林显明

Key Skills

Software

Other

Top Subject Matter

Autonomous intelligent vehicle / AI vision for track features

Analog circuits / signal distortion measurement for AI-ready evaluation data

Top Data Types

Image

Text

Video

Top Task Types

Classification

Freelancer Overview

AIElectromagnetic Smart Car — collected track features for AI training model (AI vision + embedded deployment). Brings 1+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Other. Education includes Bachelor of Engineering, Guilin University of Electronic Technology (2022) and Master of Engineering, University of Science and Technology of China (2024). AI-training focus includes data types such as Image and labeling workflows including Classification, Evaluation, and Rating.

Labeling Experience

Nonlinear Amplifier Distortion Research Device — collected ADC measurements and calculated THD for evaluated data sets

OtherImage

Built an analog nonlinear amplifier distortion research device to generate distorted waveforms for quantitative assessment. Used an ADC to collect distorted signals and calculate THD as part of evaluating the experimental outcomes used for model-ready measurements. The work involved producing labeled/evaluable signal data for downstream analysis and comparison across distortion modes. • Implemented multiple waveform distortion modes using analog components • Captured distorted signals through an ADC • Computed THD for objective evaluation of distortion behavior • Produced measurement data across modes for comparative analysis

2020 - 2020

AIElectromagnetic Smart Car — collected track features for AI training model (AI vision + embedded deployment)

OtherImageClassification

Collected track features using a camera and electromagnetic sensors to produce an AI training model for smart-car racing. Converted the collected signals into training inputs and validated the deployed model behavior on the MCU during the race. Focused on preparing and using training data derived from multimodal observations for downstream model use. • Source data acquisition from camera feeds and sensor readings • Training dataset creation from track features and ADC-converted signals • Model deployment on an embedded MCU for real-time inference • Race execution using only electromagnetic sensing with the trained model

2020 - 2020

Education

Work History