检索结果-内蒙古大学图书馆

Attention-Based Distributional Reinforcement Learning for Safe and Efficient Autonomous Driving

IEEE ROBOTICS AND AUTOMATION LETTERS 2024年第9期9卷 7477-7484页

作者： Liu, Jia Yin, Jianwen Jiang, Zhengmin Liang, Qingyi Li, Huiyun Chinese Acad Sci Shenzhen Inst Adv Technol CAS Key Lab Human Machine Intelligence Synergy Sys Shenzhen 518055 Peoples R China

Autonomous driving vehicles play a critical role in intelligent transportation systems and have garnered considerable attention. Currently, the popular approach in autonomous driving systems is to design separate optimal objectives for each independent module. Therefore, a major concern arises from the fact that these diverse optimal objectives may have an impact on the final driving policy. However, reinforcement learning provides a promising solution to tackle the challenge through joint training and its exploration ability. This letter aims to develop a safe and efficient reinforcement learning approach with advanced features for autonomous navigation in urban traffic scenarios. Firstly, we develop a novel distributional reinforcement learning method that integrates an implicit distribution model into an actor-critic framework. Subsequently, we introduce a spatial attention module to capture interaction features between the ego vehicle and other traffic vehicles, and design a temporal attention module to extract the long-term sequential feature. Finally, we utilize bird's-eye-view as a context-aware representation of traffic scenarios, fused by the above spatio-temporal features. To validate our approach, we conduct experiments on the NoCrash and CoRL benchmarks, especially on our closed-loop openDD scenarios. The experimental results demonstrate the impressive performance of our approach in terms of convergence and stability compared to the baselines.

关键词： Training Navigation Decision making Estimation Benchmark testing Feature extraction Deep reinforcement learning Autonomous vehicles efficient reinforcement learning spatio-temporal attention

来源：评论

学校读者我要写书评

暂无评论

Single-Wavelength Laminar Optical Tomography for In Vivo Microvascular Three-Dimensional Imaging 46

Single-Wavelength Laminar Optical Tomography for In Vivo Mic...

引用

46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024

作者： Cui, Han Han, Dewei Liu, Wenquan Deng, Xinping Xin, Zhixuan Li, Guanglin Cas Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology Shenzhen China

ISBN: (纸本)9798350371499

Laminar Optical Tomography (LOT) is a promising non-invasive technique for three-dimensional imaging of complex biological structures, combining high resolution and deep penetration. In this study, a LOT system was assembled using a 520nm continuous-wave laser, exploiting the contrast mechanism provided by the unique optical absorption coefficient of hemoglobin at this wavelength for microvascular imaging. The system utilizes raster scanning to illuminate the target tissue's surface, capturing backscattered light intensity with a multi-channel Photomultiplier Tubes. The inverse problem of light propagation within the tissue is solved to reconstruct a three-dimensional image of microvasculature. Phantom and in-vivo rat ear results demonstrate the system's ability to image micro vessels with diameters of several hundred micrometers within the tissue. The implemented LOT system, known for its simplicity and cost-effectiveness, showcases its potential for applications in microvascular physiological and pathological research, as well as clinical diagnostics. © 2024 IEEE.

关键词： Clinical research

来源：评论

学校读者我要写书评

暂无评论

Exploring the Relationship Between Imitated and Associated Mechanism on Performance of Visual Imagery Brain-Computer Interface 46

Exploring the Relationship Between Imitated and Associated M...

引用

46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024

作者： Tai, Pengrui Yang, Jingcheng Qi, Shaowen Li, Guanglin Fu, Yunfa Li, Yongcheng Kunming University of Science and Technology Kunming China Cas Key Laboratory of Human-Machine Intelligence-Synergy Systems SIAT-CAS China Cas Key Laboratory of Human-Machine Intelligence-Systems SIAT-CAS China

ISBN: (纸本)9798350371499

Visual Imagery (VI) can be defined as the manipulation of visual information derived from memory rather than perception. Currently, the brain responses underlying imitation and associative VI are not clear. In this study, we explore the differences from imitation to associative VI on the brain responses based on EEG signals. In this study, eight participants were instructed to observe visual cues from three predefined images or characters (tree, computer, or sphere), and then imagine the same cues. The results indicate that there is a significant difference in power intensity among electrode channels in the occipital lobe, posterior parietal lobe, and temporal lobe during the imagination phase between imitative tasks and associative tasks, as revealed by t-tests (p © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Spasticity assessment with muscle coactivation of elbow flexors during passive stretch in Post-stroke Hemiplegia

Spasticity assessment with muscle coactivation of elbow flex...

引用

45th Annual International Conference of the IEEE Engineering in Medicine and Biology Conference, EMBC 2023

作者： Wang, Hui Geng, Yanjuan Fang, Peng Li, Guanglin Cas Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen518055 China

ISBN: (纸本)9798350324471

the assessment of muscle properties is an essential prerequisite in the treatment of post-stroke muscle spasticity. Previous studies have shown that muscle coactivation, which reflects the simultaneous activation of agonist and antagonist muscle groups, is associated with muscle spasticity during voluntary contraction. However, current spasticity assessment approaches do not often consider muscle coactivation for passive contraction measured with surface electromyography (sEMG). The purpose here is to evaluate the validity and reliability of muscle co-activation based on sEMG for assessing spasticity of post-stroke patients. This study was conducted on 39 chronic hemiplegia post-stroke patients with varying degrees of elbow flexor spasticity. The severity of spasticity was assessed with Modified Ashworth Scale (MAS). The patients produced elbow flexion passively on affected arm. Two-channel surface sEMG recordings were acquired simultaneously for the biceps and triceps muscles. The effectiveness and reliability of the EMG-based spasticity assessment method were evaluated using Spearman's correlation analysis and intra class correlation coefficients (ICCs). The results showed that there was a statistically significant positive relationship between the level of activity and the coactivation index (R=0.710, P=0.003), while the ICCs for intra trial measures ranged between 0.928 and 0.976. Muscle coactivation is a promising tool for continuously quantifying muscle spasticity in post-stroke patients, suggesting that the EMG-based muscle coactivation index could be useful for assessing motor function. © 2023 IEEE.

关键词： Muscle

来源：评论

学校读者我要写书评

暂无评论

Multifunctional polyaniline nanofiber conductive hydrogel for supercapacitors and flexible sensors

引用

NEW JOURNAL OF CHEMISTRY 2024年第44期48卷 18943-18956页

作者： Fan, Xingwen Tao, Yulun Liu, Fuchen Li, Shuo Liu, Mingao Anhui Univ Sci & Technol Sch Mat Sci & Engn Huainan Anhui Peoples R China Chinese Acad Sci Key Lab Human Machine Intelligence Synergy Syst Shenzhen Guangdong Peoples R China

A series of polyaniline (PANI) nanofibers were prepared as conductive fillers. A polyvinyl alcohol (PVA)/agarose (AG) double network hydrogel was used as a flexible substrate. A PANI/PVA/AG conductive hydrogel was prepared via in situ polymerization of polyaniline nanofibers in a PVA/AG double network hydrogel. The electrochemical performance of the PANI/PVA/AG hydrogel electrode material was linked to the fiber morphology of polyaniline. The doping of polyaniline with 0.020 mol L-1 citric acid demonstrated superior fiber morphology compared to doping with other citric acid concentrations, achieving fiber ratios of 80%. The specific capacitance of the PANI/PVA/AG hydrogel electrode materials doped with 0.020 mol L-1 citric acid was 285 mF cm-2, while the conductivity was 7.1 S m-1. The doping of polyaniline with 0.5 mol L-1 hydrochloric acid demonstrated superior fiber morphology compared to doping with other hydrochloric acid concentrations, achieving fiber ratios of 65%. The specific capacitance of PANI/PVA/AG hydrogel electrode materials doped with 0.5 mol L-1 hydrochloric acid was 249 mF cm-2, while their conductivity was 7.6 S m-1. After 500 cycles of charge-discharge, the specific capacitance retention of the material was 73%. Photosensitivity tests indicated that the hydrogel exhibited high sensitivity to shorter wavelengths of blue light (460 nm) and ultraviolet light (380 nm). The hydrogel sensor possessed high sensitivity to strain in the range of 0-120%. Gauge factors (GF) of the hydrogel strain sensor were 1.280, 2.141, 1.907, and 1.261 for strain ranges of 0-30%, 30-60%, 60-90%, and 90-120%, respectively. Cyclic strain tensile tests indicated that the relative resistance change rate (Delta R/R0) of the hydrogel sensor demonstrated a certain degree of repeatability and stability within the range of 0-100%. Thus, the hydrogel sensor is reliable and stable in the signal transmission process of detecting human movements as a flexible strain sensor. These re

关键词： Nanofibers

来源：评论

学校读者我要写书评

暂无评论

Self-supporting multi-functional two-dimensional nanofilms for flexible perceptual devices: review

引用

JOURNAL OF MATERIALS SCIENCE-MATERIALS IN ELECTRONICS 2024年第12期35卷 813页

作者： Mijit, Abduweli Awan, Muhammad Nouman Siddique Li, Shuo Huang, Jiaxin Deng, Xiongjun Wang, Hao Chen, Dazhu Zhu, Shanshan Tai, Yanlong Chinese Acad Sci Shenzhen Inst Adv Technol Key Lab Human Machine Intelligence Synergy Syst Shenzhen 518055 Peoples R China Shenzhen Univ Coll Mat Sci & Engn Shenzhen Key Lab Polymer Sci & Technol Shenzhen 518055 Peoples R China

The extraordinary mechanical capabilities of 2D self-supporting nanofilms render them highly desirable for fabricating flexible devices. These films possess unique structural properties at the nanoscale, translating into exceptional rigidity or flexibility at the macroscopic level. Their remarkable ability to maintain structural integrity and shape under stress situations empowers them to bend, fold, and twist without compromising performance. Furthermore, the excellent elasticity of film enables them to adapt to curved surfaces, facilitating their seamless integration into wearable electronics. 2D self-supporting films with outstanding superior properties surpass substrate-based films and hold tremendous promise for various applications in energy storage, sensing, membranes and biomedical devices. Achieving their full potential in multiple applications necessitates a comprehensive understanding of the mechanical flexibility of these 2D nanomaterials. Researchers can gain insights into the material's responses to applied force or deformation by analyzing its mechanical behavior, which is crucial for designing and developing. The primary objectives of this study are to provide in-depth elucidation of the mechanical characteristics of 2D nanomaterials, their formation into nanofilms, and the subsequent removal of these films from the substrate. Such a comprehensive investigation enables researchers to understand the intrinsic behavior of 2D nanomaterials and develop strategies to optimize their properties for a wide range of applications.

关键词： Substrates

来源：评论

学校读者我要写书评

暂无评论

Enhanced spatio-temporal motion prediction using transformer-augmented graph convolutional networks

引用

INTERNATIONAL JOURNAL OF machine LEARNING AND CYBERNETICS 2025年 1-17页

作者： Ren, Ziliang Jin, Miaomiao Qin, Yong Gao, Xiangyang Zhang, Qieshi Dongguan Univ Technol Sch Comp Sci & Technol Dongguan 523808 Guangdong Peoples R China Chinese Acad Sci Shenzhen Inst Adv Technol Key Lab Human Machine Intelligence Synergy Syst Shenzhen 518055 Guangdong Peoples R China

Mining temporal and spatial correlations from observed data is a crucial challenge in human motion prediction. Traditional methods mainly rely on artificially designed features, which cannot accurately capture complex motion patterns and often ignore the reliability of motion. In recent years, deep learning methods have made significant progress in spatiotemporal representation, especially when dealing with human motion prediction tasks. Although temporal and spatial features have different characteristics, existing methods often fail to fully consider the temporal and spatial features. Correlation leads to inaccurate modeling of spatiotemporal information. In this paper, we propose a novel branch network based on the Transformer and augmented graph convolutional network (TAGCN). This method innovatively combines the global dependency modeling capability of the Transformer model with the local feature extraction capability of the graph convolution network. The Transformer model effectively captures long-distance dependencies in time series through a self-attention mechanism and is able to identify complex temporal patterns. At the same time, GCN models the spatial dependence between joints through a graph structure and can effectively extract local spatial features. Our method significantly improves the expressive ability of motion information by learning temporal and spatial features simultaneously, making it richer and more representative. In addition, we design an improved loss function to further improve the accuracy of spatiotemporal prediction. Experimental results show that our method achieves state-of-the-art prediction performance on human3.6M, CMU Mocap and 3DPW datasets, significantly outperforming existing mainstream methods.

关键词： human motion prediction Spatio-temporal modelling Transformer Graph convolutional network

来源：评论

学校读者我要写书评

暂无评论

Autonomous 3D Self-Sensing Hybrid Membrane Actuator for Interactive Communicating

引用

ACS APPLIED MATERIALS & INTERFACES 2025年第22期17卷 2025 Apr 29页

作者： Hou, Yuanyuan Huang, Jiaxin Ma, Hao Li, Qingsong Xiang, Zerong Qian, Jiasheng Li, Guanglin Tai, Yanlong Xia, Ru Zhu, Shanshan Anhui Univ Sch Chem & Chem Engn Key Lab Environm Friendly Polymer Mat Anhui Prov Hefei 230601 Anhui Peoples R China Chinese Acad Sci Shenzhen Inst Adv Technol CAS Key Lab Human Machine Intelligence Synergy Sys Shenzhen 518055 Peoples R China

The advancement of intelligent soft actuators is progressively emphasizing the incorporation of environmental sensing capability to actuation, thereby enhancing the adaptability and interactivity of artificial systems. In the current situation where the sensing and actuation functions of soft actuators are generally separated, this work proposes an autonomous three-dimensional (3D) noncontact sensory actuator (NSA), based on the coupling of '' dielectric polarization-electrothermal conversion-thermal actuation '' triple effects. Specifically, the NSA hybrid membrane is composed of multiple interpenetrating networks, including a boron nitride nanosheet (BNNS) dielectric network for electrostatic field sensing and polarization, a silver nanowires (AgNWs) percolation network for dielectric enhancement and electrothermal conversion, and thermally contracted shape memory fiber (SMF) and thermally expanded polydimethylsiloxane (PDMS) networks for directional actuation. Based on the principle of electrostatic field and dielectric polarization, the SMF/BNNS composite (SMF-BN) fibrous membrane can logically sense the noncontact 3D motion, static/dynamic state of external objects, and distinguish material categories. Subsequently, the output sensing potential facilitates the built-in AgNWs nanonetwork heater to trigger electrothermal actuation of NSA. Lastly, as a biomimetic tongue, the autonomous noncontact "sensing-decision-actuating" of NSA is verified by seamless energy conversion in the process of sensing "prey" approaching and capturing. The proposed sensory actuator would facilitate multimodal integration for future wearable and human-machine-environment interaction technologies.

关键词： 3D noncontact sensing soft sensory actuator energy conversion human-machine-environment interaction biomimetic device

来源：评论

学校读者我要写书评

暂无评论

Simulation and Fabrication of PMN-PT Single Crystals Phased Array Ultrasonic Transducer Based on Alternating and Direct Current Poling

引用

IEEE TRANSACTIONS ON DIELECTRICS AND ELECTRICAL INSULATION 2024年第5期31卷 2321-2329页

作者： Xu, Jialin Du, Cheng Xue, Yuan Wang, Li Zhang, Hao Wu, Fei Li, Guanglin Fang, Peng Shenzhen Mindray Biomed Elect Co Ltd Shenzhen 518057 Peoples R China Chinese Acad Sci CAS Key Lab Human Machine Intelligence Synergy Sys Shenzhen Insti tute Adv Technol Shenzhen 518055 Peoples R China

In this article, the design, fabrication, and comparison of Pb(Mg-1/3 Nb-2/3) O-3-0.25PbTiO(3) (PMN-0.25PT) single crystals (SCs) by alternating current poling (ACP) and direct current poling (DCP)-based 2.8-MHz phased array ultrasonic transducers were investigated. Pzflex finite element simulation was used to model and compare the electro-acoustic properties of ACP and DCP phased arrays. The finite element analysis (FEA) results indicated that the ACP phased arrays can exhibit a greater sensitivity, a broader -6-dB bandwidth (BW), and a lower center frequency under the same acoustic structure and the same thickness of matching layers. In addition, the high coincidence of simulated and measured impedance proves the stability of the transducer fabrication processes. By comparing the permittivity of the SCs in the processes of transducer fabrication, it is shown that the ACP SCs are more sensitive to the clamping force during the pressurization process and to the cutting force during the dicing process, respectively. Compared with the DCP phased arrays, the ACP phased arrays have been shown to exhibit 7.90% increase in observed -6-dB BW and 0.82-dB increase in relative sensitivity (RS). These results suggest that ACP phased arrays can enhance both the longitudinal resolution and penetration depth of ultrasonic imaging. Finally, a typical phantom image is created to compare the imaging capabilities of ACP and DCP phased arrays. The findings indicate that phased arrays based on ACP PMNT SCs might be promising for medical ultrasound (US) imaging applications.

关键词： Alternating current poling (ACP) direct current poling (DCP) finite element modeling Pb(Mg1/3Nb2/3)O-3-PbTiO3 (PMN-PT) single crystals (SCs) phased arrays ultrasonic transducer

来源：评论

学校读者我要写书评

暂无评论

Cross-Modality Compensation Convolutional Neural Networks for RGB-D Action Recognition

引用

IEEE TRANSACTIONS ON CIRCUITS AND systems FOR VIDEO TECHNOLOGY 2022年第3期32卷 1498-1509页

作者： Cheng, Jun Ren, Ziliang Zhang, Qieshi Gao, Xiangyang Hao, Fusheng Chinese Acad Sci Shenzhen Inst Adv Technol CAS Key Lab Human Machine Intelligence Synergy Sy Shenzhen 518055 Peoples R China

RGB-D-based human action recognition has attracted much attention recently because it can provide more complementary information than a single modality. However, it is difficult for two modalities to effectively learn spatial-temporal information from each other. To facilitate information interaction between different modalities, a cross-modality compensation convolutional neural network (ConvNet) is proposed for human action recognition, which enhances the discriminative ability by jointly learning compensation features from the RGB and depth modalities. Moreover, we design a cross-modality compensation block (CMCB) to extract compensation features from the RGB and depth modalities. Specifically, CMCB is incorporated into two typical network architectures, ResNet and VGG, to verify the ability to improve the performance of our model. The proposed architecture has been evaluated on three challenging datasets: NTU RGB+D 120, THU-READ and PKU-MMD. We experimentally verify that our proposed model with CMCB is effective for different input types, such as pairs of raw images and dynamic images constructed from the entire RGB-D sequence, and the experimental results show that the proposed framework achieves state-of-the-art performance on all three datasets.

关键词： Feature extraction Image recognition Optical imaging Task analysis Dynamics Data mining Three-dimensional displays Action recognition cross modality compensation learning joint optimization dynamic image

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：