Research
"Unlocking the Insights Hidden in Vast Unstructured Data - Empowered by Advanced Data Mining Technology"
Our lab specializes in data mining machine learning and natural language processing, with a focus on the biomedical and molecular biology domains. Our lab is actively involved in several projects related to clinical natural language processing, including the development of tools for cancer research and early detection. Additionally, our lab is involved in bio-text mining and has developed several software tools, such as the MicroRNA Identification web service and the BIOSMILE WEB SEARCH application. Our lab has a strong focus on using advanced technologies, such as artificial intelligence and computer vision, to analyze and interpret large amounts of data. Our team's expertise in these areas enables us to extract knowledge nuggets from unstructured data and turn them into actionable insights. Overall, our lab's focus on cutting-edge technologies and its involvement in several active projects and software development projects demonstrate a commitment to advancing the field of biomedical research and improving patient outcomes.
Biomedical Text Mining
Extract knowledge nuggets from texts and literature of the biomedical and molecular biology domain.
Clinical Natural Language Processing
Extract and structure clinically-relevant outcomes from clinical texts to aid decision support.
Social Media Mining
Extract, analyze and visualize patterns and trends from social media data.
Computer Vision
Enabling computers to understand what they see
Project
Here illustrates our active projects. Click HERE to view the list of our grants, funding and projects.
Software
Here list the recent released softwares developed by our lab. Click HERE to view the full list of our tools
MRI - MicroRNA Identification
MRI: A RESTful web service for identifying miRNAs from literature and a corpus for miRNA identification.
SPRENO
A BioC module for identifying organism terms in figure captions
nttmuClinical.NET
A nttmuClinical.NET is a set of C# library developed for processing discharge summaries.
T-HOD
A literature-based candidate gene database for hypertension, obesity and diabetes.
PubMed-EX
A web browser extension to enhance PubMed search with text mining features.
BIOSMILE Web Search
A web-based PubMed-like search application power with semantic analysis
Publication
Here list our most recent publications. Click HERE to view the full list of our publications.
Journal
-
An Incremental Learning Method for Preserving World Coffee Aromas by Using an Electronic Nose and Accumulated Specialty Coffee Datasets (SCI) -
The development of thermal error compensation on CNC machine tools by combining ridge parameter selection and backward elimination procedure (SCI) -
Unlocking the Secrets Behind Advanced Artificial Intelligence Language Models in De-Identifying Chinese-English Mixed Clinical Text Journal of Medical Internet Research (SCI) -
Automatic Extraction of Medication Mentions from Tweets—Overview of the BioCreative VII Shared Task 3 Competition -
Augmenting DSM-5 diagnostic criteria with self- attention-based BiLSTM models for psychiatric diagnosis (SCI) -
Robust fault recognition and correction scheme for induction motors using an effective IoT with deep learning approach (SCI) -
Vickers Hardness Value Test via Multi-Task Learning Convolutional Neural Networks and Image Augmentation (SCI) -
Principle-Based Approach for the De-Identification of Code-Mixed Electronic Health Records (SCI) -
Cancer Registry Coding via Hybrid Neural Symbolic Systems in the Cross-Hospital Setting IEEE Access (SCI) -
Cohort selection for construction of a clinical natural language processing corpus Computer Methods and Programs in Biomedicine Update
Conference/Workshop
Here list our most recent Conferences/Seminars. Click HERE to view the full list.
-
Investigating Cross-Institutional Recognition of Cancer Registration Items: A Case Study on Catastrophic Forgetting -
Protected Health Information Recognition of Unstructured Code-Mixed Electronic Health Records in Taiwan -
An Ensemble Neural Network Model for Benefiting Pregnancy Health Stats from Mining Social Media -
NTTMUNSW System for n2c2 Track1: Cohort Selection for Clinical Trails -
Ensemble of Different Sequential Labeling Algorithms for Medication and Adverse Drug Event Extraction -
Family History Information Extraction with Neural Sequence Labeling Model -
Identification of Adverse Drug Reactions and Medication Intakes on Twitter Using Various Combinations of Language Features -
NTTMU System in the 2nd Social Media Mining for Health Applications Shared Task -
Pregnant Women Recognition from Social Media for Health-related Information Exploration -
Principle base Approach for Classifying Tweets with Flu-related Information in NTCIR-13 MedWeb Task