|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Extreme learning machines: new trends and applications显示文摘Extreme learning machine(ELM), as a new learning framework, draws increasing attractions in the areas of large-scale computing, high-speed signal processing, artificial intelligence, and so on. ELM aims to break the barriers between the conventional artificial learning techniques and biological learning mechanism and represents a suite of machine learning techniques in which hidden neurons need not to be tuned. ELM theories and algorithms argue that 'random hidden neurons' capture the essence of some brain learning mechanisms as well as the intuitive sense that the efficiency of brain learning need not rely on computing power of neurons.Thus, compared with traditional neural networks and support vector machine, ELM offers significant advantages such as fast learning speed, ease of implementation, and minimal human intervention. Due to its remarkable generalization performance and implementation efficiency, ELM has been applied in various applications. In this paper, we first provide an overview of newly derived ELM theories and approaches. On the other hand,with the ongoing development of multilayer feature representation, some new trends on ELM-based hierarchical learning are discussed. Moreover, we also present several interesting ELM applications to showcase the practical advances on this subject. | DENG ChenWei HUANG GuangBin XU Jia TANG JieXiong | 2015 | Science China(Information Sciences)2015，58，2： | 50 |
| 2 | Image Quality Evaluation Method Based on Human Visual System显示文摘 | ZHAO Bao DENG Chenwei | 2010 | Chinese Journal of Electronics2010，19，1： | 4 |
| 3 | Real-Time Coding Scheme for High-Resolution Remote Sensing Images显示文摘 | DENG Chenwei ZHAO Baojun | 2009 | Chinese Journal of Electronics2009，18，3： | 3 |
| 4 | Compressed-domain Ship Detection on Spaceborne Optical Image Using Deep Neural Network and Extreme Learning Machine显示文摘 | Tang Jiexiong Deng Chenwei Huang Guangbin | 2014 | IEEE Transactions on Geoscience and Remote Sensing2014，53，3： | 1 |
| 5 | Im- age Retargeting Quality Assessment: A Study of Subjective Scores and Objective Metrics显示文摘 | MA Lin LIN Weisi DENG Chenwei | 2012 | IEEE Journal of Selected Topics in Signal Pro- cessing2012，6，6： | 1 |
| 6 | 264/AVC FRExt for high resolution video coding显示文摘 | Chenwei Deng Weisi Lin:Performance analysis parameter selection and extensions to H | 2011 | Journal of visual communication&image representation2011，22，8： | 1 |
| 7 | Ro-bust image coding based upon compressive sensing显示文摘 | DENG Chenwei LIN Weisi LEE Bu-sung | 2012 | IEEE Transactions on Multimedia2012，14，2： | 1 |
| 8 | Reducing the carbon emissions from Qianxi tomato fruits preservation by cold atmospheric plasma显示文摘China has pledged to reach its dual-carbon goals(i.e.,carbon peak and carbon neutrality)at the end of 2060.To reduce carbon emission in food preservation industry,the preservation effects of cold atmospheric plasma intermittent treatment(1 min/6 h each day,PL4)combined with 15℃ and 4℃ only on Qianxi tomato fruits during 7 d storage were investigated.Results indicated that the firmness,L*,sensory taste,glutathione(GSH)content,mineral(Fe,P,K)content,polyphenol oxidase activity of PL4 tomatoes were significantly increased than that in Control during earlier period storage,with worse weight loss,titratable acid,a*,b*,lycopene content,·OH radical scavenging capacity and same moisture content,total soluble solids,polysaccharide content,total phenolics content,total flavonoid content,ascorbic acid content,1,1-diphenyl-2-picrylhydrazyl radical scavenging capacity,pectin methylesterase activity.Moreover,the power and R134a consumption of PL4 were highly decreased by around 56.4 kW·h and 0.3 g respectively during whole storage as compared to Control,and reduced more than 99.8%carbon emission based on equipment using stage.All in all,this study illustrated that PL4 treatment can be applied as an ecofriendly,low carbon and sustainable preservation strategy for short-term storage of fruits under 4℃ or higher temperature. | Tao Jin Yan Chen Chenwei Dai Jimin Deng Qinghua Xu Zhengwei Wu | 2023 | International Journal of Agricultural and Biological Engineering2023，16，5： | 0 |
| 9 | Tailoring morphology symmetry of bismuth vanadate photocatalysts for efficient charge separation显示文摘Although spatial charge separation between different facets of semiconductor crystals has been recognized as a general strategy in photocatalysis, the vital role of crystal morphology symmetry in charge separation properties still remains elusive. Herein,taking monoclinic bismuth vanadate(BiVO_(4)) as a platform, we found distinct charge separation difference via rationally tailoring the morphology symmetry from octahedral to truncated octahedral crystals. For octahedral BiVO_(4), photogenerated electrons and holes can be separated between edges and quasi-equivalent facets. However, as for truncated octahedral crystals,photogenerated electrons tend to transfer to {010} facets while photogenerated holes prefer to accumulate on {120} facets, thus realizing the spatial separation of photogenerated charge between different facets. Morphology tailoring of BiVO_(4) crystals leads to a significantly improved photogenerated charge separation efficiency and photocatalytic water oxidation activity. The built-in electric field for driving the separation of photogenerated electrons and holes is considered to be modulated by tuning the morphology symmetry of BiVO_(4) crystals. This work discloses the significant roles of morphology symmetry in photogenerated charge separation and facilitates the rational design of artificial photocatalysts. | Yuting Deng Hongpeng Zhou Chenwei Ni Fengke Sun Wenchao Jiang Ruotian Chen Wenming Tian Can Li Rengui Li | 2023 | Science China Chemistry2023，66，12： | 0 |
| 10 | 视觉信号质量评估显示文摘随着计算机与网络技术的快速发展,人们创造了大量的视觉信号——目前生活中随处可见的视频、图形图像、动画等等都属于视觉信号的范畴。随着这些视觉数据的海量涌现,视觉体验质量(QoE)在多媒体技术与服务中也扮演着越来越重要的作用。在过去的20年间,视觉质量评估领域的发展可谓日新月异。这一方面要归功于图形图像识别设备的快速发展,另一方面,人类在精神物理学以及神经学方面的发现又让我们对人类视觉系统有了更加清晰的认识。 | Chenwei Deng 臧光明 | 2015 | 国外科技新书评介2015，0，7： | 0 |
| 11 | Robust Clustering with Topological Graph Partition显示文摘Clustering is fundamental in many fields with big data. In this paper, a novel method based on Topological graph partition(TGP) is proposed to group objects. A topological graph is created for a data set with many objects, in which an object is connected to k nearest neighbors. By computing the weight of each object, a decision graph under probability comes into being. A cut threshold is conveniently selected where the probability of weight anomalously becomes large. With the threshold,the topological graph is cut apart into several sub-graphs after the noise edges are cut off, in which a connected subgraph is treated as a cluster. The compared experiments demonstrate that the proposed method is more robust to cluster the data sets with high dimensions, complex distribution, and hidden noises. It is not sensitive to input parameter, we need not more priori knowledge. | WANG Shuliang LI Qi YUAN Hanning GENG Jing DAI Tianru DENG Chenwei | 2019 | Chinese Journal of Electronics2019，28，1： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员