A5041037769- Topic Modeling
- Natural Language Processing Techniques
- Semantic Web and Ontologies
- Data Quality and Management
- Web Data Mining and Analysis
- Expert finding and Q&A systems
- Biomedical Text Mining and Ontologies
- Natural product bioactivities and synthesis
- Advanced Text Analysis Techniques
- Recommender Systems and Techniques
- Text and Document Classification Technologies
- Gout, Hyperuricemia, Uric Acid
- Biological and pharmacological studies of plants
- Computational and Text Analysis Methods
- Digital Filter Design and Implementation
- Child Therapy and Development
- Coagulation, Bradykinin, Polyphosphates, and Angioedema
- Machine Learning and Data Classification
- Fetal and Pediatric Neurological Disorders
- Information Retrieval and Search Behavior
- Face and Expression Recognition
- Advanced Adaptive Filtering Techniques
- Traditional Chinese Medicine Analysis
- Tea Polyphenols and Effects
- Cognitive Computing and Networks
Bethune International Peace Hospital
2020-2024
Hebei University of Chinese Medicine
2023
First People's Hospital of Yunnan Province
2023
Kunming University of Science and Technology
2023
Hebei University of Technology
2023
Fujian Agriculture and Forestry University
2020
University of Massachusetts Amherst
2009-2013
Tsinghua University
2007-2011
University of Electronic Science and Technology of China
2005
This paper addresses several key issues in the ArnetMiner system, which aims at extracting and mining academic social networks. Specifically, system focuses on: 1) Extracting researcher profiles automatically from Web; 2) Integrating publication data into network existing digital libraries; 3) Modeling entire network; 4) Providing search services for network. So far, 448,470 have been extracted using a unified tagging approach. We integrate publications online Web databases propose...
Topic models provide a powerful tool for analyzing large text collections by representing high dimensional data in low subspace. Fitting topic model given set of training documents requires approximate inference techniques that are computationally expensive. With today's large-scale, constantly expanding document collections, it is useful to be able infer distributions new without retraining the model. In this paper, we empirically evaluate performance several methods previously unseen...
In this article, we study the problem of Web user profiling, which is aimed at finding, extracting, and fusing “semantic”-based profile from Web. Previously, profiling was often undertaken by creating a list keywords for user, (sometimes even highly) insufficient main applications. This article formalizes as several subtasks: extraction, integration, interest discovery. We propose combination approach to deal with tasks. Specifically, employ classification model identify relevant documents...
This paper addresses the issue of extraction an academic researcher social network. By network extraction, we are aimed at finding, extracting, and fusing 'semantic '-based profiling information a from Web. Previously, was often undertaken separately in ad-hoc fashion. first gives formalization entire problem. Specifically, it identifies 'relevant documents' Web by classifier. It then proposes unified approach to perform using conditional random fields (CRF). integrates publications existing...
Previous chapter Next Full AccessProceedings Proceedings of the 2009 SIAM International Conference on Data Mining (SDM)Multi-topic based Query-oriented SummarizationJie Tang, Limin Yao, and Dewei ChenJie Chenpp.1148 - 1159Chapter DOI:https://doi.org/10.1137/1.9781611972795.98PDFBibTexSections ToolsAdd to favoritesExport CitationTrack CitationsEmail SectionsAboutAbstract summarization aims at extracting an informative summary from a document collection for given query. It is very useful help...
This paper addresses the issue of researcher profiling. By profiling, we mean building a semantic profile for an academic researcher, by identifying and annotating information from Web. Previously, person annotation was often undertaken separately in ad-hoc fashion. first gives formalization entire problem proposes unified approach to perform task using Conditional Random Fields (CRF). The shows that with introduction set tags, most tasks can be performed within this approach. Experiments...
Categorizing entities by their types is useful in many applications, including knowledge base construction, relation extraction and query intent prediction. Fine-grained entity type ontologies are especially valuable, but typically difficult to design because of unavoidable quandaries about level detail boundary cases. Automatically classifying challenging as well, usually involving hand-labeling data training a supervised predictor.
This paper addresses several key issues in extraction and mining of an academic social network: 1) a researcher network from the existing Web; 2) integration publications digital libraries; 3) expertise search on given topic; 4) association between researchers. We developed system, called ArnetMiner, based proposed methods to above problems. In total, 448,470 profiles 981,599 were extracted/integrated after system having been operation for two years. The describes architecture main features...
Psoriasis is an immune-related disease caused by genetic factors, abnormalities in the immune system and environmental while pemphigus autoimmune attacking skin mucosal tissues. Herein, we aimed to report a rare case of adalimumab induced exacerbation psoriasis patients with pemphigus. The causes considerable challenges for clinical diagnosis treatment.
In this paper, we present a novel method for the design of fractional order FIR differentiators. Firstly, differentiator (FOD) power digital signal is defined in frequency domain. Secondly, filter chosen to approximate ideal FOD under weighting mean square error (MSE) sense response. Finally, example and derivative simulation are given advantages proposed illustrated.
Abstract Background Artemisiae argyi Folium (AF) has been used as herbal medicine and a food supplement in China other Asian countries. There is no report about whether the different developmental stages can influence bioactive compositions of AF. Objective To investigate dynamic changes constituents AF collected at stages. Method The volatile nonvolatile components six were analyzed by gas chromatography-mass spectrometry (GC-MS) high-performance liquid chromatography (HPLC). Chemometrics...
To investigate the ultrasonographic classification of fetal umbilical-portal-systemic venous shunts (UPSVS) and correlations with chromosomal abnormalities.We retrospectively analyzed ultrasound characteristics corresponding abnormalities 26 cases UPSVS prenatally diagnosed.A total fetuses diagnosed as were included, including four type I UPSVS, ten II, three IIIA, nine IIIB. Four all complicated by heart enlargement insufficiency, which one case had multiple malformations, terminated...
Support vector machines (SVMs) aim to find an optimal separating hyper-plane that maximizes separation between two classes of training examples (more precisely, the margin examples). The choice cost parameter for SVM model is always a critical issue. This analysis studies how determines hyper-plane; especially classifications using only positive data and unlabeled data. An algorithm given entire solution path by choosing 'best' while model. performance compared with conventional...