Human action recognition has attracted considerable research attention in the field of computer vision, especially for classroom environments. However, most relevant studies have focused on one specific behavior of students. Therefore, this paper proposes a student behavior recognition system based on skeleton pose estimation and person detection. First, consecutive frames captured with a classroom camera were used as the input images of the proposed system. Then, skeleton data were collected using the OpenPose framework. An error correction scheme was proposed based on the pose estimation and person detection techniques to decrease incorrect connections in the skeleton data. The preprocessed skeleton data were subsequently used to eliminate several joints that had a weak effect on behavior classification. Second, feature extraction was performed to generate feature vectors that represent human postures. The adopted features included normalized joint locations, joint distances, and bone angles. Finally, behavior classification was conducted to recognize student behaviors. A deep neural network was constructed to classify actions, and the proposed system was able to identify the number of students in a classroom. Moreover, a system prototype was implemented to verify the feasibility of the proposed system. The experimental results indicated that the proposed scheme outperformed the skeleton-based scheme in complex situations. The proposed system had a 15.15% higher average precision and 12.15% higher average recall than the skeleton-based scheme did.

Existing intelligent transport systems (ITS) do not fully consider and resolve accuracy, instantaneity, and compatibility challenges while resolving traffic congestion in Internet of Vehicles (IoV) environments. This paper proposes a traffic congestion monitoring system, which includes data collection, segmented structure establishment, traffic‐flow modelling, local segment traffic congestion prediction, and origin‐destination traffic congestion service for drivers. Macroscopic model‐based traffic‐flow factors were formalized on the basis of the analysis results. Fuzzy rules‐based local segment traffic congestion prediction was performed to determine the traffic congestion state. To enhance prediction efficiency, this paper presents a verification process for minimizing false predictions which is based on the Rankine‐Hugoniot condition and an origin‐destination traffic congestion service is also provided. To verify the feasibility of the proposed system, a prototype was implemented. The experimental results demonstrate that the proposed scheme can effectively monitor traffic congestion in terms of accuracy and system response time.

With the rapid development of automatic driving and advanced driver assistance systems, vehicle safety has improved greatly. These systems mainly use sensors installed on the vehicle and help drivers deal with human operation errors. Traffic accidents are inherently unpredictable, and it is difficult to prevent mistakes made by others. Therefore, the concept of defensive driving has attracted much interest. Defensive driving aims to increase drivers’ self-awareness to prevent accidents. Future self-driving vehicles should integrate defensive driving to improve driver safety. This paper proposes a framework based on the risk evaluation value of defensive driving that rapidly transmits information about high-accident-likelihood zones to drivers or vehicles by using Internet of Vehicles technology. This should enable drivers or selfdriving vehicles to predict risks and operate vehicles safely. To send alert messages in a timely manner, it is essential to overcome the challenge of processing real-time data during driving. We design five kinds of services in this rapid response framework, including raw data receiver, warning area decision, accident pattern recognition, message generator and user profile to analyze driver information using distributed system architecture. Message-oriented middleware is used for communication between services. This framework identifies high-accident-likelihood zones by using DBSCAN, simplifying the process of association calculation. After the calculation, this framework uses the weighted severity index to weight and compare risk severities. According to our experimental results, the service-oriented middleware design increases the speed and stability of information transmission.

The limitation of battery capacity is a cause of range anxiety that reduces the wide use of electric bicycles (e-bikes). Therefore, many works have developed systems that provide assistance to cyclists to deal with the range anxiety problem. However, these systems may have limited applications since they can only work with the e-bike manufacturers’ hardware and communication protocols. This paper proposes an energy monitoring system (EMS) for e-bikes, which is based on EnergyBus, a standardized hardware and communication protocol for e-bikes. EnergyBus standard is based on controller area network (CAN) bus and CANopen protocols. EMS comprises a gateway connected to EnergyBus of e-bike and an EMS application installed on a smart device that connects to the gateway via Bluetooth. The gateway provides CAN bus monitoring and CANopen device data access services to the smart device. These services are modeled to determine gateway parameters to ensure the efficient performance of the gateway and to keep the working status of the monitored e-bike safe. The EMS application provides the cyclist information about battery status, rider efforts, and other related information such as distance and speed. Experimental results show that the proposed gateway can monitor data in real-time and ensure monitored system safety.