Query：
学者姓名：赵永翔
Refining：
Year
Type
Indexed by
Source
Complex
Former Name
Co-
Language
Clean All
Abstract ：
To address the challenges in E-learning engagement detection, such as dependence on specialized equipment, intrusive and disruptive methods, and limited detection dimensions, a novel framework based on behavioral and emotional cues for E-learning engagement detection is proposed. Utilizing the MediaPipe module, we developed four feature models: head posture, blink rate, gaze, and facial emotion. Subsequently, we introduced engagement evaluation metrics, such as the unit time distraction/smile ratio, and captured and analyzed learners’ behavioral performance and emotional changes by integrating facial feature information across different time units. Ultimately, an efficient, low-cost, and easy-to-deploy automatic learner engagement recognition system was created. Experimental results demonstrated that the proposed head posture evaluation model outperformed the latest machine learning methods in terms of accuracy, robustness, and computational efficiency. The blinking detection model based on dynamic EAR thresholds improved the limitations of the current fixed EAR threshold method in handling individual differences. The gaze tracking model exhibited superior overall performance compared to the latest computer vision schemes based on the MediaPipe iris module. The smile detection model based on XGBoost and MediaPipe facial landmarks also outperformed deep learning methods in accuracy, training, and inference time. Overall, compared to other recent research achievements, the proposed models achieved satisfactory recognition accuracy, higher computational efficiency, and lower hardware requirements, making them suitable for widespread deployment on edge devices and demonstrating their practical application value in E-learning scenarios. © 2025 Elsevier Ltd
Keyword ：
Deep learning Deep learning Face recognition Face recognition
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wang, Jie , Yuan, Shuiping , Lu, Tuantuan et al. Video-based real-time monitoring of engagement in E-learning using MediaPipe through multi-feature analysis [J]. | Expert Systems with Applications , 2025 , 288 . |
| MLA | Wang, Jie et al. "Video-based real-time monitoring of engagement in E-learning using MediaPipe through multi-feature analysis" . | Expert Systems with Applications 288 (2025) . |
| APA | Wang, Jie , Yuan, Shuiping , Lu, Tuantuan , Zhao, Hao , Zhao, Yongxiang . Video-based real-time monitoring of engagement in E-learning using MediaPipe through multi-feature analysis . | Expert Systems with Applications , 2025 , 288 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Learning engagement is regarded as an important metric for assessing E-learning since it is related to the quality of online education and student performance. Previous studies have identified a correlation between heart rate variability (HRV) and learning engagement. However, a comprehensive and systematic investigation of the underlying mechanisms remains lacking. In this study, a GRU-TCN model was developed to classify learner engagement levels in E-learning based on photoplethysmography (PPG). PPG signals were collected from 40 participants as they learned the video course under task conditions of no-interference, music & bullet chat stimuli, and mental arithmetic. Twenty-eight HR/HRV metrics (including time-domain, frequency-domain, and Non-linear metrics) were examined, among which 10 metrics were sensitive to changes in learner engagement. To adjust for individual differences in heart response in learning tasks and to enhance the data, a three-step processing procedure was conducted to evaluate the PPG signals of each participant: (1) defined three levels of learning engagement: full attention, external, and internal divided attention, (2) normalized HRV metrics for different engagement levels by using the average metric of participants' baseline states, (3) Enhanced data with sliding time windows. The GRU-TCN classification model achieved F1-scores of 95% in the training set and 85% in the testing set, respectively, enabling effective automatic real-time tracking of learner engagement in Elearning.
Keyword ：
Divided attention Divided attention HRV HRV Learning engagement Learning engagement
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wang, Jie , Lu, Tuantuan , Huang, Ruogu et al. Classifying engagement in E-learning through GRU-TCN model using photoplethysmography signals [J]. | BIOMEDICAL SIGNAL PROCESSING AND CONTROL , 2024 , 90 . |
| MLA | Wang, Jie et al. "Classifying engagement in E-learning through GRU-TCN model using photoplethysmography signals" . | BIOMEDICAL SIGNAL PROCESSING AND CONTROL 90 (2024) . |
| APA | Wang, Jie , Lu, Tuantuan , Huang, Ruogu , Zhao, Yongxiang . Classifying engagement in E-learning through GRU-TCN model using photoplethysmography signals . | BIOMEDICAL SIGNAL PROCESSING AND CONTROL , 2024 , 90 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
The rapid advancements in computer vision technology present significant potential for the automatic recognition of learner engagement in E-learning. We conducted a two-stage experiment to assess learner engagement based on behavioural (external observations) and physiological (internal factors) cues. Using computer vision technology and wearable sensors, we extracted three feature sets: action, head posture and heart rate variability (HRV). Subsequently, we integrated our constructed YOLOv5s-MediaPipe behaviour detection model with a physiological detection model based on HRV to comprehensively evaluate learners' behavioural, affective and cognitive engagement. Additionally, we developed a method and criteria for assessing distraction based on behaviour, ultimately creating a comprehensive, efficient, low-cost and easy-to-use system for the automatic recognition of learner engagement. Experimental results showed that our improved YOLOv5s model achieved a mean average precision of 92.2 %, while halving both the number of parameters and model size. Unlike other deep learning-based methods, using MediaPipe-OpenCV for head posture analysis offers advantages in real-time performance, making it lightweight and easy to deploy. Our proposed long short-term memory classifier, based on sensitive HRV metrics and their normalisation, demonstrated satisfactory performance on the test set, with an accuracy = 80 %, precision = 81 %, recall = 80 % and an F1 score = 80 %.
Keyword ：
Computer vision Computer vision HRV HRV Learner engagement Learner engagement MediaPipe MediaPipe
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wang, Jie , Yuan, Shuiping , Lu, Tuantuan et al. Fusing YOLOv5s-MediaPipe-HRV to classify engagement in E-learning: From the perspective of external observations and internal factors [J]. | KNOWLEDGE-BASED SYSTEMS , 2024 , 305 . |
| MLA | Wang, Jie et al. "Fusing YOLOv5s-MediaPipe-HRV to classify engagement in E-learning: From the perspective of external observations and internal factors" . | KNOWLEDGE-BASED SYSTEMS 305 (2024) . |
| APA | Wang, Jie , Yuan, Shuiping , Lu, Tuantuan , Zhao, Hao , Zhao, Yongxiang . Fusing YOLOv5s-MediaPipe-HRV to classify engagement in E-learning: From the perspective of external observations and internal factors . | KNOWLEDGE-BASED SYSTEMS , 2024 , 305 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Increasing information can make actions more effective, thereby improving cooperation levels. However, this assumption lacks experimental support in the case of long-range migration, and the potential mechanism for higher cooperation rates resulting from inter-group migration is not yet clear. Therefore, we mainly studied the impact of four different information levels on group cooperation behavior from an experimental perspective through public goods game experiments in the context of long-range migration. The results indicate that the amount of information can significantly affect individual mobility and cooperation evolution. Defection prevails among players in the absence of information, leading to the formation of a stable cluster of defectors. However, with increased information about profit calculation rules, players tend to settle in favorable cooperative groups. Increased information about the decisions of other players speeds up the formation of stable cooperative groups. Excessive information disclosure about payoffs leads to increased mobility and reduced cooperation among group members. These findings provide insights into our understanding of the evolution history of human cooperation and the formation of groups.
Keyword ：
Behavioral experiment Behavioral experiment Black box Black box Cooperation evolution Cooperation evolution Information Information Mobility Mobility Social dilemma game Social dilemma game
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Ran, Meng , Li, Meifang , Zhao, Yongxiang . Long-range mobility and cooperation evolution under condition of different information amounts [J]. | CHAOS SOLITONS & FRACTALS , 2023 , 173 . |
| MLA | Ran, Meng et al. "Long-range mobility and cooperation evolution under condition of different information amounts" . | CHAOS SOLITONS & FRACTALS 173 (2023) . |
| APA | Ran, Meng , Li, Meifang , Zhao, Yongxiang . Long-range mobility and cooperation evolution under condition of different information amounts . | CHAOS SOLITONS & FRACTALS , 2023 , 173 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
This paper investigates a new lane reservation problem with task merging that consists of optimally determining which lanes in a transportation network have to be reserved and designing reserved lane-based routes in the network for time-crucial transport tasks. Part of the tasks whose destinations are geographically close is merged to reduce the number of vehicles and transport costs. Reserved lanes can reduce the travel time of task vehicles passing through them, while they will generate negative impact on normal traffic, such as traffic delay to the vehicles on adjacent non-reserved lanes. The objective is to minimize the total negative impact of all reserved lanes. For this problem, two new integer linear programming (ILP) models are first developed. The complexity of the problem is proved to be NP-hard. Since commercial solver (like CPLEX) is time-consuming for solving it when the problem size increases, a fast and effective improved differential evolution algorithm (IDEA) is developed based on explored problem properties. Extensive experimental results for a real-life case and benchmark instances of up to 500 nodes in the network and 30 transport tasks show the favorable performance of the IDEA, as compared to CPLEX, differential evolution algorithm and genetic algorithm. Management insights are also drawn to support practical decision-making.
Keyword ：
Costs Costs differential evolution algorithm differential evolution algorithm Games Games integer linear programming integer linear programming Lane reservation Lane reservation Merging Merging Roads Roads Task analysis Task analysis task merging task merging Transportation Transportation Uncertainty Uncertainty
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wu, Peng , Xu, Ling , D'Ariano, Andrea et al. Novel Formulations and Improved Differential Evolution Algorithm for Optimal Lane Reservation With Task Merging [J]. | IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS , 2022 , 23 (11) : 21329-21344 . |
| MLA | Wu, Peng et al. "Novel Formulations and Improved Differential Evolution Algorithm for Optimal Lane Reservation With Task Merging" . | IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 23 . 11 (2022) : 21329-21344 . |
| APA | Wu, Peng , Xu, Ling , D'Ariano, Andrea , Zhao, Yongxiang , Chu, Chengbin . Novel Formulations and Improved Differential Evolution Algorithm for Optimal Lane Reservation With Task Merging . | IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS , 2022 , 23 (11) , 21329-21344 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
In this paper, a modified floor field model is presented to study crowd dynamics involving individuals with disabilities (i.e. pedestrians on crutches, seniors with sticks, pedestrians in manual wheelchairs and blind pedestrians). Multi-speed characteristics, overtaking and helping behaviors are considered in our model. Through simulations in unidirectional pedestrian flow in a corridor, it is observed that overtaking behavior has a positive effect on pedestrian flow at low density. Helping behavior can significantly improve the maximum flow rate and critical density of a system. In comparison with overtaking behavior, helping behavior is more beneficial to heterogeneous crowd movement, when density is higher than the critical density. The phenomenon that the proportion of individuals with disabilities has a negative influence on crowd movement efficiency is reproduced. It is hoped that this study will enrich movement rules and modeling approaches for individuals with disabilities, and be helpful in crowd management and evacuation organization.
Keyword ：
traffic and crowd dynamics traffic and crowd dynamics traffic models traffic models
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Fu, Libi , Liu, Yuxing , Shi, Yongqian et al. Unidirectional pedestrian flow in a corridor involving individuals with disabilities: a modified floor field modelling approach [J]. | JOURNAL OF STATISTICAL MECHANICS-THEORY AND EXPERIMENT , 2021 , 2021 (7) . |
| MLA | Fu, Libi et al. "Unidirectional pedestrian flow in a corridor involving individuals with disabilities: a modified floor field modelling approach" . | JOURNAL OF STATISTICAL MECHANICS-THEORY AND EXPERIMENT 2021 . 7 (2021) . |
| APA | Fu, Libi , Liu, Yuxing , Shi, Yongqian , Zhao, Yongxiang . Unidirectional pedestrian flow in a corridor involving individuals with disabilities: a modified floor field modelling approach . | JOURNAL OF STATISTICAL MECHANICS-THEORY AND EXPERIMENT , 2021 , 2021 (7) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Stairs are usually one of the most important evacuation routes in emergencies, such as serious fire accidents or other emergencies. However, experimental data on human movement characteristics on stairs under invisible conditions are limited. A series of pedestrian evacuation experiments were conducted on a staircase to uncover typical behavior characteristics of staircase evacuation for both ascent and descent without visibility. After obtaining the trajectories of pedestrians by video tracking technology, the route-choice behavior, speeds on the stairs and speeds on the landing were analyzed. Firstly, results demonstrate that pedestrians tend to use the enclosure for help when ascending and descending without visibility for safety consideration, and offset angle is correlated with pedestrians' route-choice behavior. Interestingly, there is no significant difference of speeds on the stairs between ascent and descent, which is different from the finding that descending is faster than ascending under good visibility conditions. Further detailed features including density-speed relations, headway-speed relations and speed-amplitude relations for both upward and downward are discussed. Especially, it is found that the headway-speed relation on the stairs has a correlation with tread depth and arm length due to the constraint of staircase structure as well as the touch behavior. Finally, it is discovered that the mid landing has different effects on speed between ascending and descending. When stepping on the landing, people lengthen stride lengths and increase speeds during ascending, but they shorten strides and decrease speeds during descending. These enrichments are helpful to understand pedestrian evacuation characteristics on stairs without visibility.
Keyword ：
Behavior characteristics Behavior characteristics Headway-speed relation Headway-speed relation Mid landing Mid landing Route choice Route choice Stairs Stairs Visibility Visibility
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lu, Tuantuan , Zhao, Yongxiang , Wu, Peng et al. Pedestrian ascent and descent behavior characteristics during staircase evacuation under invisible conditions [J]. | SAFETY SCIENCE , 2021 , 143 . |
| MLA | Lu, Tuantuan et al. "Pedestrian ascent and descent behavior characteristics during staircase evacuation under invisible conditions" . | SAFETY SCIENCE 143 (2021) . |
| APA | Lu, Tuantuan , Zhao, Yongxiang , Wu, Peng , Zhu, Pengfei . Pedestrian ascent and descent behavior characteristics during staircase evacuation under invisible conditions . | SAFETY SCIENCE , 2021 , 143 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
In this paper, a modified floor field model is proposed to study dynamics of counter flow in a corridor involving various types of members, i.e., normal pedestrians, pedestrians on crutches, seniors with sticks, pedestrians in manual wheelchairs and blind pedestrians. Multi-speed characteristics, occupation difference and typical behaviors (i.e., overtaking, helping and avoidance behaviors) are simulated in our model. Through simulations in bidirectional flow, typical phenomena (namely lane formation and congestion) are created. The negative effect of the proportion of individuals with disabilities on movement efficiency of heterogeneous counter flow is reproduced. Results suggest that appropriate overtaking willingness has a positive influence on pedestrian counter flow. Helping behavior can induce pedestrian counter flow more orderly, and improve crowd movement efficiency. The proposed model is helpful to enrich modeling approaches for individuals with disabilities, and is beneficial to heterogeneous crowd management. (C) 2021 Published by Elsevier B.V.
Keyword ：
Counter flow Counter flow Floor field model Floor field model Helping behavior Helping behavior Individuals with disabilities Individuals with disabilities Overtaking behavior Overtaking behavior Simulation Simulation
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Fu, Libi , Liu, Yuxing , Shi, Yongqian et al. Dynamics of bidirectional pedestrian flow in a corridor including individuals with disabilities [J]. | PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS , 2021 , 580 . |
| MLA | Fu, Libi et al. "Dynamics of bidirectional pedestrian flow in a corridor including individuals with disabilities" . | PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS 580 (2021) . |
| APA | Fu, Libi , Liu, Yuxing , Shi, Yongqian , Zhao, Yongxiang . Dynamics of bidirectional pedestrian flow in a corridor including individuals with disabilities . | PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS , 2021 , 580 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
In order to uncover the characteristics of pedestrian movement under different social distancing measures, we performed a series of single-file experiments considering two types of social distancing measures, namely 1 m and 2 m, and compared them with normal experiments conducted before Covid-19. Firstly, the findings indicate that social distancing measures do make pedestrians keep a greater distance, but there are social distance violations. When the density is greater than 0.23 m(-1), pedestrians have more violations under the measure of 2 m than that of 1 m at the same density. Although the typical stop-and-go wave is still observed in social distancing experiments, the increase in social distancing causes pedestrian stopping behavior to occur at lower density, and shortens the density range of the transition from free flow to jammed flow. Moreover, the headway-speed relation under social distancing measures is not a simple horizontal displacement of that under normal conditions. Although their free speeds are similar, the increase in social distancing makes pedestrians need longer adaption time and more space to transform the motion state. Finally, fundamental diagrams are obtained, and the maximum specific flows for social distancing of 1 m and 2 m is 0.62 s(-1) and 0.53 s(-1), respectively. Apart from the comparison with normal conditions, the comparison with the two-dimensional social distancing experiments shows that pedestrians are more able to comply with the prescribed social distance and stop less in single-file movement. These enrichments offer empirical data of pedestrian movement under different social distancing measures and benefit pedestrian modeling during pandemics.
Keyword ：
traffic and crowd dynamics traffic and crowd dynamics
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lu, Tuantuan , Zhao, Yongxiang , Wu, Peng et al. Dynamic analysis of single-file pedestrian movement with maintaining social distancing in times of pandemic [J]. | JOURNAL OF STATISTICAL MECHANICS-THEORY AND EXPERIMENT , 2021 , 2021 (9) . |
| MLA | Lu, Tuantuan et al. "Dynamic analysis of single-file pedestrian movement with maintaining social distancing in times of pandemic" . | JOURNAL OF STATISTICAL MECHANICS-THEORY AND EXPERIMENT 2021 . 9 (2021) . |
| APA | Lu, Tuantuan , Zhao, Yongxiang , Wu, Peng , Zhu, Pengfei . Dynamic analysis of single-file pedestrian movement with maintaining social distancing in times of pandemic . | JOURNAL OF STATISTICAL MECHANICS-THEORY AND EXPERIMENT , 2021 , 2021 (9) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
With the increase of transport demands, more pressure and challenges are being imparted into efficient transportation. As a conventional and direct congestion alleviation strategy, constructing new roads and lanes are increasingly restricted by limited land resources and high costs. Thus, making full use of existing transport network via appropriate management is critical to realize the sustainable development of transportation systems. As a flexible management strategy, lane reservation strategy has been widely adopted in real life. The reserved lanes can improve the efficiency of special transports, while they bring negative impact such as travel delay for general-purpose transports. In addition, the setting and operating of reserved lanes require a certain amount of cost. This paper proposes a new dual-objective integer linear programming model for optimally determining reserved lanes on a network for time-guaranteed special transports in order to simultaneously maximize the benefits and minimize the negative impact brought by reserved lanes, which incorporates road residual capacity and limited budget to the actual decision. Moreover, an iterative weighted sum-based method is proposed to solve it, in which a new relax-and-optimize algorithm is developed to exactly solve the single-objective optimization problems. Results of extensive numerical experiments show the effectiveness and efficiency of the proposed model and approach.
Keyword ：
IP networks IP networks Iterative methods Iterative methods Lane reservation (LR) Lane reservation (LR) modeling and simulation modeling and simulation multiobjective optimization multiobjective optimization Numerical models Numerical models Optimization Optimization relax-and-optimize relax-and-optimize Roads Roads Task analysis Task analysis transportation transportation
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wu, Peng , Chu, Feng , Che, Ada et al. Dual-Objective Optimization for Lane Reservation With Residual Capacity and Budget Constraints [J]. | IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS , 2020 , 50 (6) : 2187-2197 . |
| MLA | Wu, Peng et al. "Dual-Objective Optimization for Lane Reservation With Residual Capacity and Budget Constraints" . | IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS 50 . 6 (2020) : 2187-2197 . |
| APA | Wu, Peng , Chu, Feng , Che, Ada , Zhao, Yongxiang . Dual-Objective Optimization for Lane Reservation With Residual Capacity and Budget Constraints . | IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS , 2020 , 50 (6) , 2187-2197 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
