Shenyang Institute of Automation,Chinese Academy Of Sciences
Not a member yet
23582 research outputs found
Sort by
FINE-GRAINED AND MULTI-SCALE MOTIF FEATURES FOR CROSS-SUBJECT MENTAL WORKLOAD ASSESSMENT USING BI-LSTM
No full textMental workload (MW) assessment is crucial for understanding human mental state. Cross-subject MW analysis based on electroencephalogram (EEG) signals is an important way. In this paper, a fine-grained and multi-scale motif (FGMSM) features extraction method is proposed, and the proposed features together with original EEG data are used as the input of bidirectional long short-term memory (Bi-LSTM) to evaluate the cross-subject mental workload. First, the EEG signal of each channel is decomposed based on improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) algorithm. Second, for the motif structure consisting of three nodes, multi-scale detection is carried out in each intrinsic mode function, and the proportion of each motif structure is extracted as the newly extracted features. Then, the statistical differences of the extracted features between different MW levels are analyzed by using the t-test, and the features with statistical differences are selected for the cross-subject MW assessment. Finally, based on the public dataset with 26 subjects, Bi-LSTM and a variety of machine learning algorithms are used to classify the levels of cross-subject MW. The results show that the Bi-LSTM classification method with the original EEG data and the proposed features show the most positive results. Therefore, the FGMSM features proposed in this paper with Bi-LSTM provide a new technique for the assessment of cross-subject MW based on EEG signals
J-MSF：A new Infrared Dim Target Detection algorithm based on multi-channel and multiscale
No full text针对经典的基于深度学习的红外弱小目标检测算法存在目标信息在高层感受野消失导致无法检出的问题，提出一种新的基于多通道多尺度特征融合的红外弱小目标检测算法（J-MSF）。首先，该算法提出了一种新的多通道JAnet结构，基于此结构搭建了主干特征提取网络；其次，设计了下降门限式特征金字塔池化结构(DSPP)，并提出了多尺度融合检测策略；最后，设计了高斯损失优化函数。实验结果表明，所提出的算法在“地/空背景下红外图像弱小飞机目标检测跟踪数据集”上的检测效果与YOLOv3、YOLOv4算法对比，检出率、整体AP值分别提升9.07%、9.89%和1.67%、3.16%，提出算法优于目前主流检测算法，体现出了良好的鲁棒性和适应性，可以有效的应用于红外弱小目标的检测。</p
On Improving the Robustness of MEC with Big Data Analysis for Mobile Video Communication
No full textMobile video communication and Internet of Things are playing a more and more important role in our daily life. Mobile Edge Computing (MEC), as the essential network architecture for the Internet, can significantly improve the quality of video streaming applications. The mobile devices transferring video flow are often exposed to hostile environment, where they would be damaged by different attackers. Accordingly, Mobile Edge Computing Network is often vulnerable under disruptions, against either natural disasters or human intentional attacks. Therefore, research on secure hub location in MEC, which could obviously enhance the robustness of the network, is highly invaluable. At present, most of the attacks encountered by edge nodes in MEC in the IoT are random attacks or random failures. According to network science, scale-free networks are more robust than the other types of network under the random failures. In this paper, an optimization algorithm is proposed to reorganize the structure of the network according to the amount of information transmitted between edge nodes. BA networks are more robust under random attacks, while WS networks behave better under human intentional attacks. Therefore, we change the structure of the network accordingly, when the attack type is different. Besides, in the MEC networks for mobile video communication, the capacity of each device and the size of the video data influence the structure significantly. The algorithm sufficiently takes the capability of edge nodes and the amount of the information between them into consideration. In robustness test, we set the number of network nodes to be 200 and 500 and increase the attack scale from 0% to 100% to observe the behaviours of the size of the giant component and the robustness calculated for each attack method. Evaluation results show that the proposed algorithm can significantly improve the robustness of the MEC networks and has good potential to be applied in real-world MEC systems
Study of matrix effects in laser-induced breakdown spectroscopy by laser defocus and temporal resolution
No full textThe laser-induced breakdown spectroscopy (LIBS) analysis method displays significant matrix effects which greatly hinder the application of this technology. Even if the concentration of a certain element is constant, the physical properties and composition of the sample will affect the element signal. In order to further deepen the understanding of matrix effects, in this paper, the effect of matrix effects (Al matrix and Fe matrix) on the quantitative analysis of Si, Mn, Cr and Cu under different laser defocusing amounts and spectrometer delays is researched. This study found that the matrix effects have different degrees of effect on the analysis line under different experimental parameters. Moreover, the effect of the matrix effects can be reduced by adjusting the laser defocus amount and spectrometer delay. In addition, taking the spectrum generated by the pure sample as the matrix background and subtracting the intensity value of the matrix background at the analysis line can reduce the interference of the matrix effects. After deducting the matrix background, the determination coefficient of mixed quantitative analysis of the three elements Si, Cu, and Cr in Al and Fe matrixes can reach more than 0.99. Besides, for the Mn 257.6 nm, which is severely interfered by the spectrum of the Al matrix and Fe matrix, respectively, the determination coefficient of the mixed quantitative analysis can reach 0.9855.</p
一种心脏除颤机器人
No full text本发明属于救援机器人领域，具体地说是一种心脏除颤机器人，机器人车体两侧对称设有摆臂机构，两侧摆臂机构通过安装在机器人车体内的摆臂驱动机构同步转动；除颤作业模块包括除颤仪和作业机械臂，作业机械臂前端安装除颤仪的电极板，通过摆臂机构的转动可以调节机器人车体的抬起角度，配合作业机械臂的运动可以调节除颤仪的电极板的位置和角度，对心脏病复发人员的心脏实施电击治疗，消除心率失常，增加被困人员的生存机率。本发明可以面向复杂环境内人员实施心脏除颤治疗，机器人环境适应性强，可以在非结构环境内自由翻越障碍、跨越沟壑、攀爬台阶，具有运动灵活、适应性广泛、结构紧凑等特点
A distributed integrated energy trading solution
No full textBlockchain technology can bring profound changes to the energy industry and is now becoming a new driving force for the rapid development of this sector. In order to build a secure, reliable, and stable energy service system, it is necessary to study the framework and interaction mechanism of the energy trading system. This paper introduces a distributed integrated energy trading solution, proposes a new overall architecture, and analyses the blockchain model. This paper presents an algorithm to calculate the score directly in the client. Through this algorithm, users can choose service providers, get rid of cloud control, and realize users' free choice of electricity purchase and interaction between users through the smart contract. The test results show that the system has high performance and efficiency, can meet the needs of integrated energy transactions, and provides a solution for the application of blockchain in energy trading
An Improved Method for Correcting the Eccentricity Error of Circular Projection in the Binocular Visual System
No full textTo correct the eccentricity error in the circular projection, this paper proposes an improved algorithm to compensate for various eccentricity errors in the circular projection by using geometric features with the projection model of the binocular vision system. The experiment indicates that our method performs better than the traditional method
Industrial wireless network resource allocation method based on multi-agent deep reinforcement learning
No full text本发明涉及工业无线网络技术，具体地说，是一种基于多智能体深度强化学习的工业无线网络资源分配方法，包括以下步骤：建立端边协同的工业无线网络；确立工业无线网络端边资源分配的优化问题；建立马尔科夫决策模型；采用多智能体深度强化学习方法，构建资源分配神经网络模型；离线训练神经网络模型，直至奖励收敛到稳定值；基于离线训练结果，工业无线网络在线执行资源分配，处理工业任务。本发明能够实时、高能效地对工业无线网络进行端边协同的资源分配，在满足有限能量、计算资源约束下，最小化系统开销
一种基于自主水下机器人平台的浊度数据处理方法
No full text本发明属于海洋运动平台的浊度数据处理领域，具体说是一种基于自主水下机器人平台的浊度数据处理方法。本发明包括以下步骤：搭载水质仪设备的自主水下机器人在规划线路上进行探测运动，测量并记录路线上的水质仪浊度数据；根据水质仪浊度数据进行数字化建模，根据已探测水质仪浊度数据的线性关系预测未探测区域的浊度，根据自主水下机器人的探测运动构建大地系浊度数据地图。本发明将大量离散的浊度数据融合成数字化模型，使浊度数据满足线性关系，为海水浊度研究提供更加显明证据
Adaptive Integrated Coordinated Control Strategy Based on Sliding Mode Control for MMC-MTDC
No full textTraditional double closed-loop PI control and DC voltage-active power droop control are suitable for the modular multilevel converter based Multi terminal flexible DC transmission system (MMC-MTDC). However, due to the strong nonlinearity of the system and the fixed droop coefficient, the system has poor stability under transient conditions, which is prone to full load. In order to improve the response speed and stability of the system, an adaptive integrated coordinated control strategy based on sliding mode theory is proposed. The strategy adopts a double closed loop cascade control structure, the outer-loop controller performs adaptive droop control based on the comparison of the MMC real-time power margin with the power reference command, and the inner-loop controller is designed based on a sliding film variable structure with current error as the sliding film plane. The simulation model of MMCMTDC direct current transmission system was built in PSCAD/EMTDC. The simulation results of the proposed control strategy show that the control strategy can effectively avoid the full load margin of the system when the MMC is small, and the strategy also can improve the adaptability and dynamic performance of the system compared with the traditional control strategy