|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Copula based analysis of rainfall severity and duration : a case study显示文摘 | Ummul F A R Panlop Z | 2014 | Theoretical & Applied Climatolo- gyl2014，115，： | 1 |
| 2 | Citation practices among non-native expert and novice scientific writers显示文摘 | MANSOURIZADEH K AHMAD K Ummul | 2011 | Journal of English for Academic Purposes2011，，10： | 1 |
| 3 | Consider this:The role of imperatives in scholarly writing显示文摘 | Swales J Ahmad Ummul K Chang Yu-Ying | | 0，，01： | 1 |
| 4 | Citation practices among non-native expert and novice scientific writers显示文摘 | Kobra Mansourizadeh Ummul K. Ahmad | 2011 | Journal of English for Academic Purposes2011，，3： | 1 |
| 5 | Development and evaluation of a one-step SYBR-Green I-based real- time RT-PCR assay for the detection and quantification of Chikungunya virus in human, monkey and mosquito samples 显示文摘 | Ummul HA Vasan SS Ravindran T | 2010 | Trop Biomed2010，27，3： | 1 |
| 6 | Development andevaluation of a one-step SYBR-GreenⅠ-based RT-PCR assay forthe detection and quantification of Chikungunya virus in human,monkey and mosquito samples显示文摘 | Ummul HA Vasan SS Ravindran T | 2010 | Trop Biomed2010，27，3： | 1 |
| 7 | Highly adhesive metal plating on Zylon ? fiber via iodine pretreatment显示文摘 | Ummul Khair Fatema Yasuo Gotoh | 2011 | Applied Surface Science2011，，2： | 1 |
| 8 | Enhancing Collaborative and Geometric Multi-Kernel Learning Using Deep Neural Network显示文摘This research proposes a method called enhanced collaborative andgeometric multi-kernel learning (E-CGMKL) that can enhance the CGMKLalgorithm which deals with multi-class classification problems with non-lineardata distributions. CGMKL combines multiple kernel learning with softmaxfunction using the framework of multi empirical kernel learning (MEKL) inwhich empirical kernel mapping (EKM) provides explicit feature constructionin the high dimensional kernel space. CGMKL ensures the consistent outputof samples across kernel spaces and minimizes the within-class distance tohighlight geometric features of multiple classes. However, the kernels constructed by CGMKL do not have any explicit relationship among them andtry to construct high dimensional feature representations independently fromeach other. This could be disadvantageous for learning on datasets with complex hidden structures. To overcome this limitation, E-CGMKL constructskernel spaces from hidden layers of trained deep neural networks (DNN).Due to the nature of the DNN architecture, these kernel spaces not onlyprovide multiple feature representations but also inherit the compositionalhierarchy of the hidden layers, which might be beneficial for enhancing thepredictive performance of the CGMKL algorithm on complex data withnatural hierarchical structures, for example, image data. Furthermore, ourproposed scheme handles image data by constructing kernel spaces from aconvolutional neural network (CNN). Considering the effectiveness of CNNarchitecture on image data, these kernel spaces provide a major advantageover the CGMKL algorithm which does not exploit the CNN architecture forconstructing kernel spaces from image data. Additionally, outputs of hiddenlayers directly provide features for kernel spaces and unlike CGMKL, do notrequire an approximate MEKL framework. E-CGMKL combines the consistency and geometry preserving aspects of CGMKL with the compositionalhierarchy of kernel spaces extracted from DNN hidden layers to enhance the predictive performance of CGMKL significantly. The experimental results onvarious data sets demonstrate the superior performance of the E-CGMKLalgorithm compared to other competing methods including the benchmarkCGMKL. | Bareera Zafar Syed Abbas Zilqurnain Naqvi Muhammad Ahsan Allah Ditta Ummul Baneen Muhammad Adnan Khan | 2022 | Computers, Materials & Continua2022，，9： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员