Thanh Tran

ORCID: 0000-0001-8663-1652
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Semantic Web and Ontologies
  • Data Quality and Management
  • Advanced Database Systems and Queries
  • Web Data Mining and Analysis
  • Topic Modeling
  • Data Management and Algorithms
  • Natural Language Processing Techniques
  • Information Retrieval and Search Behavior
  • Advanced Graph Neural Networks
  • Text and Document Classification Technologies
  • Advanced Malware Detection Techniques
  • Video Surveillance and Tracking Methods
  • Network Security and Intrusion Detection
  • Big Data Technologies and Applications
  • Service-Oriented Architecture and Web Services
  • Advanced Image and Video Retrieval Techniques
  • Spam and Phishing Detection
  • Machine Learning in Bioinformatics

FPT University
2024-2025

Flinders University
2022

Utah State University
2016

San Jose State University
2014-2015

Karlsruhe Institute of Technology
2007-2013

Keyword queries enjoy widespread usage as they represent an intuitive way of specifying information needs. Recently, answering keyword on graph-structured data has emerged important research topic. The prevalent approaches build dedicated indexing techniques well search algorithms aiming at finding substructures that connect the elements matching keywords. In this paper, we introduce a novel paradigm for data, focusing in particular RDF model. Instead computing answers directly previous...

10.1109/icde.2009.119 article EN Proceedings - International Conference on Data Engineering 2009-03-01

As the commercial implications of Likes in online social networks multiply, number fake also increase rapidly. To maintain a healthy ecosystem, however, it is critically important to prevent and detect such Likes. Toward this goal, paper, we investigate problem detecting so-called "fake likers" who frequently make for illegitimate reasons. uncover networks, we: (1) first collect substantial profiles both legitimate Likers using linkage honeypot approaches, (2) analyze characteristics types...

10.1145/2983323.2983695 article EN 2016-10-24

Abstract Directed evolution has been the most effective method for protein engineering that optimizes biological functionalities through a resource-intensive process of screening or selecting among vast range mutations. To mitigate this extensive procedure, recent advancements in machine learning-guided methodologies center around establishment surrogate sequence-function model. In paper, we propose Latent-based Evolution (LDE), an evolutionary algorithm designed to prioritize exploration...

10.1088/2632-2153/adc2e2 article EN cc-by Machine Learning Science and Technology 2025-03-20

Instance matching and blocking, a preprocessing step used for selecting candidate matches, require determining the most representative attributes of instances called keys, based on which similarities between are computed. We show that problem learning blocking keys key values, both generic techniques do not exploit type information supervised optimized one single predefined perform well heterogeneous Web data capturing is too general. That is, they actually belong to some subtypes explicitly...

10.1145/2433396.2433439 article EN 2013-02-04

Structured data representing entity descriptions often lacks precise type information. That is, it is not known to which an belongs to, or the too general be useful. In this work, we propose deal with novel problem of inferring semantics structured data, called typification. We formulate as a clustering and discuss features needed obtain several solutions based on existing solutions. Because schema perform best, but are abundantly available, approach automatically derive them from data....

10.1109/icde.2013.6544826 article EN 2022 IEEE 38th International Conference on Data Engineering (ICDE) 2013-04-01

10.1109/tevc.2024.3439690 article EN IEEE Transactions on Evolutionary Computation 2024-01-01

The use of semantics and semantic technologies for search retrieval has attracted interests both from academia industry in recent years. What is now commonly known as Semantic Search fact a broad field encompassing ideas concepts different areas, including Information Retrieval, Web database. This the fourth edition workshop which aims to bring together researchers practitioners various communities, provide forum dissemination, discussion, exchange transfer knowledge related retrieval....

10.1145/1963192.1963329 article EN 2011-03-28

An increasing amount of structured data on the Web has attracted industry attention and renewed research interest in what is collectively referred to as semantic search. These solutions exploit explicit semantics captured such RDF for enhancing document representation retrieval, or finding answers by directly searching over data. have been used different tasks a wide range corresponding search proposed past. However, it widely recognized that standardized setting evaluate analyze current...

10.2139/ssrn.3199069 article EN SSRN Electronic Journal 2013-01-01

Semantic relatedness is essential for different text processing tasks, especially in the cross-lingual setting due to vocabulary mismatch problem. Many concept-based solutions semantic have been proposed, which vary notions of concept and document representation. In our contribution, we provide a unified model that generalizes over existing approaches relatedness. It shows main represent ways constructing space, result representations implications computation. particular, it al- lows us...

10.1145/2808194.2809450 article EN 2015-09-22

Linked Data consists of billions RDF triples from hundreds different sources on the Web. The effective construction and maintenance links between these largely depend data integration solutions that scale to large volume heterogeneity In this context, a promising direction is pay-as-you-go paradigm advocates use user feedback for an interactive incremental approach integration---to obtain solution continuously improves as underlying system evolves. paper, we study in context entity search....

10.1145/2380718.2380759 article EN 2012-06-22
Coming Soon ...