检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Xu, Fangzhi Lin, Qika Liu, Jun Zhang, Lingling Zhao, Tianzhe Chai, Qi Pan, Yudai Department of Computer Science and Technology Xi'an Jiaotong University China National Engineering Lab for Big Data Analytics Xi'an Jiaotong University China Shaanxi Province Key Laboratory of Satellite and Terrestrial Network Tech. R&D Xi'an Jiaotong University China

Textbook Question Answering (TQA) is a complex multimodal task to infer answers given large context descriptions and abundant diagrams. Compared with Visual Question Answering(VQA), TQA contains a large number of uncommon terminologies and various diagram inputs. It brings new challenges to the representation capability of language model for domain-specific spans. And it also pushes the multimodal fusion to a more complex level. To tackle the above issues, we propose a novel model named MoCA, which incorporates multi-stage domain pretraining and multimodal cross attention for the TQA task. Firstly, we introduce a multi-stage domain pretraining module to conduct unsupervised post-pretraining with the span mask strategy and supervised pre-finetune. Especially for domain post-pretraining, we propose a heuristic generation algorithm to employ the terminology corpus. Secondly, to fully consider the rich inputs of context and diagrams, we propose cross-guided multimodal attention to update the features of text, question diagram and instructional diagram based on a progressive strategy. Further, a dual gating mechanism is adopted to improve the model ensemble. The experimental results show the superiority of our model, which outperforms the state-of-the-art methods by 2.21% and 2.43% for validation and test split respectively. Copyright © 2021, The Authors. All rights reserved.

关键词： Textbooks

来源：评论

学校读者我要写书评

暂无评论

Context-Aware Feature Attention Model for Coreference Resolution on Biomedical Texts

Research Square

引用

Research Square 2021年

作者： Li, Yufei Zhou, Xiangyu Ma, Jie Ma, Xiaoyong Li, Chen School of Computer Science and Technology Xi’an Jiaotong University Shaanxi Xi’an China National Engineering Lab for Big Data Analytics Xi’an Jiaotong University Shaanxi Xi’an China Shaanxi Province Key Laboratory of Satellite and Terrestrial Network Technology Research and Development Xi’an Jiaotong University Shaanxi Xi’an China

Background: Bio-entity Coreference resolution is an important task to gain a complete understanding of biomedical texts automatically. Previous neural network-based studies on this topic are domain system based methods which rely on some domain-specific information integration. However, for the identical mentions, this may lead to misleading information, as the model tends to get similar or even identical representations, which further leads to wrongful predictions. Results: we propose a new context-aware Feature Attention model to distinguish identical mentions effectively to better resolve coreference. The new model can represent identical mentions based on different contexts by adaptively exploiting features effectively. The proposed model substantially outperforms the state-of-the-art baselines on the BioNLP dataset with a 64.0% F1 score and further demonstrates superior performance on the differential representation and coreferential link of identical mentions. Conclusion: The context-aware Feature Attention model adaptively exploit features and represent identical mentions according to different contexts, which significantly makes the system obtain semantic information effectively and make more accurate predictions. Considering that this approach is still limited when context information is insufficient, we expect to utilize such information more fine-grained with the help of the external knowledge base in coreference resolution. © 2021, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Federated dynamic neural network for deep MIMO detection

arXiv

引用

arXiv 2021年

作者： Yang, Yuwen Gao, Feifei Xue, Jiang Zhou, Ting Xu, Zongben Department of Automation Tsinghua University Beijing100084 China The National Engineering Laboratory for Big Data Analytics Xi'an International Academy for Mathematics and Mathematical Technology School of Mathematics and Statistics Xi'an Jiaotong University Xi'an710049 China The Shanghai Advanced Research Institute CAS Shanghai Frontier Innovation and Research Institute Shanghai201210 China

In this paper, we develop a dynamic detection network (DDNet) based detector for multiple-input multiple-output (MIMO) systems. By constructing an improved DetNet (IDetNet) detector and the OAMPNet detector as two independent network branches, the DDNet detector performs sample-wise dynamic routing to adaptively select a better one between the IDetNet and the OAMPNet detectors for every samples under different system conditions. To avoid the prohibitive transmission overhead of dataset collection in centralized learning (CL), we propose the federated averaging (FedAve)-DDNet detector, where all raw data are kept at local clients and only locally trained model parameters are transmitted to the central server for aggregation. To further reduce the transmission overhead, we develop the federated gradient sparsification (FedGS)-DDNet detector by randomly sampling gradients with elaborately calculated probability when uploading gradients to the central server. Based on simulation results, the proposed DDNet detector consistently outperforms other detectors under all system conditions thanks to the sample-wise dynamic routing. Moreover, the federated DDNet detectors, especially the FedGS-DDNet detector, can reduce the transmission overhead by at least 25.7% while maintaining satisfactory detection accuracy. Copyright © 2021, The Authors. All rights reserved.

关键词： MIMO systems

来源：评论

学校读者我要写书评

暂无评论

An automated workflow for integrating environmental sustainability assessment into parametric part design through standard reference models

引用

Procedia CIRP 2020年 90卷 102-108页

作者： William Z. Bernstein Melissa Tensa Maxwell Praniewicz Soonjo Kwon Devarajan Ramanujan Engineering Laboratory National Institute of Standards and Technology MD USA School of Mechanical Industrial and Manufacturing Engineering Oregon State University OR USA George W. Woodruff School of Mechanical Engineering Georgia Institute of Technology Atlanta GR USA Associate Engineering Laboratory National Institute of Standards and Technology MD USA Korea Advanced Institute of Science and Technology Daejeon Republic of Korea Mechanical Engineering Section & Center for Digitalization Big Data and Data Analytics Aarhus University Aarhus 8000 Denmark

Integrating environmental sustainability assessment into parametric design presents an opportunity for enabling sustainable product design. However, this is a challenging task as quantitative methods for sustainability assessment are poorly integrated with parametric design and optimization tools. Furthermore, current streamlined approaches for computing environmental impact during the design stage often ignore manufacturing-related impacts resulting from the geometric complexity of parts. To address these gaps, we present a systematic workflow for computing environmental indicators from parametric design models. Our workflow utilizes the unit manufacturing process information model to evaluate manufacturing-phase resource consumption from process planning data, and consequently enables quantitative correlation of design parameters to the calculated environmental indicators. We demonstrate our workflow through a case study involving the design of a rigid flange coupling, wherein we evaluate the influence of geometric design parameters on the corresponding environmental impact of the design.

关键词： Life cycle assessment (LCA) Computer aided design (CAD) Computer aided manufacturing (CAM) Screening design

来源：评论

学校读者我要写书评

暂无评论

Weakly supervised learning for textbook question answering

TechRxiv

引用

TechRxiv 2021年

作者： Ma, Jie Chai, Qi Huang, Jingyue Liu, Jun You, Yang Zheng, Qinghua National Engineering Lab for Big Data Analytics School of Computer Science and Technology Xi’an Jiaotong University Shaanxi Xi’an710049 China Shaanxi Province Key Laboratory of Satellite and Terrestrial Network Tech. R&D School of Computer Science and Technology Xi’an Jiaotong University Shaanxi Xi’an710049 China The High Performance Computing for Artificial intelligence Lab Department of Computer Science National University of Singapore 117417 Singapore

Textbook Question Answering (TQA) is the task of answering diagram and non-diagram questions given large multimodal contexts consisting of abundant text and diagrams. Deep text understandings and effective learning of diagram semantics are important for this task due to its specificity. In this paper, we propose a Weakly Supervised learning method for TQA (WSTQ), which regards the incompletely accurate results of essential intermediate procedures for this task as supervision to develop Text Matching (TM) and Relation Detection (RD) tasks and then employs the tasks to motivate itself to learn strong text comprehension and excellent diagram semantics respectively. Specifically, we apply the result of text retrieval to build positive as well as negative text pairs. In order to learn deep text understandings, we first pre-train the text understanding module of WSTQ on TM and then fine-tune it on TQA. We build positive as well as negative relation pairs by checking whether there is any overlap between the items/regions detected from diagrams using object detection. The RD task forces our method to learn the relationships between regions, which are crucial to express the diagram semantics. We train WSTQ on RD and TQA simultaneously, i.e., multitask learning, to obtain effective diagram semantics and then improve the TQA performance. Extensive experiments are carried out on CK12-QA and AI2D to verify the effectiveness of WSTQ. Experimental results show that our method achieves significant accuracy improvements of 5.02% and 4.12% on test splits of the above datasets respectively than the current state-of-the-art baseline. We have released our code on https://***/dr-majie/WSTQ. © 2021, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

An integrated GIS-based multivariate adaptive regression splines-cat swarm optimization for improving the accuracy of wildfire susceptibility mapping

引用

Geocarto International 2023年第1期38卷

作者： Hai, Tao Theruvil Sayed, Biju Majdi, Ali Zhou, Jincheng Sagban, Rafid Band, Shahab S. Mosavi, Amir School of Computer and Information Qiannan Normal University for Nationalities Guizhou Duyun China Key Laboratory of Complex Systems and Intelligent Optimization of Guizhou Guizhou Duyun China Institute for Big Data Analytics and Artificial Intelligence (IBDAAI) Universiti Teknologi MARA Selangor Shah Alam Malaysia Department of Computer Science Dhofar University Salalah Oman Department of Building and Construction Technologies Engineering Al-Mustaqbal University College Hilla Iraq Department of Computer Technology Engineering Technical Engineering College Al-Ayen University Thi-Qar Iraq Future Technology Research Center National Yunlin University of Science and Technology Yunlin Douliou Taiwan John von Neumann Faculty of Informatics Obuda University Budapest Hungary German Research Center for Artificial Intelligence Oldenburg Germany Institute of the Information Society University of Public Service Budapest Hungary

A hybrid machine learning method is proposed for wildfire susceptibility mapping. For modeling a geographical information system (GIS) database including 11 influencing factors and 262 fire locations from 2013 to 2018 is used for developing an integrated multivariate adaptive regression splines (MARS). The cat swarm optimization (CSO) algorithm tunes the parameters of the MARS in order to generate accurate susceptibility maps. From the Pearson correlation results, it is observed that land use, temperature, and slope angle have strong correlation with the fire severity. The results demonstrate that the prediction capability of the MARS-CSO model outperforms model tree, reduced error pruning tree and MARS. The resulting wildfire risk map using MARS-CSO reveals that 20% of the study areas is categorized in the very low wildfire risk class, whereas 40% is under the very high class of fire hazard. © 2023 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.

关键词： artificial intelligence cat swarm optimization geospatial machine learning natural hazard Wildfire susceptibility

来源：评论

学校读者我要写书评

暂无评论

Meta Mask Correction for Nuclei Segmentation in Histopathological Image

Meta Mask Correction for Nuclei Segmentation in Histopatholo...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Jiangbo Shi Chang Jia Zeyu Gao Tieliang Gong Chunbao Wang Chen Li National Engineering Lab for Big Data Analytics Xi’an Jiao tong University Xi’an Shaanxi China School of Computer Science and Technology Xi’an Jiao tong University Xi’an Shaanxi China Shaanxi Province Key Laboratory of Satellite and Terrestrial Network Tech.R&D Xi’an Jiao tong University Xi’an Shaanxi China the First Affiliated Hospital of Xi’an Jiaotong University Xi’an Shaanxi China

ISBN: (纸本)9781665429825

Nuclei segmentation is a fundamental task in digital pathology analysis and can be automated by deep learning-based methods. However, the development of such an automated method requires a large amount of data with precisely annotated masks which is hard to obtain. Training with weakly labeled data is a popular solution for reducing the workload of annotation. In this paper, we propose a novel meta-learning-based nuclei segmentation method which follows the label correction paradigm to leverage data with noisy masks. Specifically, we design a fully conventional meta-model that can correct noisy masks using a small amount of clean meta-data. Then the corrected masks can be used to supervise the training of the segmentation model. Meanwhile, a bi-level optimization method is adopted to alternately update the parameters of the main segmentation model and the meta-model in an end-to-end way. Extensive experimental results on two nuclear segmentation datasets show that our method achieves the state-of-the-art result. It even achieves comparable performance with the model training on supervised data in some noisy settings.

关键词： Training Learning systems Image segmentation Pathology Annotations Biological system modeling Optimization methods

来源：评论

学校读者我要写书评

暂无评论

A sparse semismooth Newton based proximal majorization-minimization algorithm for nonconvex square-root-loss regression problem

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2020年第1期21卷 9253-9290页

作者： Peipei Tang Chengjing Wang Defeng Sun Kim-Chuan Toh School of Computer and Computing Science Zhejiang University City College Hangzhou China School of Mathematics and National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu China Department of Applied Mathematics The Hong Kong Polytechnic University Hung Hom Hong Kong Department of Mathematics and Institute of Operations Research and Analytics National University of Singapore Singapore

In this paper, we consider high-dimensional nonconvex square-root-loss regression problems and introduce a proximal majorization-minimization (PMM) algorithm for solving these problems. Our key idea for making the proposed PMM to be efficient is to develop a sparse semismooth Newton method to solve the corresponding subproblems. By using the Kurdyka-Łojasiewicz property exhibited in the underlining problems, we prove that the PMM algorithm converges to a d-stationary point. We also analyze the oracle property of the initial subproblem used in our algorithm. Extensive numerical experiments are presented to demonstrate the high efficiency of the proposed PMM algorithm.

关键词： nonconvex square-root regression problems proximal majorization-minimization semismooth Newton method

来源：评论

学校读者我要写书评

暂无评论

Meta mask correction for nuclei segmentation in histopathological image

arXiv

引用

arXiv 2021年

作者： Shi, Jiangbo Jia, Chang Gao, Zeyu Gong, Tieliang Wang, Chunbao Li, Chen National Engineering Lab for Big Data Analytics Xi'an Jiao Tong University Shaanxi Xi'an710049 China School of Computer Science and Technology Xi'an Jiao tong University Shaanxi Xi'an710049 China Shaanxi Province Key Laboratory of Satellite and Terrestrial Network Tech.R&D Xi'an Jiao tong University Shaanxi Xi'an710049 China Department of Pathology The First Affiliated Hospital of Xi'an Jiaotong University Shaanxi Xi'an710061 China

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Scientific data Lake for High Luminosity LHC project and other data-intensive particle and astro-particle physics experiments 5

Scientific Data Lake for High Luminosity LHC project and oth...

引用

5th International Conference on Particle Physics and Astrophysics, ICPPA 2020

作者： Alekseev, A. Kiryanov, A. Klimentov, A. Korchuganova, T. Mitsyn, V. Oleynik, D. Smirnov, A. Smirnov, S. Zarochentsev, A. Compiler Technology Department Ivannikov Institute for System Programming of the Ras Moscow109004 Russia Cloud Technologies and Big Data Analytics Laboratory Plekhanov Russian University of Economics Moscow117997 Russia Atlas Group Universidad Andres Bello Santiago7550196 Chile Department of Computing Resources and Technologies Nrc "kurchatov Institute"-PNPI Gatchina188300 Russia Physics Department Brookhaven National Laboratory UptonNY11973 United States Laboratory of Information Technologies Joint Institute for Nuclear Research Dubna141980 Russia Institute of Nuclear Physics and Engineering National Research Nuclear University MEPhI Moscow115409 Russia Laboratory of Ultra-High Energy Physics Saint Petersburg State University Saint Petersburg198504 Russia

The next phase of LHC Operations-High Luminosity LHC (HL-LHC), which is aimed at ten-fold increase in the luminosity of proton-proton collisions at the energy of 14 TeV, is expected to start operation in 2027-2028 and will deliver an unprecedented scientific data volume of multi-exabyte scale. This amount of data has to be stored and the corresponding storage system should ensure fast and reliable data delivery for processing by scientific groups distributed all over the world. The present LHC computing and data processing model will not be able to provide the required infrastructure growth even taking into account the expected hardware technology evolution. To address this challenge the new state-of-The-Art computing infrastructure technologies are now being developed and are presented here. The possibilities of application of the HL-LHC distributed data handling technique for other particle and astro-particle physics experiments dealing with large-scale data volumes like DUNE, LSST, Belle-II, JUNO, SKAO etc. are also discussed. © Published under licence by IOP Publishing Ltd.

关键词： Luminance

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：