• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2019년도 추계학술대회
• /
• pp.169-171
• /
• 2019

This paper proposes an algorithm to detect persons in bitstream domain by skipping a reconstruction picture process in HEVC decoding. A new 3-channel feature extraction map is introduced in this paper by modelling the relationship between bits per CU density, average PU shape in CU, and total transform coefficients in CU from syntax elements. A state-of-the-art of YOLOv3 detection algorithm is used to detect and localize person on extracted feature maps. Based on the experimental results, the proposed person detection framework can achieve mAP of 0.68 and be able to find persons on feature maps. In addition, the proposed person detection can save decoding time about 60% by removing reconstruction picture process.

• 한국생산제조학회지
• /
• 제6권4호
• /
• pp.46-53
• /
• 1997

This paper presents a method of detection localized defects on tapered roller bearing in main spindle of machine tool system. The feature vectors, i.e. statistical parameters, in time-domain analysis technique have been calculated to extract useful features from acoustic emission signals. These feature vectors are used as the input feature of an neural network to classify and detect bearing defects. As a results, the detection of bearing defect conditions could be sucessfully performed by using an neural network with statistical parameters of acoustic emission signals.

• Journal of Communications and Networks
• /
• 제12권6호
• /
• pp.605-615
• /
• 2010

Intercarrier interference (ICI) in orthogonal frequency division multiplexing (OFDM) systems, which causes substantial performance degradation in time-varying fading channels, is analyzed. An equivalent spreading code formulation is derived based on the analogy of OFDM and code division multiple access (CDMA) systems. Techniques as linear multiuser detection in CDMA systems are applied to suppress the ICI in OFDM systems. The performance of linear detection, measured using multiuser efficiency and asymptotic multiuser efficiency, is analyzed given the assumption of perfect channel state information (CSI), which serves as an upper bound for the performance of practical systems. For systems without CSI, time domain and frequency domain channel estimation based linear detectors are proposed. The performance gains and robustness of a linear minimum mean square error (LMMSE) filter over a traditional filter (TF) and matched filter (MF) in the high signal-to-noise ratio (SNR) regime are demonstrated with numerical simulation results.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2008년도 제39회 하계학술대회
• /
• pp.1541-1542
• /
• 2008

In this paper, we introduce a live wire power transmission line fault detection system using time-frequency domain reflectometry(TFDR). The TFDR is known that is more precise method than the other conventional ones. However, the TFDR is generally adopted only in fault detection for communication cable, and dead line power transmission line. Therefore, this paper suggests a TFDR system with coupler which separates 220V, 60Hz signal and TFDR reference signal for implementation the live wire fault detection system. This approach is verified by circuit simulation.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 하계종합학술대회 논문집(4)
• /
• pp.381-384
• /
• 2002

In speech signal processing, it Is very important to detect the pitch exactly in speech recognition, synthesis and analysis. but, it is very difficult to pitch detection from speech signal because of formant and transition amplitude affect. therefore, in this paper, we proposed a pitch detection using the spectrum flattening techniques. Spectrum flattening is to eliminate the formant and transition amplitude affect. In time domain, positive center clipping is process in order to emphasize pitch period with a glottal component of removed vocal tract characteristic. And rough formant envelope is computed through peak-fitting spectrum of original speech signal in frequency domain. As a results, well get the flattened harmonics waveform with the algebra difference between spectrum of original speech signal and smoothed formant envelope. After all, we obtain residual signal which is removed vocal tract element The performance was compared with LPC and Cepstrum, ACF 0wing to this algorithm, we have obtained the pitch information improved the accuracy of pitch detection and gross error rate is reduced in voice speech region and in transition region of changing the phoneme.

• Journal of information and communication convergence engineering
• /
• 제15권4호
• /
• pp.244-249
• /
• 2017

Wearable sensor-based gait analysis has been widely conducted to analyze various aspects of human ambulation abilities under the free-living condition. However, there have been few research efforts on using wearable sensors to analyze human walking on an unstable surface such as on a ship during a sea voyage. Since the motion of a ship on the unstable sea surface imposes significant differences in walking strategies, investigation is suggested to find better performing wearable sensor-based gait analysis algorithms on this unstable environment. This study aimed to compare two representative gait event algorithms including time domain and frequency domain analyses for detecting heel strike on an unstable platform. As results, although two methods did not miss any heel strike, the frequency domain analysis method perform better when comparing heel strike timing. The finding suggests that the frequency analysis is recommended to efficiently detect gait event in the unstable walking environment.

• 정보처리학회논문지:컴퓨터 및 통신 시스템
• /
• 제1권1호
• /
• pp.55-60
• /
• 2012

최근 봇넷(Botnet)은 탐지 기술을 피하기 위하여 C&C(Command and Control)서버 접속시 DNS(Domain Name System) 서비스를 이용하고 있다. DNS 서비스를 이용한 비정상 행위에 대응하기 위해서 DNS 트래픽 기반의 분석 연구가 필요하다. 본 논문에서는 좀비PC의 C&C서버 도메인주소 질의와 같은 DNS트래픽 기반의 비정상 도메인 분류(Classification)를 위해서 DNS트래픽 수집 및 지도학습(Supervised Learning)에 대해 연구한다. 특히, 본 논문에서는 PCA(Principal Component Analysis) 주성분분석 기술을 통해 DNS 기반의 분류시스템에서의 효과적인 분석 성분들을 구성할 수 있다.

• 로봇학회논문지
• /
• 제18권3호
• /
• pp.346-351
• /
• 2023

With the release of numerous open driving datasets, the demand for domain adaptation in perception tasks has increased, particularly when transferring knowledge from rich datasets to novel domains. However, it is difficult to solve the change 1) in the sensor domain caused by heterogeneous LiDAR sensors and 2) in the environmental domain caused by different environmental factors. We overcome domain differences in the semi-supervised setting with 3-stage model parameter training. First, we pre-train the model with the source dataset with object scaling based on statistics of the object size. Then we fine-tine the partially frozen model weights with copy-and-paste augmentation. The 3D points in the box labels are copied from one scene and pasted to the other scenes. Finally, we use the knowledge distillation method to update the student network with a moving average from the teacher network along with a self-training method with pseudo labels. Test-Time Augmentation with varying z values is employed to predict the final results. Our method achieved 3rd place in ECCV 2022 workshop on the 3D Perception for Autonomous Driving challenge.

• 한국광학회지
• /
• 제23권1호
• /
• pp.23-31
• /
• 2012

본 논문에서는 근적외선(NIR, near-infrared) 영역의 레이저 광원 및 광검출기를 이용한 주파수영역(frequency-domain) 확산 광이미징(DOI, diffuse optical imaging) 시스템을 구현하였다. 검출신호의 진폭 및 위상 추출에는 70MHz의 단일 변조주파수를 사용하는 호모다인(homodyne) 검출기법을 적용하였으며, 4개의 검출기를 이용해 동시측정이 가능하도록 시스템을 최적화하였다. 각 검출기들이 서로 다른 결합계수(coupling coefficient)를 가짐으로써 발생하는 진폭 및 위상의 편차를 보정하였다. 본 논문에서 제작한 DOI 시스템을 이용하여, 생체조직을 모사한 액체팬텀에 이형성분(anomaly)을 삽입하여 흡수 및 산란 분포에 대한 영상을 복원함으로써 이형성분의 위치 및 광학적 특성에 대한 정보를 획득하였으며, 단일 광검출기를 사용하는 순차적인 측정에 의한 결과보다 영상복원 성능이 개선되었음을 보였다. 또한, 동일한 액체팬텀에 대해서, 측정위치를 이동해가며 각 단층 슬라이스에 대한 흡수계수 및 산란계수 분포영상을 복원함으로써 구현된 시스템을 이용해 단층촬영이 가능함을 보였다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.539-542
• /
• 2003

A motor is the workhorse of our industry. The issues of preventive and condition-based maintenance, online monitoring, system fault detection, diagnosis, and prognosis are of increasing importance. Different internal motor faults (e.g., inter-turn short circuits, broken bearings, broken rotor bars) along with external motor faults (e.g., phase failure, mechanical overload, blocked rotor) are expected to happen sooner or later. This paper introduces the fault detection technique of induction motors based upon the stator current. The fault motors have rotor bar broken or rotor unbalance defect, respectively. The stator currents are measured by the current meters and stored by the time domain. The time domain is not suitable to represent the current signals, so the frequency domain is applied to display the signals. The Fourier Transformer is used for the conversion of the signal. After the conversion of the signals, the features of the signals have to be extracted by the signal processing methods like a wavelet analysis, a spectrum analysis, etc. The discovered features are entered to the pattern classification model such as a neural network model, a polynomial neural network, a fuzzy inference model, etc. This paper describes the fault detection results that use wavelet decomposition. The wavelet analysis is very useful method for the time and frequency domain each. Also it is powerful method to detect the features in the signals.