• Nuclear Engineering and Technology
• /
• 제56권2호
• /
• pp.745-752
• /
• 2024

A method for gamma/neutron event classification based on frequency-domain analysis for mixed radiation environments is proposed. In contrast to the traditional charge comparison method for pulse-shape discrimination, which requires baseline removal and pulse alignment, our method does not need any preprocessing of the digitized data, apart from removing saturated traces in sporadic pile-up scenarios. It also features the identification of neutron events in the detector's full energy range with a single device, from thermal neutrons to fast neutrons, including low-energy pulses, and still provides a superior figure-of-merit for classification. The proposed frequency-domain analysis consists of computing the fast Fourier transform of a triggered trace and integrating it through a simplified version of the transform magnitude components that distinguish the neutron features from those of the gamma photons. Owing to this simplification, the proposed method may be easily ported to a real-time embedded deployment based on Field-Programmable Gate Arrays or Digital Signal Processors. We target an off-the-shelf detector based on a small CLYC (Cs2LiYCl6:Ce) crystal coupled to a silicon photomultiplier with an integrated bias and preamplifier, aiming at lightweight embedded mixed radiation monitors and dosimeter applications.

• 한국공작기계학회논문집
• /
• 제16권1호
• /
• pp.26-32
• /
• 2007

This study was carried out fusion-welded butt joints in SWS 490A high strength steel subjected to tensile test that load-deflection curve. The windowed or short-time Fourier transform(WFT or STFT) makes possible for the analysis of non-stationary or transient signals into a joint time-frequency domain and the wavelet transform(WT) is used to decompose the acoustic emission(AE) signal into various discrete series of sequences over different frequency bands. In this paper, for acoustic emission signal analysis to use a continuous wavelet transform, in which the Gabor wavelet base on a Gaussian window function is applied to the time-frequency domain. A wavelet transform is demonstrated and the plots are very powerful in the recognition of the acoustic emission features. As a result, the technique of acoustic emission is ideally suited to study variables which control time and stress dependent fracture or damage process in metallic materials.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2005년도 춘계학술대회 논문집
• /
• pp.342-348
• /
• 2005

This study was carried out fusion-welded butt joints in SWS 490A high strength steel subjected to tensile test that load-deflection curve. The windowed or short-time Fourier transform (WFT or SIFT) makes possible for the analysis of non-stationary or transient signals into a joint time-frequency domain and the wavelet transform (WT) is used to decompose the acoustic emission (AE) signal into various discrete series of sequences over different frequency bands. In this paper, for acoustic emission signal analysis to use a continuous wavelet transform, in which the Gabor wavelet base on a Gaussian window function is applied to the time-frequency domain. A wavelet transform is demonstrated and the plots are very powerful in the recognition of the acoustic emission features. As a result, the technique of acoustic emission is ideally suited to study variables which control time and stress dependent fracture or damage process in metallic materials.

• 대한기계학회논문집A
• /
• 제39권8호
• /
• pp.801-806
• /
• 2015

저널베어링은 회전하는 축과 베어링 지지부 사이에 유막을 형성하여 회전체를 지지하는 구조물이며, 고속 및 고하중 조건에서도 안정적이기 때문에 발전소와 같은 대형 시스템에 널리 사용되고 있다. 본 연구에서는 저널베어링 시스템의 신뢰성을 확보하기 위한 감독학습 기반의 상태진단 알고리즘을 연구하였다. 기존에는 진동신호 특성인자들의 정의에 대한 연구가 주로 진행되었으나, 본 연구에서는 정의된 특성인자의 추출단위인 데이텀의 적용 기준에 대한 연구가 수행되었다. 데이텀의 효용성 평가를 통해 저널베어링 회전체 특성인자의 추출기준은 시간영역에서 1 회전, 주파수영역에서 60 회전 기준이 타당하다는 결론을 도출하였다.

• 한국콘텐츠학회논문지
• /
• 제10권1호
• /
• pp.19-26
• /
• 2010

본 논문은 사각형 특징 기반 분류기를 제안하여 실시간으로 얼굴 영역을 검출하며, 계산의 효율성과 검출 성능을 동시에 만족시키는 강인한 검출 알고리즘을 구현하고자 한다. 제안한 알고리즘은 특징 생성, 분류기 학습, 실시간 얼굴 영역 검출의 세 단계로 구성된다. 특징 생성은 제안된 5개의 사각형 특징으로 특징 집합을 구성하며, SAT(Summed-Area Tables)를 이용하여 특징 값을 효율적으로 계산한다. 분류기 학습은 AdaBoost 알고리즘을 이용하여, 분류기를 계층적으로 생성한다. 또한 중요한 얼굴 패턴은 다음 레벨에 반복적으로 적용함으로써 우수한 검출 성능을 가진다. 실시간 얼굴 영역 검출은 생성된 사각형 특징 기반 분류기를 통해, 빠르고 효율적으로 얼굴 영역을 찾아낸다. 또한 얼굴 영역을 검출한 영역을 인식의 입력 영상으로 사용하여 PCA와 KNN 알고리즘을 이용하여 기존의 매칭 방법인 Point to point 방법이 아닌 Class to Class 방식을 이용하여 인식률을 향상시켰다.

• Journal of Information Processing Systems
• /
• 제17권2호
• /
• pp.337-351
• /
• 2021

Automatically recognizing facial expressions in video sequences is a challenging task because there is little direct correlation between facial features and subjective emotions in video. To overcome the problem, a video facial expression recognition method using spatiotemporal recurrent neural network and feature fusion is proposed. Firstly, the video is preprocessed. Then, the double-layer cascade structure is used to detect a face in a video image. In addition, two deep convolutional neural networks are used to extract the time-domain and airspace facial features in the video. The spatial convolutional neural network is used to extract the spatial information features from each frame of the static expression images in the video. The temporal convolutional neural network is used to extract the dynamic information features from the optical flow information from multiple frames of expression images in the video. A multiplication fusion is performed with the spatiotemporal features learned by the two deep convolutional neural networks. Finally, the fused features are input to the support vector machine to realize the facial expression classification task. The experimental results on cNTERFACE, RML, and AFEW6.0 datasets show that the recognition rates obtained by the proposed method are as high as 88.67%, 70.32%, and 63.84%, respectively. Comparative experiments show that the proposed method obtains higher recognition accuracy than other recently reported methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권1호
• /
• pp.105-125
• /
• 2024

Gliomas are the most common malignant brain tumor and cause the most deaths. Manual brain tumor segmentation is expensive, time-consuming, error-prone, and dependent on the radiologist's expertise and experience. Manual brain tumor segmentation outcomes by different radiologists for the same patient may differ. Thus, more robust, and dependable methods are needed. Medical imaging researchers produced numerous semi-automatic and fully automatic brain tumor segmentation algorithms using ML pipelines and accurate (handcrafted feature-based, etc.) or data-driven strategies. Current methods use CNN or handmade features such symmetry analysis, alignment-based features analysis, or textural qualities. CNN approaches provide unsupervised features, while manual features model domain knowledge. Cascaded algorithms may outperform feature-based or data-driven like CNN methods. A revolutionary cascaded strategy is presented that intelligently supplies CNN with past information from handmade feature-based ML algorithms. Each patient receives manual ground truth and four MRI modalities (T1, T1c, T2, and FLAIR). Handcrafted characteristics and deep learning are used to segment brain tumors in a Global Convolutional Neural Network (GCNN). The proposed GCNN architecture with two parallel CNNs, CSPathways CNN (CSPCNN) and MRI Pathways CNN (MRIPCNN), segmented BraTS brain tumors with high accuracy. The proposed model achieved a Dice score of 87% higher than the state of the art. This research could improve brain tumor segmentation, helping clinicians diagnose and treat patients.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 1998년도 추계학술대회 논문집
• /
• pp.164-169
• /
• 1998

This paper deals with condition monitoring for tool wear during tuning operation. To develop economic sensing and identification methods for turning processes, sound pressure measurement and digital signal processing technique are proposed. To identify noise sources of tool wear and reject background noise, noise rejection methodology is proposed. features to represent condition of tool wear are obtained through analysis using adaptive filter and FFT in time and frequency domain. By using fuzzy pattern recognition, we extract features, which are sensitive to condition of tool wear, from several features and make a decision on tool wear. The validity of the proposed system is condirmed through the large number of cutting tests in two cutting conditions.

• 전기학회논문지
• /
• 제63권11호
• /
• pp.1559-1563
• /
• 2014

Recently, the prevention of crime using CCTV draws special in accordance with the higher crime incidence rate. Therefore security systems like a CCTV with audio capability are developing for giving an instant alarm. This paper proposes a scream detecting engine from various ambient noises in real environment for surveillance systems. The proposed engine detects scream signals among the various ambient noises using the features extracted in time/frequency domain. The experimental result shows the performance of our engine is very promising in comparison with the traditional engines using the model based features like LPC, LPCC and MFCC. The proposed method has a low computational complexity by using FFT and cross correlation coefficients instead of extracting complex features like LPC, LPCC and MFCC. Therefore the proposed engine can be efficient for audio-based surveillance systems with low SNRs in real field.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.28.5-28
• /
• 2001

This paper investigates a classification method of the electrocardiogram (ECG) into different disease categories. The features for the classification of the ECG are the coefficients of the discrete wavelet transform (DWT) of ECG signals. The coefficients are calculated with Haar wavelet, and after DWT we can get 64 coefficients. Each coefficient has morphological information and they may be good features when conventional time-domain features are not available. Since all of them are not meaningful, it is needed to reduce the size of meaningful coefficients set. The distributions of each coefficient can be the rules to classify ECG signal. The optimally reduced feature set is obtained by fuzzy c-means algorithm and rough set theory. First, the each coefficient is clustered by fuzzy c-means algorithm and the clustered ...