Nanoinformatics and Artificial Intelligence Research Team
Advancing AI and nanoscale informatics for healthcare and environmental solutions
About Our Team
The Nanoinformatics and Artificial Intelligence Research Team (NAI) focuses on the development and application of artificial intelligence (AI) and nanoscale informatics technologies to address various problems and challenges, particularly in healthcare and the environment.
Our research covers the development of a peer-to-peer artificial intelligence computing platform (PeerAI) to enhance large-scale data processing, as well as the development of intelligent computer systems for diagnosing and classifying disorders in elderly patients with early-stage cognitive decline, using an integrative approach combining mathematics, neuroscience, and artificial intelligence.
Additionally, we focus on developing AI models to classify the types and severity of mild cognitive impairment (MCI) and to test the effectiveness of transcranial electrical stimulation, as well as developing a learning platform that integrates knowledge in computer science, mathematical modeling, and artificial intelligence through the study of the relationship between behavior and brain signals.
Projects
PeerAI: Peer-to-Peer Artificial Intelligence Computing Platform
PeerAI is an innovative decentralized computing platform that enables distributed AI model training and inference. By leveraging idle computing resources from participants worldwide, it creates a sustainable ecosystem for AI development while providing rewards to contributors. The platform supports various AI workloads including deep learning, machine learning, and data processing tasks.
Developing computer-based models to improve diagnostic tools for mild cognitive impairment (MCI) using an integrative approach that combines quantitative models in computational neuroscience and artificial intelligence
This project focuses on developing advanced diagnostic tools for early detection of cognitive decline in elderly patients. By integrating mathematical modeling, neuroscience, and AI techniques, we create comprehensive assessment systems that analyze multiple biomarkers, behavioral patterns, and neuroimaging data to provide accurate early-stage diagnosis and personalized intervention strategies.
Developing AI-based models to identify mild cognitive impairment (MCI) subtypes and severity, and to test the effectiveness of transcranial stimulation
This initiative develops sophisticated AI models to classify MCI subtypes and assess severity levels using multimodal data analysis. The project also investigates the therapeutic potential of transcranial electrical stimulation, combining AI-driven patient profiling with personalized stimulation protocols to optimize treatment outcomes.
A learning platform in computer programming, mathematical modeling and artificial intelligence through the lens of computational neuroscience (Brain Code Camp)
Brain Code Camp is an innovative educational platform that bridges computational neuroscience with AI education. It provides interactive tools and simulations for understanding brain-behavior relationships, offering hands-on experience in mathematical modeling, programming, and AI applications in neuroscience research.
Digital X-ray Annotation System
This system revolutionizes medical imaging analysis by providing an advanced digital platform for X-ray annotation and collaborative review. It features AI-assisted annotation tools, real-time collaboration capabilities, and comprehensive documentation features to enhance diagnostic accuracy and streamline medical workflows.
Image-based Analysis of Nutrient Deficiency in Crops and Fertilizer Recommendation
This project develops an intelligent agricultural system that uses computer vision and AI to analyze plant health through image processing. It accurately identifies nutrient deficiencies, provides real-time fertilizer recommendations, and offers predictive analytics for optimal crop management and yield improvement.
Thailand CCUS Alliance Platform: Advancing the Nation's Path to Carbon Neutrality
This platform serves as a comprehensive hub for Carbon Capture, Utilization, and Storage (CCUS) initiatives in Thailand. It facilitates collaboration between stakeholders, provides real-time monitoring of carbon reduction efforts, and offers AI-powered analytics for optimizing carbon management strategies across industries.
AI-driven Colorimetric Nucleic Acid Test Platform
This innovative platform combines AI with colorimetric nucleic acid testing to provide rapid, accurate, and cost-effective diagnostic solutions. It features automated image analysis, real-time result interpretation, and cloud-based data management for efficient disease screening and monitoring.
Accelerating MOFs Development via Solvent Simulation for CO₂ Capture and Utilization
This project develops advanced computational models to accelerate the design and optimization of Metal-Organic Frameworks (MOFs) for CO₂ capture. Using AI-driven molecular simulations and solvent system analysis, it enables rapid screening of MOF candidates and optimization of their performance in carbon capture applications.
Platform for Electrochemical Sensors to Detect Multiple Health Biomarkers from Urine
This platform integrates electrochemical sensors with AI analytics to provide comprehensive health monitoring through urine analysis. It enables simultaneous detection of multiple biomarkers, real-time data processing, and personalized health insights for preventive healthcare and disease management.
AI System for Microplastic Detection
This system employs advanced AI algorithms and computer vision to detect and analyze microplastics in various environments. It provides automated identification, classification, and quantification of microplastic particles, supporting environmental monitoring and pollution control efforts.
Development of a Database and AI Model for Growth Stage Study of Wolffia for Smart Agriculture Technology Advancement
This project creates a comprehensive database and AI models for studying Wolffia growth stages. It combines image analysis, environmental monitoring, and machine learning to optimize cultivation conditions and develop smart agriculture solutions for this important aquatic plant species.
Development of an in silico platform for nanotoxicity assessment and investigation of underlying molecular mechanisms
This platform provides advanced computational tools for nanotoxicity assessment and molecular mechanism analysis. It integrates molecular dynamics simulations, machine learning algorithms, and comprehensive toxicity databases to predict and analyze nanoparticle interactions with biological systems.