您的检索：
学者姓名：刘博
精炼检索结果：
年份
成果类型
收录类型
来源
综合
曾用名
合作者
语言
清除所有精炼条件
摘要 ：
大气污染领域本体的半自动构建及语义推理
关键词 ：
语义推理 语义推理 注意力机制 注意力机制 大气污染 大气污染 自然语言处理 自然语言处理 实体关系抽取 实体关系抽取 本体 本体
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | 刘博 , 张佳慧 , 李建强 et al. 大气污染领域本体的半自动构建及语义推理 [J]. | 刘博 , 2021 , 47 (3) : 246-259 . |
| MLA | 刘博 et al. "大气污染领域本体的半自动构建及语义推理" . | 刘博 47 . 3 (2021) : 246-259 . |
| APA | 刘博 , 张佳慧 , 李建强 , 李永 , 郎建垒 , 北京工业大学学报 . 大气污染领域本体的半自动构建及语义推理 . | 刘博 , 2021 , 47 (3) , 246-259 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
一种生成式问答的评价方法涉及自然语言处理领域。本发明针对生成式问答的答案在语言质量和语义准确度上存在的各种问题，分别构建数据集的正负样本。通过在数据集构建上进行处理，就能使问答评价网络在训练后能够结合语言质量和语义准确性两方面对生成的答案进行打分。相比传统的评价方法对答案的评价更全面、准确。
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | 刘博 , 王星文 , 徐宽 et al. 一种生成式问答的评价方法 : CN202110184397.4[P]. | 2021-02-10 . |
| MLA | 刘博 et al. "一种生成式问答的评价方法" : CN202110184397.4. | 2021-02-10 . |
| APA | 刘博 , 王星文 , 徐宽 , 胡志超 . 一种生成式问答的评价方法 : CN202110184397.4. | 2021-02-10 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
本实验对3组同规格SBR反应器分别采用分阶段法(A/O-A/O/A)异步驯化、连续曝气A/OA同步驯化和间歇曝气A/O/A同步驯化的方式运行.以人工配水为进水基质,接种絮状污泥,通过水力选择压颗粒化,探讨了不同运行方式下短程硝化反硝化颗粒污泥的驯化及脱氮除磷特性.结果表明,在较短曝气时长(140 min)联合较低曝气强度[3.5 L·(h·L)~(-1)]下,间歇曝气A/O/A同步驯化最具优势,后期稳定运行期间碳、氮、磷的平均去除率分别为90.74%、91.15%和95.66%,可实现同步去除.粒径为895μm,颗粒虽小但均匀致密,f值(MLVSS/MLSS)平稳保持在0.8～0.85,有较高...
关键词 ：
同步驯化 同步驯化 曝气强度 曝气强度 曝气时长 曝气时长 短程硝化反硝化除磷 短程硝化反硝化除磷 间歇曝气 间歇曝气 颗粒污泥 颗粒污泥
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | 王文琪 , 李冬 , 高鑫 et al. 短程硝化反硝化除磷颗粒污泥的同步驯化 [J]. | 环境科学 , 2021 , 42 (06) : 2946-2956 . |
| MLA | 王文琪 et al. "短程硝化反硝化除磷颗粒污泥的同步驯化" . | 环境科学 42 . 06 (2021) : 2946-2956 . |
| APA | 王文琪 , 李冬 , 高鑫 , 刘博 , 张杰 . 短程硝化反硝化除磷颗粒污泥的同步驯化 . | 环境科学 , 2021 , 42 (06) , 2946-2956 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
为了明确大气污染物、污染源、影响因素、评价指标、危害等之间的关系,分析大气污染传播路径,建立了一个较为清晰、完善的大气污染领域本体.首先,基于机器学习和自然语言处理等技术,提出一种基于注意力机制的序列标注联合抽取实体关系的方法,在双向长短时记忆(long short-term memory,LSTM)网络模型中加入注意力机制,并将实体和关系联合标注,从而进行实体关系抽取.其次,结合词频-逆文档频率(term frequency-inverse document frequency,TF-IDF)核心概念挖掘方法进行知识抽取,并将概念、属性、关系和实例组织起来,从而实现大气污染本体模型的半自动构建.最后,在本体和实例的基础上通过Protégé的SPARQL Query模块和HermiT推理机分别进行条件推理和可视化推理.结果表明,基于注意力机制的序列标注实体关系联合抽取方法所构建的大气污染领域本体包含核心实体68个,实例数360个,相较于现有的本领域本体,在全面性、有效性、准确性和可重用性方面都有较好表现,同时推理出了Ca2+和K+等污染离子的传播路径.因此,基于注意力机制的序列标注联合抽取实体关系的方法能够有效地半自动构建大气污染领域本体,推理出清晰的大气污染传播路径.
关键词 ：
大气污染 大气污染 实体关系抽取 实体关系抽取 本体 本体 注意力机制 注意力机制 自然语言处理 自然语言处理 语义推理 语义推理
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | 刘博 , 张佳慧 , 李建强 et al. 大气污染领域本体的半自动构建及语义推理 [J]. | 北京工业大学学报 , 2021 , 47 (3) : 246-259 . |
| MLA | 刘博 et al. "大气污染领域本体的半自动构建及语义推理" . | 北京工业大学学报 47 . 3 (2021) : 246-259 . |
| APA | 刘博 , 张佳慧 , 李建强 , 李永 , 郎建垒 . 大气污染领域本体的半自动构建及语义推理 . | 北京工业大学学报 , 2021 , 47 (3) , 246-259 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
对深度学习模型应用于时空序列预测的最新进展进行总结.首先介绍时空序列数据的属性及类型,并进行相应的实例化与表示.接着针对时空序列数据存在的3个问题分别提出相应的数据预处理方法,对基于传统参数模型、传统机器学习模型以及深度学习模型的时空序列预测方法逐一阐述并对比分析,为研究者选择模型提供指导,之后总结深度学习模型在不同领域内对时空序列预测的应用.最后指出当前研究的不足以及时空序列预测进一步的研究方向.
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | 刘博 , 王明烁 , 李永 et al. 深度学习在时空序列预测中的应用综述 [J]. | 北京工业大学学报 , 2021 , 47 (8) : 925-941 . |
| MLA | 刘博 et al. "深度学习在时空序列预测中的应用综述" . | 北京工业大学学报 47 . 8 (2021) : 925-941 . |
| APA | 刘博 , 王明烁 , 李永 , 陈洪丽 , 李建强 . 深度学习在时空序列预测中的应用综述 . | 北京工业大学学报 , 2021 , 47 (8) , 925-941 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
As an important method to diagnose gastric cancer, gastric pathological sections images (GPSI) are hard and time-consuming to be recognized even by an experienced doctor. An efficient method was designed to detect gastric cancer in magnified (20x) GPSI using deep learning technology. A novel DenseNet architecture was applied, modified with a multistage attention module (MSA-DenseNet). To develop this model focusing on gastric features, a two-stage-input attention module was adopted to select more semantic information of cancer. Moreover, the pretraining process was divided into two steps to improve the effect of the attention mechanism. After training, our method achieved a state-of-the-art performance yielding 0.9947 F1 score and 0.9976 ROC AUC on a test dataset. In line with our expectation in clinical practice, a high recall (0.9929) was produced with high sensitivity to the positive samples. These results indicate that this new model performs better than current artificial detection approaches and its effectiveness is therefore validated in cancer pathological diagnoses.
关键词 ：
computer‐ computer‐ assisted diagnosis assisted diagnosis gastric pathological sections gastric pathological sections gastric cancer gastric cancer deep learning deep learning
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Liu, Bo , Zhao, Yelong , Yang, Bin et al. A gastric cancer recognition algorithm on gastric pathological sections based on multistage attention-DenseNet [J]. | CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE , 2021 , 33 (10) . |
| MLA | Liu, Bo et al. "A gastric cancer recognition algorithm on gastric pathological sections based on multistage attention-DenseNet" . | CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE 33 . 10 (2021) . |
| APA | Liu, Bo , Zhao, Yelong , Yang, Bin , Zhao, Shuangtao , Gu, Rentao , Gahegan, Mark . A gastric cancer recognition algorithm on gastric pathological sections based on multistage attention-DenseNet . | CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE , 2021 , 33 (10) . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
Atmospheric visibility is an indicator of atmospheric transparency and its range directly reflects the quality of the atmospheric environment. With the acceleration of industrialization and urbanization, the natural environment has suffered some damages. In recent decades, the level of atmospheric visibility shows an overall downward trend. A decrease in atmospheric visibility will lead to a higher frequency of haze, which will seriously affect people's normal life, and also have a significant negative economic impact. The causal relationship mining of atmospheric visibility can reveal the potential relation between visibility and other influencing factors, which is very important in environmental management, air pollution control and haze control. However, causality mining based on statistical methods and traditional machine learning techniques usually achieve qualitative results that are hard to measure the degree of causality accurately. This article proposed the seq2seq-LSTM Granger causality analysis method for mining the causality relationship between atmospheric visibility and its influencing factors. In the experimental part, by comparing with methods such as linear regression, random forest, gradient boosting decision tree, light gradient boosting machine, and extreme gradient boosting, it turns out that the visibility prediction accuracy based on the seq2seq-LSTM model is about 10% higher than traditional machine learning methods. Therefore, the causal relationship mining based on this method can deeply reveal the implicit relationship between them and provide theoretical support for air pollution control.
关键词 ：
granger causality granger causality deep learning deep learning multidimensional time series multidimensional time series Atmospheric visibility Atmospheric visibility
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Liu, Bo , He, Xi , Song, Mingdong et al. A Method for Mining Granger Causality Relationship on Atmospheric Visibility [J]. | ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA , 2021 , 15 (5) . |
| MLA | Liu, Bo et al. "A Method for Mining Granger Causality Relationship on Atmospheric Visibility" . | ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA 15 . 5 (2021) . |
| APA | Liu, Bo , He, Xi , Song, Mingdong , Li, Jiangqiang , Qu, Guangzhi , Lang, Jianlei et al. A Method for Mining Granger Causality Relationship on Atmospheric Visibility . | ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA , 2021 , 15 (5) . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
Whether sub-optimal local minima and saddle points exist in the highly non-convex loss landscape of deep neural networks has a great impact on the performance of optimization algorithms. Theoretically, we study in this paper the existence of non-differentiable sub-optimal local minima and saddle points for deep ReLU networks with arbitrary depth. We prove that there always exist non-differentiable saddle points in the loss surface of deep ReLU networks with squared loss or cross-entropy loss under reasonable assumptions. We also prove that deep ReLU networks with cross-entropy loss will have non-differentiable sub-optimal local minima if some outermost samples do not belong to a certain class. Experimental results on real and synthetic datasets verify our theoretical findings. (C) 2021 Elsevier Ltd. All rights reserved.
关键词 ：
Deep learning Deep learning Local minima Local minima Loss landscape Loss landscape Loss surface Loss surface Saddle points Saddle points
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Liu, Bo , Liu, Zhaoying , Zhang, Ting et al. Non-differentiable saddle points and sub-optimal local minima exist for deep ReLU networks [J]. | NEURAL NETWORKS , 2021 , 144 : 75-89 . |
| MLA | Liu, Bo et al. "Non-differentiable saddle points and sub-optimal local minima exist for deep ReLU networks" . | NEURAL NETWORKS 144 (2021) : 75-89 . |
| APA | Liu, Bo , Liu, Zhaoying , Zhang, Ting , Yuan, Tongtong . Non-differentiable saddle points and sub-optimal local minima exist for deep ReLU networks . | NEURAL NETWORKS , 2021 , 144 , 75-89 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
In this experiment, three replicated SBR reactors were operated using asynchronous acclimation of the phased method (A/O-A/O/A), simultaneous domestication of continuous aeration by A/O/A, and simultaneous domestication of intermittent aeration by A/O/A. Using artificial water distribution as the influent substrate, flocculent sludge was inoculated and granulated by hydraulic selection. The domestication and nitrogen and phosphorus removal characteristics of shortcut nitrification denitrifying phosphorus removal granules under different operation modes were assessed. The results show that simultaneous domestication of intermittent aeration by A/O/A has the most efficient under the combination of short aeration time (140 min) and low aeration strength[3.5 L·(h·L)-1]. The average removal rates of carbon, nitrogen, and phosphorus were 90.74%, 91.15%, and 95.66%, respectively, which could achieve synchronous removal during later stable operation. The particle size was 895 μm, and the particles were small but uniformly dense in microscope observations. The f value (MLVSS/MLSS) was kept stable at 0.8-0.85 and sludge had a high biomass due to the alternate aerobic/anoxic operation with intermittent aeration. This supported anoxic heterotrophic bacteria at the core of the particles, which was conducive to the stability of the granular sludge structure. Batch experiments showed that the specific ammonia-oxidation rate of the simultaneous domestication of intermittent aeration by A/O/A system was 3.38 mg·(g·h)-1, and denitrifying phosphate accumulating organisms (DPAOs) able to utilize nitrite as electron acceptor accounted for 65.46%. This was more conducive to the simultaneous domestication and enrichment of ammonia-oxidizing bacteria (AOB) and NO2--type DPAOs, ensuring a stable treatment effect.
关键词 ：
aeration intensity aeration intensity aeration time aeration time granules sludge granules sludge intermittent aeration intermittent aeration short-cut nitrification denitrifying phosphorus removal short-cut nitrification denitrifying phosphorus removal simultaneous domestication simultaneous domestication
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Wang Wen-Qi , Li Dong , Gao Xin et al. [Simultaneous Domestication of Short-cut Nitrification Denitrifying Phosphorus Removal Granules]. [J]. | Huanjing kexue , 2021 , 42 (6) : 2946-2956 . |
| MLA | Wang Wen-Qi et al. "[Simultaneous Domestication of Short-cut Nitrification Denitrifying Phosphorus Removal Granules]." . | Huanjing kexue 42 . 6 (2021) : 2946-2956 . |
| APA | Wang Wen-Qi , Li Dong , Gao Xin , Liu Bo , Zhang Jie . [Simultaneous Domestication of Short-cut Nitrification Denitrifying Phosphorus Removal Granules]. . | Huanjing kexue , 2021 , 42 (6) , 2946-2956 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
In this paper, we studied infrared (IR) maritime salient object detection based on convolutional neural networks (CNNs). There are mainly two contributions. Firstly, we constructed a large extended IR ship image dataset (ExtIRShip) for salient maritime target detection, including 9,123 labelled IR images. Secondly, we proposed a global guided lightweight non-local depth feature (DG-Light-NLDF) model. We introduced Dilated Linear Bottleneck (DLB) to replace the standard convolution and adding a simplified global module to provide the location information of the potential salient object, the proposed method can significantly improve the efficiency of Light-NLDF. Experimental results demonstrate that the proposed DG-Light-NLDF model could detect IR maritime salient objects more accurately with less parameters. In addition, comparison experiments between two datasets validated that the larger dataset is also much more beneficial in improving saliency detection performance. © 2021 Elsevier B.V.
关键词 ：
Large dataset Large dataset Object recognition Object recognition Ships Ships Convolution Convolution Neural networks Neural networks Object detection Object detection Infrared imaging Infrared imaging Feature extraction Feature extraction
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Liu, Zhaoying , Zhang, Xuesi , Jiang, Tianpeng et al. Infrared salient object detection based on global guided lightweight non-local deep features [J]. | Infrared Physics and Technology , 2021 , 115 . |
| MLA | Liu, Zhaoying et al. "Infrared salient object detection based on global guided lightweight non-local deep features" . | Infrared Physics and Technology 115 (2021) . |
| APA | Liu, Zhaoying , Zhang, Xuesi , Jiang, Tianpeng , Zhang, Ting , Liu, Bo , Waqas, Muhammad et al. Infrared salient object detection based on global guided lightweight non-local deep features . | Infrared Physics and Technology , 2021 , 115 . |
| 导入链接 | NoteExpress RIS BibTex |
导出
| 数据： |
选中 到 |
| 格式： |
