis of Risky Driving Behaviour at Closely Spaced Tunnel-interchange Section

Yunjie Ju,Tiantian Chen,Feng Chen 대한교통학회 2024 대한교통학회 학술대회지 Vol.90 No.-

Experimental study on thermo-hydraulic performance of nanofluids in diverse axial ratio elliptical tubes with a built-in turbulator

Cong Qi,Tiantian Chen,Yuxing Wang,Liyuan Yang 한국화학공학회 2020 Korean Journal of Chemical Engineering Vol.37 No.9

Due to the low heat transfer efficiency of common heat exchange systems, an improved heat exchange system was developed. Enhanced tubes (elliptical tubes with a built-in turbulator) instead of a smooth tube were used and TiO2-water nanofluids were substituted for water to intensify the heat transfer. The influences of turbulator (presence or absence), axial ratios of elliptical tubes (Z=1.235, 1.471, 1.706), nanoparticle concentration (=0.0 wt%, 0.1 wt%, 0.3 wt%, 0.5 wt%), and Reynolds number (Re=400-12,000) on the flow and heat transfer properties of TiO2-water nanofluids were studied. Thermal and exergy efficiency were used to research the comprehensive thermo-hydraulic characteristics of these heat transfer enhancement technologies. The thermo-hydraulic properties of nanofluids all showed an increasing trend with the growing axial ratio, nanoparticle concentration and Reynolds number. Nanofluids (=0.5 wt%) in an elliptical tube (Z=1.706) with a built-in turbulator showed the best thermal performance, which could be increased by 33.8% in comparison with water at best. The thermal efficiency index increased first and then decreased with the Re. Nanofluids in elliptical tubes with a built-in turbulator can clearly promote heat transfer under the identical condition.

Effects of heat sink structure on heat transfer performance cooled by semiconductor and nanofluids

Cong Qi,Tiantian Chen,Jianglin Tu,Yuxing Wang 한국화학공학회 2020 Korean Journal of Chemical Engineering Vol.37 No.12

On account of the low heat dissipation problem of common cooling systems, an experimental system with enhanced structures was set to improve the heat transfer of heat sink cooled by semiconductor and TiO2-water nanofluids. The influences of structures (smooth surface, metal foam with PPI=30, cylindrical bulge (height: H=2mm, staggered arrangement), cylindrical groove (depth: D'=2 mm, staggered arrangement)), nanoparticle mass fractions (= 0.0-0.5 wt%), input power of the semiconductor (P=2W, 4W, 6W), and Reynolds numbers (Re=414-1,119) on the flow and heat transfer properties of TiO2-water nanofluids were studied. The compositive thermal and hydraulic properties of the enhanced technologies were analyzed by thermal efficiency. Results indicated that the combination of semiconductor and metal foam shows the most excellent performance compared with other combinations and it can be enhanced by 48.1% at best. Nanofluids with =0.4 wt% display the best cooling capacity instead of the highest concentration. The cooling effect shows an increasing trend with the input power of the semiconductor.

Integrating Deep Learning and Extreme Value Theory for Analyzing Traffic Conflicts at Signalized Intersections

Yukai Wang,Tiantian Chen 대한교통학회 2024 대한교통학회 학술대회지 Vol.90 No.-

In an era where urban traffic complexities escalate, this study innovates in traffic conflict analysis at signalized intersections by integrating advanced Deep Learning (DL) techniques with Extreme Value Theory (EVT). We elevate the methodology by transitioning from Machine Learning to a more sophisticated ensemble of DL models-Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Autoencoders-each meticulously chosen for their proficiency in anomaly detection within traffic video data. This refined approach ensures a nuanced identification of anomalous traffic patterns. Leveraging EVT, we rigorously assess the severity and forecast the likelihood of extreme events, thereby providing a robust framework for traffic safety evaluation. Empirical validation, conducted with surveillance footage from Daejeons Wongol intersection, elucidates the augmented capability of our DL-EVT model over conventional ML methods in discerning and prognosticating critical traffic scenarios. This significant methodological enhancement not only validates the fusion of cutting-edge DL techniques with EVT for traffic safety analysis but also pioneers a new paradigm in AIs role in urban traffic management, paving the way for the formulation of proactive safety measures.

Automatic identification and analysis of multi-object cattle rumination based on computer vision

Yueming Wang,Tiantian Chen,Baoshan Li,Qi Li 한국축산학회 2023 한국축산학회지 Vol.65 No.3

Rumination in cattle is closely related to their health, which makes the automatic monitoring of rumination an important part of smart pasture operations. However, manual monitoring of cattle rumination is laborious and wearable sensors are often harmful to animals. Thus, we propose a computer vision-based method to automatically identify multi-object cattle rumination, and to calculate the rumination time and number of chews for each cow. The heads of the cattle in the video were initially tracked with a multi-object tracking algorithm, which combined the You Only Look Once (YOLO) algorithm with the kernelized correlation filter (KCF). Images of the head of each cow were saved at a fixed size, and numbered. Then, a rumination recognition algorithm was constructed with parameters obtained using the frame difference method, and rumination time and number of chews were calculated. The rumination recognition algorithm was used to analyze the head image of each cow to automatically detect multi-object cattle rumination. To verify the feasibility of this method, the algorithm was tested on multi-object cattle rumination videos, and the results were compared with the results produced by human observation. The experimental results showed that the average error in rumination time was 5.902% and the average error in the number of chews was 8.126%. The rumination identification and calculation of rumination information only need to be performed by computers automatically with no manual intervention. It could provide a new contactless rumination identification method for multi-cattle, which provided technical support for smart pasture.

Spatial Analysis of the Impact of Street-level Built Environment and Perception Features on the Crashes by Severity

Liu Yiping,Chen Tiantian,Chung Hyungchul,Jang Kitae 대한교통학회 2024 대한교통학회 학술대회지 Vol.90 No.-

Urban traffic accidents are closely related to street characteristics, and investigating this relationship is crucial for enhancing traffic safety. Street-level features primarily include the built environment elements that makes up the streets, such as greenery, sky, and other elements. As users of urban street spaces, travelers perception indicators of various streets also include subjective perspectives describing the differential characteristics among urban streets. Therefore, this study focuses on exploring the impact of the street built-environment and travelers perception indicators on the crash frequencies. The modeling process considers severity levels related to traffic crashes and then extends analysis to geospatial dimension to account for the spatial heterogeneity and correlation of coefficients. The study uses 587 road segments in the central area of Daejeon in Korea, with traffic crash data from the full year of 2019. All crashes are classified into killed/severe injury (KSI) and slight injury. Street built-environment elements are extracted from the street view images of the studied road sections using semantic segmentation technology, while street perception indicators are scored using deep learning methods based on the street view images, outputting results in six perceptual dimensions to create related variables. In addition, the impact of traffic variables such as AADT and road geometry (number of lanes, speed limits, etc.) is considered. The results suggest significant correlations among street built-environment, travelers perception indicators and the frequency of traffic crashes, with different trends of impact for various crash classification. The estimation results of coefficients also show variations in the spatial influence of different feature, which could help traffic authorities identify high-risk areas and understand contributing factors, thereby taking precaution actions.