The development of single-cell RNA sequencing (scRNA-seq) technology provides a good opportunity to study cell heterogeneity and diversity. Especially, clustering is an important step in scRNA-seq analysis. With the a...
详细信息
A Multimodal Emotion Perception model with Audio and Visual modalities(MEP-AV) is proposed to detect the individual emotions in public *** framework of MEP-AV model consists of four parts,i.e.,data collection module,a...
详细信息
ISBN:
(数字)9789887581536
ISBN:
(纸本)9781665482561
A Multimodal Emotion Perception model with Audio and Visual modalities(MEP-AV) is proposed to detect the individual emotions in public *** framework of MEP-AV model consists of four parts,i.e.,data collection module,audio expression analysis module,visual expression analysis module and multimodal fusion *** order to ensure that the emotion perception results meet the requirement of short-term continuity,a Context-Aware Decision-Level Fusion(CADLF) model is proposed and applied in multimodal fusion *** CADLF model estimates the affective status by using context information of multimodal *** short-term continuity is considered to improve the accuracy of the emotion perception *** experiment results evaluated by various metrics demonstrate that the performance of the multimodal structure is improved compared with that of unimodal emotion *** MEP-AV model using multimodal fusion algorithm provides the accuracies of70.89% and 77.07% in valence and arousal *** F1-scores reaches 70.2% and 75.6% respectively,indicating the boost performance on emotion perception.
As an advancedcontrol method of permanent magnet synchronous motor(PMSM),finite control set model predictive control(FCS-MPC) has earned widespread attention for its advantages of intuitive concept,splendid dynamic p...
详细信息
ISBN:
(数字)9789887581536
ISBN:
(纸本)9781665482561
As an advancedcontrol method of permanent magnet synchronous motor(PMSM),finite control set model predictive control(FCS-MPC) has earned widespread attention for its advantages of intuitive concept,splendid dynamic performance and capability of handling the constraints and ***,the dependence on the model parameter accuracy is the main barrier for FCS-MPC to be applied to the industry *** order to solve this issue,this paper presents a robust FCS-MPC against parameter *** proposed strategy utilizes the prediction error in the d-and q-axis currents during the past instant to calculate the compensation which should be added to the predicted currents in the next ***,the cost function in the proportional-integral form is designed as ***,the simulation results and experimental results prove the proposed method's effectiveness in suppressing the influence of model parameter mismatch on the control performance of PMSM.
In this paper,a fault tolerant control method based on active disturbance rejection control(ADRC) and radial basis function neural network(RBFNN) is proposed for a class of multi-input-multi-output nonlinear system wi...
详细信息
ISBN:
(纸本)9781538629185
In this paper,a fault tolerant control method based on active disturbance rejection control(ADRC) and radial basis function neural network(RBFNN) is proposed for a class of multi-input-multi-output nonlinear system with actuator faults,components faults and sensor *** proposed method does not rely on the plant *** regarding the faults and plant uncertainties as the disturbance,through the observation of extended state observer and the compensation of feedback control signal,this method achieves the fault tolerance control of the plant with component fault and actuator *** sensor faults,in this work,radial basis function neural network is applied to estimate the real output of the *** this output estimation is utilized by active disturbance rejection control to achieve the fault tolerance of ***,the effectiveness of the proposed method is validated by the simulation results of the three-tank system.
The inter-class similarity of facial expressions is one of the key challenges in Facial Expression Recognition(FER).In this manuscript,a Latent Facial Action Units Network(LAUNet) is proposed for the problem of inter-...
详细信息
ISBN:
(数字)9789887581536
ISBN:
(纸本)9781665482561
The inter-class similarity of facial expressions is one of the key challenges in Facial Expression Recognition(FER).In this manuscript,a Latent Facial Action Units Network(LAUNet) is proposed for the problem of inter-class similarity of facial expressions in *** proposed method recognizes subtle differences between facial expressions by learning Latent Facial Action Units Features(LAUFs).Specifically,LAUNet is composed of two parts:the Latent Facial Action Units Features Extraction Network(LEN) and the Latent Facial Action Units Selection Network(LSN).Firstly,LEN extracts LAUFs from the feature map of the backbone using the spatial attention ***,taking advantage of the channel attention mechanism,LSN captures the latent relationships between features from LAUFs to select effective features for *** are performed on the dataset after removing the invalid data of non-face images from the original FER2013 *** with some previous state-of-the-art methods,LAUNet achieves the highest accuracy rate of 71.31%.Depending on the backbone,LAUNet can improve the accuracy by up to 5.46% compared to the original architecture of the backbone.
Model predictive current control(MPCC) is widely applied in electrical drives and power electronics because of its simplicity and ***,steady-state errors are always present because of the inaccurate prediction induced...
详细信息
ISBN:
(数字)9789887581536
ISBN:
(纸本)9781665482561
Model predictive current control(MPCC) is widely applied in electrical drives and power electronics because of its simplicity and ***,steady-state errors are always present because of the inaccurate prediction induced by changing actual *** paper proposes a simple strategy for improving MPCC performance,which reduces steadystate errors and eliminates the additional prediction *** cost function,which is made up of tracking mistakes,is used in MPCC to choose the best switching *** paper introduces a new cost function that also includes actual current *** is a coefficient of actual current errors that enhances the appropriateness of permanent magnet synchronous motor(PMSM) *** results show superior performance of the proposed MPCC to that of conventional MPCC.
It is a tendency for Internet of Things to research Zigbee-WiFi hybrid *** paper introduces a heterogeneous network integration module based on protocol conversion which can integrate 802.15.4 network with 802.11 b **...
详细信息
ISBN:
(纸本)9781509009107
It is a tendency for Internet of Things to research Zigbee-WiFi hybrid *** paper introduces a heterogeneous network integration module based on protocol conversion which can integrate 802.15.4 network with 802.11 b *** heterogeneous network integration module resolves mismatch problems on physical layer,MAC layer and address mapping,meanwhile it makes a contrast with existing Zigbee-WiFi gateway and found to be advanced and effective in three performance indexes:network connection speed,SINR(signal interference noise ratio) and network *** design and realization of heterogeneous network integration are based on QualNet simulation software.
This paper is aimed at the second-order linear multi-agent formation *** to the failure of the actuator in a node,the wrong interactive information is transmitted between nodes,so that the entire system cannot complet...
详细信息
ISBN:
(数字)9789887581536
ISBN:
(纸本)9781665482561
This paper is aimed at the second-order linear multi-agent formation *** to the failure of the actuator in a node,the wrong interactive information is transmitted between nodes,so that the entire system cannot complete the expected task.A distributed adaptive fault isolation and fault tolerance method based on consistency theory is *** the consistency error variable is designed according to the connection relationship between nodes and the faulty node,which eliminates the influence of the faulty node on the neighbor ***,an overall distributed adaptive fault isolation and fault tolerance approach is designed according to the local information of neighbor *** stability of the designed approach is proved by constructing a reasonable Lyapunov *** results show that the proposed adaptive control approach has good robustness.
Currently,the multi-legged robots have to confront the problem of low energy utilization that restricts the moving radius of *** at the problem of energy consumption for mobile robots,this paper provides the analysis ...
详细信息
ISBN:
(纸本)9781509009107
Currently,the multi-legged robots have to confront the problem of low energy utilization that restricts the moving radius of *** at the problem of energy consumption for mobile robots,this paper provides the analysis in terms of the gait ***,two kinds of gait curves respectively,cycloid curve and Bezier curve are introduced and the main difference of two gait patterns is that the Bezier curve can achieve the swing leg retraction(SLR).The length of step(S),the height of step(H) and the duty ratio of gait cycle(P) are set as the primary research points about the gait of mobile *** this work,we formulate two indexes to quantitatively describe the performance of the quadruped robot and related simulations are carried out for gait ***,the results provide some recommendations for the gait planning of the quadruped robot,that is,the changes of gait parameters influence the index of energy consumption and SLR can effectively reduce energy consumption.
In one-stage methods for video moment retrieval,the common representations indirectly supervised by boundary prediction fail to fully preserve the inherent characteristic of the video and query,which limits the retrie...
详细信息
ISBN:
(数字)9789887581536
ISBN:
(纸本)9781665482561
In one-stage methods for video moment retrieval,the common representations indirectly supervised by boundary prediction fail to fully preserve the inherent characteristic of the video and query,which limits the retrieval *** solve this problem,an Adversarial Video Moment Retrieval(AVMR) algorithm is proposed to learn the common representations with modality invariance and cross-modal *** is implemented through the process of adversarial learning between a feature projector and a modality *** feature projector tries to generate a modality-invariant common representation and to confuse the modality *** modality classifier tries to discriminate between different modalities based on the generated representation by the feature *** triplet constraints are further imposed on the feature projector to preserve the underlying cross-modal semantic structure of *** experimental results show that AVMR surpasses the baseline Attentive Cross-modal Relevance Matching(ACRM) by 1.10% and 1.73% in the "mIoU" metric on two public datasets Charades-STA and TACoS,respectively.
暂无评论