检索结果-南通市图书馆

A Survey and Tutorial of EEG-Based Brain Monitoring for Driver State Analysis

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2021年第7期8卷 1222-1242页

作者： ce zhang Azim Eskandarian Virginia Tech Mechanical Engineering Department ASIM Lab Virginia 24061-0131 USA

The driver’s cognitive and physiological states affect his/her ability to control the ***,these driver states are essential to the safety of *** design of advanced driver assistance systems(ADAS)or autonomous vehicles will depend on their ability to interact effectively with the driver.A deeper understanding of the driver state is,therefore,***(EEG)is proven to be one of the most effective methods for driver state monitoring and human error *** paper discusses EEG-based driver state detection systems and their corresponding analysis algorithms over the last three ***,the commonly used EEG system setup for driver state studies is ***,the EEG signal preprocessing,feature extraction,and classification algorithms for driver state detection are ***,EEG-based driver state monitoring research is reviewed in-depth,and its future development is *** is concluded that the current EEGbased driver state monitoring algorithms are promising for safety ***,many improvements are still required in EEG artifact reduction,real-time processing,and between-subject classification accuracy.

关键词： Advanced driver assistance systems(ADAS) data analysis electroencephalography(EEG) intelligent vehicles machine learning algorithms neural network.

Microstructure evolution and strengthening mechanism of high -performance powder metallurgy TA15 titanium alloy by hot rolling

在线全文

学校读者我要写书评

暂无评论

International Journal of Minerals,Metallurgy and Materials 2024年第6期31卷 1426-1436页

作者： Ying Gao ce zhang Jiazhen zhang Xin Lu Beijing Advanced Innovation center for Materials Genome Engineering State Key Laboratory for Advanced Metals and MaterialsInstitute for Advanced Ma-terials and TechnologyUniversity of Science and Technology BeijingBeijing 100083China National Engineering Research center for Advanced Rolling Technology National Engineering Research Center for Flat Rolling EquipmentInstitute of Engin-eering TechnologyUniversity of Science and Technology BeijingBeijing 100083China

Hot deformation of sintered billets by powder metallurgy(PM)is an effective preparation technique for titanium alloys,which is more significant for high-alloying *** this study,Ti–6.5Al–2Zr–Mo–V(TA15)titanium alloy plates were prepared by cold press-ing sintering combined with high-temperature hot *** microstructure and mechanical properties under different process paramet-ers were *** microscope,electron backscatter diffraction,and others were applied to characterize the microstructure evolution and mechanical properties strengthening *** results showed that the chemical compositions were uniformly dif-fused without segregation during sintering,and the closing of the matrix craters was accelerated by increasing the sintering *** block was hot rolled at 1200℃ with an 80%reduction under only two passes without *** strength and elongation of the plate at 20–25℃ after solution and aging were 1247 MPa and 14.0%,respectively,which were increased by 24.5%and 40.0%,respect-ively,compared with the as-sintered alloy at 1300℃.The microstructure was significantly refined by continuous dynamic recrystalliza-tion,which was completed by the rotation and dislocation absorption of the substructure surrounded by low-angle grain *** hot rolling combined with heat treatment,the strength and plasticity of PM-TA15 were significantly improved,which resulted from the dense,uniform,and fine recrystallization structure and the synergistic effect of multiple slip systems.

关键词： elemental powder powder metallurgy titanium alloy hot rolling strength and plasticity

Temporal sequence Object-based CNN(TS-OCNN) for crop classification from fine resolution remote sensing image time-series

在线全文

学校读者我要写书评

暂无评论

The Crop Journal 2022年第5期10卷 1507-1516页

作者： Huapeng Li Yajun Tian ce zhang Shuqing zhang Peter MAtkinson Northeast Institute of Geography and Agroecology Chinese Academy of SciencesChangchun 130012JilinChina Lancaster Environment centre Lancaster UniversityLancaster LA14YQUK Faculty of Science and Technology Lancaster UniversityLancaster LA14YRUK

Accurate crop distribution mapping is required for crop yield prediction and field management. Due to rapid progress in remote sensing technology, fine spatial resolution(FSR) remotely sensed imagery now offers great opportunities for mapping crop types in great detail. However, within-class variance can hamper attempts to discriminate crop classes at fine resolutions. Multi-temporal FSR remotely sensed imagery provides a means of increasing crop classification from FSR imagery, although current methods do not exploit the available information fully. In this research, a novel Temporal Sequence Object-based Convolutional Neural Network(TS-OCNN) was proposed to classify agricultural crop type from FSR image time-series. An object-based CNN(OCNN) model was adopted in the TS-OCNN to classify images at the object level(i.e., segmented objects or crop parcels), thus, maintaining the precise boundary information of crop parcels. The combination of image time-series was first utilized as the input to the OCNN model to produce an ‘original’ or baseline classification. Then the single-date images were fed automatically into the deep learning model scene-by-scene in order of image acquisition date to increase successively the crop classification accuracy. By doing so, the joint information in the FSR multi-temporal observations and the unique individual information from the single-date images were exploited comprehensively for crop classification. The effectiveness of the proposed approach was investigated using multitemporal SAR and optical imagery, respectively, over two heterogeneous agricultural areas. The experimental results demonstrated that the newly proposed TS-OCNN approach consistently increased crop classification accuracy, and achieved the greatest accuracies(82.68% and 87.40%) in comparison with state-of-the-art benchmark methods, including the object-based CNN(OCNN)(81.63% and85.88%), object-based image analysis(OBIA)(78.21% and 84.83%), and standard pixel-wise

关键词： Convolutional neural network Multi-temporal imagery Object-based image analysis(OBIA) Crop classification Fine spatial resolution imagery

Effects of adverse pressure gradient on Reynolds stresses inturbulent boundary layers

在线全文

学校读者我要写书评

暂无评论

航空动力学报 2017年第2期32卷 463-469页

作者： LUO Xiao-tian zhang ce MA Wei TENG Jin-fang School of Aeronautics and Astronautics Shanghai Jiao Tong University

The effects of adverse pressure gradient(APG)on Reynolds stresses in turbulent boundary layers(TBLs)with APG were *** difficulty of this work was attributable to the Reynolds stresses in TBLs with APG under two combined effects,i.e.:effect of upstream flow and effect of *** effect of upstream flow is an inherent effect no matter pressure gradient exists or *** individual effect was analyzed from absolute developments of Reynolds stresses in TBLs with zero pressure gradient(ZPG)*** of APG was then analyzed from absolute developments of Reynolds stresses in TBLs with *** showed that,for absolute development of mean streamwise Reynolds stresses,APG accelerated its development in TBL with ZPG;for absolute development of mean normal or shear Reynolds stresses,APG increased their magnitude in the outer part,and decreased their extent of large value region.

关键词： turbulent boundary layer adverse pressure gradient zero pressure gradient Reynolds stresses flat plate

Land cover classification from remote sensing images based on multi-scale fully convolutional network

在线全文

学校读者我要写书评

暂无评论

Geo-Spatial Information Science 2022年第2期25卷 278-294页

作者： Rui Li Shunyi Zheng Chenxi Duan Libo Wang ce zhang School of Remote Sensing and Information Engineering Wuhan UniversityWuhanChina Faculty of Geo-Information Science and Earth Observation(ITC) University of TwenteEnschedeThe Netherlands The State Key Laboratory of Information Engineering in Surveying Mapping and Remote SensingWuhan UniversityWuhanChina Lancaster Environment centre Lancaster UniversityLancasterUK UK centre for Ecology&Hydrology LancasterUK

Although the Convolutional Neural Network(CNN)has shown great potential for land cover classification,the frequently used single-scale convolution kernel limits the scope of informa-tion ***,we propose a Multi-Scale Fully Convolutional Network(MSFCN)with a multi-scale convolutional kernel as well as a Channel Attention Block(CAB)and a Global Pooling Module(GPM)in this paper to exploit discriminative representations from two-dimensional(2D)satellite ***,to explore the ability of the proposed MSFCN for spatio-temporal images,we expand our MSFCN to three-dimension using three-dimensional(3D)CNN,capable of harnessing each land cover category’s time series interac-tion from the reshaped spatio-temporal remote sensing *** verify the effectiveness of the proposed MSFCN,we conduct experiments on two spatial datasets and two spatio-temporal *** proposed MSFCN achieves 60.366%on the WHDLD dataset and 75.127%on the GID dataset in terms of mIoU index while the figures for two spatio-temporal datasets are 87.753%and 77.156%.Extensive comparative experiments and abla-tion studies demonstrate the effectiveness of the proposed MSFCN.

关键词： Spatio-temporal remote sensing images Multi-Scale Fully Convolutional Network land cover classification

Direct power control for three-level PWM rectifier based on hysteresis strategy

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2012年第11期55卷 3019-3028页

作者： SHI TingNa WANG Jian zhang ce XIA ChangLiang School of Electrical Engineering and Automation Tianjin UniversityTianjin 300072China Tianjin Key Laboratory of Advanced Technology of Electrical Engineering and Energy Tianjin Polytechnic UniversityTianjin 300387China

This paper presents a mathematical model of three-level voltage PWM rectifier,and derives a power control model from the theory of instantaneous *** the vector-space,the influences on instantaneous power exercised by all the switching vectors are studied and illustrated separately,then a direct power control(DPC) scheme for three-level PWM rectifier which uses multistage band hysteresis comparator is proposed,and a novel switching table is ***,the neutralpoint voltage unbalance is inhibited by selecting the redundancy switching states of small voltage *** and experimental results show that the proposed strategy can not only stabilize the DC bus voltage but also realize the unity power factor operation and the balance of neutral-point ***,the proposed method can improve the performance of the three-level rectifier.

关键词： direct power control hysteresis control instantaneous power neutral-point voltage balance switching table three-levelPWM rectifier

A novel non-separation opening scheme of front cover for rocket launch canister

在线全文

学校读者我要写书评

暂无评论

Defence Technology（防务技术） 2019年第6期15卷 905-911页

作者： ce zhang Xin Zhao Zonglai Mo Zhuoyu Guo Jun Li School of Mechanical Engineering Nanjing University of Science and Technology

In view of that existing opening technologies of front cover for rocket launch canister have disadvantages such as causing damage on the ground equipment,not being reused and easily broken.A novel reusable non-separation spring-driven opening scheme is proposed to achieve rapid and reliable opening of the front *** mathematical model of the opening process of the front cover is established by the rigid body dynamics *** establish a response surface model to optimize the opening scheme,three main influencing factors of the opening process are obtained through the designed experiments,including the pre-compression,the stiffness of the thrust spring,and the thrust spring force arm *** addition,the prescribed kinematic law was taken as constraint,and the smaller thrust spring preliminary pressure and angular velocity was taken as optimization *** results show that the opening scheme meets the design requirements on opening process *** also shows that the optimized scheme can reduce the kinetic energy of the front cover,and the impact on the canister effectively,achieving a reliable and rapid opening of the front cover.

关键词： Canister covers Spring-driven Non-separation Optimized opening scheme Rocket launch canisters Launch safety

Differences between physiological and pathological convulsive thresholds in patients with epilepsy

在线全文

学校读者我要写书评

暂无评论

Neural Regeneration Research 2008年第3期3卷 250-256页

作者： Yuxi Liu Leiyu Geng Jiali Xu Mingzheng Wang ce zhang Yu zhang Research Institute of Epilepsy of Shanxi Medical University Taiyuan 030001 Shanxi Province China Department of Neurology Third Hospital of Shanxi Medical University Taiyuan 030053 Shanxi Province China Research Institute of function of Shanxi Medical University Taiyuan 030001 Shanxi Province China

BACKGROUND： Physiological convulsive thresholds degrade when the brain is in some pathologic states; thus, a level of stimulus that cannot provoke a convulsion may evoke a seizure or epileptic seizure. OBJECTIVE： To investigate the changes that occur in the brain when the physiological convulsive threshold becomes pathological, and to determine what differences occur in pathological and physiological convulsive thresholds during the development of epilepsy. DESIGN： A randomized controlled animal experiment. SETTING： Research Institute of Epilepsy of Shanxi Medical University; Department of Neurology, The Third Hospital of Shanxi Medical University; Research Institute of Function of Shanxi Medical University. MATERIALS： Thirty-six female Wistar rats were selected for this study. The rats were obtained from the experimental animal center of Shanxi Medical University. All laboratory procedures complied with animal ethical standards. The animals were randomly divided into three groups： a strong current group, a weak current group and a control group, with 12 rats in each group. An automatic determinator of seizure threshold was made at Shanxi Medical University and Taiyuan University of Technology. Two bipolar stainless steel stimulating electrodes and an electrode connector （diameter 1.2 ram） were made at Taiyuan University of Technology. METHODS： This study was performed in the laboratory of Research Institute of the Epilepsy of Shanxi Medical University between December 2005 and August 2006. The threshold of localized seizures was measured by performing direct cortical stimulation in rats under anesthesia. After 1 week of post-operative recovery, electric stimulation was started with three different kinds of stimulation. Seizure activity was induced by a ramp-shaped single train of biphasic pulses （50 Hz, total pulse duration of 2 ms, increasing from 0 to 2 000μ A in 15 seconds）. The threshold of localized seizures （TLS） has been defined as the minimum current intens

关键词： epilepsy physiological convulsive threshold pathological convulsive threshold epileptic threshold cortical stimulation model

A Scale Sequence Object-based Convolutional Neural Network(SS-OCNN)for crop classification from fine spatial resolution remotely sensed imagery

在线全文

学校读者我要写书评

暂无评论

International Journal of Digital Earth 2021年第11期14卷 1528-1546页

作者： Huapeng Li ce zhang Yong zhang Shuqing zhang Xiaohui Ding Peter M.Atkinson Chinese Academy of Sciences Northeast Institute of Geography and AgroecologyChangchunPeople’s Republic of China School of Electrical and Information Engineering Changchun Guanghua UniversityChangchunPeople’s Republic of China Lancaster Environment centre Lancaster UniversityLancasterUK Guangzhou Institute of Geography GuangzhouPeople’s Republic of China

The highly dynamic nature of agro-ecosystems in space and time usually leads to high intra-class variance and low inter-class separability in the fine spatial resolution(FSR)remotely sensed *** makes traditional classifiers essentially relying on spectral information for crop mapping from FSR imagery an extremely challenging *** mine effectively the rich spectral and spatial information in FSR imagery,this paper proposed a Scale Sequence Object-based Convolutional Neural Network(SS-OCNN)that classifies images at the object level by taking segmented objects(crop parcels)as basic units of analysis,thus,ensuring that the boundaries between crop parcels are delineated *** segmented objects were subsequently classified using a CNN model integrated with an automatically generated scale sequence of input patch *** scale sequence can fuse effectively the features learned at different scales by transforming progressively the information extracted at small scales to larger *** effectiveness of the SS-OCNN was investigated using two heterogeneous agricultural areas with FSR SAR and optical imagery,*** results revealed that the SS-OCNN consistently achieved the most accurate classification *** SS-OCNN,thus,provides a new paradigm for crop classification over heterogeneous areas using FSR imagery,and has a wide application prospect.

关键词： CNNs multi-scale deep learning object-based mapping crop classification image classification