CAU Scholar's Space: Sohn, Kee Min

Detailed Information

Sohn, Kee Min (손기민)

공과대학 (도시시스템공학)

Research Area: Forecasting traffic speeds, Human activity inference, Measuring with image

Tel 02-820-5850
Homepage

ResearcherID ORCiD Scopus Google Scholar ID ResearchGate

Keyword

Latent variable:4||convolutional neural network (CNN):3||traffic surveillance:3||Smartcard data:3||Variational autoencoder (VAE):3||Reinforcement learning:3||Choice model:2||road capacity:2||life cycle model:2||logregression:2||machine learning:2||maintenance:2||mode share:2||Adaptive traffic signal control:2||network reshuffling:2||traffic density:2||Built environment:2||traffic impact:2||accessibility:2||deep neural network:2||Probabilistic graphical model (PGM):2||defect model:2||Deep convolutional neural network (CNN):2||Expectationmaximization (EM) algorithm:2||transport planning:2||travel behavior:2||Support vector machine (SVM):2||Activitybased model:2||Route choice:2||public transport:2||rail:2||Cheonggye Stream Restoration:2||rail inspection:2||winding lines:2||Computer vision:2||Trip chain:2||Random coefficient:2||Discrete choice model:1||Discretionary lanechanging:1||Duration:1||Entire Path Deletion:1||Expectationmaximization algorithm:1||Express train:1||Factor Analysis:1||Forecasting:1||Freeway:1||Fully connected structural equation:1||Gaussian mixture model:1||Generative adversarial framework:1||Graph convolution:1||Graph convolutional neural network (GCN):1||Hazard:1||Heterogeneity:1||Hidden Markov model (HMM):1||Integrated choice and latent variable (ICLV) model:1||K Shortest Cost Path:1||K path finding algorithm:1||Kmeans:1||Kalman filtering:1||Latent Behaviour:1||Latent Variable:1||Latent variables:1||Leaderfollower relationship:1||Leisurecyclist:1||Link Label:1||Load modeling:1||Loading diversity:1||Loading diversity factor:1||Lorentz transformation:1||Machine learning:1||Maximum likelihood estimation:1||Maximum simulated likelihood:1||Metaheuristics:1||Metro boardings:1||Metro crowding:1||Metro ridership:1||Minkowski metric:1||Mobile data:1||Mode Choice Model:1||Modechoice:1||Model transferability:1||Multicriteria decision:1||Multiobjective genetic algorithm:1||Multiobjective optimization:1||Multiple regression analysis:1||Nested logit model:1||Network design:1||Object detection:1||Optimal Path:1||Optimization:1||Origindestination flow:1||Overpass:1||Pairwise comparison technique:1||Passenger load in transit:1||Passing time:1||Pathsize:1||Pedestrian walking behavior:1||Personal communication networks:1||Platoonbased traffic control:1||Public transportation information:1||RP/SP결합모형:1||Railway Operation:1||Railway Schedule:1||Railway capacity:1||Ranking (statistics):1||Ranking model:1||Regression analysis:1||Regressionbased model:1||Restricted Boltzmann Machine:1||Reversible jump Markov chain Monte Carlo (MCMC) sampler:1||Road diet:1||Route Perception:1||Seemingly unrelated regression (SUR):1||Siding:1||Simulated maximum likelihood:1||Smart cards:1||Social force model:1||Sociodemographic attributes:1||Spatiotemporal dependencies:1||Special relativity:1||Stationtostation level:1||Statistics:1||Structural equation model (SEM):1||TOD:1||TPS:1||TPS 시뮬레이션:1||Throughput maximization:1||Time series analysis:1||Traffic delay estimation:1||Traffic density:1||Traffic management:1||Traffic probe:1||Traffic signal control:1||Traffic speed forecasting:1||Traffic state forecasting:1||Traffic surveillance:1||Traffic volume:1||Train car choice:1||Training:1||Transit oriented development (TOD):1||Transportation networks:1||Travel time:1||Trip purpose:1||Variance analysis:1||Variational Bayes (VB):1||Variational inference:1||Variational inference (VI):1||Vehicle counting:1||alighting locations:1||alternative path set:1||artificial intelligence (AI):1||artificial neural network (ANN):1||autoencoder:1||automatic fare collection system:1||boarding locations:1||bus passengers:1||calibration:1||carbon nanotube:1||clustering:1||collective travel information:1||computational modelling:1||crystal structure prediction:1||crystal system:1||cycleconsistent adversarial network (CycleGAN):1||deep convolutional neural network:1||deep learning:1||deeplearning:1||deeplearning architecture:1||destinations forecasting:1||driver heterogeneity:1||entire path deletion method:1||entryonly smartcard data:1||global shortcut connection:1||high density:1||imagebased learning:1||impact analysis:1||inorganic materials:1||landuse characteristics:1||learning (artificial intelligence):1||macroscopic evaluation:1||metro:1||metro crowding:1||multiregime model:1||networkinnetwork:1||new transportation service index:1||objects as points:1||path planning:1||personal rapid transit:1||piezoresistive:1||portable keypad:1||powder Xray diffraction:1||probe vehicle:1||properties of solids:1||public policy:1||public transportation users:1||random parameter:1||reinforcement learning (RL):1||residual learning:1||revitalization:1||selforganizing map:1||shortest path:1||smart cards:1||space mean speed:1||spatiotemporal dependency:1||station:1||station area:1||statistical analysis:1||supervised machinelearning model:1||tactile sensing:1||throughput:1||traffic engineering:1||traffic information systems:1||traffic prediction:1||traffic signal control systems:1||traffic speed:1||trainstop location:1||transitoriented development:1||transport management:1||twofluid model:1||urban railway:1||user information:1||vehicle counting:1||vehicle detection:1||waiting time:1||waveoff rate:1||경로열거:1||경로인지비용:1||고밀도:1||교통영향분석:1||굴곡도:1||급행열차:1||노선망 재조정:1||대중교통중심개발:1||대피선:1||도로용량축소:1||도시재생:1||도착지기반 최적경로탐색:1||레일:1||로그 회귀분석:1||생애주기:1||수단선택모형:1||수송 분담률:1||신교통지표:1||양방향 최적경로탐색:1||열차 스케쥴:1||영향분석:1||요인분석:1||운전선도:1||유지관리:1||잠재변수:1||잠재행태:1||접근성:1||청계천복원:1||최적경로트리:1||최적링크인지경로트리:1||출발지기반 최적경로탐색:1||탐상:1||통행행태변화:1||AFC system:1||하자모형:1||ATIS:1||Activity chain:1||Activity imputation:1||Activity inference:1||Autoencoder:1||Automobiles:1||Bayesian estimation:1||Bounding ellipse:1||Branch & Bound:1||Branch &Bound:1||CAV:1||Calibration:1||Cameras:1||Car following model:1||Cardependence:1||Carfollowing model:1||Cellular communication system:1||Centrality:1||CentralityClosenessBetweennessStraightnessNeighborhood effectKernel function:1||Changepoint algorithm:1||Collision avoidance:1||Combined RP/SP Model:1||Commutercyclist:1||Computational modeling:1||Conditional generative adversarial networks:1||Connected and autonomous vehicle:1||Continuous hidden Markov model:1||Convolutional neural network:1||Covariate effect:1||Crowd counting:1||CycleGAN:1||Deep Qnetwork:1||Deep belief network:1||Deep graph Qnetwork (DGQN):1||Deep learning:1||Direct demand model:1||

RSS_1.0 RSS_2.0 ATOM_1.0

84, Heukseok-ro, Dongjak-gu, Seoul, Republic of Korea (06974)02-820-6194

Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.

Detailed Information

Keyword

BROWSE