LIVIVO - The Search Portal for Life Sciences

zur deutschen Oberfläche wechseln
Advanced search

Search results

Result 1 - 10 of total 13

Search options

  1. Article ; Online: A Generalized Nesterov-Accelerated Second-Order Latent Factor Model for High-Dimensional and Incomplete Data.

    Li, Weiling / Wang, Renfang / Luo, Xin

    IEEE transactions on neural networks and learning systems

    2023  Volume PP

    Abstract: High-dimensional and incomplete (HDI) data are frequently encountered in big date-related applications for describing restricted observed interactions among large node sets. How to perform accurate and efficient representation learning on such HDI data ... ...

    Abstract High-dimensional and incomplete (HDI) data are frequently encountered in big date-related applications for describing restricted observed interactions among large node sets. How to perform accurate and efficient representation learning on such HDI data is a hot yet thorny issue. A latent factor (LF) model has proven to be efficient in addressing it. However, the objective function of an LF model is nonconvex. Commonly adopted first-order methods cannot approach its second-order stationary point, thereby resulting in accuracy loss. On the other hand, traditional second-order methods are impractical for LF models since they suffer from high computational costs due to the required operations on the objective's huge Hessian matrix. In order to address this issue, this study proposes a generalized Nesterov-accelerated second-order LF (GNSLF) model that integrates twofold conceptions: 1) acquiring proper second-order step efficiently by adopting a Hessian-vector algorithm and 2) embedding the second-order step into a generalized Nesterov's acceleration (GNA) method for speeding up its linear search process. The analysis focuses on the local convergence for GNSLF's nonconvex cost function instead of the global convergence has been taken; its local convergence properties have been provided with theoretical proofs. Experimental results on six HDI data cases demonstrate that GNSLF performs better than state-of-the-art LF models in accuracy for missing data estimation with high efficiency, i.e., a second-order model can be accelerated by incorporating GNA without accuracy loss.
    Language English
    Publishing date 2023-10-13
    Publishing country United States
    Document type Journal Article
    ISSN 2162-2388
    ISSN (online) 2162-2388
    DOI 10.1109/TNNLS.2023.3321915
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  2. Book ; Online: Seismic Traveltime Tomography with Label-free Learning

    Wang, Feng / Yang, Bo / Wang, Renfang / Qiu, Hong

    2024  

    Abstract: Deep learning techniques have been used to build velocity models (VMs) for seismic traveltime tomography and have shown encouraging performance in recent years. However, they need to generate labeled samples (i.e., pairs of input and label) to train the ... ...

    Abstract Deep learning techniques have been used to build velocity models (VMs) for seismic traveltime tomography and have shown encouraging performance in recent years. However, they need to generate labeled samples (i.e., pairs of input and label) to train the deep neural network (NN) with end-to-end learning, and the real labels for field data inversion are usually missing or very expensive. Some traditional tomographic methods can be implemented quickly, but their effectiveness is often limited by prior assumptions. To avoid generating labeled samples, we propose a novel method by integrating deep learning and dictionary learning to enhance the VMs with low resolution by using the traditional tomography-least square method (LSQR). We first design a type of shallow and simple NN to reduce computational cost followed by proposing a two-step strategy to enhance the VMs with low resolution: (1) Warming up. An initial dictionary is trained from the estimation by LSQR through dictionary learning method; (2) Dictionary optimization. The initial dictionary obtained in the warming-up step will be optimized by the NN, and then it will be used to reconstruct high-resolution VMs with the reference slowness and the estimation by LSQR. Furthermore, we design a loss function to minimize traveltime misfit to ensure that NN training is label-free, and the optimized dictionary can be obtained after each epoch of NN training. We demonstrate the effectiveness of the proposed method through numerical tests.

    Comment: 15 pages, 19 figures. Submitted to IEEE Transactions on Geoscience and Remote Sensing
    Keywords Physics - Geophysics ; Computer Science - Machine Learning
    Subject code 006
    Publishing date 2024-01-31
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  3. Book ; Online: Adaptive Divergence-based Non-negative Latent Factor Analysis

    Yuan, Ye / Yuan, Guangxiao / Wang, Renfang / Luo, Xin

    2022  

    Abstract: High-Dimensional and Incomplete (HDI) data are frequently found in various industrial applications with complex interactions among numerous nodes, which are commonly non-negative for representing the inherent non-negativity of node interactions. A Non- ... ...

    Abstract High-Dimensional and Incomplete (HDI) data are frequently found in various industrial applications with complex interactions among numerous nodes, which are commonly non-negative for representing the inherent non-negativity of node interactions. A Non-negative Latent Factor (NLF) model is able to extract intrinsic features from such data efficiently. However, existing NLF models all adopt a static divergence metric like Euclidean distance or {\alpha}-\b{eta} divergence to build its learning objective, which greatly restricts its scalability of accurately representing HDI data from different domains. Aiming at addressing this issue, this study presents an Adaptive Divergence-based Non-negative Latent Factor (ADNLF) model with three-fold ideas: a) generalizing the objective function with the {\alpha}-\b{eta}-divergence to expand its potential of representing various HDI data; b) adopting a non-negative bridging function to connect the optimization variables with output latent factors for fulfilling the non-negativity constraints constantly; and c) making the divergence parameters adaptive through particle swarm optimization, thereby facilitating adaptive divergence in the learning objective to achieve high scalability. Empirical studies are conducted on four HDI datasets from real applications, whose results demonstrate that in comparison with state-of-the-art NLF models, an ADNLF model achieves significantly higher estimation accuracy for missing data of an HDI dataset with high computational efficiency.
    Keywords Computer Science - Machine Learning
    Subject code 006
    Publishing date 2022-03-30
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  4. Article ; Online: A Smoothed Matrix Multivariate Elliptical Distribution-Based Projection Method for Feature Extraction.

    Qiu, Hong / Wang, Renfang / Sun, Dechao / Liu, Xinwei / Zhang, Liang / Liu, Yunpeng

    Computational intelligence and neuroscience

    2022  Volume 2022, Page(s) 2551137

    Abstract: Big data has the traits such as "the curse of dimensionality," high storage cost, and heavy computation burden. Self-representation-based feature extraction methods cannot effectively deal with the image-level structural noise in the data, so how to ... ...

    Abstract Big data has the traits such as "the curse of dimensionality," high storage cost, and heavy computation burden. Self-representation-based feature extraction methods cannot effectively deal with the image-level structural noise in the data, so how to character a better relationship of reconstruction representation is very important. Recently, sparse representation with smoothed matrix multivariate elliptical distribution (SMED) using structural information to handle low-rank error images caused by illumination or occlusion has been proposed. Based on SMED, we present a new method named SMEDP for feature extraction. SMEDP firstly utilizes SMED to automatically construct an adjacency graph and then obtains an optimal projection matrix by maximizing the ratio of the local scatter matrix and the total scatter matrix in the PCA subspace. Experiments on the COIL-20 object database, ORL face database, and CMU PIE face database prove that SMEDP works well and can achieve considerable visual and recognition performance than the relevant methods.
    MeSH term(s) Algorithms ; Databases, Factual ; Lighting ; Pattern Recognition, Automated/methods ; Recognition, Psychology
    Language English
    Publishing date 2022-09-30
    Publishing country United States
    Document type Journal Article
    ZDB-ID 2388208-6
    ISSN 1687-5273 ; 1687-5273
    ISSN (online) 1687-5273
    ISSN 1687-5273
    DOI 10.1155/2022/2551137
    Database MEDical Literature Analysis and Retrieval System OnLINE

    Full text online

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  5. Article: Prof. Yi Hu: a doctor of acute insight and action.

    Wang, Renfang / Yu, Tanlun

    Journal of thoracic disease

    2017  Volume 9, Issue Suppl 11, Page(s) S1168–S1175

    Language English
    Publishing date 2017-03-27
    Publishing country China
    Document type News
    ZDB-ID 2573571-8
    ISSN 2077-6624 ; 2072-1439
    ISSN (online) 2077-6624
    ISSN 2072-1439
    DOI 10.21037/jtd.2017.09.148
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  6. Article: Prof. Li Zhang, a brisk PUMCH doctor with sunshine.

    Wang, Renfang / He, Chao-Xiu Melanie

    Journal of thoracic disease

    2017  Volume 9, Issue Suppl 11, Page(s) S1234–S1241

    Language English
    Publishing date 2017-03-27
    Publishing country China
    Document type News
    ZDB-ID 2573571-8
    ISSN 2077-6624 ; 2072-1439
    ISSN (online) 2077-6624
    ISSN 2072-1439
    DOI 10.21037/jtd.2017.09.156
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  7. Article: Shugeng Gao: a cool-headed and virtuous thoracic surgeon.

    Liao, Lili / Wang, Renfang

    Journal of thoracic disease

    2017  Volume 10, Issue Suppl 11, Page(s) S1274–S1279

    Language English
    Publishing date 2017-07-19
    Publishing country China
    Document type News
    ZDB-ID 2573571-8
    ISSN 2077-6624 ; 2072-1439
    ISSN (online) 2077-6624
    ISSN 2072-1439
    DOI 10.21037/jtd.2018.05.48
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  8. Article: [CT and MRI fusion based on generative adversarial network and convolutional neural networks under image enhancement].

    Liu, Yunpeng / Li, Jin / Wang, Yu / Cai, Wenli / Chen, Fei / Liu, Wenjie / Mao, Xianhao / Gan, Kaifeng / Wang, Renfang / Sun, Dechao / Qiu, Hong / Liu, Bangquan

    Sheng wu yi xue gong cheng xue za zhi = Journal of biomedical engineering = Shengwu yixue gongchengxue zazhi

    2023  Volume 40, Issue 2, Page(s) 208–216

    Abstract: Aiming at the problems of missing important features, inconspicuous details and unclear textures in the fusion of multimodal medical images, this paper proposes a method of computed tomography (CT) image and magnetic resonance imaging (MRI) image fusion ... ...

    Abstract Aiming at the problems of missing important features, inconspicuous details and unclear textures in the fusion of multimodal medical images, this paper proposes a method of computed tomography (CT) image and magnetic resonance imaging (MRI) image fusion using generative adversarial network (GAN) and convolutional neural network (CNN) under image enhancement. The generator aimed at high-frequency feature images and used double discriminators to target the fusion images after inverse transform; Then high-frequency feature images were fused by trained GAN model, and low-frequency feature images were fused by CNN pre-training model based on transfer learning. Experimental results showed that, compared with the current advanced fusion algorithm, the proposed method had more abundant texture details and clearer contour edge information in subjective representation. In the evaluation of objective indicators, Q
    MeSH term(s) Image Processing, Computer-Assisted/methods ; Neural Networks, Computer ; Tomography, X-Ray Computed ; Magnetic Resonance Imaging/methods ; Algorithms
    Language Chinese
    Publishing date 2023-05-01
    Publishing country China
    Document type English Abstract ; Journal Article
    ZDB-ID 2576847-5
    ISSN 1001-5515
    ISSN 1001-5515
    DOI 10.7507/1001-5515.202209050
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    In stock of ZB MED Cologne/Königswinter

    Zs.A 6887: Show issues Location:
    Je nach Verfügbarkeit (siehe Angabe bei Bestand)
    bis Jg. 2021: Bestellungen von Artikeln über das Online-Bestellformular
    ab Jg. 2022: Lesesaal (EG)

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  9. Article: Comfort index evaluating the water and thermal characteristics of proton exchange membrane fuel cell

    Wang, Renfang / Guobin Zhang / Zhongjun Hou / Keyong Wang / Yangyang Zhao / Kui Jiao

    Energy conversion and management. 2019 Apr. 01, v. 185

    2019  

    Abstract: Water and thermal management is of great importance to proton exchange membrane fuel cell. A comfort index is proposed to comprehensively evaluate the water and thermal characteristics in proton exchange membrane fuel cell. It refers to the concept of ... ...

    Abstract Water and thermal management is of great importance to proton exchange membrane fuel cell. A comfort index is proposed to comprehensively evaluate the water and thermal characteristics in proton exchange membrane fuel cell. It refers to the concept of comfort index in meteorology and selects the cathode liquid water accumulation and anode membrane drying as two basic factors so as to prevent water flooding and low proton conductivity simultaneously. The anode and cathode comfort degrees corresponding to the anode membrane drying and cathode liquid water accumulation, respectively, are quantified and fitted at various operation conditions, of which the parameters in the calculation process are determined utilizing a carefully validated quasi-two-dimensional model. The influences of cathode stoichiometric ratio, operating pressure, coolant temperature difference, cathode relative humidity, coolant temperature, anode recirculating ratio, current density and membrane thickness at wide-range temperature are studied in detail by the comfort index. It is found that the comfort index usually first increases and then decreases with the increment of temperature, because the low water saturation pressure at low temperature makes the water condensation easier and thus leads to water flooding. Compared to analytical simulation models, the comfort index is able to instantly obtain the quantified water and thermal characteristics in proton exchange membrane fuel cell, which is of great significance to the stack design and in-situ system controlling in practical design.
    Keywords anodes ; cathodes ; condensation (phase transition) ; drying ; fuel cells ; liquids ; meteorology ; relative humidity ; simulation models ; temperature ; thermal properties
    Language English
    Dates of publication 2019-0401
    Size p. 496-507.
    Publishing place Elsevier Ltd
    Document type Article
    ZDB-ID 2000891-0
    ISSN 0196-8904
    ISSN 0196-8904
    DOI 10.1016/j.enconman.2019.02.021
    Database NAL-Catalogue (AGRICOLA)

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  10. Article: Characteristics of Cold Start Behavior of PEM Fuel Cell with Metal Foam as Cathode Flow Field under Subfreezing Temperature

    Huo, Sen / Li, Lincai / Shi, Weiyu / Wang, Renfang / Lu, Bingbing / Yin, Yan / Zhu, Chaoyi / Wang, Yang / Jiao, Kui / Hou, Zhongjun

    International journal of green energy. 2021 Sept. 02, v. 18, no. 11

    2021  

    Abstract: Cold start has been realized as an important issue for PEMFC in its global commercialization. As is well-known, the conventional “channel-rib” type flow field will surely lead to several problems, such as water accumulation under the rib, resulting in ... ...

    Abstract Cold start has been realized as an important issue for PEMFC in its global commercialization. As is well-known, the conventional “channel-rib” type flow field will surely lead to several problems, such as water accumulation under the rib, resulting in slow water removal and serious ice blockage in the pores. In recent years, with the fast development of metal foam materials, metal foam has been recognized as a promising alternative replacement of the conventional “channel-rib” type flow field. In this study, a cold start model of PEMFC is established under sub-zero temperature. The coupled transport processes of heat, mass and charge in PEMFC under various subzero temperatures and startup modes are simulated. The results show that ice formation is slower in the PEMFC with metal foam as cathode flow field in cold start process, due to the superior performance of metal foam in water removal and uniform distribution of gas supply. However, the excellent thermal conductivity of metal foam could also result in faster heat loss from PEMFC. Furthermore, ice formation is highly dependent on the supercooled water transfer behavior, though small amount of supercooled water is maintained in the cell. This work aims to provide a systematic analysis for the cold start behavior of PEMFC with metal foam flow field.
    Keywords cathodes ; cold ; commercialization ; foams ; fuel cells ; heat ; ice ; models ; temperature ; thermal conductivity
    Language English
    Dates of publication 2021-0902
    Size p. 1129-1146.
    Publishing place Taylor & Francis
    Document type Article
    ISSN 1543-5083
    DOI 10.1080/15435075.2021.1891911
    Database NAL-Catalogue (AGRICOLA)

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

To top