检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Han, Haochen Zheng, Qinghua Luo, Minnan Miao, Kaiyao Tian, Feng Chen, Yan The National Engineering Lab for Big Data Analytics Xi’an Jiaotong University Xi’an710049 China The School of Computer Science and Technology Xi’an Jiaotong University Xi’an710049 China The Key Laboratory of Intelligent Networks and Network Security Xi’an Jiaotong University Ministry of Education Xi’an710049 China The School of Cyber Science and Engineering Xi’an Jiaotong University Xi’an710049 China

Recently, video recognition is emerging with the help of multi-modal learning, which focuses on integrating distinct modalities to improve the performance or robustness of the model. Although various multi-modal learning methods have been proposed and offer remarkable recognition results, almost all of these methods rely on high-quality manual annotations and assume that modalities among multi-modal data provide semantically relevant information. Unfortunately, the widely used video datasets are usually coarse-annotated or collected from the Internet. Thus, it inevitably contains a portion of noisy labels and noisy correspondence. To address this challenge, we use the audio-visual action recognition task as a proxy and propose a noise-tolerant learning framework to find anti-interference model parameters against both noisy labels and noisy correspondence. Specifically, our method consists of two phases that aim to rectify noise by the inherent correlation between modalities. First, a noise-tolerant contrastive training phase is performed to make the model immune to the possible noisy-labeled data. Despite the benefits brought by contrastive training, it would overfit the noisy correspondence and thus provide false supervision. To alleviate the influence of noisy correspondence, we propose a cross-modal noise estimation component to adjust the consistency between different modalities. As the noisy correspondence existed at the instance level, we further propose a category-level contrastive loss to reduce its interference. Second, in the hybrid-supervised training phase, we calculate the distance metric among features to obtain corrected labels, which are used as complementary supervision to guide the training. Furthermore, due to the lack of suitable datasets, we establish a benchmark of real-world noisy correspondence in audio-visual data by relabeling the Kinetics dataset. Extensive experiments on a wide range of noisy levels demonstrate that our method significant

关键词： Modal analysis

来源：评论

学校读者我要写书评

暂无评论

Continual learning via inter-task synaptic mapping

arXiv

引用

arXiv 2021年

作者： Fubing, Mao Weiwei, Weng Pratama, Mahardhika Kien Yee, Edward Yapp National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab. Cluster and Grid Computing Lab. School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China School of Computer Science and Engineering Nanyang Technological University Singapore Singapore Singapore Institute of Manufacturing Technology A*Star Singapore Singapore

Learning from streaming tasks leads a model to catastrophically erase unique experiences it absorbs from previous episodes. While regularization techniques such as LWF, SI, EWC have proven themselves as an effective avenue to overcome this issue by constraining important parameters of old tasks from changing when accepting new concepts, these approaches do not exploit common information of each task which can be shared to existing neurons. As a result, they do not scale well to large-scale problems since the parameter importance variables quickly explode. An Inter-Task Synaptic Mapping (ISYANA) is proposed here to underpin knowledge retention for continual learning. ISYANA combines task-to-neuron relationship as well as concept-to-concept relationship such that it prevents a neuron to embrace distinct concepts while merely accepting relevant concept. Numerical study in the benchmark continual learning problems has been carried out followed by comparison against prominent continual learning algorithms. ISYANA exhibits competitive performance compared to state of the arts. Codes of ISYANA is made available in https://***/ContinualAL/ISYANAKBS. © 2021, CC BY-NC-SA.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Matching Ontologies Through Evolutionary Algorithm with Context-Based Reasoning 6th

Matching Ontologies Through Evolutionary Algorithm with Cont...

引用

6th International Conference on Advanced Machine Learning Technologies and Applications, AMLTA 2021

作者： Yang, Chaofan Xue, Xingsi Yue, Cai Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou Fujian350118 China Intelligent Information Processing Research Center Fujian University of Technology Fuzhou Fujian350118 China College of Information Science and Engineering Fujian University of Technology Fuzhou Fujian350118 China Fujian Key Lab for Automotive Electronics and Electric Drive Fujian University of Technology Fuzhou Fujian350118 China Guangxi Key Laboratory of Automatic Detecting Technology and Instruments Guilin University of Electronic Technology Guilin Guangxi541004 China School of Information and Communication Guilin University of Electronic Technology Guilin Guangxi541004 China

ISBN: (纸本)9783030697167

Ontology matching can solve the heterogeneity problem between two ontologies, and EA represents a state-of-the-art technique for matching ontologies. However, there are two defects concerning the EA-based ontology matching technique: (1) a reference alignment between two ontologies to be matched is required in advance;(2) the confidence of entity similarity measure is low computational complexity of measuring the similarity value is high. To overcome these drawbacks, in this paper, an Evolutionary Algorithm with Context-based Reasoning method (EA-CR) is proposed, where: (1) an approximate metric without the reference alignment is utilized for evaluating the alignment’s quality;(2) a Context-based Reasoning method is presented to distinguish the heterogeneous entities. The experimental results show that the proposed approach is effective. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Prediction of Chemical Oxygen Demand in Sewage Based on Support Vector Machine and Neural Network 1

引用

15th International Conference on Intelligent Computing, ICIC 2019

作者： Zhou, Jian Huang, Qian-Jing Wang, Xiao-Feng Zou, Le Department of Environmental Engineering Hefei University HefeiAnhui230601 China Anhui Provincial Engineering Laboratory of Big Data Technology Application for Urban Infrastructure Department of Computer Science and Technology Hefei University Hefei230601 China

ISBN: (数字)9783030267636

ISBN: (纸本)9783030267629

Aiming at the problem that the detection accuracy of effluent COD (chemical oxygen demand) in sewage treatment needs to be further improved, a combined model based on support vector machine and neural network is proposed to predict effluent COD. It can reduce the influence of local optimum on the global scope so as to improve the accuracy of prediction. Firstly, the sample data are divided into two categories by support vector machine. Then the BP neural network model and the Echo State Network (ESN) model are established on two sub-samples respectively. Compared with single neural network model, the mean absolute error and root mean square error of combined model are both reduced. Besides, the proposed model has better comprehensive prediction performance and can meet the actual demand of effluent COD prediction in sewage treatment. © 2019, Springer Nature Switzerland AG.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A Vision-based Lane Departure Warning Framework

A Vision-based Lane Departure Warning Framework

引用

IEEE International Conference on e-Business engineering (ICEBE)

作者： Jiaju Wu Pengshuai Yin Xin Shu Huichou Huang Fei Liu Qingyao Wu School of Software Engineering South China University of Technology China Key Laboratory of Big Data and Intelligent Robot Ministry of Education City University of Hong Kong Hong Kong China Pazhou Lab Guangzhou China

ISBN: (纸本)9781665444194

Lane departure warning is an essential function of driver assistance systems. In this paper, we propose a vision-based lane departure warning framework, which can determine whether the vehicle deviates from the lane only with images as input. Our framework combines the deep learning method and traditional line detection algorithm. Specifically, the framework consists of a Lane Boundaries Localization module, a Lane Boundaries Generator module, and a Departure Warning module. The Lane Boundaries Localization module is a deep neural network for finding the area containing lane Boundaries. Then the Lane Boundaries Generator module performs backbone detection and line detection to generate lane boundaries on the located area. After identifying the lane boundaries, the Departure Warning module can quickly determine whether the vehicle deviates from the lane. Additionally, we implemented and deployed our framework to an Android platform and tested its running speed.

关键词： Location awareness Deep learning Conferences Neural networks Transforms Generators Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Ginsenoside compound-K attenuates OVX-induced osteoporosis via the suppression of RANKL-induced osteoclastogenesis and oxidative stress

引用

Natural Products and Bioprospecting 2023年第1期13卷 159-170页

作者： Lingli Ding Zhao Gao Siluo Wu Chen Chen Yamei Liu Min Wang Yage Zhang Ling Li Hong Zou Guoping Zhao Shengnan Qin Liangliang Xu Key Laboratory of Orthopaedics and Traumatology Lingnan Medical Research CenterThe First Affiliated Hospital of Guangzhou University of Chinese MedicineGuangzhou University of Chinese MedicineGuangzhouChina Er Sha Sports Training Center of Guangdong Province GuangzhouChina School of Basic Medical Science Guangzhou University of Chinese MedicineGuangzhouChina Engineering Laboratory for Nutrition Shanghai Institute of Nutrition and HealthChinese Academy of SciencesShanghaiChina Master Lab for Innovative Application of Nature Products National Center of Technology Innovation for Synthetic BiologyTianjin Institute of Industrial BiotechnologyChinese Academy of SciencesTianjinChina CAS Key Laboratory of Quantitative Engineering Biology Shenzhen Institute of Synthetic BiologyShenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhenChina CAS-Key Laboratory of Synthetic Biology CAS Center for Excellence in Molecular Plant SciencesShanghai Institute of Plant Physiology and EcologyChinese Academy of SciencesShanghaiChina Bio-Med Big Data Center Shanghai Institute of Nutrition and HealthChinese Academy of SciencesShanghaiChina State Key Laboratory of Genetic Engineering Department of Microbiology and ImmunologySchool of Life SciencesFudan UniversityShanghaiChina Department of Microbiology The Chinese University of Hong KongHong KongChina Department of Orthopaedics Guangzhou Institute of Traumatic SurgeryGuangzhou Red Cross HospitalMedical CollegeJinan UniversityGuangzhouChina

Osteoporosis(OP),a systemic and chronic bone disease,is distinguished by low bone mass and destruction of bone *** Compound-K(CK),one of the metabolites of ginsenoside Rb1,has anti-aging,anti-inflammatory,anti-cancer,and hypolipidemic *** have demonstrated CK could promote osteogenesis and fracture healing in our previous ***,the contribution of CK to osteoporosis has not been *** the present study,we investigated the effect of CK on osteoclastogenesis and ovariectomy(OVX)-induced *** results showed that CK inhibited receptor activator for nuclear factor-κB ligand(RANKL)-mediated osteoclast differentiation and reactive oxygen species(ROS)activity by inhibiting the phosphorylation of NF-κB p65 and oxidative stress in RAW264.7 *** addition,we also demonstrated that CK could inhibit bone resorption using bone marrow-derived ***,we demonstrated that CK attenuated bone loss by suppressing the activity of osteoclast and alleviating oxidative stress in *** together,these results showed CK could inhibit osteoclastogenesis and prevent OVX-induced bone loss by inhibiting NF-κB signaling pathway.

关键词： Ginsenoside CK NF-κB signaling pathway Osteoporosis Oxidative stress

来源：评论

学校读者我要写书评

暂无评论

Fast extraction of word embedding from Q-contexts

arXiv

引用

arXiv 2021年

作者： Kong, Junsheng Li, Weizhao Liu, Zeyi Liao, Ben Qiu, Jiezhong Hsieh, Chang-Yu Cai, Yi Zhang, Shengyu School of Software Engineering South China University of Technology China University of Cambridge United Kingdom Tencent Quantum Lab China Tsinghua University China The Key Laboratory of Big Data and Intelligent Robot South China University of Technology Ministry of Education

The notion of word embedding plays a fundamental role in natural language processing (NLP). However, pre-training word embedding for very large-scale vocabulary is computationally challenging for most existing methods. In this work, we show that with merely a small fraction of contexts (Q-contexts) which are typical in the whole corpus (and their mutual information with words), one can construct high-quality word embedding with negligible errors. Mutual information between contexts and words can be encoded canonically as a sampling state, thus, Q-contexts can be fast constructed. Furthermore, we present an efficient and effective WEQ method, which is capable of extracting word embedding directly from these typical contexts. In practical scenarios, our algorithm runs 11∼ 13 times faster than well-established methods. By comparing with well-known methods such as matrix factorization, word2vec, GloVe and fasttext, we demonstrate that our method achieves comparable performance on a variety of downstream NLP tasks, and in the meanwhile maintains run-time and resource advantages over all these baselines. © 2021, CC BY.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Optimizing non-coalesced memory access for irregular applications with GPU computing

引用

Frontiers of Information technology & Electronic engineering 2020年第9期21卷 1285-1301页

作者： Ran ZHENG Yuan-dong LIU Hai JIN National Engineering Research Center for Big Data Technology and System Huazhong University of Science and TechnologyWuhan 430074China Services Computing Technology and System Lab Huazhong University of Science and TechnologyWuhan 430074China Cluster and Grid Computing Lab Huazhong University of Science and TechnologyWuhan 430074China School of Computer Science and Technology Huazhong University of Science and TechnologyWuhan 430074China

General purpose graphics processing units(GPGPUs)can be used to improve computing performance considerably for regular ***,irregular memory access exists in many applications,and the benefits of graphics processing units(GPUs)are less substantial for irregular *** recent years,several studies have presented some solutions to remove static irregular memory ***,eliminating dynamic irregular memory access with software remains a serious challenge.A pure software solution without hardware extensions or offline profiling is proposed to eliminate dynamic irregular memory access,especially for indirect memory *** reordering and index redirection are suggested to reduce the number of memory transactions,thereby improving the performance of GPU *** improve the efficiency of data reordering,an operation to reorder data is offloaded to a GPU to reduce overhead and thus transfer *** concurrently executing the compute unified device architecture(CUDA)streams of data reordering and the data processing kernel,the overhead of data reordering can be *** these optimizations,the volume of memory transactions can be reduced by 16.7%-50%compared with CUSPARSE-based benchmarks,and the performance of irregular kernels can be improved by 9.64%-34.9%using an NVIDIA Tesla P4 GPU.

关键词： General purpose graphics processing units Memory coalescing Non-coalesced memory access data reordering

来源：评论

学校读者我要写书评

暂无评论

CKG: Dynamic Representation Based on Context and Knowledge Graph

CKG: Dynamic Representation Based on Context and Knowledge G...

引用

International Conference on Pattern Recognition

作者： Xunzhu Tang Tiezhu Sun Rujie Zhu Shi Wang National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Momenta Suzhou China University of Central Florida Orlando FL USA Institute of Computing Technology Chinese Academy beijing China

Recently, neural language representation models pre-trained on large corpus can capture rich co-occurrence information and be fine-tuned in downstream tasks to improve the performance. As a result, they have achieved state-of-the-art results in a large range of language tasks. However, there exists other valuable semantic information such as similar, opposite, or other possible meanings in external knowledge graphs (KGs). We argue that entities in KGs could be used to enhance the correct semantic meaning of language sentences. In this paper, we propose a new method CKG: Dynamic Representation Based on Context and Knowledge Graph. On the one side, CKG can extract rich semantic information of large corpus. On the other side, it can make full use of inside information such as co-occurrence in large corpus and outside information such as similar entities in KGs. We conduct extensive experiments on a wide range of tasks, including QQP, MRPC, SST-5, SQuAD, CoNLL 2003, and SNLI. The experiment results show that CKG achieves SOTA 89.2 on SQuAD compared with SAN (84.4), ELMo (85.8), and BERTBase (88.5).

关键词： Semantics data mining Task analysis Context modeling

来源：评论

学校读者我要写书评

暂无评论

Balanced Tree Partitioning with Succinct Logic

Balanced Tree Partitioning with Succinct Logic

引用

IEEE International Conference on big Knowledge (ICBK)

作者： Xindong Wu Shaojing Sheng Peng Zhou Key Laboratory of Knowledge Engineering with Big Data (Heifei Unversity of Technology) Ministry of Education Heifei China School of Compuster Science and Technology Anhui University Heifei China

ISBN: (数字)9781728181561

ISBN: (纸本)9781728181578

As a widely used data structure, graphs are good at characterizing data with internal associations, such as social and biological data. Tree structured data are special and are widely used in many real-world applications, such as organizational structure analysis and genealogical knowledge graph reasoning. For example, in kinship knowledge graph analysis, when a genealogical tree is particularly large (more than 25 levels and 45,000 nodes), it is a great challenge to partition this large tree into a specified number of subtrees with succinct logic and a balanced number of nodes. Therefore, in this paper, we propose the TPA (tree partitioning algorithm) algorithm to achieve a balanced and succinct logic partition of large-scale tree structured data. TPA first extracts all related nodes from a massive graph database and then constructs the convergent subgraph into a complete tree with a specified root node. Specifically, several virtual nodes are supplemented for generation-skipping connected nodes to achieve correct node numbering and partitioning. Finally, a graph partitioning algorithm is executed on the complete tree to obtain a specified number of subtrees with succinct logic and balanced node scales. Experiments conducted on four real-world datasets verify the effectiveness of our TPA algorithm.

关键词： Partitioning algorithms data visualization Convergence data analysis Distributed databases big data

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：