Two-dimensional temperature distribution estimation for a cross-flow planar solid oxide fuel cell stack

The uniform temperature distribution of a cross-flow planar solid oxide fuel cell (SOFC) stack plays an essential role in stack thermal safety and electrical property. However, because of the strict requirements in stack sealing struture, it is hard to acquire the temperature inside the stack using thermal detection devices within an acceptable cost. Therefore, accurately estimating the two-dimensional (2-D) temperature distribution of the cross-flow stack is crucial for its thermal management. In this paper, Firstly, a 2-D mechanism model of a cross-flow planar SOFC stack is established. The stack is divided into 5*5 nodes along the gas flow directions, which can reflect the stack states with moderate computational burden. Then, experimental test data is utilized to modify and validate the stack model, guaranteeing the model accuracy as well as the reliability of model-based state estimator design. Finally, easily-measured stack inputs and outputs are selected, and a temperature distribution estimator combined with unscented kalman filter (UFK) approach is developed to achieve accurate and fast temperature distribution estimation of a cross-flow SOFC stack. Simulation results demonstrate that the UKF-based temperature distribution estimator can precisely and quickly achieve the temperature distribution estimation of the cross-flow stack under both static state and dynamic state changes and is applicable to cross-flow stacks with different size or cell number as well, the maximum estimated absolute error is less than 0.15 K with an absolute error rate of 0.015%, which indicates the developed estimator has good estimation performances.     

基于深度学习的秀丽隐杆线虫显微图像分割方法

利用计算机实现自动、准确的秀丽隐杆线虫(C.elegans)的各项形态学参数分析,至关重要的是从显微图像上分割出线虫体态,但由于显微镜下的图像噪声较多,线虫边缘像素与周围环境相似,而且线虫的体态具有鞭毛和其他附着物需要分离,多方面因素导致设计一个鲁棒性的C.elegans分割算法仍然面临着挑战。针对这些问题,提出了一种基于深度学习的线虫分割方法,通过训练掩模区域卷积神经网络(Mask R-CNN)学习线虫形态特征实现自动分割。首先,通过改进多级特征池化将高级语义特征与低级边缘特征融合,结合大幅度软最大损失(LMSL)损失算法改进损失计算;然后,改进非极大值抑制;最后,引入全连接融合分支等方法对分割结果进行进一步优化。实验结果表明,相比原始的Mask R-CNN,该方法平均精确率(AP)提升了4.3个百分点,平均交并比(mIOU)提升了4个百分点。表明所提出的深度学习分割方法能够有效提高分割准确率,在显微图像中更加精确地分割出线虫体。     

Enhanced 3D residual network for video event recognition in shipping monitoring

The three-dimensional convolutional neural network is widely used in video recognition, action recognition and other tasks because it can directly extract temporal and spatial features. Due to the large number of parameters, many computing resources, and difficulty in training, the structure of three-dimensional convolutional neural network is generally shallow. For example, the traditional C3D [17] method uses only the 11-layer VGGNet structure, and the traditional Res3D [18] method adopts a residual network of 18 and 34 layers. Some experience of two-dimensional convolutional neural network shows that the deeper the network structure is, the higher the recognition accuracy will be. Therefore, this paper proposes a new method 3D ResNet-66, which combines a 50-layer 3D residual network and four-layer residual blocks, effectively reducing the number of parameters while increasing the depth of the network, and we finally obtain a better video recognition model through experiments. We evaluate our method on shipping event datasets. Compared to the traditional C3D and Res3D method, our method has improved the accuracy from 91.48% to 96.33%, the model size has been reduced from 561 MB to 135 MB, and the average processing time has become half of the original.

     

Alternative methods to determine the elastoplastic properties of sintered hydroxyapatite from nanoindentation testing

This study introduces alternative methods to determine the elastoplastic properties of bovine-derived Hydroxyapatite (HA) porous bone graft through a set of nanoindentation tests with a Berkovich indenter. Generally, experimental data obtained from nanoindentation tests are force displacement, hardness and elastic modulus. However, to determine plastic properties such as strength coefficient and work hardening exponent of bovine HA, analytical or inverse finite element models are required. In this paper, the effect of sintering temperature on these properties of HA is studied for the range of 1000–1400 °C. The direct and inverse Finite Element (FE) simulation models for nanoindentation tests were written in MSC, MARC^® software. A special algorithm for the inverse technique was developed to infer the most suitable elastoplastic material model for HA. A semi-empirical method was adapted to calculate the elastoplastic material properties of HA. The numerical results of harder hydroxyapatite showed better agreement with the experiments while the work hardening exponent, or n-value, and strength coefficient k of hard HA were found to be 0.23 and 8.05 GPa respectively. A comparison between the experimental and predicted load–displacement curves showed that the proposed inverse technique is effective in predicting the elastoplastic material properties from the nanoindentation test with error below 4% at maximum load.     

A learning-based approach for leaf detection in traffic surveillance video

Multidimensional Systems and Signal Processing - Traffic surveillance video is recorded in uncontrolled outdoor scenarios. If the camera view gets obstructed by the leaves, the video will fail to...     

Geometric calibration based on B-spline with multi-parameter and color correction based on transition template and decay function

Multimedia Tools and Applications - To achieve low-cost and fast multi-channel surface projection geometric correction, the quadratic quasi-uniform B-spline surface is used to reconstruct the...     

An efficient task mapping algorithm with power-aware optimization for network on chip

More and more cores are integrated onto a single chip to improve the performance and reduce the power consumption of CPU without the increased frequency. The cores are connected by lines and organized as a network, which is called network on chip (NOC) as the promising paradigm of the processor design. However, it is still a challenge to enhance performance with lower power consumption. The core issue is how to map the tasks to the different cores to take full advantages of the on-chip network. In this paper, we proposed a novel mapping algorithm with power-aware optimization for NOC. The traffic of the tasks will be analyzed. The tasks of the same application with high communication with the others will be mapped to the on-chip network as neighborhoods. And then the tasks of different applications are mapped to the cores step by step. The mapping of the tasks and the cores is computed at run-time dynamically and implement online. The experimental results showed that this proposed algorithm can reduce the power consumption in communication and the performance enhanced.     

Detection of rust defects on steel bridge coatings via digital image recognition

One of the major expenses for steel structures is the anti-corrosion maintenance tasks. The maintenance of a steel structure depends on regular inspections, and visual inspections are often adopted in Taiwan. Using the naked eye to determine the rusted area percentage greatly depends on the experience of the inspector, resulting in subjective results. As an alternative, an algorithm consisting of three different approaches is proposed to automatically process images. The Hue percentage and coefficient of variation (COV) of the gray levels are used to divide images into three groups in which each group is assessed using a specific recognition technique. The three proposed techniques are the following: the traditional K-means method in the H component, the double-center-double-radius (DCDR) algorithm in the Red-Green-Blue (RGB) color space and DCDR in the Hue-Saturation-Intensity (HSI) color space. Additionally, the Least Square Support Vector Machine (LS-SVM) was adopted to predict the radii in the DCDR approaches. One hundred images, mostly collected outdoors, were used to verify the proposed algorithm. Promising performance was observed, particularly for images with non-uniform illumination.     

Robust passive autofocus system for mobile phone camera applications

A robust autofocus system is a ubiquitous function in today’s mobile phone camera applications. However, due to the power consumption and size requirements, it is difficult for the autofocus function to be implemented into the design of mobile phone cameras. This paper presents a passive autofocus system with low computational complexity. This system uses a novel contrast measurement to determine degree of image sharpness, which can better reflect the information about image discontinuities. In order to gauge the performance of this measurement, a modified peak search strategy is used in the experiments. The experimental results from several typical image sequences validate the effectiveness of the proposed method.     

浅谈导师制项目在毕业设计的积极作用

高校中的本科生导师制在本科生教育中起到积极作用,针对网络工程专业特点,创新地推行导师制项目制度,由学生在学习阶段直接参加导师的科研项目。在指导教师指导下设计项目方案、进行系统设计和系统编码、撰写科研报告,并探索导师制项目在毕业设计所起到的积极作用．为校内其他专业及校外推广这项制度打下良好的基础。