본 발명에 따른 목적 기반 차량의 승객 성향 분류 방법은, 목적 기반 차량을 이용하는 승객들의 운전 성향 데이터를 시간 순으로 수집하여 시계열 데이터를 생성하고, 상기 시계열 데이터를 인공 신경망에 의해 학습시켜 차원 축소하여 중간 결과물인 복수의 새로운 피처(feature)를 출력하며, 상기 축소된 차원의 새로운 피처에 K-평균 군집화 알고리즘을 적용하여 상기 승객들의 운전 성향을 분류하도록 이루어진 것을 특징으로 한다.
A method and system for passenger propensity classification for purpose-built vehicles perform operations including: generating time series data by collecting driving propensity data of passengers, who use the purpose-built vehicles, in a time order; outputting a plurality of new features which are an intermediate result by reducing a dimension of the time series data by training the time series data by an artificial neural network; and classifying driving propensities of passengers by applying a K-means clustering algorithm to the new features generated by reducing the dimension of the time series data.
Passenger propensity classification method and system for purpose-built vehicles
목적 기반 차량의 승객 성향 분류 방법 및 시스템
2025-01-07
Patent
Electronic Resource
Korean
FUEL TANK FILLER CONDITIONS - PASSENGER CAR, MULTI-PURPOSE PASSENGER VEHICLES, AND LIGHT DUTY TRUCKS
SAE Technical Papers | 1988
FUEL TANK FILLER CONDITIONS—PASSENGER CAR MULTI-PURPOSE PASSENGER VEHICLES, AND LIGHT DUTY TRUCKS
SAE Technical Papers | 1978
SAE Technical Papers | 2012
Integrated control system for purpose built vehicles reflecting various driver tendencies
European Patent Office | 2024
|