A5081863278- Topic Modeling
- Natural Language Processing Techniques
- Advanced Database Systems and Queries
- Complex Network Analysis Techniques
- Recommender Systems and Techniques
- Data Quality and Management
- Data Management and Algorithms
- Human Mobility and Location-Based Analysis
- ECG Monitoring and Analysis
- Software Engineering Research
- Online Learning and Analytics
- Advanced Graph Neural Networks
- Expert finding and Q&A systems
- Semantic Web and Ontologies
- Image Retrieval and Classification Techniques
- Consumer Market Behavior and Pricing
- Online and Blended Learning
- Advanced Clustering Algorithms Research
- Biomedical Text Mining and Ontologies
- Bioinformatics and Genomic Networks
- Data Mining Algorithms and Applications
- Mobile Crowdsensing and Crowdsourcing
- Advanced Image and Video Retrieval Techniques
- Genomics and Rare Diseases
- Data-Driven Disease Surveillance
University of Pennsylvania
2024
Singapore Management University
2015-2024
Kingmed Diagnostics
2021-2024
China Railway Group (China)
2019
China Railway 18th Bureau Group Corporation
2019
National University of Defense Technology
2019
National University of Singapore
2006-2012
University of Victoria
2009
Drexel University
2007
Tsinghua University
1996-2002
Biomedical ontologies provide essential domain knowledge to drive data integration, information retrieval, annotation, natural-language processing and decision support. BioPortal (http://bioportal.bioontology.org) is an open repository of biomedical that provides access via Web services browsers developed in OWL, RDF, OBO format Protégé frames. functionality includes the ability browse, search visualize ontologies. The interface also facilitates community-based participation evaluation...
The design of automatic solvers to arithmetic math word problems has attracted considerable attention in recent years and a large number datasets methods have been published. Among them, Math23K is the largest data corpus that very helpful evaluate generality robustness proposed solution. best performer seq2seq model based on LSTM generate expression. However, suffers from performance degradation space target expressions. In this paper, we propose template-based solution recursive neural...
Solving mathematical word problems (MWPs) automatically is challenging, primarily due to the semantic gap between human-readable words and machine-understandable logics. Despite long history dated back 1960s, MWPs have regained intensive attention in past few years with advancement of Artificial Intelligence (AI). successfully considered as a milestone towards general AI. Many systems claimed promising results self-crafted small-scale datasets. However, when applied on large diverse...
Several deep learning models have been proposed for solving math word problems (MWPs) automatically. Although these the ability to capture features without manual efforts, their approaches capturing are not specifically designed MWPs. To utilize merits of with simultaneous consideration MWPs’ specific features, we propose a group attention mechanism extract global quantity-related quantity-pair and question-related in MWPs respectively. The experimental results show that approach performs...
It's challenging work to identify disease-causing genes from the next-generation sequencing (NGS) data of patients with Mendelian disorders. To improve this situation, researchers have developed many phenotype-driven gene prioritization methods using a patient's genotype and phenotype information, or information only as input rank candidate's pathogenic genes. Evaluations these ranking provide practitioners convenience for choosing an appropriate tool their workflows, but retrospective...
While Math Word Problem (MWP) solving has emerged as a popular field of study and made great progress in recent years, most existing methods are benchmarked solely on one or two datasets implemented with different configurations. In this paper, we introduce the first open-source library for MWPs called MWPToolkit, which provides unified, comprehensive, extensible framework research purpose. Specifically, deploy 17 deep learning-based MWP solvers 6 our toolkit. These advanced models solving,...
This article discusses a cost-effective portable home unit for electrocardiogram (ECG) and blood pressure (BP) monitoring. Based on feedback from our previous work concerning PC-based ECG/BP telemonitoring system, the system described helps to overcome past problems by simplifying installation, operation, maintenance, reducing cost. The strategy methodology used in design development of as well results, are presented.
The star schema is widely accepted as the de facto data model for warehouse design. A popular approach developing a to develop it from an entity-relationship diagram with some heuristics. Most of existing approaches analyze semantics ERD generate schema. In this paper, we present SAMSTAR method, which semi-automatically generates schemas by analyzing its well structure. novel features are (1) use notion Connection Topology Value (CTV) in identifying candidates facts and dimensions (2)...
The Lanzhou Yellow River Tunnel is the first metro shield tunnel that undercrosses in China. It was completed after successfully overcoming several construction challenges, including strata with a high proportion of large‐sized sandy cobble stratum being saturated, large‐scale sand pits along bank River, and combination boulders erratic blocks rock. Given difficulties constructing tunnel, this paper summarizes scheme employed to transform cutter head design be applicable key technology used...
Developing automatic Math Word Problem (MWP) solvers has been an interest of NLP researchers since the 1960s. Over last few years, there are a growing number datasets and deep learning-based methods proposed for effectively solving MWPs. However, most existing benchmarked soly on one or two datasets, varying in different configurations, which leads to lack unified, standardized, fair, comprehensive comparison between methods. This paper presents MWPToolkit, first open-source framework In we...
In recent years, there are trends toward cleaner port environments through enforcement by imposed legislation. Transit optimisation of fuel-based service boats like harbour tugs has emerged as a critical task to reduce fuel consumption and carbon emission. this paper, an innovative learning-based method, comprising Reinforcement Learning (RL) model together with prediction model, was proposed formulate fuel-saving transit routes. Firstly, ensemble is established combining Long Short-Term...
Validation of multi-column schema matchings is essential for successful database integration. This task especially difficult when the databases to be integrated contain little overlapping data, as often case in practice (e.g., customer bases different companies). Based on intuition that values present columns related by a matching will have similar "semantic type", and this can captured using distributions over ("statistical types"), we develop method validating 1-1 compositional matchings....
Link prediction is an important problem in social network mining. Traditional neighborhood based methods such as Common neighbors, Jaccard Coefficient and Adamic/Adar are well studied link prediction. However, the concept of structural holes does not receive significant attention As a preliminary work studying holes, we focus on bipartite networks, which special class networks that consists two distinct roles for users, links between users different roles. In this study, few implementations...
Previous chapter Next Full AccessProceedings Proceedings of the 2012 SIAM International Conference on Data Mining (SDM)Structural Analysis in Multi-Relational Social NetworksBing Tian Dai, Freddy Chong Tat Chua, and Ee-Peng LimBing Limpp.451 - 462Chapter DOI:https://doi.org/10.1137/1.9781611972825.39PDFBibTexSections ToolsAdd to favoritesExport CitationTrack CitationsEmail SectionsAboutAbstract Modern social networks often consist multiple relations among individuals. Understanding structure...
EM algorithm is a very popular iteration-based method to estimate the parameters of Gaussian Mixture Model from large observation set. However, in most cases, not guaranteed converge global optimum. Instead, it stops at some local optimums, which can be much worse than Therefore, usually required run multiple procedures with different initial configurations and return best solution. To improve efficiency this scheme, we propose new an upper bound on logarithm likelihood optimum, based...
The objective of the medical teleconsultation system presented in this paper is to demonstrate use World Wide Web (WWW) for telemedicine and interactive information exchange. system, which developed based on Java, could provide several basic Java tools fulfill requirements applications, including a file manager, data tool, bulletin board, digital audio tool. tool uses point-to-point structure enable two physicians communicate directly through voice. others multipoint structure. manager...
Data quality is a serious concern in every data management application, and variety of measures have been proposed, e.g., accuracy, freshness completeness, to capture common sources degradation. We identify focus attention on novel measure, column heterogeneity, that seeks quantify the problems can arise when merging from different sources. desiderata heterogeneity measure should intuitively satisfy, describe our technique database based using combination cluster entropy soft clustering....
To determine the feasibility of home monitoring patients with cardiac disease or hypertension. An improved electrocardiographic and blood pressure telemonitoring system linked to a central workstation was tested in 10 Macau for 3 months. The total number connections 1377. Of automatic alarm connections, 32.5% were false positive, percentage positives ranging from 7.6 54.6 different patients. Both physicians found easy use. Further investigation is required match capacity. A more robust...
A home electrocardiography (ECG) and blood pressure (BP) monitoring network was established in Beijing. The consisted of three parts: (1) the ECG BP devices; (2) centre at hospital; (3) data communication network, for which we chose public telephone network. system tested our university hospital two months with 30 patients six normal volunteers. preliminary evaluation by users indicated that acceptable terms its efficiency effectiveness. This paper describes design, testing procedure, results.