检索结果-内蒙古大学图书馆

SARLR: Self-adaptive recommendation of learning resources 14

学校读者我要写书评

暂无评论

SARLR: Self-adaptive recommendation of learning resources

14th International Conference on Intelligent Tutoring Systems Workshops, ITS 2018

作者： Liu, Liping Wu, Wenjun Huang, Jiankun State Key Lab of Software Development Environment Department of Computer Science and Engineering Beihang University Beijing China

Personalized recommendation is important for online students to select rich learning resources and make their own learning schedules. We propose SARLR, a new self-adaptive recommendation algorithm of online learning resources. The SARLR algorithm integrates an IRT-based learning cognitive model named T-BMIRT into the recommendation framework and is able to adaptively adjust learning path recommendations based on dynamic of individual learning process. The experimental results show that the SARLR algorithm outperforms the existing recommendation algorithms. © 2019 CEUR-WS. All rights reserved.

关键词： Learning algorithms

Noninherited Factors in Fetal Congenital Heart Diseases Based on Bayesian Network:A Large Multicenter Study

学校读者我要写书评

暂无评论

Congenital Heart Disease 2021年第6期16卷 529-549页

作者： Yanping Ruan Xiangyu Liu Haogang Zhu Yijie Lu Xiaowei Liu Jiancheng Han Lin Sun Ye Zhang Xiaoyan Gu Ying Zhao Lei Li Suzhen Ran Jingli Chen Qiong Yu Yan Xu Hongmei Xia Yihua He Department of Echocardiography Maternal-Fetal Medicine Research Consultation CenterBeijing Anzhen HospitalCapital Medical UniversityBeijing100029China School of Biological Science and Medical Engineering Beihang UniversityBeijing100083China State Key Laboratory of Software Development Environment School of Computer Science and EngineeringBeihang UniversityBeijing100191China Department of Ultrasound Chongqing Health Center for Women and ChildrenChongqing400013China Department of Ultrasound Urumqi Maternal and Child Health HospitalUrumqi830001China Department of Ultrasound Pingxiang Maternal and Child CarePingxiang337055China Department of Ultrasound People’s Hospital of RizhaoRizhao276800China Department of Ultrasound Xinqiao Hospital Army Medical UniversityChongqing400038China

Background:Current studies have confirmed that fetal congenital heart diseases(CHDs)are caused by various ***,the quantitative risk of CHD is not clear given the combined effects of multiple ***:This cross-sectional study aimed to detect associated factors of fetal CHD using a Bayesian network in a large sample and quantitatively analyze relative risk ratios(RRs).Methods:Pregnant women who underwent fetal echocardiography(N=16,086 including 3,312 with CHD fetuses)were ***-six maternal and fetal factors were obtained.A Bayesian network is constructed based on all variables through structural learning and parameter learning methods to find the environmental factors that directly and indirectly associated with outcome,and the probability of fetal CHD in the two groups is predicted through a junction tree reasoning algorithm,so as to obtain RR for fetal CHD under different exposure factor *** into account the effect of gestational week on the accuracy of model prediction,we conducted sensitivity analysis on gestational week ***:The single-factor analysis showed that the RRs for the numbers of births,spontaneous abortions,and parental smoking were 1.50,1.38,and 1.11(P<0.001),*** risk gradually increased with the synergistic effect of ranging from one to more environmental factors *** risk was higher among subjects with five synergistic factors,including the number of births,upper respiratory tract infection during early pregnancy,anemia,and mental stress as well as a history of spontaneous abortions or parental smoking,than in those with less than 5 factors(RR=2.62 or 2.28,P<0.001).This result was consistent across the participants grouped by ***:We identified six factors that were directly associated with fetal CHD.A higher number of these factors led to a higher risk of *** findings suggest that it is important to strengthen healthcare and prenatal counseling for women

关键词： Congenital heart diseases bayesian network risk ratio factor

Online variant of parcel allocation in last-mile delivery 12

学校读者我要写书评

暂无评论

Online variant of parcel allocation in last-mile delivery

12th International Conference on Measuring Technology and Mechatronics Automation, ICMTMA 2020

作者： Liang, Yuan Mao, Changmei Bao, Xiuguo State Key Laboratory of Software Development Environment School of Computer Science Beihang University Beijing100191 China School of Information Management and Engineering Shanghai University of Finance and Economics Shanghai200433 China National Computer Network Emergency Response Technical Team/Coordination Center of China Beijing100029 China

ISBN: (纸本)9781728170817

We investigate the problem of last-mile delivery, where a large amount of crowd-workers have performed a great quantity of location-specific urban logistics parcels. Current existing approaches mainly focus on offline scenarios, where all the spatial-temporal information of parcels and workers are given. However, the offline scenarios can be impractical since parcels and workers appear dynamically in reality, and the information of workers is unknown in advance. In this paper, we study the problem of last-mile delivery on online scenarios to resolve the shortcomings of the offline setting. We first formalize the online parcel allocation in last-mile delivery problem, where all parcels were put in pop-stations in advance, and workers arrive dynamically. Then we propose a baseline algorithm with no competitive ratio, and an algorithm providing theoretical guarantee for the parcel allocation in last-mile delivery. Finally, we verify the effectiveness and efficiency of proposed algorithms through extensive experiments on real and synthetic datasets. © 2020 IEEE.

关键词： Greedy Last-mile delivery Online matching Primal-dual algorithm

Many-to-one distribution learning and K-nearest neighbor smoothing for thoracic disease identification

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhou, Yi Huang, Lei Zhou, Tianfei Shao, Ling School of Computer Science and Engineering Southeast University Nanjing China State Key Laboratory of Software Development Environment Beihang University Beijing China Computer Vision Laboratory ETH Zurich Switzerland Inception Institute of Artificial Intelligence Abu Dhabi United Arab Emirates

Chest X-rays are an important and accessible clinical imaging tool for the detection of many thoracic diseases. Over the past decade, deep learning, with a focus on the convolutional neural network (CNN), has become the most powerful computer-aided diagnosis technology for improving disease identification performance. However, training an effective and robust deep CNN usually requires a large amount of data with high annotation quality. For chest X-ray imaging, annotating large-scale data requires professional domain knowledge and is time-consuming. Thus, existing public chest X-ray datasets usually adopt language pattern based methods to automatically mine labels from reports. However, this results in label uncertainty and inconsistency. In this paper, we propose many-to-one distribution learning (MODL) and Knearest neighbor smoothing (KNNS) methods from two perspectives to improve a single model’s disease identification performance, rather than focusing on an ensemble of models. MODL integrates multiple models to obtain a soft label distribution for optimizing the single target model, which can reduce the effects of original label uncertainty. Moreover, KNNS aims to enhance the robustness of the target model to provide consistent predictions on images with similar medical findings. Extensive experiments on the public NIH Chest X-ray and CheXpert datasets show that our model achieves consistent improvements over the state-of-the-art methods. © 2021, CC0.

关键词： computer aided diagnosis

Entity concept-enhanced few-shot relation extraction

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Yang, Shan Zhang, Yongfei Niu, Guanglin Zhao, Qinhua Pu, Shiliang Beijing Key Laboratory of Digital Media School of Computer Science and Engineering BeiHang University Beijing100191 China State Key Laboratory of Virtual Reality Technology and Systems BeiHang University Beijing100191 China Pengcheng Laboratory Shenzhen518055 China State Key Laboratory of Software Development Environment School of Computer Science and Engineering BeiHang University Beijing100191 China Hikvision Research Institute Hangzhou311500 China

Few-shot relation extraction (FSRE) is of great importance in long-tail distribution problem, especially in special domain with low-resource data. Most existing FSRE algorithms fail to accurately classify the relations merely based on the information of the sentences together with the recognized entity pairs, due to limited samples and lack of knowledge. To address this problem, in this paper, we proposed a novel entity CONCEPTenhanced FEw-shot Relation Extraction scheme (ConceptFERE), which introduces the inherent concepts of entities to provide clues for relation prediction and boost the relations classification performance. Firstly, a conceptsentence attention module is developed to select the most appropriate concept from multiple concepts of each entity by calculating the semantic similarity between sentences and concepts. Secondly, a self-attention based fusion module is presented to bridge the gap of concept embedding and sentence embedding from different semantic spaces. Extensive experiments on the FSRE benchmark dataset FewRel have demonstrated the effectiveness and the superiority of the proposed ConceptFERE scheme as compared to the state-of-the-art baselines. Code is available at https://***/LittleGuoKe/ConceptFERE. Copyright © 2021, The Authors. All rights reserved.

关键词： Embeddings

Nucleus-aware Self-supervised Pretraining Using Unpaired Image-to-image Translation for Histopathology Images

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Song, Zhiyun Du, Penghui Yan, Junpeng Li, Kailu Shou, Jianzhong Lai, Maode Fan, Yubo Xu, Yan The School of Biological Science and Medical Engineering State Key Laboratory of Software Development Environment Key Laboratory of Biomechanics and Mechanobiology of Ministry of Education Research Institute of Beihang University in Shenzhen Beijing Advanced Innovation Center for Biomedical Engineering Beihang University Beijing100191 China The Department of Urology National Cancer Center National Clinical Research Center for Cancer Cancer Hospital Chinese Academy of Medical Sciences Peking Union Medical College Chaoyang District Beijing100021 China The Department of Pathology School of Medicine Zhejiang University Zhejiang Provincial Key Lab Disease Proteomics Alibaba-Zhejiang University Joint Research Center of Future Healthcare Hangzhou310053 China

Self-supervised pretraining attempts to enhance model performance by obtaining effective features from unlabeled data, and has demonstrated its effectiveness in the field of histopathology images. Despite its success, few works concentrate on the extraction of nucleus-level information, which is essential for pathologic analysis. In this work, we propose a novel nucleus-aware self-supervised pretraining framework for histopathology images. The framework aims to capture the nuclear morphology and distribution information through unpaired image-to-image translation between histopathology images and pseudo mask images. The generation process is modulated by both conditional and stochastic style representations, ensuring the reality and diversity of the generated histopathology images for pretraining. Further, an instance segmentation guided strategy is employed to capture instance-level information. The experiments on 7 datasets show that the proposed pretraining method outperforms supervised ones on Kather classification, multiple instance learning, and 5 dense-prediction tasks with the transfer learning protocol, and yields superior results than other self-supervised approaches on 8 semi-supervised tasks. Our project is publicly available at https://***/zhiyuns/UNITPathSSL. Copyright © 2023, The Authors. All rights reserved.

关键词： Stochastic systems

Knowledge Grounded Pre-Trained Model For Dialogue Response Generation

学校读者我要写书评

暂无评论

Knowledge Grounded Pre-Trained Model For Dialogue Response G...

International Joint Conference on Neural Networks (IJCNN)

作者： Yanmeng Wang Wenge Rong Jianfei Zhang Yuanxin Ouyang Zhang Xiong State Key Laboratory of Software Development Environment Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China

ISBN: (数字)9781728169262

ISBN: (纸本)9781728169279

Teaching machine to answer arbitrary questions is a long-term goal of natural language processing. In real dialogue corpus, informative words like named entities can often be infrequent and hard to model, and one primary challenge of dialogue system is how to promote the model's capability of generating high-quality responses with those informative words. In order to address this problem, we propose a novel pre-training based encoder-decoder model, which can enhance the multiturn dialogue response generation by incorporating external textual knowledge. We adopt BERT as encoder to merge external knowledge into dialogue history modeling, and a multi-head attention based decoder is designed to incorporate the semantic information from both knowledge and dialogue hidden representations into decoding process to generate informative and proper dialogue responses. Experiments on two response generation tasks indicate our model to be superior over competitive baselines on both automatic and human evaluations.

关键词：

I/O Optimizations Based on Workload Characteristics for Parallel File Systems 16th

学校读者我要写书评

暂无评论

I/O Optimizations Based on Workload Characteristics for Para...

16th IFIP WG 10.3 International Conference on Network and Parallel Computing, NPC 2019

作者： Wei, Bing Xiao, Limin Zhou, Bingyu Qin, Guangjun Yan, Baicheng Huo, Zhisheng State Key Laboratory of Software Development Environment Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China

ISBN: (纸本)9783030307080

Parallel file systems usually provide a unified storage solution, which fails to meet specific application needs. In this paper, we propose an extended file handle scheme to address this problem. It allows the file systems to specify optimizations for individual file or directory based on workload characteristics. One case study shows that our proposed approach improves the aggregate throughput of large files and small files by up to 5% and 30%, respectively. To further improve the access performance of small files in parallel file systems, we also propose a new metadata-based small file optimization method. The experimental results show that the aggregate throughput of small files can be effectively improved through our method. © 2019, IFIP International Federation for Information Processing.

关键词： File organization

Transformers in Medical Image Analysis: A Review

学校读者我要写书评

暂无评论

arXiv 2022年

作者： He, Kelei Gan, Chen Li, Zhuoyuan Rekik, Islem Yin, Zihao Ji, Wen Gao, Yang Wang, Qian Zhang, Junfeng Shen, Dinggang Medical School of Nanjing University Nanjing China National Institute of Healthcare Data Science Nanjing University Nanjing China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China BASIRA Lab Faculty of Computer and Informatics Engineering Istanbul Technical University Istanbul Turkey School of Science and Engineering Computing University of Dundee United Kingdom School of Biomedical Engineering ShanghaiTech University Shanghai China Department of Research and Development Shanghai United Imaging Intelligence Co. Ltd. Shanghai China

Transformers have dominated the field of natural language processing, and recently impacted the computer vision area. In the field of medical image analysis, Transformers have also been successfully applied to full-stack clinical applications, including image synthesis/reconstruction, registration, segmentation, detection, and diagnosis. Our paper aims to promote awareness and application of Transformers in the field of medical image analysis. Specifically, we first overview the core concepts of the attention mechanism built into Transformers and other basic components. Second, we review various Transformer architectures tailored for medical image applications and discuss their limitations. Within this review, we investigate key challenges revolving around the use of Transformers in different learning paradigms, improving the model efficiency, and their coupling with other techniques. We hope this review can give a comprehensive picture of Transformers to the readers in the field of medical image analysis. © 2022, CC BY-SA.

关键词： Diagnosis