The present technology relates to a spiking neural network-based risk driving behavior predicting system and a method. According to an implementation example of the present embodiment, in predicting a risk driving behavior through a spiking neural network (SNN), which models actual nerve cell characteristics based on biological plausibility, a structure of the spiking neural network is simple compared to an existing artificial neural network, and thus computational complexity can be reduced. Additionally, based on a lightweight device, optimal risk driving behavior prediction can be performed with a low electric power. As a result, versatility of the driving risk predicting system can be improved. The spiking neural network-based risk driving behavior predicting system of the present invention comprises: a memory; and at least one processor.
본 기술은 스파이크 신경망 기반 위험운전행동 예측 시스템 및 방법에 관한 것으로, 본 실시예의 구현 예에 따르면, 생물학적 타당성에 기반하여 실제 신경세포 특징을 모델링한 스파이크 신경망(Spiking Neural Network, SNN)을 통해 위험운전행동을 예측함에 있어, 스파이크 신경망의 구조가 기존의 인공신경망과 비교하여 단순하고 이에 연산 복잡도를 줄일 수 있고, 경량의 디바이스에 의거 최적의 위험운전행동 예측을 저전력으로 수행할 수 있고, 이에 운전위험 예측 시스템의 범용성을 향상시킬 수 있다.
SYSTEM AND METHOD FOR PREDICTING DANGEROUS DRIVING BEHAVIOR USING SPIKING NEURAL NETWORK
스파이크 신경망 기반으로 위험운전행동 예측 시스템 및 방법
26.10.2023
Patent
Elektronische Ressource
Koreanisch
IPC: | B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen |
Europäisches Patentamt | 2025
|Europäisches Patentamt | 2022
|Europäisches Patentamt | 2021
|