Accidents are still an issue in an intelligent transportation system,despite developments in self-driving technology(ITS).Drivers who engage in risky behavior account for more than half of all road accidents.As a resu...Accidents are still an issue in an intelligent transportation system,despite developments in self-driving technology(ITS).Drivers who engage in risky behavior account for more than half of all road accidents.As a result,reckless driving behaviour can cause congestion and delays.Computer vision and multimodal sensors have been used to study driving behaviour categorization to lessen this problem.Previous research has also collected and analyzed a wide range of data,including electroencephalography(EEG),electrooculography(EOG),and photographs of the driver’s face.On the other hand,driving a car is a complicated action that requires a wide range of body move-ments.In this work,we proposed a ResNet-SE model,an efficient deep learning classifier for driving activity clas-sification based on signal data obtained in real-world traffic conditions using smart glasses.End-to-end learning can be achieved by combining residual networks and channel attention approaches into a single learning model.Sensor data from 3-point EOG electrodes,tri-axial accelerometer,and tri-axial gyroscope from the Smart Glasses dataset was utilized in this study.We performed various experiments and compared the proposed model to base-line deep learning algorithms(CNNs and LSTMs)to demonstrate its performance.According to the research results,the proposed model outperforms the previous deep learning models in this domain with an accuracy of 99.17%and an F1-score of 98.96%.展开更多
The paper deals with active drive system for colonoscope. The system is mainly composed of soft mobile mechanism for earthworm locomotion and turning mechanism based on shape memory effect. The soft mobile mechanism c...The paper deals with active drive system for colonoscope. The system is mainly composed of soft mobile mechanism for earthworm locomotion and turning mechanism based on shape memory effect. The soft mobile mechanism contacts colon wall with air in inflatable balloons, so the robot has better soft and non invasive properties. The turning mechanism can be actively bent by shape memory alloy components. It ensures the colonoscope to adapt to the tortuous shape of colon. Some experiment results are given in the paper.展开更多
With the continual increase in switching speed and rating of power semiconductors, the switching voltage spike becomes a serious problem. This paper describes a new technique of driving pulse edge modulation for insul...With the continual increase in switching speed and rating of power semiconductors, the switching voltage spike becomes a serious problem. This paper describes a new technique of driving pulse edge modulation for insulated gate bipolar transistors(IGBTs). By modulating the density and width of the pulse trains, without regulating the hardware circuit, the slope of the gate driving voltage is controlled to change the switching speed. This technique is used in the driving circuit based on complex programmable logic devices(CPLDs), and the switching voltage spike of IGBTs can be restrained through software, which is easier and more flexible to adjust. Experimental results demonstrate the effectiveness and practicability of the proposed method.展开更多
High-frequency switching of power transistors in power electronic systems can cause electromagnetic emissions.Simple approaches for reducing high-frequency disturbances,such as inserting an additional gate resistor,le...High-frequency switching of power transistors in power electronic systems can cause electromagnetic emissions.Simple approaches for reducing high-frequency disturbances,such as inserting an additional gate resistor,lead to increased power losses.This makes achieving both electromagnetic compatibility and power efficiency difficult.Active gate drivers help to find a trade-off between these two.Typically,only narrow-band disturbances must be reduced.Accordingly,a target signal with a spectrum notched at some frequencies can be defined.The target signal can be reached by a target-signal-oriented control of the transistor’s gate.This leads to steeper switching slopes,such that the power losses are less increased.Generating arbitrary target signals is impossible.The transistor signal exhibits some physical limitations.A constraint satisfaction problem must be solved,and the gate drive signal must be optimized by applying a residual and Newton’s method.The proposed optimization process in the frequency domain is based on the circuit simulation method named“harmonic balance”.Measurements on a DC/DC converter exhibit the benefits of this method.展开更多
基金support provided by Thammasat University Research fund under the TSRI,Contract Nos.TUFF19/2564 and TUFF24/2565for the project of“AI Ready City Networking in RUN”,based on the RUN Digital Cluster collaboration scheme.This research project was also supported by the Thailand Science Research and Innovation fund,the University of Phayao(Grant No.FF65-RIM041)supported by National Science,Research and Innovation(NSRF),and King Mongkut’s University of Technology North Bangkok,Contract No.KMUTNB-FF-66-07.
文摘Accidents are still an issue in an intelligent transportation system,despite developments in self-driving technology(ITS).Drivers who engage in risky behavior account for more than half of all road accidents.As a result,reckless driving behaviour can cause congestion and delays.Computer vision and multimodal sensors have been used to study driving behaviour categorization to lessen this problem.Previous research has also collected and analyzed a wide range of data,including electroencephalography(EEG),electrooculography(EOG),and photographs of the driver’s face.On the other hand,driving a car is a complicated action that requires a wide range of body move-ments.In this work,we proposed a ResNet-SE model,an efficient deep learning classifier for driving activity clas-sification based on signal data obtained in real-world traffic conditions using smart glasses.End-to-end learning can be achieved by combining residual networks and channel attention approaches into a single learning model.Sensor data from 3-point EOG electrodes,tri-axial accelerometer,and tri-axial gyroscope from the Smart Glasses dataset was utilized in this study.We performed various experiments and compared the proposed model to base-line deep learning algorithms(CNNs and LSTMs)to demonstrate its performance.According to the research results,the proposed model outperforms the previous deep learning models in this domain with an accuracy of 99.17%and an F1-score of 98.96%.
文摘The paper deals with active drive system for colonoscope. The system is mainly composed of soft mobile mechanism for earthworm locomotion and turning mechanism based on shape memory effect. The soft mobile mechanism contacts colon wall with air in inflatable balloons, so the robot has better soft and non invasive properties. The turning mechanism can be actively bent by shape memory alloy components. It ensures the colonoscope to adapt to the tortuous shape of colon. Some experiment results are given in the paper.
基金Project supported by the National Natural Science Foundation of China(No.51177147)the Zhejiang Key Science and Technology Innovation Group Program,China(No.2010R50021)
文摘With the continual increase in switching speed and rating of power semiconductors, the switching voltage spike becomes a serious problem. This paper describes a new technique of driving pulse edge modulation for insulated gate bipolar transistors(IGBTs). By modulating the density and width of the pulse trains, without regulating the hardware circuit, the slope of the gate driving voltage is controlled to change the switching speed. This technique is used in the driving circuit based on complex programmable logic devices(CPLDs), and the switching voltage spike of IGBTs can be restrained through software, which is easier and more flexible to adjust. Experimental results demonstrate the effectiveness and practicability of the proposed method.
文摘High-frequency switching of power transistors in power electronic systems can cause electromagnetic emissions.Simple approaches for reducing high-frequency disturbances,such as inserting an additional gate resistor,lead to increased power losses.This makes achieving both electromagnetic compatibility and power efficiency difficult.Active gate drivers help to find a trade-off between these two.Typically,only narrow-band disturbances must be reduced.Accordingly,a target signal with a spectrum notched at some frequencies can be defined.The target signal can be reached by a target-signal-oriented control of the transistor’s gate.This leads to steeper switching slopes,such that the power losses are less increased.Generating arbitrary target signals is impossible.The transistor signal exhibits some physical limitations.A constraint satisfaction problem must be solved,and the gate drive signal must be optimized by applying a residual and Newton’s method.The proposed optimization process in the frequency domain is based on the circuit simulation method named“harmonic balance”.Measurements on a DC/DC converter exhibit the benefits of this method.