Two-stream adaptive-attentional subgraph convolution networks for skeleton-based action recognition

Multimedia Tools and Applications - Recently, skeleton-based action recognition has modeled the human skeleton as a graph convolution network (GCN), and has achieved remarkable results. However,...     

A model of PEMFC-battery system to evaluate inner operating status and energy consumption under different energy management strategies

A hybrid system with jointed battery and PEMFC is popular and of great potential in New Energy Vehicle (NEV) application. However, reliability and efficiency remain to be improved for commercial products. To reflect the complicated physics inside the proton exchange membrane fuel cell (PEMFC), the PEMFC model consisting of inner muti-physics process and other accessories was built, then a complete hybrid system was established when a matched battery, DC/DC, regenerative braking were taken into consideration. Based on the above model, the stack state and system performance under standard cycle for heavy duty vehicle-CWTVC were obtained. According to the simulation results, fuel cell states such as pressure, water content and voltage suffers severe oscillation with external load, especially in the highway cycle. Membrane electrode assembly (MEA) suffers from pressure impact with average value of more than 24 kPa in highway cycle. In the aspect of relative humidity, the PEMFC stack is most threatened in road cycle. As for the hybrid system, its efficiency and state of charge (SOC) fluctuation perform worst in urban cycle and road cycle respectively, while its highest efficiency occurs in road test. Operating mode of fuel cell has influence on hybrid system. When 3-level mode of fuel cell output was applied, the efficiency increased to its peak value at medium level of 28 kW and then declined gradually. H₂ consumption had an opposite trend compared to efficiency. In the aspect of battery SOC, it declines in operating process and its fluctuations decreases when medium level got bigger. The 3-level mode and 4-level mode were compared using this model. It can be concluded that although 3-level mode performs slightly better in hybrid system efficiency, H₂ consumption, pressure impact, it does not have absolute advantage over 4-level mode in other indicators.     

基于小波变换的分数阶微分算法在肝脏肿瘤CT图像纹理增强中的应用

图像纹理增强过程中容易丢失平滑区域纹理细节，而分数阶微分增强虽然能够非线性保留平滑区域纹理细节，但对频率分辨率敏感。针对这个问题，提出一种基于小波变换的分数阶微分纹理增强算法，应用于平扫计算机断层扫描（CT）图像的肝脏肿瘤区域的纹理增强。首先，通过小波变换将图像感兴趣区分解成多个子带分量；其次，基于分数阶微分定义构造一个带补偿参数的分数阶微分掩膜；最后，使用该掩膜与每个高频子带分量进行卷积并利用小波逆变换重组图像感兴趣区。实验结果表明，该方法在使用较大分数阶次显著增强肿瘤区域的高频轮廓信息的同时，有效地保留了低频平滑的纹理细节：增强后的肝细胞癌区域与原区域相比，信息熵平均增加36.56%，平均梯度平均增加321.56%，平均绝对差值平均为9.287；增强后的肝血管瘤区域与原区域相比，信息熵平均增加48.77%，平均梯度平均增加511.26%，平均绝对差值平均为14.097。     

A web-based 3D ontology navigation system for spinal disease diagnosis

The Journal of Supercomputing - This paper presents a web-based three-dimensional (3D) navigation system for a spinal disease ontology using a 3D virtual human spine. The 3D navigation system...     

Human interaction recognition using spatial-temporal salient feature

Multimedia Tools and Applications - Depth sensor is widely used today and has great impact in object pose estimation, camera tracking, human actions, and scene reconstruction. This paper presents a...     

Compiler compatible 5.66 Mb/mm2 8T 1R1W register file in 14 nm FinFET technology

1-read/1-write (1R1W) register file (RF) is a popular memory configuration in modern feature rich SoCs requiring significant amount of embedded memory. A memory compiler is constructed using the 8T RF bitcell spanning a range of instances from 32 b to 72 Kb. An 8T low-leakage bitcell of 0.106 μm² is used in a 14 nm FinFET technology with a 70 nm contacted gate pitch for high-density (HD) two-port (TP) RF memory compiler which achieves 5.66 Mb/mm² array density for a 72 Kb array which is the highest reported density in 14 nm FinFET technology. The density improvement is achieved by using techniques such as leaf-cell optimization (eliminating transistors), better architectural planning, top level connectivity through leaf-cell abutment and minimizing the number of unique leaf-cells. These techniques are fully compatible with memory compiler usage over the required span. Leakage power is minimized by using power-switches without degrading the density mentioned above. Self-induced supply voltage collapse technique is applied for write and a four stack static keeper is used for read Vmin improvement. Fabricated test chips using 14 nm process have demonstrated 2.33 GHz performance at 1.1 V/25 °C operation. Overall V_min of 550 mV is achieved with this design at 25 °C. The inbuilt power-switch improves leakage power by 12x in simulation. Approximately 8% die area of a leading 14 nm SoC in commercialization is occupied by these compiled RF instances.     

A note on stability analysis of 2-D linear discrete systems based on the Fornasini–Marchesini second model: Stability with asymmetric Lyapunov matrix

A recently reported Lyapunov based criterion (Singh (2014) [7]) for the asymptotic stability of two-dimensional (2-D) linear discrete systems described by the Fornasini–Marchesini second local state-space (FMSLSS) model is reviewed. It is established in this paper that, despite utilizing a more general Lyapunov matrix, Singh's criterion will never lead to an enhanced stability region in the parameter-space as compared to that obtainable via Hinamoto–Lu's criterion.     

Graph-based video fingerprinting using double optimal projection

A double optimal projection method that involves projections for intra-cluster and inter-cluster dimensionality reduction are proposed for video fingerprinting. The video is initially set as a graph with frames as its vertices in a high-dimensional space. A similarity measure that can compute the weights of the edges is then proposed. Subsequently, the video frames are partitioned into different clusters based on the graph model. Double optimal projection is used to explore the optimal mapping points in a low-dimensional space to reduce the video dimensions. The statistics and geometrical fingerprints are generated to determine whether a query video is copied from one of the videos in the database. During matching, the video can be roughly matched by utilizing the statistics fingerprint. Further matching is thereafter performed in the corresponding group using geometrical fingerprints. Experimental results show the good performance of the proposed video fingerprinting method in robustness and discrimination.