Carbon tax and low-carbon credit: Which policy is more beneficial to the capital-constrained manufacturer's remanufacturing activities?

Remanufacturing has attracted much attention for its enormous potential in resource recycling and low-carbon emission reduction. To investigate the effects of different government intervention policies on remanufacturing and carbon emissions, two profit maximization models of the capital-constrained manufacturer under carbon tax and low-carbon credit policies are constructed respectively. Then, through theoretical and numerical analyses, some significant findings are drawn: (1) Both carbon tax and low-carbon credit policies can encourage capital-constrained manufacturers to produce more remanufactured products, but which intervention policy is more advantageous also depends on the carbon emission cost of new products or financing cost of the remanufactured products. (2) Although carbon tax policy can effectively control carbon emissions, it is always at the expense of both capital-constrained manufacturers and consumers; while low-carbon credit policy can help capital-constrained manufacturers achieve the goal of win-win economic and environmental benefits when the remanufacturing carbon savings advantages are more apparent. (3) From the perspective of consumer benefits, carbon tax is more advantageous when the consumer willingness to pay for remanufactured products is higher; otherwise, low-carbon credit policy should be implemented. (4) The higher the environmental damage coefficient is, the more it can highlight the advantages of the two intervention policies in social welfare enhancement, especially the carbon tax policy; and when the environmental damage coefficient is given, the stronger the consumers' willingness to pay for remanufactured products is, the more it is conducive to reducing the negative effects caused by the carbon tax or low-carbon credit policy in social welfare enhancement, or increasing the corresponding positive effects. Based on above findings, some managerial insights and policy implications are provided to capital-constrained manufacturers and policy-makers.

Influence of emotions on the aggressive driving behavior of online -car-hailing drivers based on association rule mining.

Emotion is an important factor that can lead to the occurrence of aggressive driving. This paper proposes an association rule mining-based method for analysing contributing factors associated with aggressive driving behaviour among online car-hailing drivers. We collected drivers' emotion data in real time in a natural driving setting. The findings show that 29 of the top 50 association rules for aggressive driving are related to emotions, revealing a strong relationship between driver emotions and aggressive driving behaviour. The emotions of anger, surprised, happy and disgusted are frequently associated with aggressive driving behaviour. Negative emotions combined with other factors (for example, driving at high speeds and high acceleration rates and with no passengers in the vehicle) are more likely to lead to aggressive driving behaviour than negative emotions alone. The results of this study provide practical implications for the supervision and training of car-hailing drivers.

Based on the association rule mining method, we found a close connection between drivers' emotional states and the manifestation of aggressive driving behaviours. The findings indicate that the combination of negative emotions and various contributing factors significantly amplifies the likelihood of aggressive driving.

Bullying Victimization and Internalizing Problems among Adolescents: A Moderated Mediation Model of Peer Autonomy Support and Self-Esteem.

The present study employed the social-ecological diathesis-stress model as a theoretical framework to extend previous research by examining the underlying mechanism and conditional process that contribute to the positive association between bullying victimization and internalizing problems among adolescents. A moderated mediation model involving peer autonomy support and self-esteem was tested using a sample of 1723 adolescents (50.7% girls; M age = 12.79, SD = 1.58), who completed questionnaires assessing internalizing problems, bullying victimization, peer autonomy support, and self-esteem. The findings revealed that self-esteem partially mediated the positive association between bullying victimization and adolescents' internalizing problems. Specifically, bullying victimization was inversely related to self-esteem, which, in turn, was negatively associated with internalizing problems. Further moderation analyses demonstrated that these direct and indirect associations varied based on levels of peer autonomy support. Simple slope analyses specifically indicated that (a) peer autonomy support buffered against the negative association of bullying victimization with self-esteem and internalizing problems, and (b) peer autonomy support mitigated the negative association of self-esteem with internalizing problems. The elucidation of this mechanism and conditional process holds important implications for early interventions and prevention efforts aimed at mitigating the detrimental association of bullying victimization with adolescents' healthy emotional functions.

Real-time driving risk prediction using a self-attention-based bidirectional long short-term memory network based on multi-source data.

Early warning of driving risks can effectively prevent collisions. However, numerous studies that predicted driving risks have suffered from the use of single data sources, insufficiently advanced models, and lack of time window analysis. To address these issues, this paper proposes a self-attention-based bidirectional long short-term memory (Att-Bi-LSTM) network model to predict driving risk based on multi-source data. First, driving simulation tests are conducted. Driver demographic, operation, visual, and physiological data as well as kinematic data are collected. Then, the driving risks are classified into no risk, low risk, medium risk, and high risk. Next, the Att-Bi-LSTM model is constructed, and convolutional neural network (CNN), CNN-LSTM, CatBoost, LightGBM, and XGBoost are employed for comparison. To generate the inputs and outputs of the models, observation, interval, and prediction time windows are introduced. The results show that the Att-Bi-LSTM model using early-fusion method significantly outperforms the five comparison models, with a macro-average F1-score of 0.914. The results of ablation studies indicate that the Bi-LSTM layers and self-attention layer have achieved the expected effect, which is crucial for improving the model's performance. As the interval or prediction time window is extended, the accuracy of the prediction results gradually decreases. However, as the observation time window is extended, the results first improve and then become stable. Compared to using only relative kinematic data, using all data (i.e., multi-source data) is shown to improve the F1-score by 0.061. This study provides an effective method for driving risk prediction and supports the improvement of advanced driver assistance systems.

Influence of distracted driving of online car-hailing drivers on overall driving performance.

The distraction affects driving performance and induces serious safety issues. To better understand distracted driving, this study examines the influence of distracted driving on overall driving performance. This paper analyzes the distraction behavior (mobile phone use, entertainment activities, and passenger interference) under three driving tasks. The statistical results show that viewing or sending messages is common during driving. Smoking, phone calls, and talking to passengers are evident in cruising, ride request and drop-off, respectively. Then, overall driving performance is proposed based on velocity, longitudinal acceleration (longacc) and yaw_rate. It is divided into three categories, high, medium, and low, by k-means algorithms. The average speed increases from low to high performance; however, the longacc and yaw_rate decrease. Finally, the influence of distracted driving on overall driving performance is analyzed using C4.5 algorithm. The result shows that when time is peak, the probability of high performance (HP) is higher than off-peak. The possibility of HP increases with the increase of duration; the number of, talking to passengers, listening to music or radio, eating; the duration of, viewing or sending messages, phone calls; but reduces with the increase of the number of phone calls. These findings provide theoretical support for driving performance evaluation.

Recognition of aggressive driving behavior under abnormal weather based on Convolutional Neural Network and transfer learning.

OBJECTIVES: Aggressive driving behavior can lead to potential traffic collision risks, and abnormal weather conditions can exacerbate this behavior. This study aims to develop recognition models for aggressive driving under various climate conditions, addressing the challenge of collecting sufficient data in abnormal weather. METHODS: Driving data was collected in a virtual environment using a driving simulator under both normal and abnormal weather conditions. A model was trained on data from normal weather (source domain) and then transferred to foggy and rainy weather conditions (target domains) for retraining and fine-tuning. The K-means algorithm clustered driving behavior instances into three styles: aggressive, normal, and cautious. These clusters were used as labels for each instance in training a CNN model. The pre-trained CNN model was then transferred and fine-tuned for abnormal weather conditions. RESULTS: The transferred models showed improved recognition performance, achieving an accuracy score of 0.81 in both foggy and rainy weather conditions. This surpassed the non-transferred models' accuracy scores of 0.72 and 0.69, respectively. CONCLUSIONS: The study demonstrates the significant application value of transfer learning in recognizing aggressive driving behaviors with limited data. It also highlights the feasibility of using this approach to address the challenges of driving behavior recognition under abnormal weather conditions.

Exploring the impact of right-turn safety measures on E-bike-heavy vehicle conflicts at signalized intersections.

A major safety hazard for e-bike riders crossing an intersection is encountering heavy vehicles turning right in the same direction, which often results in severe casualties. Recently, some cities in China have implemented right-turn safety improvement treatments (i.e., right-turn yielding rules and right-turn warning facilities) at intersections to reduce the occurrence of such accidents. However, the risk perception and behavior of e-bike riders and heavy vehicle drivers dynamically change during the right-turn interaction process, and the safety effects of different right-turn safety measures remain unclear. This study aims to investigate the safety effect of right-turn safety measures on E-Bike-Heavy Vehicle (EB-HV) right-turn conflicts at signalized intersections. The right-turn conflicts and potential influencing factors are extracted from aerial video data, including characteristics of right-turn warning facilities, characteristics and behavior of e-bike riders and heavy vehicle drivers, environmental factors, and traffic-related factors. Moreover, traffic conflict indicators such as the Time to Collision (TTC), Post Encroachment Time (PET), and Jerk are selected and calculated. Multinomial and binary logit models are used to estimate and analyze the EB-HV right-turn conflict severity and drivers yielding behavior. The results reveal that: (a) right-turn warning facilities can decrease the probability of slight and severe EB-HV right-turn conflicts, while the presence of law enforcement cameras could prompt heavy vehicle drivers to comply with the yielding rules and adopt more cautious behavior; (b) increased heavy vehicle speed and acceleration before turning right have strong correlation to illegitimate yielding behavior of the driver and higher EB-HV right-turn conflict severity; and (c) aggressive behavior of e-bike rider increases the severe conflict probability, especially at intersections without right-turn warning facilities. Based on the study findings, several practical implications are suggested to reduce the risk of EB-HV right-turn conflicts, enhance the effectiveness of right-turn safety measures, and improve crossing safety for e-bike riders.

Associations between parental autonomy support and depressive symptoms among Chinese college students: the chain-mediating effects of mindfulness and self-esteem.

Introduction: Despite extensive research on contextual factors will relieve college students' depressive symptoms, significant gaps remain in understanding the underlying mechanisms of this relationship, particularly through individual strength factors such as mindfulness and self-esteem. Based on self-determination theory, we explore the association between parental autonomy support and depressive symptoms among Chinese college students and whether mindfulness and self-esteem serve as mediators. Methods: A total of 1,182 Chinese college students aged 16 to 27 years (Mage = 20.33, SD = 1.63; female = 55.7%) participated in this research. Questionnaires pertaining to parental autonomy support, mindfulness, self-esteem, and depressive symptoms were administered. Results: The results revealed that depressive symptoms were negatively correlated with both paternal and maternal autonomy support, with mindfulness and self-esteem acting as chain-mediators. Specifically, mindfulness and self-esteem were positively impacted by parental autonomy support, whereas depressive symptoms were negatively impacted by mindfulness and self-esteem. Furthermore, paternal and maternal autonomy support significantly impacted depressive symptoms via both direct and indirect pathways. Indirect effects included three paths: mediation through mindfulness, mediation through self-esteem, and mediation through the mindfulness and self-esteem chain. Discussion: The study highlights the fundamental mechanisms that account for the association between Chinese college students' parental autonomy support and depressive symptoms, these insights can be used to prevent and manage mental health problems among Chinese college students. For example, parents' autonomy support can directly reduce depressive symptoms, but we can also indirectly promote college students' mental health by emphasizing the mediation role of students' mindfulness and self-esteem.

Research on the Heterogeneity Threshold Effect of Foreign Direct Investment and Corporate Social Responsibility on Haze Pollution.

Carrying out environmental protection and governance in the process of using foreign capital to develop the economy is a realistic problem that China needs to solve urgently. In order to reduce environmental pollution, all enterprises are called upon by the local government to fulfil CSR and improve the quality of FDI use. However, previous studies have rarely explored the threshold effect of FDI and CSR on haze pollution. This paper employs the threshold effect model to explore the above problem based on panel data of 30 provinces in China from 2009 to 2018. The empirical study found the following: (1) FDI has a significantly positive double-threshold effect on haze pollution. Meanwhile, the promotion effect of FDI on haze pollution is the strongest in the two threshold ranges. (2) CSR has a significantly negative single-threshold effect on haze pollution; that is, the increase in CSR intensity inhibits haze pollution. Such a negative effect shows the characteristics of increasing marginal efficiency. (3) In addition, the provinces in different thresholds display obvious geographical distribution characteristics. Through the above analysis, it can be observed that FDI and CSR have distinct impacts on haze pollution. Thus, the country and the government can reduce haze pollution by improving the investment structure, using environmentally friendly technology, guiding enterprises to abide by business ethics and promoting social responsibilities fulfilment.

Identify travel and health factors influencing well-being of the older adults-a case study in China.

Objective: With the increase in aging populations worldwide, the travel well-being of the elders has gained attention. The objective of this study is to examine the nonlinear relationships between the well-being of the older people in China and factors associated with travel and health. Method: Based on the data collected in China, combined embedded feature selection and decision tree built by Gini index were utilized to screen for influential factors and to determine the importance of the features selected. Tamhane's T2 was used to study the differences in the important factors among older people with different levels of travel well-being. Results: This study found that the travel well-being of older adults depends mainly on accessibility to public places, such as schools and medical facilities, and the availability of bus services. Out of expectation, the most important influential factor of travel well-being of older people is the distance from home to high school. This is related to the traditional Chinese concept of education. In addition, it was found that the body mass index is more important than self-perceived health as an influence factor of travel well-being of the elders in China. Social skills are important factors too. Conclusion: This study investigated various health-related and travel-related factors and their impacts on the travel well-being of older adults Chinese with the overall goal to improve the quality of life of the elders in China. The findings may provide a theoretical basis for the implementation of various transportation management and urban planning and design -related policies to improve the travel well-being of older adults in China.

A dynamic method to predict driving risk on sharp curves using multi-source data.

Traffic accidents are likely to occur on sharp curves under poor driving conditions, and the severity level of such accidents is high. Therefore, predicting the risk associated with driving on curved roadways in real time can effectively improve driving safety. This paper aims to develop a dynamic real-time method that fuses multiple data sources to predict risk when driving on sharp curves in the context of the connected vehicle environment. Six curves with three small radii (60 m, 100 m, 150 m) and two driving directions (left and right) were designed for a driving simulation experiment. Driver maneuvering data, vehicle kinematic data, and physiological data of 55 drivers were collected for this study. The data were combined and spatially and dynamically segmented. The mean value of the critical lateral acceleration of the vehicle was set as the risk assessment index. K-means clustering was used to classify the driving risk into three levels: low, medium, and high. Then, the risk level was predicted using the maneuvering data, vehicle kinematic data, and physiological data as well as road alignment characteristics as input features for the proposed model that employs the long short-term memory (LSTM) network algorithm. Models with different combinations of observation window (lookback) and interval window (delay) were compared to derive the best window combination. The algorithms selected for comparison against the LSTM algorithm are random forest, XGBoost, and LightGBM. The results show that the proposed LSTM-based method can effectively predict dangerous driving behavior on sharp curves. The optimal window combination derived using the LSTM algorithm is lookback = 20 m and delay = 20 m. The prediction performance of the proposed model is significantly better than that of the other three compared algorithms, with F1-scores of 84.8% and 86.0% for the medium and high risk categories, respectively. In addition, the proposed LSTM-based model that fuses multiple data sources is proven to outperform the model that uses only vehicle kinematics data. The dynamic prediction method proposed in this paper can contribute to the development of a real-time prediction and warning system for driving risks at vehicle terminals in the intelligent connected vehicle environment.

Prediction and analysis of likelihood of freeway crash occurrence considering risky driving behavior.

The prediction of the likelihood of vehicle crashes constitutes an indispensable component of freeway safety management. Due to data collection limitations, studies have used mainly traffic flow-related variables to develop freeway crash prediction models but rarely have considered the effect of risky driving behavior on the likelihood of crashes. This study employed navigation software to collect driving behavior data and integrated multi-source data that include vehicle speed, traffic volume, and congestion index values. The study also employed the 'synthesizing minority oversampling technique and edited nearest neighbor' (SMOTE + ENN) coupled method for data balance processing. Three freeway crash likelihood prediction models were built based on the binomial logit, eXtreme Gradient Boosting (XGBoost), and support vector machine algorithms, respectively. The Shapley additive explanation (SHAP) algorithm was utilized to explore the effect of each feature variable on the likelihood of crashes. The results show that the prediction accuracy of the XGBoost model is the best of the three compared models. Under the optimal control-to-case ratio (1:1), the prediction accuracy of the XGBoost model reached 0.96 in this study, and the recall rate, specificity, and area-under-the-curve values were 0.86, 0.96, and 0.907, respectively. Comparative test results demonstrate that ranking risky driving behavior into three levels of intensity can effectively enhance the predictive accuracy of the XGBoost model. Moreover, the XGBoost model with its ten-minute time step outperformed the XGBoost model with its five-minute time step in terms of prediction accuracy. The results of the SHAP-based analysis show that the likelihood of highway crashes is high when the traffic congestion level is high and the distribution of the vehicle speed in the upstream roadway section is significant. Also, both sharp acceleration and sharp deceleration lead to greater likelihood of crashes. This paper aims to provide an effective framework for predicting and interpreting the likelihood of freeway crashes, thereby providing guidance for crash prevention, driver training, and the development of traffic regulations.

Parental Autonomy Support and Mental Health among Chinese Adolescents and Emerging Adults: The Mediating Role of Self-Esteem.

Guided by the dual-factor model and self-determination theory, this study explored the relationship between parental autonomy support and mental health (i.e., life satisfaction and emotional problems) in adolescents and emerging adults, with a focus on the mediating role of self-esteem. We conducted two studies among independent samples in China, including 1617 adolescents aged 10 to 17 years (Mage =12.79, SD = 1.63; 50.7% girls; Study 1) and 1274 emerging adults aged 17 to 26 years (Mage = 20.31, SD = 1.63; 56.6% women; Study 2). All participants completed a set of self-reported questionnaires. The results of both studies validated our hypothesis; specifically, parental autonomy support was positively associated with life satisfaction, but negatively associated with emotional problems (emotional symptoms in Study 1 and depressive symptoms in Study 2). Meanwhile, self-esteem partially mediated the positive relationship between parental autonomy support and life satisfaction (R2 = 0.33 in Study 1; R2 = 0.38 in Study 2), and partially mediated the negative relationship between parental autonomy support and emotional problems (R2 = 0.16 in Study 1; R2 = 0.42 in Study 2). In summary, this suggests that the common antecedents of positive and negative indicators of mental health addressed in this study are prevalent in adolescents and emerging adults. These findings have important implications for preventive and interventional efforts aimed at mental health problems in both demographics.

Teacher autonomy support and externalizing problems: Variations based on growth mindset toward personality and ethnicity.

Introduction: Given the prevalence of externalizing problems during adolescence, the present study investigated the main and interactive relationships between environmental-level (teacher autonomy support) and person-level (growth mindset toward personality) factors related to externalizing problems. This study further estimated ethnic variations of these relationships among the majority Han and one ethnic minority group (Hui) in China. Methods: To achieve the research objectives, the study involved 704 Han (M age = 12.57; 53.7% female) and 642 Hui adolescents (M age = 12.45; 49.4% female) who completed a suite of research questionnaires. Results: The results of the hierarchical linear regression analysis, after controlling for sociodemographic characteristics and comorbid internalizing problems, showed that teacher autonomy support was directly and negatively related to externalizing problems. This negative relationship was also moderated by growth mindset toward personality and ethnicity. More specifically, a high growth mindset buffered the undesirable effect of low teacher autonomy support on externalizing problems for Hui adolescents but not Han adolescents. Discussion: The finding from the current research suggests that teacher autonomy support plays a universally beneficial role in youth mental health across two selected ethnic groups. At the same time, identifying the protective role of growth mindset has important practical implications for the design of personalized school-based activities that aim to facilitate adaptive youth behaviors.

Openness to Experience Moderates the Association of Warmth Profiles and Subjective Well-Being in Left-Behind and Non-Left-Behind Youth.

Crouched in the socioecological framework, the present research compared the subjective well-being of left-behind youth with their non-left-behind peers. Furthermore, this research investigated the association of parental warmth and teacher warmth using a person-centered approach with adolescents' subjective well-being on the whole sample, and examined its conditional processes by ascertaining the moderating role of openness to experience and left-behind status in this association. A total of 246 left-behind youth (53.6% girls; Mage = 15.77; SD = 1.50) and 492 socio-demographically matched, non-left-behind peers (55.1% girls; Mage = 15.91; SD = 1.43) was involved in this study. During school hours, these adolescents were uniformly instructed to complete a set of self-report questionnaires. The results from ANCOVA exhibited no significant differences in subjective well-being between these two groups of youth. Moreover, four warmth profiles were revealed: congruent low, congruent highest, congruent lowest, and incongruent moderate, and youth within the congruent highest profile were more likely than the other three profiles to report higher subjective well-being. Additionally, moderation analyses demonstrated that high openness was one protective factor for subjective well-being, when left-behind youth perceived the lowest levels of parental warmth and teacher warmth congruently. These findings indicate that left-behind youth may not be psychologically disadvantaged in terms of positive psychosocial outcomes, such as subjective well-being, and school activities or social initiatives emphasizing openness to experience would be essential for them to facilitate positive adaptive patterns after parental migration.

Parental Autonomy Support and Pathological Internet Use among Chinese Undergraduate Students: Gratitude Moderated the Mediating Effect of Filial Piety.

Applying an integrated theoretical model consisting of the socioecological theory, the self-determination theory, and the broaden-and-build theory, the present study tested a moderated mediation model of parental autonomy support, filial piety, and gratitude to study how these factors are jointly related to pathological Internet use (PIU) in Chinese undergraduate students. A total of 1054 Chinese undergraduate students (M age = 20.35, SD = 1.00, 34.7% females) aged between 16 and 24 years participated in this study. They were instructed to complete self-reported questionnaires on parental autonomy support, filial piety, gratitude, and PIU. The results showed that parental autonomy support was negatively associated with PIU, and filial piety partially mediated this relation. Specifically, parental autonomy support was positively related to filial piety, which, in turn, was negatively associated with PIU. In addition, gratitude moderated the first path of the indirect relation and the direct relation of this mediation effect. To be specific, undergraduate students with higher gratitude showed high filial piety and low PIU, in the context of low parental autonomy support, than those with lower gratitude. Taken together, the current study contributes to extant research by highlighting the vital role of parental autonomy support in mitigating undergraduate students' PIU and illustrating how filial piety explains the underlying mechanism of this association. This study also provides novel insights into intervention or prevention programs by demonstrating that gratitude alleviates the adverse effect of low parental autonomy support on students' PIU.

The Correlation between Serum Sclerostin Level and Arterial Stiffness in Peritoneal Dialysis Patients.

Objective: To study the correlation between serum sclerostin (SO) and arterial stiffness in peritoneal dialysis (PD) patients. Methods: The study included 50 Parkinson's disease (PD) patients on continuous ambulatory peritoneal dialysis (CAPD) for more than 6 months at the nephrology department of our hospital. Without regard for age, the eligible patients were assigned to a low PWV group and a high PWV group with brachial-ankle pulse wave velocity (Ba PWV) of 1400 cm/s as the cutoff value. Patient characteristics such as age, gender, height, weight, BMI, smoking history, dialysis age, systolic blood pressure (SBP), diastolic blood pressure (DBP), urea clearance index (Kt/V), residual renal function (RRF), and diabetes mellitus (DM) were analyzed. Biochemical indices for analysis include hemoglobin (Hb), albumin (ALB), total cholesterol (TC), urea nitrogen (BUN), creatinine (CREA), triglyceride (TG), uric acid (UA), parathyroid hormone (PTH), blood phosphorus(P), fasting blood glucose (GLU), corrective calcium (Ca), calcium-phosphorus product, low-density lipoprotein (LDL-C), high-density lipoprotein (HDL-C), SO, and arterial stiffness. Results: There were 9 males and 16 females in the low PWV group and 12 males and 13 females in the high PWV group. Statistical significance was absent in patient characteristics despite more males in the high PWV group (P=0.055). The low PWV group had significantly lower mean age, SBP, SO, and PWV level, fewer diabetic patients, and higher CREA than the control group. Analysis of PWV-related factors showed that PWV was positively correlated with age, P, Ca, GLU, SBP, PTH, and SO while negatively correlated with CREA. Multiple stepwise regression analysis showed that age, SO, and SBP demonstrated great potential to predict PWV (P < 0.05). Conclusion: The degree of vascular sclerosis is highly correlated with SO level in Parkinson's disease patients, which might provide a theoretical basis for the evaluation of cardiovascular illness in Parkinson's disease patients. High serum sclerostin level is a risk factor for deteriorated arterial stiffness. Given the limited sample size, the relevant results require further validation by expanding the sample size.

What Affects Emotional Well-Being during Travel? Identifying the Factors by Maximal Information Coefficient.

Traveler emotional well-being as a specific domain of subjective well-being has attracted attention across the field of transportation. Studies on identifying factors of travel-related emotional well-being can help policy makers to formulate concrete strategies to improve travelers' experiences and public health. This research used the Maximal Information Coefficient (MIC) to select important factors which have much influence on emotional well-being during travel. American Time Use Survey data collected in 2010, 2012, and 2013 were used in this study and 10 factors have been selected to illustrate the relationship with emotional well-being, including rest, weekly earnings, activity time for well-being, health, self-evaluation of activities, pain medication taken yesterday, travel purpose, travel duration, weekly working hours and age based on MIC values in Descending sort. Among these 10 selected features, 2 factors, travel purpose and travel duration, are related to travel contexts; the other factors are related to personal and social characteristics. It is found that an individual's physical condition and self-evaluation of activities have much influence on travel-related emotional well-being, while traveling mode and interaction during travel have a relatively small impact on emotional well-being compared to other identified factors. This finding is different from previous research findings. The paper presents traffic strategies related to improving emotional well-being of travelers while traveling based on the findings from this research.

Driving style recognition and comparisons among driving tasks based on driver behavior in the online car-hailing industry.

As a product of the shared economy, online car-hailing platforms can be used effectively to help maximize resources and alleviate traffic congestion. The driver's behavior is characterized by his or her driving style and plays an important role in traffic safety. This paper proposes a novel framework to classify driving styles (defined as aggressive, normal, and cautious) based on online car-hailing data to investigate the distinct characteristics of drivers when performing various driving tasks (defined as cruising, ride requests, and drop-off) and undergoing certain maneuvers (defined as turning, acceleration, and deceleration). The proposed model is constructed based on the detection and classification of driving maneuvers using a threshold-based endpoint detection approach, principal component analysis, and k-means clustering. The driving styles that the driver exhibits for the different driving tasks are compared and analyzed based on the classified maneuvers. The empirical results for Nanjing, China demonstrate that the proposed framework can detect driving maneuvers and classify driving styles accurately. Moreover, according to this framework, driving tasks lead to variations in driving style, and the variations in driving style during the different driving tasks differ significantly for turning, acceleration, and deceleration maneuvers.

Real-Time Driving Behavior Identification Based on Multi-Source Data Fusion.

Real-time driving behavior identification has a wide range of applications in monitoring driver states and predicting driving risks. In contrast to the traditional approaches that were mostly based on a single data source with poor identification capabilities, this paper innovatively integrates driver expression into driving behavior identification. First, 12-day online car-hailing driving data were collected in a non-intrusive manner. Then, with vehicle kinematic data and driver expression data as inputs, a stacked Long Short-Term Memory (S-LSTM) network was constructed to identify five kinds of driving behaviors, namely, lane keeping, acceleration, deceleration, turning, and lane changing. The Artificial Neural Network (ANN) and XGBoost algorithms were also employed as a comparison. Additionally, ten sliding time windows of different lengths were introduced to generate driving behavior identification samples. The results show that, using all sources of data yields better results than using the kinematic data only, with the average F1 value improved by 0.041, while the S-LSTM algorithm is better than the ANN and XGBoost algorithms. Furthermore, the optimal time window length is 3.5 s, with an average F1 of 0.877. This study provides an effective method for real-time driving behavior identification, and thereby supports the driving pattern analysis and Advanced Driving Assistance System.