Jin-Su Kim
YOU?
Author Swipe
View article: Fake Electrocardiogram Signal Analysis to Detect Spoofing Attacks in Biometrics
Fake Electrocardiogram Signal Analysis to Detect Spoofing Attacks in Biometrics Open
View article: ECoRAG: Evidentiality-guided Compression for Long Context RAG
ECoRAG: Evidentiality-guided Compression for Long Context RAG Open
Large Language Models (LLMs) have shown remarkable performance in Open-Domain Question Answering (ODQA) by leveraging external documents through Retrieval-Augmented Generation (RAG). To reduce RAG overhead, from longer context, context com…
View article: ECoRAG: Evidentiality-guided Compression for Long Context RAG
ECoRAG: Evidentiality-guided Compression for Long Context RAG Open
View article: Design Optimization of Nuclear Fusion Reactor through Deep Reinforcement Learning
Design Optimization of Nuclear Fusion Reactor through Deep Reinforcement Learning Open
This research explores the application of Deep Reinforcement Learning (DRL) to optimize the design of a nuclear fusion reactor. DRL can efficiently address the challenging issues attributed to multiple physics and engineering constraints f…
View article: Multi-Session Electrocardiogram–Electromyogram Database for User Recognition
Multi-Session Electrocardiogram–Electromyogram Database for User Recognition Open
Current advancements in biosignal-based user recognition technology are paving the way for a next-generation solution that addresses the limitations of face- and fingerprint-based user recognition methods. However, existing biosignal bench…
View article: Multi-Stream Conformer-Based User Identification System Using 2D CQT Spectrogram Tailored to Multiple Biosignals
Multi-Stream Conformer-Based User Identification System Using 2D CQT Spectrogram Tailored to Multiple Biosignals Open
Recent studies actively researching user identification utilizing physiological information to verify identity. However, there is a problem with biometric information exposed to the outside of the body being susceptible to forgery and fals…
View article: Stress Classification Using ECGs Based on a Multi-Dimensional Feature Fusion of LSTM and Xception
Stress Classification Using ECGs Based on a Multi-Dimensional Feature Fusion of LSTM and Xception Open
In the information age, people are increasingly being exposed to stress as societies are experiencing sudden changes fueled by advancements in cutting-edge scientific technology and the Information Technology (IT) industry. Consequently, r…
View article: A Study on the Volatility Clustering of Trading Volume Turnover Ratio: Evidence from a GARCH Model with Asia-Pacific Stock Exchanges Data
A Study on the Volatility Clustering of Trading Volume Turnover Ratio: Evidence from a GARCH Model with Asia-Pacific Stock Exchanges Data Open
View article: High Electrocatalytic Activities of Electrochemically Exfoliated Graphene-Oxide Deposited Carbon Paper Electrodes for the Vanadium Redox Flow Battery
High Electrocatalytic Activities of Electrochemically Exfoliated Graphene-Oxide Deposited Carbon Paper Electrodes for the Vanadium Redox Flow Battery Open
View article: Supervised low-rank semi-nonnegative matrix factorization with frequency regularization for forecasting spatio-temporal data
Supervised low-rank semi-nonnegative matrix factorization with frequency regularization for forecasting spatio-temporal data Open
We propose a novel methodology for forecasting spatio-temporal data using supervised semi-nonnegative matrix factorization (SSNMF) with frequency regularization. Matrix factorization is employed to decompose spatio-temporal data into spati…
View article: Electromyogram Based Personal Recognition Using Attention Mechanism for IoT Security
Electromyogram Based Personal Recognition Using Attention Mechanism for IoT Security Open
As Internet of Things (IoT) technology develops, integrating network functions into diverse equipment introduces new challenges, particularly in dealing with counterfeit issues. Over the past few decades, research efforts have focused on l…
View article: Multi-Session Surface Electromyogram Signal Database for Personal Identification
Multi-Session Surface Electromyogram Signal Database for Personal Identification Open
Surface electromyogram (sEMG) refers to a biosignal acquired from the skin surface during the contraction of skeletal muscles, and a different signal waveform is generated, depending on the motion performed. Therefore, in contrast to gener…
View article: Multi-Stream CNN-Based Personal Recognition Method Using Surface Electromyogram for 5G Security
Multi-Stream CNN-Based Personal Recognition Method Using Surface Electromyogram for 5G Security Open
As fifth generation technology standard (5G) technology develops, the possibility of being exposed to the risk of cyber-attacks that exploits vulnerabilities in the 5G environment is increasing. The existing personal recognition method use…
View article: A study on implementation of real-time intelligent video surveillance system based on embedded module
A study on implementation of real-time intelligent video surveillance system based on embedded module Open
Conventional surveillance systems for preventing accidents and incidents do not identify 95% thereof after 22 min when one person monitors a plurality of closed circuit televisions (CCTV). To address this issue, while computer-based intell…
View article: Two-Step Biometrics Using Electromyogram Signal Based on Convolutional Neural Network-Long Short-Term Memory Networks
Two-Step Biometrics Using Electromyogram Signal Based on Convolutional Neural Network-Long Short-Term Memory Networks Open
Electromyogram (EMG) signals cannot be forged and have the advantage of being able to change the registered data as they are characterized by the waveform, which varies depending on the gesture. In this paper, a two-step biometrics method …
View article: A Study on ECG-based Biometrics using Open Source Hardware
A Study on ECG-based Biometrics using Open Source Hardware Open
Biometric technology uses unique physical features as bioinformation. Electrocardiogram(ECG) isa signal recording potential changes related to heartbeats in the form of voltage, and each individualhas unique ECG signals in terms of heart l…
View article: A Study on EMG-based Biometrics
A Study on EMG-based Biometrics Open
Biometrics is a technology that recognizes user's information by using unique physical features of his or her body such as face, fingerprint, and iris. It also uses behavioral features such as signature, electrocardiogram (ECG), electromyo…
View article: An Energy Consumption Model using Two-Tier Clustering in Mobile Sensor Networks
An Energy Consumption Model using Two-Tier Clustering in Mobile Sensor Networks Open
View article: Cutting Performance of a Developed Small-angle Spindle Tool
Cutting Performance of a Developed Small-angle Spindle Tool Open
View article: Effects of Initial SOC of 270-Volt Battery on Operating Performance of Gasoline Engine and Electric motor in a Parallel Hybrid Vehicle under IM240 Driving Cycle Mode
Effects of Initial SOC of 270-Volt Battery on Operating Performance of Gasoline Engine and Electric motor in a Parallel Hybrid Vehicle under IM240 Driving Cycle Mode Open
Next-generation vehicles are under energy and environmental pressure to increase fuel economy and reduce emissions of green-house-gases (GHG) such as carbon dioxide, which is the main cause of global warming, while maintaining the performa…
View article: A Research for Detour Simulation of Reaction Risk Factor
A Research for Detour Simulation of Reaction Risk Factor Open
건축물의 대형화, 고층화, 심층화는 재난 발생 시 인명안전에 대한 위험성을 증대시켰다. 인명안전을 위해 2007년 성능위주설계가 입법이 되었다. 위험성 평가는 화재해석 프로그램과 대피 시뮬레이션이 사용된다. 대피 시뮬레이션은 $A^*$알고리즘이 사용된다. $A^*$알고리즘은 최단경로 대피가 가능하나 위험인자 감지 및 우회대피는 불가능함으로써 위험인자에 대한 우회대피 기능의 구현 없이 통과하여 대피한 불안전한 특성을 갖는다. …
View article: Study on the Deep Stead Fire Spread Temperature by the Change of the Wood Flour Density
Study on the Deep Stead Fire Spread Temperature by the Change of the Wood Flour Density Open
산업의 발달과 소득의 증가로 인해 목재와 같은 다공성 물질의 수요 및 생산은 지속적으로 증가하고 있다. 축산 농가를 비롯한 가공 산업 분야에서 목분의 활용이 증대됨에 따라 화재 위험도 높아지고 있다. 화재 발생시 목분은 깊이 방향으로 연소의 전이가 발생하며 내부 산화제의 소멸에 따라 화염이 없는 훈소로 진행되기도 한다. 훈소로 진행되는 경우는 화원의 위치 파악 곤란으로 초동진화에 실패하여 2차 피해를 키우는 직접적 원인으로 …
View article: A study on evacuation characteristic by cross-sectional areas and smoke control velocity at railway tunnel fire
A study on evacuation characteristic by cross-sectional areas and smoke control velocity at railway tunnel fire Open
본 연구에서는 정량적 위험도 평가를 위한 시나리오 구축시 제반인자가 화재안전성에 미치는 영향을 검토하기 위하여 대피로 폭에 따른 하차시간을 분석하고 단면적별로 제연풍속, 제연방향, 대피방향의 상관관계에 따른 화재특성 및 대피특성을 분석하였다. 적용 단면적은 복선고속철도는 $97m^2$, 단선고속철도는 $58m^2$, 단선일반철도는 $38m^2$로 하였으며, 터널풍속은 0.5~3.5 m/s 조건으로 하였다. 본 연구 결과, 터…
View article: Electrical Characteristics of Enhancement-Mode n-Channel Vertical GaN MOSFETs and the Effects of Sidewall Slope
Electrical Characteristics of Enhancement-Mode n-Channel Vertical GaN MOSFETs and the Effects of Sidewall Slope Open
Gallium nitride (GaN) is a promising material for next-generation high-power applications due to its wide bandgap, high breakdown field, high electron mobility, and good thermal conductivity. From a structure point of view, the vertical de…
View article: Study on The Status of Welded Parts According to The Types of Shielding Gas in TIG Welding
Study on The Status of Welded Parts According to The Types of Shielding Gas in TIG Welding Open
Tungsten inert gas (TIG) welding is commonly used in industries that require airtightness, watertightness, oiltightness, and precision. It is a non-consumable welding method that is commonly used for the welding of non-ferrous metals, but …
View article: Development of One Day-Ahead Renewable Energy Generation Assessment System in South Korea
Development of One Day-Ahead Renewable Energy Generation Assessment System in South Korea Open
This paper proposes a probabilistic generation assessment model of renewable energy generators(REGs) considering uncertainty of resources, mainly focused on Wind Turbine Generator(WTG) and Solar Cell Generator(SCG) which are dispersed wide…
View article: Presurgical Mapping of Brain Tumors Using Statistical Probabilistic Anatomical Maps
Presurgical Mapping of Brain Tumors Using Statistical Probabilistic Anatomical Maps Open
Purpose: Multi-tracer neuroimaging is widely used for the diagnosis, radiotherapy, and neuro-surgery of brain gliomas. Anatomical and functional information is important to avoid having neurological deficits induced during the resection or…