고광호 교수
Gwang-ho Ko
성균관대학교 응용AI융합학부 · 공학
연구실 소개
고광호 교수의 연구실은 자동차의 연료 소비와 이산화탄소 배출을 정밀하게 분석하고 최적화하는 데 초점을 맞추고 있습니다. 차량의 GPS 및 OBD 데이터를 기반으로 한 딥러닝 기반 연비 예측 모델과, 연료차단 기능의 효율적 활용 전략을 연구하며, 특히 고속도로 내리막 주행에서의 CO₂ 감축 가능성을 실증하고 있습니다. 또한 기업의 신용 리스크 예측과 주택 가격 변동 요인 분석을 통해 교통, 에너지, 금융 분야의 데이터 기반 정책 제안에도 기여하고 있습니다.
연구 현황
연구 성과 추이
표시된 성과는 수집된 데이터 기준으로 산출되며, 일부 차이가 있을 수 있습니다.
주요 논문
15A monitoring method for energy consumption of vehicles is proposed in the study. It is necessary to have parameters estimating fuel economy with GPS data obtained while driving in the proposed method. The parameters are trained by fuel consumption data measured with a data logger for the reference cars. The data logger is equipped with a GPS sensor and OBD connection capability. The GPS sensor measures vehicle speed, acceleration rate and road gradient. The OBD connector gathers the fuel consump
The South Korean residential real estate market is influenced by both the traditional dynamics of demand and supply and external factors such as housing policies and macroeconomic conditions. Considering the proportion of housing assets in individual wealth, market fluctuations can have significant implications. While previous studies have utilized variables such as GDP growth rate, patent issuance, and birth rate, and employed models such as LSTM and ARIMA for housing price predictions, many ha
엔진 회전속도가 1,500rpm 이상 일 때 차량의 가속 페달을 놓은 경우 인젝터 연료분사가 중지된다. 이것을 연료차단(fuel-cut) 기능이라 부르고, 현대의 대부분의 차량들은 이 기능을 장착하고 있다. 이 기능은 많은 경우 고속도로의 내리막 구간에서 작동된다. 이렇게 연료차단이 발생하는 경우 차량의 <TEX>$CO_2$</TEX> 배출 가스는 '0'이 된다. 서해안 고속도로에서 이 연료 차단 기능을 사용하면 2,000cc 승용차의 <TEX>$CO_2$</TEX> 배출량은 4% 감소한다. 그리고 내리막 구간의 경우 가장 효율적인 운전 패턴을 찾기 위하여 연료차단 기능을 AVL사의 CRUISE 소프트웨어로 시뮬레이션 하였다. 연비향상을 위해서 급격한 내리막 구간일 경우 연료 차단을 위한 차량의 하한 속도를 높게 유지해야 한다는 것을 CRUISE 소프트웨어 시뮬레이션으로 알 수 있었다. 또한 가장 우수한 연비 성능은 내리막 구간 내에서 연료차단과 재가속이 완료되어야 함을 알 수 있었
Abstract : The fuel is not injected when the driver doesn't push acceleration pedal of a vehicle with engine speed higher than about 1,500rpm above mid vehicle speed range. This is called “fuel-cut function” and almost every modern vehicle is equipped with this function. This is activated on downhill part of a highway most often. Therefore the vehicle- exhausted CO 2 can be zero in this downhill part if the driver could recognize this part of highway. We compared the vehicle-exhausted CO 2 emiss
The reduction rate of fuel consumption by showing the fuel injection data for driver was measured in this study. The fuel injection data are composed of injection period, real time fuel economy and average fuel economy. The fuel consumption was measured by processing the voltage signal of injector and driven distance by GPS sensor. The fuel consumption was reduced by driving more carefully, i.e driving more steady without sudden acceleration and deceleration watching these fuel injection data. T
Vehicle fuel consumption increases as driving speed, engine displacement and road surface roughness goes up. But the relation between these factors is not formulated yet. If the vehicle fuel consumption can be calculated for driving speed, engine size and road surface roughness, it will be very helpful for road construction, vehicle driving schedule and transportation policy. Fuel consumption was measured for different driving speeds, engine size and road roughness in this study. The test drivin
In this paper, design methodology for printed circuit board (PCB) coils aimed at reducing temperature in domestic induction cooktops is proposed. To evaluate the thermal behavior according to the trace width, number of turns, and trace spacing, single-layer coil structures are developed and tested. To verify the applicability in IH cooktop systems, multilayer coil configurations are also designed and tested. By comparing the maximum temperature measured for each coil design through simulation an
This study investigates the prediction of small and medium-sized enterprise (SME) default rates in Republic of Korea by comparing the performance of three prominent time-series forecasting models: ARIMA, SARIMA, and Prophet. The research utilizes a comprehensive dataset provided by the Korea Credit Guarantee Fund (KODIT), which covers regional and monthly default rates from January 2012 to December 2023, spanning 12 years. By focusing on Republic of Korea’s 17 major cities, the study aims to ide
대표 연구 분야
고광호 교수의 연구를 Nubint에서 더 깊이 살펴보세요
이 연구실의 논문을 앱에서 열어 AI와 함께 읽고, 핵심을 요약하고, 내 글에 인용하세요.