Yeonghyeon Park

Title: Yeonghyeon Park: Innovator in Road Surface Analysis and Anomaly Detection

Introduction

Yeonghyeon Park is a notable inventor based in Cheonan, South Korea. He has made significant contributions to the fields of road surface analysis and anomaly detection. With a total of 6 patents to his name, Park continues to push the boundaries of innovation.

Latest Patents

One of his latest patents is an "Apparatus and method for analyzing road surface condition." This invention analyzes the condition of a road surface by utilizing a frequency-of-interest or a resonance sound in a tire. The method involves sending a training audio signal to a learning unit, a label generator, and a frequency selection model that does not complete learning. The training audio signal is collected from the driving noise generated when a vehicle travels on a road. The label generator creates a label audio-of-interest signal by attenuating frequencies outside the frequency-of-interest band in the training audio signal. The frequency selection model derives a training imitated audio-of-interest signal by applying various operations with unlearned weights to the training audio signal. The learning unit calculates a generation loss, which is the difference between the training imitated audio-of-interest signal and the label audio-of-interest signal, and optimizes the weight of the frequency selection model.

Another significant patent is the "Apparatus and method for anomaly detection." This invention employs an attention mechanism or is based on an artificial neural network to minimize computational costs. The anomaly detection method includes entering input data into a detection network, which generates an attention map and output data through multiple operations involving layer weights. The detection unit creates an attention map by overlapping it with the input data when an attention region with a value above a predetermined threshold is present. It then detects whether the input data is normal or abnormal based on the output data and provides a detection map along with the anomaly detection result.

Career Highlights

Yeonghyeon Park is currently employed at Sk Planet Co., Ltd., where he applies his expertise in developing innovative solutions. His work focuses on enhancing the efficiency and accuracy of road surface analysis and anomaly detection systems.

Collaborations

Park collaborates with talented individuals such as Jong Hee Jung and JongHee Jung, contributing to a dynamic work environment that fosters innovation.

Conclusion

Yeonghyeon Park is a distinguished