Researchers developed a multimodal dataset, TimelyTale, to gather passenger-specific sensor data for context-relevant explanations. The approach effectively identified the timing and frequency of passenger demands for explanations, enabling the creation of a machine-learning model to predict the best time for providing an explanation.
Researchers at GIST developed a cat's eye-inspired vision system that filters out unnecessary light and improves visibility in low-light conditions. The system promises to elevate the precision of drones, security robots, and self-driving vehicles, enabling them to navigate intricate environments with unparalleled accuracy.
A team of GIST researchers developed a new defect passivation strategy for polycrystalline perovskites, leading to improved power conversion efficiency and long-term operational stability. The strategy uses a chemically identical polytype of perovskite to suppress defects in the crystal structure.
Researchers at Gwangju Institute of Science and Technology developed a novel nitrogen-doped mesoporous carbon-coated thick GF electrode to suppress the crossover phenomenon in flowless zinc-bromine batteries. The new electrodes effectively prevented self-discharge, improving battery performance and lifespan.
Researchers at the Gwangju Institute of Science and Technology (GIST) have developed an innovative robotic rehabilitation system called SPINDLE to enhance the strength and dexterity of individuals with tremors. The study revealed significant benefits, including improved motor control, coordination, and neuroplasticity.
Researchers at Gwangju Institute of Science and Technology develop a new nanotechnology method that enables the creation of uniform, wafer-scale nanoparticle assemblies in just seconds. The 'mussel-inspired' technique accelerates assembly by introducing excess protons to increase electrostatic attraction.
Researchers from GIST and MIT CSAIL develop a MultiSenseBadmpton dataset to enhance badminton performance analysis and AI-based coaching. The dataset captures joint movements, muscle signals, and gaze movements of badminton players.
According to GIST researchers, extreme cold events (WACC) have intensified until the 2020s but are expected to decline post-2030s. This drastic shift in WACC trajectory has significant implications for global climate systems and weather patterns.
Western North America experiences more extreme weather events due to warming climate and changes in atmospheric circulation patterns, according to a study by GIST researchers. The study found that greenhouse gas emissions play a significant role in driving shifts in the jet stream, leading to more frequent extreme hydroclimatic events.
Researchers at Gwangju Institute of Science and Technology (GIST) have discovered a novel compound, 11c, a 5HT2A antagonist, which exhibits robust biological activity and a favorable safety profile. The compound has shown promising efficacy in preclinical models and is poised to advance the treatment of metabolic liver diseases.
GIST researchers develop tunable optical properties in nanostructures, enabling applications in wound healing, drug delivery, and secure verification. A clock-inspired design featuring magnesium nano-rotamers demonstrates programmable polarization-resolved coloration.
Researchers at GIST designed two novel polymers to explore the properties of organic mixed ionic–electronic conductors. The polymers exhibited unique molecular orientation-dependent transient behaviors in organic electrochemical transistors.
Researchers at GIST developed high-performance OECT devices based on poly(diketopyrrolopyrrole) (PDPP)-type polymers, achieving high charge carrier mobility and volumetric capacitance values. The optimized material exhibited a figure-of-merit value of over 800 F V^-1 cm^-1 s^-1.
A new study by GIST researchers provides efficient hydrogen storage solutions using clathrate hydrates, overcoming limitations such as limited gas storage capacities and slow formation rates. The study offers crucial insights for developing clathrate hydrate-based technologies for carbon dioxide separation and hydrogen storage.
Researchers from GIST have developed a new electrode using Schottky junctions to overcome the conductance limit of active catalysts, achieving high-performance water splitting and hydrogen evolution reactions. The electrode demonstrated remarkable current density and durability during continuous operation for 10 days.
Researchers at Gwangju Institute of Science and Technology developed metal-enhanced fluorescence probes for rapid and accurate detection of influenza viruses. The probes showed high sensitivity and specificity, detecting the virus even at low concentrations, with a remarkable accuracy of over 99%.
Researchers at Gwangju Institute of Science and Technology (GIST) have developed a deep learning-based biosensing platform called DeepGT, which can accurately quantify nanoscale bioparticles, including viruses. The platform harnesses the advantages of Gires-Tournois biosensors and AI to refine visual artifacts and extract relevant info...
Researchers from GIST propose a novel approach to mitigate overfitting in pretrained models used for voice pathology detection, achieving 12.36% and 15.38% improvement in recall using contrastive learning.
GIST researchers found that nano-sized pits on AlN surfaces cause graphene degradation at higher temperatures, leading to GaN film exfoliation failure. The study's results demonstrate the importance of substrate chemical and topographic properties for successful remote epitaxy.
Researchers at Gwangju Institute of Science and Technology have developed a novel mesoporous tantalum oxide-supported iridium nanostructure catalyst for efficient proton exchange membrane water electrolysis. The catalyst exhibits improved oxygen evolution reaction activity, stability, and cost-effectiveness.
Researchers have developed a highly efficient organometal halide perovskite photoanode that suppresses internal and external losses associated with photoelectrochemical water splitting, enhancing reaction kinetics. The new design achieves an unprecedented applied bias photon-to-current conversion efficiency of 12.79%.
Researchers demonstrated a 300-fold increase in electron-phonon coupling strength by reducing dimensionality, paving the way for novel engineering opportunities. The enhancement was attributed to non-local nature of coupling in synthetic SRO/STO superlattices.
Researchers from GIST have developed a hydrotropic-supporting electrolyte to enhance the solubility of organic redox molecules in aqueous systems. This improvement enables the creation of high-energy-density electrochemical capacitors with potential applications in redox flow batteries.
Researchers from GIST have developed graphene-based conductive hydrogels that are injectable, degradable, and highly compatible with biological systems. The novel electrodes outperform traditional metal electrodes in signal transmission and stability, offering promising solutions for long-term medical monitoring and treatment.
Researchers at GIST have developed an IDT-based polymer with low thermal conductivity and high electronic conductivity, improving thermoelectric performance. The new material demonstrates a 6-fold increase in efficiency compared to conventional materials.
A new VR locomotion system, Seamless-walk, offers a natural and comfortable experience without equipment or body pose recording. It uses high-resolution foot pressure imprints and machine learning to estimate the user's direction and movement speed.
A study by GIST researchers found that Arctic warming is correlated with severe winters in East Asia and North America. The 'Warm Arctic-Cold Continent' phenomenon will persist but become more difficult to predict under warmer climates.
Researchers at GIST developed a novel thermoelectric generator inspired by zebra skin, creating a high in-plane temperature gradient for generating electricity. The design uses a pattern resembling black-and-white zebra stripes to increase its applicability while reducing environmental impact.
A new AI-based classification system, AMP-BERT, was developed to identify candidate antimicrobial peptides. The model uses a deep neural network-based architecture and can extract structural and functional information from peptide sequences.
A team of researchers from GIST created a protection layer for nickel-iron catalysts using tetraphenylporphyrin, increasing their life and performance. This innovation reduces the dissolution of iron atoms during oxygen evolution reactions, resulting in prolonged hydrogen production.
A new optimization model by GIST researchers reduces operating costs and load shedding in microgrids, achieving a 20% decrease in average ENS. The model accounts for variations and uncertainty in renewable energy supply using an ANN-based prediction model, with predicted power output accuracy of 9.7%.
A new intelligent observer for Esports has been developed using a Mask R-CNN algorithm to learn from human spectating data. This approach overcomes limitations of existing automatic observers, which require extensive domain knowledge and cannot capture undefined events or changes in event significance.
A novel multi-modal image retrieval system, DenseBert4Ret, has been developed by researchers from Gwangju Institute of Science and Technology (GIST) using deep learning algorithms. The system outperforms state-of-the-art models in retrieving images based on both image and text features.
Researchers developed an AI-based model that combines artificial intelligence and weather forecast models to predict extreme wildfire danger with high accuracy. The new method can produce forecasts of extreme fire danger out to one week at finer scales (4km x 4km resolution), increasing its utility for fire suppression and management.
Researchers from Gwangju Institute of Science and Technology have developed a method to eliminate residual organic metal-binding ligands from transition metal oxide thin films, resulting in improved device stability and performance. The technique achieved a 20-fold enhancement in electrical conductivity and a 17.6% increase in efficiency.
Researchers from Gwangju Institute of Science and Technology design a novel approach to create durable organic semiconductor photocathodes, enabling high-efficiency conversion of solar energy to hydrogen. The developed photocathodes demonstrate remarkable stability and can produce hydrogen under actual sunlight.
Researchers from Gwangju Institute of Science and Technology developed a method to control active layer morphology in organic solar cells using water treatment. This approach led to more uniform thin films and higher power conversion efficiencies compared to non-treated samples. The study paves the way for large-scale, efficient organi...
Researchers from GIST developed an AI model that adjusts videogame difficulty based on player emotions, incorporating aspects such as challenge, competence, flow, and valence. The model has been verified to improve players' overall experience, regardless of their preference, and has potential applications in various fields beyond gaming.
GIST scientists create a new method to produce OSCs using zinc oxide that overcomes scalability issues without compromising PCE. The new technology uses sputtered ZnO and a ZnO nanoparticle layer obtained through blade coating, resulting in high conversion efficiencies.
Researchers at Gwangju Institute of Science and Technology improve triboelectric nanogenerators by using mesoporous carbon spheres to enhance charge transport and surface charge densities. The device achieves a 1300-fold higher output current, enabling potential sustainable energy harvesting.
Researchers from GIST have developed an amphibious artificial vision system with a panoramic field-of-view based on the Fiddler crab's eye structure. The system overcomes limitations of current artificial visions, enabling imaging in both aquatic and terrestrial environments.
Gwangju Institute of Science and Technology researchers have developed a rabbit-scale three-dimensional magnetic particle imaging system that can scan large volumes at high resolution. The system uses amplitude modulation to minimize peripheral nerve stimulation while maintaining high image quality.
Researchers at Gwangju Institute of Science and Technology have developed a new bioinformatics pipeline, CRESSP, to investigate the mechanism underlying autoimmune diseases following SARS-CoV-2 infection. The tool identified potential epitopes responsible for COVID-related autoimmune diseases and predicted cross-reactive epitopes of di...
Researchers monitored mercury levels in artificial lakes to identify sources and factors affecting concentration. Most mercury originated from soil in catchment areas, with surface runoff contributing in shorter-residence time reservoirs.
The study reveals significant information on the thermal properties of electric double-layer capacitors, which can help create safer and more reliable energy storage devices. The research team found that charging and discharging alter the heat capacity of EDLCs, leading to a decrease in capacitance.
Researchers developed a deep learning-based model to predict drug-drug interactions using gene expression data. The DeSIDE-DDI model can identify potentially dangerous pairs and act as a drug safety monitoring system, helping establish the correct usage of drugs in the development phase.
Researchers at Gwangju Institute of Science and Technology (GIST) have developed a new technique to easily visualize viruses using an optical microscope, called the Gires-Tournois immunoassay platform. The platform uses 'slow light' technology to detect coronavirus particles by slowing down light that gets reflected around them.
A new deep learning-based model called Highlights on Target Sequences (HoTS) predicts binding between drugs and target molecules, providing interpretable results. The model can predict target proteins' binding regions and interactions with drugs without a 3D complex.
Researchers at GIST have developed a new approach for designing fiber reinforced composites, which can simultaneously optimize the macrostructure and microscale fiber densities. This method, based on multiscale topology optimization, enables the creation of functionally graded composites with improved strength-to-weight ratios, benefit...
GIST researchers propose a new strategy for crime prevention using artificial intelligence, trained on a large-scale dataset of deviant incident reports and corresponding images. The model, called DevianceNet, can accurately classify and detect deviant places, making it a useful tool in urban safety development.