UKUi-Jin Kim

Ui-Jin Kim

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Ui-Jin Kim has a total of 5 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Development of an Event-Driven Low-Power Wireless System for Structural Health Monitoring of Advanced Air Mobility

    by Ji-Wan Choi, Ui-Jin Kim, In-Ha Kang, Chang-Yull Lee

    Advanced Air Mobility (AAM) vehicles may experience impacts from bird strikes and foreign object debris, motivating in-flight structural health monitoring (SHM). Periodically sampled wireless sensor networks impose a trade-off between polling delay and repeated wake-up energy. We developed an event-driven wireless SHM system in which physical sensor-line severance triggers a hardware interrupt. Flash power gating, MCU Stop 2 mode, autonomous SX1262 RX duty cycling, and compact 16-byte event records reduce power consumption and active transmission time. The hardware includes a TVS diode for electrostatic-discharge (ESD) protection and a shielded enclosure for electromagnetic-interference (EMI) mitigation. Impact tests measured a wake-up/ISR latency of 58.80 μs from sensor disconnection to ISR entry. Across three preliminary drone-hovering runs, 289 of 300 LoRa PHY frames passed CRC, yielding a 96.3% delivery rate and 2890 valid event records from 3000 transmitted records. The estimated net standby current was 516 μA, corresponding to a model-based battery life of 13.2 months under once-daily transmission. These results support physical sensor-line severance as a low-power trigger for rare-event notification in AAM monitoring.

  • Open Access

    Temperature Calibration Using Machine Learning Algorithms for Flexible Temperature Sensors

    by Ui-Jin Kim, Ju-Hun Ahn, Ji-Han Lee, Chang-Yull Lee

    Thermal imbalance can cause significant stress in large-scale structures such as bridges and buildings, negatively impacting their structural health. To assist in the structural health monitoring systems that analyze these thermal effects, a flexible temperature sensor was fabricated using EHD inkjet printing. However, the reliability of such printed sensors is challenged by complex dynamic hysteresis under rapid thermal changes. To address this, an LSTM calibration model was developed and trained exclusively on quasi-static data across the 20–70 °C temperature range, where it achieved a low prediction error, a 33.563% improvement over a conventional polynomial regression. More importantly, when tested on unseen dynamic data, this statically trained model demonstrated superior generalization, reducing the RMSE from 12.451 °C for the polynomial model to 4.899 °C. These results suggest that data-driven approaches like LSTM can be a highly effective solution for ensuring the reliability of flexible sensors in real-world SHM applications.