• International conference on construction engineering and project management
• /
• 2020.12a
• /
• pp.455-462
• /
• 2020

Noise which is unwanted sound is a serious pollutant that can affect human health, as well as the working and living environment if exposed to humans. However, current noise management on the construction project is generally conducted after the noise exceeds the regulation standard, which increases the conflicts with inhabitants near the construction site and threats to the safety and productivity of construction workers. To overcome the limitations of the current noise management methods, the activities of construction equipment which is the main source of construction noise need to be managed throughout the construction period in real-time. Therefore, this paper proposed a framework for automatically detecting noise sources in construction sites in real-time based on convolutional neural networks (CNNs) according to the following four steps: (i) Step 1: Definition of the noise sources; (ii) Step 2: Data preparation; (iii) Step 3: Noise source classification using the audio CNN; and (iv) Step 4: Noise source detection using the visual CNN. The short-time Fourier transform (STFT) and temporal image processing are used to contain temporal features of the audio and visual data. In addition, the AlexNet and You Only Look Once v3 (YOLOv3) algorithms have been adopted to classify and detect the noise sources in real-time. As a result, the proposed framework is expected to immediately find construction activities as current noise sources on the video of the construction site. The proposed framework could be helpful for environmental construction managers to efficiently identify and control the noise by automatically detecting the noise sources among many activities carried out by various types of construction equipment. Thereby, not only conflicts between inhabitants and construction companies caused by construction noise can be prevented, but also the noise-related health risks and productivity degradation for construction workers and inhabitants near the construction site can be minimized.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.4
• /
• pp.959-966
• /
• 2010

Quantitative ultrasound analysis provides fundamental information of various ultrasound parameters using spectral information of the short-gated radiofrequency(RF) data. Therefore, accurate extraction of spectral information from backscattered RF signal is crucial for further analysis of medical ultrasound parameters. In this paper, we propose two techniques for calculating a more accurate power spectrum which are based on the phase-compensation using the normalized cross-correlation to minimize estimation errors due to phase variations, and the weighted averaging technique to maximize the signal-to-noise ratio(SNR). The simulation results demonstrate that the proposed method estimates better results with 10% smaller estimation variances compared to the conventional methods.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.22 no.9
• /
• pp.825-829
• /
• 2012

The global warming caused the changes of our environment like an increasing tropical night phenomenon in the middle latitude areas. Especially, in Korea, the habitats of tropical Korean blockish cicada have changed from Jeju island located in Southern part of Korea to the whole of Korea because of the increasingly warming weather. The cicadas crying sound have been social problem because the tropical Korean blockish cicadas cry at middle of the night owing to the various outdoor lights. The cicada is positive phototaxis insect. So, the cicada is not cry at night. But if the outdoor light is very bright, then the cicada confuse the night as a day and start to cry. As a result, the cicadas crying noise has caused the resident living in downtown to an unpleasure and sleeplessness. In this research, we have measured three kinds of cicada singing noise at 16 points of urban area(Incheon, Gwangju, Busan, Gyeonggido Anyang). And then we analyzed the sound quality of the three kinds of cicada singing noise using by CADA-X signal process program. And we analyzed the acoustical characteristics by STFT(short time Fourier transform) which is a time-frequency analysis method. The characteristics of the cicada singing noise in terms of the sound quality and the time-frequency variation will be usefull to discover the relations between the human annoyance about the cicada singing noise and the acoustical characteristics.

• KIEE International Transactions on Electrophysics and Applications
• /
• v.3C no.2
• /
• pp.59-65
• /
• 2003

Electrical properties such as permittivity and tan$\delta$ of unaged (control) and aged (72 h at 18$0^{\circ}C$) mica/epoxy composites of 130 ${\mu}{\textrm}{m}$ thickness were measured and their surface conditions were characterized using scanning electron microscopy (SEM), Fourier transform infrared (FTIR), electron spectroscopy for chemical analysis (ESCA), differential scanning calorimetry (DSC) and thermogravimetric analysis (TGA). Both permittivity and tan6 of control specimens were higher than those of short-time aged specimens. FTIR results show a new peak at 1710 $cm^{-1}$ / for short-time aged specimens, originating from carbonyl group formed by the oxidation reaction during the aging process. ESCA results show that the binding energy at 532.9 eV representing the singlet state of oxygen ( $O_{1s}$) decreases by 13.7%, whereas that at 534.6 eV increases by 13.7%. Glass transition temperatures of control and short-time aged specimens are observed to be 95.4$^{\circ}C$ and 113.4$^{\circ}C$, which increase with the increase of aging time. TGA results indicate that the control specimens contain a smaller amount of volatile components than the short-time aged specimens.s.

• Proceedings of the KIPE Conference
• /
• 2013.11a
• /
• pp.63-64
• /
• 2013

Induction motors' faults detection is almost a popular topic among researchers. Monitoring the output of motors is a key factor in detecting these faults. (Short-time) Fourier, (continuous, discrete) wavelet, and extended Park vector transformations are among the methods for fault detection. One major deficiency of these methods is not being able to detect the severity of faults that carry low energy information, e.g. in ball bearing system failure, there is absolutely no way to detect the severity of fault using Fourier or wavelet transformations. In this paper, the authors have applied the Discrete Wavelet Transform (DWT) frequency-domain analysis to detect bearing faults in an induction motor. In other words, in discrete transform which the output signal is decomposed in several steps and frequency resolution increases considerably, the frequency-band analysis is performed and it will be verified that first of all, fault sidebands become more recognizable for detection in higher levels of decomposition, and secondly, the inner race bearing faults turn out easier in these levels; and all these matter because of eliminating the not-required high energy components in lower levels of decomposing.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.23 no.1
• /
• pp.85-95
• /
• 2012

In this thesis, we develop a spectral analysis scheme to eliminate the spurious peaks generated in HRR Millimeterwave Seeker based on FMICW system. In contrast to FMCW system, FMICW system generates spurious peaks in the spectrum of its IF signal, caused by the periodic discontinuity of the signal. These peaks make the accuracy of the system depend on the previously estimated range if a band pass filter is utilized to eliminate them and noise floor go to high level if random interrupted sequence is utilized and in case of using staggering process, we must transmit several waveforms to obtain overlapped information. Using the spectral analysis one of the schemes such as IAA(Iterative Adaptive Approach) and SPICE(SemiParametric Iterative Covariance-based Estimation method) which were introduced recently, the spurious peaks can be eliminated effectively. In order to utilize IAA and SPICE, since we must distinguish between reliable data and unreliable data and only use reliable data, STFT(Short Time Fourier Transform) is applied to the distinguishment process.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2002.05a
• /
• pp.286-290
• /
• 2002

두뇌-컴퓨터 인터페이스(brain-computer interface)를 적용하기 위한 연구로서 주어진 문제에서 긍/부정을 선택할 때 나타나는 뇌파를 분별하기 위해서 시간-주파수 분석을 하였다. 단시간 퓨리에 변환(short time fourier transform : STFT)을 하여 긍/부정 선택시 뇌파의 시간-주파수 변화량을 보고, 시간-주파수 분해능이 좋은 웨이블릿 변환(wavelet transform)을 적용하여 서로 비교하였다. 두 가지 분석에서 공통된 결과는 주로 RT전 0.5초 주위에서 유의미한 결과를 나타내었고, 웨이블릿 분석에서 더 좁은 구간에 나타나며, 통계적으로 더 유의미한 결과를 나타내었다.

• The Journal of the Acoustical Society of Korea
• /
• v.35 no.4
• /
• pp.303-309
• /
• 2016

This paper proposes a novel approach to the problem of audio signal clustering using a stacked autoencoder. The proposed stacked autoencoder learns an efficient representation for the input signal, enables clustering constituent signals with similar characteristics, and therefore the original sources can be separated based on the clustering results. STFT (Short-Time Fourier Transform) is performed to extract time-frequency spectrum, and rectangular windows at all the possible locations are used as input values to the autoencoder. The outputs at the middle, encoding layer, are used to cluster the rectangular windows and the original sources are separated by the Wiener filters derived from the clustering results. Source separation experiments were carried out in comparison to the conventional NMF (Non-negative Matrix Factorization), and the estimated sources by the proposed method well represent the characteristics of the orignal sources as shown in the time-frequency representation.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.33 no.3
• /
• pp.231-238
• /
• 2020

This paper investigates the soundness of porcelain insulators associated with the acoustic emission (AE) technique. The AE technique is a popular non-destructive method that measures and analyzes the burst energy that occurs mainly when a crack occurs in a high-frequency region. Typical AE methods require continuous monitoring with frequent sensor calibration. However, in this study, the AE technique excites a porcelain insulator using only an impact hammer, and it applies a high-pass filter to the signal frequency range measured only in the AE sensor by comparing the AE and the acceleration sensors. Next, the extracted time-domain signal is analyzed for the damage assessment. In normal signals, the duration is about 2ms, the area of the envelope is about 1,000, and the number of counts is about 20. In the damage signal, the duration exceeds 5ms, the area of the envelope is about 2,000, and the number of counts exceeds 40. In addition, various characteristics in the time and frequency domain for normal and damage cases are analyzed using the short-time Fourier transform (STFT). Based on the results of the STFT analysis, the maximum energy of a normal specimen is less than 0.02, while in the case of the damage specimen, it exceeds 0.02. The extracted high-frequency components can present dynamic behavior of crack regions and eigenmodes of the isolated insulator parts, but the presence, size, and distribution of cracks can be predicted indirectly. In this regard, the characteristics of the surface crack region were derived in this study.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2012.05a
• /
• pp.641-642
• /
• 2012