Surface electromyography(sEMG) can capture muscle activity and motor function,which is considered an effective tool for assessing local muscle *** to the complex environment and individual differences,the collected ...
详细信息
Surface electromyography(sEMG) can capture muscle activity and motor function,which is considered an effective tool for assessing local muscle *** to the complex environment and individual differences,the collected sEMG signals contain lots of noising information.A novel method is devised to effectively solve the problem of sEMG denoising based on complementary ensemble empirical mode decomposition(CEEMD) and multi-scale entropy(MSEn).The method uses the concept of MSEn and analyzes the feature trend of MSEn of intrinsic mode functions(IMFs) obtained by *** method adaptively determines the main components of IMFs according to the complexity of sEMG on the time scale,avoiding insufficient selection based on *** experiments verified the effectiveness of the method.
Graph Neural Networks (GNN) has become a powerful graph data processing method, which has been widely used in node classification, link prediction, and other graph analysis tasks. Due to the diversity and complexity o...
详细信息
Deep learning has been shown to be able to recognize data patterns better than humans in specific circumstances or *** parallel,quantum computing has demonstrated to be able to output complex wave functions with a few...
详细信息
Deep learning has been shown to be able to recognize data patterns better than humans in specific circumstances or *** parallel,quantum computing has demonstrated to be able to output complex wave functions with a few number of gate operations,which could generate distributions that are hard for a classical computer to *** we propose a hybrid quantum-classical convolutional neural network(QCCNN),inspired by convolutional neural networks(CNNs)but adapted to quantum computing to enhance the feature mapping *** is friendly to currently noisy intermediate-scale quantum computers,in terms of both number of qubits as well as circuit’s depths,while retaining important features of classical CNN,such as nonlinearity and *** also present a framework to automatically compute the gradients of hybrid quantum-classical loss functions which could be directly applied to other hybrid quantum-classical *** demonstrate the potential of this architecture by applying it to a Tetris dataset,and show that QCCNN can accomplish classification tasks with learning accuracy surpassing that of classical CNN with the same structure.
Multimodal information-based broad and deep learning model(MIBDL) for emotion understanding is proposed, in which facial expression and body gesture are used to achieve emotional states recognition for emotion under...
详细信息
Multimodal information-based broad and deep learning model(MIBDL) for emotion understanding is proposed, in which facial expression and body gesture are used to achieve emotional states recognition for emotion understanding. It aims to understand coexistence multimodal information in human-robot interaction by using different processing methods of deep network and broad network, which obtains the features of depth and width dimensions. Moreover, random mapping in the initial broad learning network could cause information loss and its shallow layer network is difficult to cope with complex tasks. To address this problem, we use principal component analysis to generate the nodes of the broad learning, and the stacked broad learning network is adapted to make it easier for the existing broad learning networks to cope with complex tasks by creating deep variations of the existing network. To verify the effectiveness of the proposal, experiments completed on benchmark database of spontaneous emotion expressions are developed, and experimental results show that the proposal outperforms the state-of-theart methods. According to the simulation experiments on the FABO database, by using the proposed method, the multimodal recognition rate is 17,54%, 1.24%, and 0.23% higher than those of the temporal normalized motion and appearance features(TN),the multi-channel CNN(MCCNN), and the hierarchical classification fusion strategy(HCFS), respectively.
A brain-computer interface (BCI) establishes a direct communication pathway between the human brain and a computer. It has been widely used in medical diagnosis, rehabilitation, education, entertainment, etc. Most res...
详细信息
Grinding is an energy-consuming process in mineral processing industry. Improving grinding processing capacity per unit power consumption is an effective means to reduce grinding production cost. In this paper, a new ...
详细信息
Grinding is an energy-consuming process in mineral processing industry. Improving grinding processing capacity per unit power consumption is an effective means to reduce grinding production cost. In this paper, a new index for evaluating the effective processing throughput of SAG milling is proposed. The production process model is established by BP neural network (BPNN). Through combining the process mechanism and production constraints, the genetic algorithm is adopted to optimize the operating parameters of the SAG milling process to maximize the effective throughput, thus improving the grinding efficiency. The experimental results showed that through optimization of effective throughput function proposed in this paper, the SAG mill processing capacity has been increased by 4% and the operating power drawn reduced by 1.12%. It has important guiding significance for the actual production process.
In this paper we present new (stochastic) passivity properties for Direct Current (DC) power networks, where the unknown and unpredictable load demand is modelled by a stochastic process. More precisely, the considere...
详细信息
In this paper we present new (stochastic) passivity properties for Direct Current (DC) power networks, where the unknown and unpredictable load demand is modelled by a stochastic process. More precisely, the considered power network consists of distributed generation units supplying ZIP loads, i.e., nonlinear loads comprised of impedance (Z), current (I) and power (P) components. Differently from the majority of the results in the literature, where each of these components is assumed to be constant, we consider time-varying loads whose dynamics are described by a class of stochastic differential equations. Finally, we prove that an existing distributed control scheme achieving current sharing and (average) voltage regulation ensures the asymptotic stochastic stability of the controlled network.
The improvement of urban greening level makes sanitary work more complicated and difficult, especially, for the seasonal leaf cleaning on roads in the park, campus etc.. With the rapid development of computer vision, ...
详细信息
ISBN:
(纸本)9781665405362
The improvement of urban greening level makes sanitary work more complicated and difficult, especially, for the seasonal leaf cleaning on roads in the park, campus etc.. With the rapid development of computer vision, it is a feasible and innovative way to detect and clean the fallen leaves effectively with intelligent robot. However, since the irregular shape and size, uneven distribution of fallen leaves and complex outdoor conditions, especially the densely stacked leaves, even current advanced object detection algorithm has no satisfactory effect on detection of fallen leaves. To deal with the dense leaves detection problem and improve navigation efficiency, we propose a Non-Maximum Fusion(NMF) algorithm. NMF scales the high-confidence box with the pre-defined δ to fuse intersecting and adjacent boxes instead of supressing these boxes. The experiments on the fallen leaves data set shows that NMF improves the fallen leaves detection coverage significantly and the coverage reaches to 95%. Also, NMF greatly reduces the number of goal nodes for path planning. Since NMF functions at the back end of detector to process detection boxes without training, it can be intergrated into any fallen leaves detection pipeline easily.
This paper investigates the distributed observer design for linear system under time-variant disconnected communication network. By constructing basic eigenvectors of 0-eigensubspace of disconnected Laplacian Matrix a...
详细信息
This paper investigates the distributed observer design for linear system under time-variant disconnected communication network. By constructing basic eigenvectors of 0-eigensubspace of disconnected Laplacian Matrix and using LMIs method, we prove the distributed observer cannot achieve omniscience asymptotically under switching topology without constraining the system matrix or alternative topologies set. To deal with this problem, this paper investigates three kinds of constraints and the system matrix only needs to satisfy any one of them. Then a group of sufficient conditions corresponding to the asymptotic omniscience of distributed observer under switching topology are proved by Lyapunov analysis. Finally, a numerical simulation shows the validity of our method.
In this paper, a novel approach combining Q-learning method and two-stage optimization is proposed to solve linear quadratic tracking(LQT) problem for unknown discrete-time switched system. An augmented system consist...
详细信息
In this paper, a novel approach combining Q-learning method and two-stage optimization is proposed to solve linear quadratic tracking(LQT) problem for unknown discrete-time switched system. An augmented system consisting of switched subsystem and reference trajectory is built and Q-learning method is introduced to identify each subsystem without requiring any knowledge of augmented system state dynamics. Then, based on the optimal control laws for each subsystem obtained by Q-learning in advance, the optimal hybrid control law including switching mode and control input is obtained by the two-stage optimization framework. Furthermore, the optimality of the algorithm is proved. Finally, a simulation case is used to testify the effectiveness of the proposed algorithm.
暂无评论