A5048582530- Topic Modeling
- Natural Language Processing Techniques
- Advanced Text Analysis Techniques
- Data Quality and Management
- Video Analysis and Summarization
- Complex Network Analysis Techniques
- Semantic Web and Ontologies
- Data Management and Algorithms
- Recommender Systems and Techniques
- Opinion Dynamics and Social Influence
- Web Data Mining and Analysis
- Misinformation and Its Impacts
- Advanced Image and Video Retrieval Techniques
- Information Retrieval and Search Behavior
- Image Retrieval and Classification Techniques
- Spam and Phishing Detection
- Time Series Analysis and Forecasting
- Human Mobility and Location-Based Analysis
- Advanced Database Systems and Queries
- Hydrological Forecasting Using AI
- Algorithms and Data Compression
- Speech and dialogue systems
- Data Stream Mining Techniques
- Advanced Malware Detection Techniques
- Text and Document Classification Technologies
University of Houston
2025
University Medical Center HCMC
2024
International Center for Tropical Agriculture
2023
The University of Queensland
2023
University of America
2019-2023
Catholic University of America
2019-2023
MedStar National Rehabilitation Hospital
2019-2023
University of Wisconsin–Whitewater
2010-2022
Tra Vinh University
2022
Ho Chi Minh University of Banking
2020-2021
Online social networks have become an effective and important platform for communication, opinions exchange, information sharing. However, they also make it possible rapid wide misinformation diffusion, which may lead to pernicious influences on individuals or society. Hence, is extremely necessary detect the propagation by placing monitors. In this article, we first define a general misinformation-detection problem case where knowledge about sources lacking, show its equivalence...
We propose an approach to diagnosing brain hemorrhage by using deep learning. In particular, three types of convolutional neural networks that are LeNet, GoogLeNet, and Inception-ResNet employed. the training phase, we only train last fully-connected layers GoogLeNet Inception-ResNet, but do all LeNet. build a dataset consisting 100 cases collected from 115 Hospital, Ho Chi Minh City, Vietnam. The experimental results show achieve accuracy 0.997, 0.982, 0.992 respectively on dataset. Through...
Single-molecule localization microscopy techniques are emerging as vital tools to unravel the nanoscale world of living cells by understanding spatiotemporal organization protein clusters at nanometer scale. Current analyses define spatial nanoclusters based on detections but neglect important temporal information such cluster lifetime and recurrence in "hotspots" plasma membrane. Spatial indexing is widely used video games detect interactions between moving geometric objects. Here, we use...
This article presents research conducted to establish how information is shared across the personal social network in sensitive context of a health crisis. We worked with parents very sick babies who were cared for hospital's Neonatal Unit (NNU). Through combination interviews, focus group, and surveys, we developed user model that wanted share, they adapted this individual recipients. then prototype software tool which created adaptive updates members parents' network. The contained...
The study examined the natural and social capital of Bo Hon villagers in central Vietnam, before after resettlement within Binh Thanh commune due to building Dien Hydroelectric dam on Huu Trach River. (1) Background: two-fold aim was develop solutions impacts capital, strategies for timely intervention new livelihoods households were resettled. (2) Methods: Livelihood survey all 46 conducted 2010, asked about 2004, resettlement, 2009, when occupants village had been moved a location 15 km...
Named entities (NE) are phrases that contain the names of persons, organizations, locations, times and quantities, monetary values, percentages, etc. Entity Recognition (NER) is task recognizing named in documents. NER an important subtask Information Extraction, which has attracted researchers all over world since 1990s. For Vietnamese language, although there exists some research projects publications on before 2016, no systematic comparison performance systems been done. In organizing...
Experiencing emotional distress is the number one reason why people who are undergoing behaviour modification (e.g. quitting smoking, dieting) suffer from relapses. Providing support an effective way to help them overcome unpleasant effects of negative affect and adhere their regimen. Building computers with such ability has grabbed attention HCI community in recent years. Early research shown some promising results when adopting strategies how we comfort others, but many questions on build...
Drawing on the extended unified theory of acceptance and use technology (UTAUT2) task-technology fit (TTF) theory, we developed an integrated research model to explore factors affecting ChatGPT its subsequent effects whether users continue using recommend it others. We also examined main activities as well moderating role curiosity in relationships between various influencing use. conducted a quantitative study with data that collected from 671 Vietnam. found that, first, most UTAUT2 TTF...
Although Aboriginal students encounter educational challenges, few post-secondary mentorship programs that facilitate positive and mental health outcomes within this population are described in the literature. This study describes development evaluation of a program for university students. Program was informed by literature review needs assessment. Using mixed-methods design, 12 completed pre- post-program measures resilience ethnic identity awareness. Post-program, improvements social...
Background The decision of which arm to use achieve a goal depends on energetic costs and performance abilities each arm. Following stroke, there is reduction in the more-impaired Is it because are increased, or its dictates lower chance success? Objective We sought elucidate impact cost task success choice stroke survivors. Methods Thirteen chronic survivors thirteen neurologically-intact subjects participated an experiment where they reached towards visual targets virtual-reality...
Currently, for named entity disambiguation, the short-age of training data is a problem. This paper presents novel method that overcomes this problem by automatically generating an annotated corpus based on specific ontology. Then was enriched with new and informative features extracted from Wikipedia data. Moreover, rather than pursuing rule-based methods as in literature, we employ machine learning model to not only disambiguate but also identify entities. In addition, our explores details...
Given an aftermath of a cascade in the network, i.e. set VI "infected" nodes after epidemic outbreak or propagation rumors/worms/viruses, how can we infer sources cascade? Answering this challenging question is critical for computer forensic, vulnerability analysis, and risk management. Despite recent interest towards problem, most existing works focus only on single source detection simple network topologies, e.g. trees grids. In paper, propose new approach to identify infection by...
Dam development is widespread in central Vietnam. Interviews were conducted with households that had been resettled and those not to determine the type of agricultural livelihoods re-established nine years after resettlement due Ta Trach reservoir project. Results showed households, despite having more forest land, economically worse off compared moved. This discrepancy between was attributed less arable land allocated households. The provision good-quality able grow crops food trees,...
We propose an efficient method for compressing Vietnamese text using n -gram dictionaries. It has a significant compression ratio in comparison with those of state-of-the-art methods on the same dataset. Given text, first, proposed splits it into -grams and then encodes them based In encoding phase, we use sliding window size that ranges from bigram to five grams obtain best stream. Each is encoded by two four bytes accordingly its corresponding dictionary. collected 2.5 GB corpus some news...