Single image super resolution (SR) aims to estimate high resolution (HR) image from the low resolution (LR) one, and estimating accuracy of HR image gradient is very important for edge directed image SR methods. In th...
详细信息
Face image super resolution, also referred to as face hallucination, is aiming to estimate the high-resolution (HR) face image from its low-resolution (LR) version. In this paper, a novel two-layer face hallucination ...
详细信息
With the popularity of stereoscopic 3D (S3D) images and videos, many advanced objective quality assessment methods have been proposed to evaluate viewers' Quality of Experience (QoE). Among them, most algorithms t...
详细信息
ISBN:
(纸本)9781509053179
With the popularity of stereoscopic 3D (S3D) images and videos, many advanced objective quality assessment methods have been proposed to evaluate viewers' Quality of Experience (QoE). Among them, most algorithms take advantages of the disparity maps to extract useful features. On the other hand, deep learning has been one of the hottest research topics during these years, but limited efforts focused on the field in objective quality evaluation of S3D images. In this paper, we propose a S3D image quality assessment (S3D IQA) method based on deep learning. In this method, the Convolutional Restricted Boltzmann Machines (CRBM) combined with Factored Third-Order RBM (FTO-RBM) is considered as learning model to extract feature maps from pre-processed left and right images automatically. Then an improved traversal algorithm based on two pooling strategies is put forward to optimize extracted feature maps, which improves the final quality assessment performance significantly. Experimental results show that our S3D IQA method achieves good performance on 3D databases tested.
The EEG signal is an important tool for the diagnosis and prediction of epilepsy due to EEG containing a large number of physiological and pathological *** on alpha rhythm multi-channel EEG(electroencephalogram),this ...
详细信息
ISBN:
(纸本)9781510823808
The EEG signal is an important tool for the diagnosis and prediction of epilepsy due to EEG containing a large number of physiological and pathological *** on alpha rhythm multi-channel EEG(electroencephalogram),this paper applied inner composition alignment(IOTA) algorithm to construct brain functional network and visualize the network *** is to apply the algorithm to calculate and analyze IOTA coefficient,the node average degree and clustering coefficient of epileptic brain network for studying if epileptic brain network is significantly different from those of *** results show that IOTA coefficient of epileptic brain network obviously differs from the normal by calculating T testing with SPSS software,which proved that the effectiveness of the algorithm to distinguish IOTA coefficient of epileptic brain network.
Most stereoscopic 3D (S3D) image visual discomfort predictors use the Support Vector Regressor (SVR) as the regression model. However, there are other good regression models such as the Random Forests (RF) and Gradien...
详细信息
ISBN:
(纸本)9781467390453
Most stereoscopic 3D (S3D) image visual discomfort predictors use the Support Vector Regressor (SVR) as the regression model. However, there are other good regression models such as the Random Forests (RF) and Gradient Boost Regression Tree (GBRT). Here we study the efficacy of these regression models for S3D image visual discomfort prediction. We deployed several regression models to predict the visual discomfort scores on S3D images using three kinds of features extracted from the images in the IEEE-SA and EPFL S3D image databases. So the prediction performance was evaluated to compare the performance of the different regression models. We also studied the issue of over-fitting which can affect model performance. The comparison results show that it is feasible and reliable to apply Random Forests or GBRT for S3D visual discomfort prediction with better performance than SVR.
The Multiscale Mutual Model Entropy algorithm is presented to quantify the coupling degree between two EEG time series collected at the same time on different *** extracted the characteristics of EEG signals from the ...
详细信息
ISBN:
(纸本)9781510823808
The Multiscale Mutual Model Entropy algorithm is presented to quantify the coupling degree between two EEG time series collected at the same time on different *** extracted the characteristics of EEG signals from the healthy and epileptics based on the *** results show that the entropy value of healthy people is higher than that of *** with the increase of scale,the difference in entropy value between them is more *** indicates that Multiscale Mutual Entropy can distinguish the coupling difference between normal samples and case samples,which is significant for the clinical pathological assessment and brain disease diagnosis.
Sleep and wake EEG have some *** studying their brain waves and calculating the sign series entropy,we use the T test for the detection of sleep and wake EEG data to figure out whether they are *** beta waves being fi...
详细信息
ISBN:
(纸本)9781510823808
Sleep and wake EEG have some *** studying their brain waves and calculating the sign series entropy,we use the T test for the detection of sleep and wake EEG data to figure out whether they are *** beta waves being filtered out by the filter,we calculate the entropy of the sign *** results of T test show that the beta waves in the state of sleep and wake are different.
Sleep EEG signals analysis is a hotspot of research recently,this paper,by using nonlinear dynamics theory knowledge,JSD algorithm and multi-scale JSD algorithm is proposed for some individual conscious period and NRE...
详细信息
ISBN:
(纸本)9781510823808
Sleep EEG signals analysis is a hotspot of research recently,this paper,by using nonlinear dynamics theory knowledge,JSD algorithm and multi-scale JSD algorithm is proposed for some individual conscious period and NREM sleep stage I analyzed the research of EEG signals,and the use of SPSS statistical software to verify the veracity and reliability of the experiment,at the same time,with the error bar graph method to analysis the two different states of sleep EEG signals,the results show that both the JSD algorithm and the multi-scale JSD algorithm can effectively distinguish between awake and NREM sleep stage I of EEG signals,these two conditions' EEG signals exist significant differences,The algorithm we proposed can be further used in the study of sleep EEG in installment,which can also provide all kinds of disease diagnosis and treatment of sleep with effective auxiliary function,the research has important practical significance in the future.
In order to achieve high performance of robotic manipulators, light-weight and high manipulability are two essential indicators. In this paper, a model of UR5 (Universal Robot) manipulator is defined and analyzed with...
详细信息
ISBN:
(纸本)9781509035762
In order to achieve high performance of robotic manipulators, light-weight and high manipulability are two essential indicators. In this paper, a model of UR5 (Universal Robot) manipulator is defined and analyzed with focus on optimizing the total mass and manipulability. The kinematics and dynamics for the robotic manipulator are used to calculate the joints torque and define quantitative measures of manipulability. Then, a design optimization problem is formulated for UR5 manipulator. It adopts the weight and manipulability of the manipulator as the objective functions. The drive train constraints associate with joint motors and gearboxes have also been considered. Finally, constrained multi-objective evolutionary algorithms (CMOEAs) are employed to solve the formulated problem. Several reasonable optimal combinations of geometrical parameters and type selection of motor and gearbox are provided. And compare them with the original structure of UR5.
Evolutionary computation (EC) has received significant attention in China during the last two decades. In this paper, we present an overview of the current state of this rapidly growing field in China. Chinese resea...
详细信息
Evolutionary computation (EC) has received significant attention in China during the last two decades. In this paper, we present an overview of the current state of this rapidly growing field in China. Chinese research in theoretical foundations of EC, EC-based optimization, EC-based data mining, and EC-based real-world applications are summarized.
暂无评论