Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


In-Soo Lee has a total of 84 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Mitigating Representation-Dependent Degradation in Acoustic Signal-Based Fault Diagnosis of BLDC Motors via Classifier-Independent Waveform Restoration

    by Seon Min Yoo, Hwi Gyo Lee, Wang Ke Hao, In Soo Lee

    Industrial noise can degrade acoustic fault diagnosis differently across input representations. This study evaluated whether classifier-independent waveform restoration could reduce this disparity in BLDC motor diagnosis. A Wave-U-Net denoiser was trained without classifier losses or outputs and applied before generating time-domain waveform and STFT magnitude inputs for six CNN, LSTM, and CNN–LSTM classifiers, which remained unchanged. The dataset comprised 13,790 one-second acoustic segments recorded from a single BLDC motor under normal operating conditions and bearing, eccentricity, and electrical fault conditions. Industrial noise environments were simulated by mixing the recorded motor signals with external noise recordings from the MIMII dataset. At 0 dB, restoration increased mean classification accuracy from 69.27% to 97.37% and reduced the mean performance gap between the two input representations from 48.61 to 1.01 percentage points. Improvements were also observed at evaluated SNRs below the training range and under noise types excluded from denoiser training. Grad-CAM and feature-space analyses indicated that restoration shifted decision patterns and class-wise feature structures toward those observed without added industrial noise. These findings support waveform restoration as a common preprocessing approach for reducing representation-dependent degradation under the evaluated conditions.

  • Open Access

    IMU-Based Time-Domain Fault Diagnosis of BLDC Motors Using an End-to-End 1D-CNN

    by Ke Hao Wang, Hwi Gyu Lee, Seon Min Yoo, In Soo Lee

    Reliable fault detection in brushless DC motors is challenging owing to environmental complexity and high equipment costs. To address these challenges, we propose an effective and cost-effective approach using an optimized end-to-end one-dimensional convolutional neural network. Specifically, a real experimental platform simulating bearing and eccentricity faults was developed. Statistical t-tests indicated that three-axis accelerometer signals from a low-cost inertial measurement unit provided sufficient fault information for the present diagnosis task. Unlike traditional methods such as support vector machines, multilayer neural networks, and random forests, which rely on manual feature extraction, our model learns directly from raw waveforms and can handle signal drift. Under the present controlled experimental setting and the leave-one-day-out evaluation protocol, the model achieved 100.00% average window-level classification accuracy, considerably outperforming traditional methods, the performances of which declined to 67.95–71.37% under environmental shifts. Moreover, with an inference time of only 0.96 ms, 32 times faster than that of random forests, this approach is well suited for real-time embedded monitoring. The proposed method demonstrates strong potential for cost-efficient and robust fault diagnosis under the present experimental setting.

  • Implementation of a User-Friendly Door Safety Control System based on Sensor Fusion

    by Da-Yeon Lee, Da-In Kang, Yeon-Woo Kwon, Jang-Hun Lee, In-Soo Lee

    가정 내 문 개폐 과정에서 발생하는 끼임 및 충돌 사고는 특히 아동과 고령자에게 발생하는 심각한 위험 요인이다. 이에 따라 본 연구는 문손잡이 조작, 문의 움직임, 반대편 위험 요소를 실시간으로 통합 감지 및 판단하여 사고를 방지하는 지능형 도어 제어 시스템을 제안한다. 제안 시스템은 터치, IMU(Inertial Measurement Unit), 초음파, IR(Infrared) 센서로 구성된 문손잡이 모듈과 액추에이터 및 브레이크를 포함한 제어 모듈로 구성되며, 각 모듈은 RF(Radio Frequency) 통신을 통해 통신한다. 실험을 통해 센서 간 통신의 안정성과 상황 기반 제어의 신뢰성을 검증하였으며, 초음파 센서를 지면 기준 약 50도 방향으로 설치할 경우 유아나 낮은 장애물도 감지함을 확인하였다. 제안 시스템은 부착형 모듈 형태로 구현되어 기존 문 구조를 변경하지 않고도 설치 가능하며, 다양한 환경의 적용이 가능하다.

  • Design and Implementation of a Smart Suitcase with User-Following and Anti-Theft Features

    by Eun-Ju Do, Jun-Ho Lee, Hyo-Geun Yoo, Sun-Ho Kim, Song-Mi Kwon, In-Soo Lee

    본 연구에서는 자동 추종 기능과 능동적 도난 방지 메커니즘을 통합한 스마트 캐리어를 제안한다. 제안된 시스템은 BLE RSSI를 활용한 거리 추정과 IMU 기반 헤딩 정보를 통해 사용자의 이동을 안정적으로 추종하며, 엔코더 기반 바퀴 잠금, ToF 센서를 이용한 들림 감지, 사이렌 알람을 연동하여 도난 시도에 실시간 대응할 수 있도록 설계하였다. 실험 결과, 제안된 스마트 캐리어는 2m 이내 거리 추정에서 높은 정확도를 보였고, 헤딩 추종 과정에서 약 6° 이하의 오차만 발생하여 안정적인 제어 성능을 입증하였다. 이를 통해 본 연구는 기존 제품이 단순 추종과 사후 신고에 머물렀던 한계를 넘어, 도난 예방과 사후 대응을 동시에 제공하는 지능형 이동 플랫폼으로 발전할 수 있음을 보여준다.

  • Open Access

    Time-Domain and Neural Network-Based Diagnosis of Bearing Faults in Induction Motors Under Variable Loads

    by Hwi Gyo Lee, Seon Min Yoo, Wang Ke Hao, In Soo Lee

    Bearing faults are the most common type of failure in induction motors, given their long operating times and mechanical loads. Because induction motors in industrial environments operate under various load conditions, effective methods for diagnosing bearing faults across these conditions have become increasingly important. Here, different load conditions were implemented with a powder clutch and a tension controller, and vibration data were acquired under both normal and faulty bearing conditions. To ensure diagnostic accuracy while improving time efficiency, a model bank-based fault diagnosis classifier is proposed, which utilizes independent classifiers trained for each load condition. For comparison, a single model-based classifier trained on all load conditions is also implemented. Both approaches are validated with three classifiers: support vector machine (SVM), multilayer neural network (MNN), and random forest (RF), with three input types: raw time-series signals, six statistical features, and three t-test–selected statistical features. Experimental results reveal that the model bank-based fault diagnosis classifier utilizing three statistical features selected by t-test maintained 98–100% accuracy while reducing operating time compared with Method 1 by 60.0, 71.2, and 60.0% for SVM, MNN, and RF, respectively. These results confirm that the proposed Method 2 utilizing time-domain analysis provides reliable and time-efficient performance for bearing fault diagnosis under variable load conditions.


  • Frequency-Domain Fault Diagnosis of Induction Motors using a Low-Cost Piezoelectric Sensor

    by Hwi Gyo Lee, Seon Min Yoo, Wang Ke Hao, In Soo Lee

    본 논문에서는 저가형 압전 센서를 이용하여 주파수 영역에서 유도전동기의 고장을 진단하는 시스템을 구현하였다. 정상, 회전자 고장 및 베어링 고장 상태의 유도전동기를 가진 시뮬레이터를 활용하여 진동 데이터를 수집하였고, 수집된 데이터를 주파수 영역으로 변환하기 위해 FFT(Fast Fourier Transform)를 적용하였다. 변환된 주파수 영역의 데이터를 입력 벡터로 하여 MNN(Multilayer Neural Network)과 1D-CNN(1D-Convolutional Neural Network) 모델을 구성하고, 두 모델 간 분류 성능을 비교하는 컴퓨터 시뮬레이션을 수행하였다. 또한, 학습된 모델을 기반으로 Raspberry Pi와 GUI를 활용한 실시간 고장 진단 프로그램을 개발하였으며, 실제 환경에서 진단 성능을 분석함으로써 저가형 하드웨어 기반에서도 효과적인 고장 진단 시스템을 구현할 수 있음을 실험적으로 검증하였다.

  • Open Access

    Induction Motor Fault Diagnosis Using Low-Cost MEMS Acoustic Sensors and Multilayer Neural Networks

    by Seon Min Yoo, Hwi Gyo Lee, Wang Ke Hao, In Soo Lee

    Induction motors are the dominant choice in industrial applications due to their robustness, structural simplicity, and high reliability. However, extended operation under extreme conditions, such as high temperatures, overload, and contamination, accelerates the degradation of internal components and increases the likelihood of faults. These faults are challenging to detect, as they typically develop gradually without clear external indicators. To address this issue, the present study proposes a cost-effective fault diagnosis system utilizing low-cost MEMS acoustic sensors in conjunction with a lightweight multilayer neural network (MNN). The same MNN architecture is employed to systematically compare three types of input feature representations: raw time-domain waveforms, FFT-based statistical features, and PCA-compressed FFT features. A total of 5040 samples were used to train, validate, and test the model for classifying three conditions: normal, rotor fault, and bearing fault. The time-domain approach achieved 90.6% accuracy, misclassifying 102 samples. In comparison, FFT-based statistical features yielded 99.8% accuracy with only two misclassifications. The FFT + PCA method produced similar performance while reducing dimensionality, making it more suitable for resource-constrained environments. These results demonstrate that acoustic-based fault diagnosis provides a practical and economical solution for industrial applications.


  • Micro-Controller and Intelligent Theory based Fault Diagnosis of Induction Motors

    by Jong Hyun Lee, Young Ryu, Chang Wook Oh, In-Soo Lee

    본 논문에서는 라즈베리파이 5와 지능이론(Intelligent theory)을 이용한 유도전동기 고장진단시스템을 제안하였다. 제안한 방법에서는 유도전동기 시뮬레이터를 통해 획득한 진동 데이터를 신경회로망 모델로 학습하였고 라즈베리파이 5를 사용하여 데이터 수집 및 진단 시스템 동작을 하나의 컨트롤러로 수행하였다. 또한 진단 결과를 터치스크린과 GUI(Graphical User Interface)를 통해 사용자가 직접 확인할 수 있다. 시스템의 성능은 유도전동기의 시뮬레이터에서 획득한 데이터를 사용하여 진단 실험 결과를 통해 시스템의 성능을 확인하였으며, CNN(Convolutional Neural Network), SVM(Support Vector Machine) 및 MNN(Multi-layer Neural Network)과의 고장진단 성능을 비교하였다.

  • Implementation of a Smart Diffuser based on Deep Learning and User's Emotion Recognition

    by Won-Hyeok Jang, Ji-Hwan Pyo, Joo-Sung Kim, Woo-Won Choi, Jin-Young Hwang, Jin-Han Jung, In-Soo Lee

    본 논문에서는 사용자의 감정상태를 인식하여 적절한 향을 낼 수 있는 딥러닝 기반의 스마트 디퓨저를 제안한다. 시스템의 전면부에 위치한 카메라센서를 통해 사용자의 얼굴표정을 인식하고, 이를 CNN을 이용한 감정인식모델을 통해 분석하여 결과값을 바탕으로 향을 자동으로 택한다. 또한 감정 유사도를 분석하여 감정의 깊이에 따라 팬의 세기를 제어하며 온습도 상황에 변동에도 일정한 정도의 발향을 위해 온습도 센서를 통해 팬의 동작시간을 조절한다. 동작예시로 행복감정을 인식하여 95.42%의 감정유사도와 25.7℃와 습도 67.3%에서 42초간 동작하였다. 본 논문에서는 스마트 디퓨저의 설계와 동작과정, CNN기반 감정분석모델과 프로토타입 동작실험 및 고찰에 대해 기술한다.