检索结果-南通市图书馆

Single Image Super-Resolution via Dynamic Lightweight Database with Local-Feature Based Interpolation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2019年第3期34卷 537-549页

作者： Na Ding Ye-Peng Liu Lin-Wei Fan cai-ming zhang School of Software Shandong UniversityJinan 250101China Shandong Co-Innovation Center of Future Intelligent Computing Yantai 264025China Digital Media Research Institute Shandong University of Finance and Economics Jinan 250061China

Single image super-resolution is devoted to generating a high-resolution image from a low-resolution one,which has been a research hotspot for its significant applications. A novel method that is totally based on the single input image itself is proposed in this paper. Firstly, a local-feature based interpolation method where both edge pixel property and location information are taken into consideration is presented to obtain a better initialization. Then, a dynamic lightweight database of self-examples is built with the aid of our in-depth study on self-similarity, from which adaptive linear regressions are learned to directly map the low-resolution patch into its high-resolution version. Furthermore, a gradually upscaling strategy accompanied by iterative optimization is employed to enhance the consistency at each *** without any external information, extensive experimental comparisons with state-of-the-art methods on standard benchmarks demonstrate the competitive performance of the proposed scheme in both visual effect and objective evaluation.

关键词： lightweight database linear regression local-feature interpolation super-resolution

A Modified Fuzzy C-Means Algorithm for Brain MR Image Segmentation and Bias Field Correction

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2016年第3期31卷 501-511页

作者： Wen-Qian Deng Xue-Mei Li Xifeng Gao cai-ming zhang School of Computer Science and Technology Shandong University Jinan 250101 China Department of Computer Science University of Houston Houston TX 77004 U.S.A.

In quantitative brain image analysis, accurate brain tissue segmentation from brain magnetic resonance image （MRI） is a critical step. It is considered to be the most important and difficult issue in the field of medical image processing. The quality of MR images is influenced by partial volume effect, noise, and intensity inhomogeneity, which render the segmentation task extremely challenging. We present a novel fuzzy c-means algorithm （RCLFCM） for segmentation and bias field correction of brain MR images. We employ a new gray-difference coefficient and design a new impact factor to measure the effect of neighbor pixels, so that the robustness of anti-noise can be enhanced. Moreover, we redefine the objective function of FCM （fuzzy c-means） by adding the bias field estimation model to overcome the intensity inhomogeneity in the image and segment the brain MR images simultaneously. We also construct a new spatial function by combining pixel gray value dissimilarity with its membership, and make full use of the space information between pixels to update the membership. Compared with other state-of-the-art approaches by using similarity accuracy on synthetic MR images with different levels of noise and intensity inhomogeneity, the proposed algorithm generates the results with high accuracy and robustness to ***.

关键词： image segmentation fuzzy c-means bias field correction anti-noise

Quasi-Developable B-Spline Surface Design with Control Rulings

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2022年第5期37卷 1221-1238页

作者： Zi-Xuan Hu Peng-Bo Bo cai-ming zhang School of Computer Science and Technology Harbin Institute of TechnologyWeihai 264209China Shandong Co-Innovation Center of Future Intelligent Computing Yantai 264005China Shandong Province Key Laboratory of Digital Media Technology Shandong University of Finance and EconomicsJinan 250061China

We propose a method for generating a ruled B-spline surface fitting to a sequence of pre-defined ruling lines and the generated surface is required to be ***,the terminal ruling lines are treated as hard *** from existing methods that compute a quasi-developable surface from two boundary curves and cannot achieve explicit ruling control,our method controls ruling lines in an intuitive way and serves as an effective tool for computing quasi-developable surfaces from freely-designed *** treat this problem from the point of view of numerical optimization and solve for surfaces meeting the distance error tolerance allowed in *** performance and the efficacy of the proposed method are demonstrated by the experiments on a variety of models including an application of the method for path planning in 5-axis computer numerical control(CNC)flank milling.

关键词： developable surface surface modeling B-spline surface numerical optimization

Two-Stream Temporal Convolutional Networks for Skeleton-Based Human Action Recognition

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2020年第3期35卷 538-550页

作者： Jin-Gong Jia Yuan-Feng Zhou Xing-Wei Hao Feng Li Christian Desrosiers cai-ming zhang School of Software Shandong UniversityJinan 250101China Department of Software and IT Engineering University of QuebecMontreal H3C 3P8Canada

With the growing popularity of somatosensory interaction devices,human action recognition is becoming attractive in many application ***-based action recognition is effective because the skeleton can represent the position and the structure of key points of the human *** this paper,we leverage spatiotemporal vectors between skeleton sequences as input feature representation of the network,which is more sensitive to changes of the human skeleton compared with representations based on distance and angle *** addition,we redesign residual blocks that have different strides in the depth of the network to improve the processing ability of the temporal convolutional networks(TCNs)for long time dependent *** this work,we propose the two-stream temporal convolutional networks(TSTCNs)that take full advantage of the inter-frame vector feature and the intra-frame vector feature of skeleton sequences in the spatiotemporal *** framework can integrate different feature representations of skeleton sequences so that the two feature representations can make up for each other’s *** fusion loss function is used to supervise the training parameters of the two branch *** on public datasets show that our network achieves superior performance and attains an improvement of 1.2%over the recent GCN-based(BGC-LSTM)method on the NTU RGB+D dataset.

关键词： skeleton action recognition temporal convolutional network(TCN) vector feature representation neural network

Research on a New Coding System for Vibrating Feeder Design

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

International Journal of Plant Engineering and Management 2010年第2期15卷 90-96页

作者： FU cai-an zhang ming DING Wei School of Mechanical Engineering Jiangnan University Wuxi 214122 P. R. China

The sUdeway design is the key in the design of the disc vibrating feeder. However, no reliable theoretical guidance has come into existence, which greatly restricted the application of CAD（ Computer-aided design）. In order to feed the application of CAD technology, we must make improvements to the existing coding method. Based on the similarity principle of Group Technology and existing coding system, a new coding method applicable to slide- way design is brought forward. The existing coding system could get optimized by means of analysing and studying the influence imposed by the parts＇ shape and posture features. More detailed information about the parts could be supplied by the new coding system, which makes the design simpler, more convenient and more accurate with the subjoin of the initial and targeted codes.

关键词： slideway design group technology new coding method posture features

Expression of SNC73, a transcript of the immunoglobulin α-1 gene, in human epithelial carcinomas

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

World Journal of Gastroenterology 2007年第16期13卷 2305-2311页

作者： Li-Yi Geng Zheng-Zhen Shi Qi Dong Xin-Han cai Yan-ming zhang Wei Cao Jia-Ping Peng Yong-ming Fang Lei Zheng Shu Zheng Cancer Institute Zhejiang University School of Medicine Hangzhou 310009 Zhejiang Province China

AIM： To investigate the expression of SNC73, a transcript of the immunoglobulin α-1 gene （IgA1-H chain）, in human epitheliα-derived tumor cells. METHODS： Total RNAs and cell lysates were prepared from five different human epithelial cell lines derived from lung, stomach, liver, skin, and breast, respectively. RT-PCR and immunoblot analysis of these five cell lines were done. Both RT-PCR and immunochemistry were used to detect the expression of SNC73 in these cell lines. We also examined the expression of SNC73 in normal epithelial cells of colon mucosa by in situ hybridization. RT-PCR and immunoblot analysis were used to determine whether the recombination activating gene1/2 （RAG1 and RAG2） is present. The expression of three immunoglobulin transcription factors, EBF, E2A and Pax5, and the heavy chain of IgA1 and two types of light chains of immunoglobulin （κ and λ） in the aforementioned cell lines were analyzed by RT-PCR and immunochemistry, respectively. All the RT-PCR products were analyzed by sequencing. RESULTS： The results of RT-PCR and immunochemistry showed that both mRNA and protein of SNC73 were expressed in five human epitheliα-derived cancer cell lines. These data were further confirmed in the normal epithelial cells of colon mucosa by in situ hybridization. Also, the heavy chain of IgA1 and κ light chain were detected in these cells, but no λ light chain was observed. Both RAG1 and RAG2 were expressed in these human epitheliα-derived cancer cell lines and the sequence was identical to that expressed in pre-B and pre-T cells. In addition to RAG1 and RAG2, the mRNA in one of the immunoglobulin transcription factors, EBF, was also detected in these cell lines, and Pax5 was only expressed in SW480 cells, but no expression of E2A was observed in all the five cell lines. CONCLUSION： Immunoglobulin A1 is originally expressed and V（D）J recombination machine is also present in non-lymphoid cells, suggesting that V（D）J recombination machine mediates the assembly

关键词： SNC73 Immunoglobulin A1 Epithelial cancer cells Recombination activating gene1/2 Immunoglobulin transcription factor

Induction of defence gene expression by oligogalacturonic acid requires in- creases in both cytosolic calcium and hydrogen peroxide in Arabidopsis thaliana

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Cell Research 2004年第3期14卷 234-240页

作者： Steven J NEILL Centre for Research in Plant Science University of the West of England Bristol Coldharbour Lane Bristol BS16 1QY UK

Responses to oligogalacturonic acid （OGA） were determined in transgenic Arabidopsis thaliana seedlings expressing the calcium reporter protein aequorin. OGA stimulated a rapid, substantial and transient increase in the concentration of cytosolic calcium （[Ca2+]cyt） that peaked after ca. 15 s. This increase was dose-dependent, saturating at ca. 50 μg Gal equiv/ml of OGA. OGA also stimulated a rapid generation of H2O2. A small, rapid increase in H2O2 content was followed by a much larger oxidative burst, with H2O2 content peaking after ca. 60 min and declining thereafter. Induction of the oxidative burst by OGA was also dose-dependent, with a maximum response again being achieved at ca. 50 μg Gal equiv/mL. Inhibitors of calcium fluxes inhibited both increases in [Ca2+]cyt and [H2O2], whereas inhibitors of NADPH oxidase blocked only the oxidative burst. OGA increased strongly the expression of the defence-related genes CHS, GST, PAL and PR-1. This induction was suppressed by inhibitors of calcium flux or

关键词： Arabidopsis thaliana cytosolic calcium defence gene expression hydrogen peroxide OGA.

SensFL:Privacy-Preserving Vertical Federated Learning with Sensitive Regularization

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2025年第1期142卷 385-404页

作者： Chongzhen zhang Zhichen Liu Xiangrui Xu Fuqiang Hu Jiao Dai Baigen cai Wei Wang School of Automation and Intelligence Beijing Jiaotong UniversityBeijing100044China Shuohuang Railway Development Co. Ltd.National Energy GroupCangzhou062350China Beijing Key Laboratory of Security and Privacy in Intelligent Transportation School of Computer Science and TechnologyBeijing Jiaotong UniversityBeijing100044China

In the realm of Intelligent Railway Transportation Systems,effective multi-party collaboration is crucial due to concerns over privacy and data *** Federated Learning(VFL)has emerged as a promising approach to facilitate such collaboration,allowing diverse entities to collectively enhance machine learning models without the need to share sensitive training ***,existing works have highlighted VFL’s susceptibility to privacy inference attacks,where an honest but curious server could potentially reconstruct a client’s raw data from embeddings uploaded by the *** vulnerability poses a significant threat to VFL-based intelligent railway transportation *** this paper,we introduce SensFL,a novel privacy-enhancing method to against privacy inference attacks in ***,SensFL integrates regularization of the sensitivity of embeddings to the original data into the model training process,effectively limiting the information contained in shared *** reducing the sensitivity of embeddings to the original data,SensFL can effectively resist reverse privacy attacks and prevent the reconstruction of the original data from the *** experiments were conducted on four distinct datasets and three different models to demonstrate the efficacy of *** results show that SensFL can effectively mitigate privacy inference attacks while maintaining the accuracy of the primary learning *** results underscore SensFL’s potential to advance privacy protection technologies within VFL-based intelligent railway systems,addressing critical security concerns in collaborative learning environments.

关键词： Vertical federated learning privacy defenses

Identifying the dynamic behaviors in complete reconstruction of Co-based complex precatalysts during electrocatalytic oxygen evolution

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Energy Chemistry 2025年第1期100卷 226-233页

作者： Jingfang zhang Danyang Wu Linke cai Youluan Lu Fanpeng Cheng Lijuan Shi Qun Yi Yao Liu Yi Huang Key Laboratory of Green Chemical Engineering Process of Ministry of Education Engineering Research Center of Phosphorus Resources Development and Utilization of Ministry of Education Hubei Key Laboratory of Novel Reactor and Green Chemical Technology School of Chemical Engineering & Pharmacy Wuhan Institute of Technology Key Laboratory of Pesticide & Chemical Biology of Ministry of Education Engineering Research Center of Photoenergy Utilization for Pollution Control and Carbon Reduction of Ministry of Education College of Chemistry Central China Normal University College of Materials Science and Engineering Fuzhou University

Transition metal-based nanomaterials have emerged as promising electrocatalysts for oxygen evolution reaction（OER）. Considerable research efforts have shown that self-reconstruction occurs on these nanomaterials under operating conditions of OER process. However, most of them undergo incomplete reconstruction with limited thickness of reconstruction layer, leading to low component utilization and arduous exploration of real catalytic mechanism. Herein, we identify the dynamic behaviors in complete reconstruction of Co-based complexes during OER. The hollow phytic acid（PA） cross-linked CoFe-based complex nanoboxes with porous nanowalls are designed because of their good electrolyte penetration and mass transport ability, in favor of the fast and complete reconstruction. A series of experiment characterizations demonstrate that the reconstruction process includes the fast substitution of PA by OH-to form Co（Fe）(OH)xand subsequent potential-driven oxidation to Co（Fe）OOH. The obtained CoFeOOH delivers a low overpotential of 290 mV at a current density of 10 mA cm-2and a long-term *** experiment results together with theory calculations reveal that the Fe incorporation can result in the electron rearrangement of reconstructed CoFeOOH and optimization of their electronic structure,accounting for the enhanced OER activity. The work provides new insights into complete reconstruction of metal-based complexes during OER and offers guidelines for rational design of high-performance electrocatalysts.

关键词： Complete reconstruction Co-based complex Precatalysts Oxygen evolution reaction