Research on Domain-independent Opinion Target Extraction

Sun Yongmei,Huo Hua 보안공학연구지원센터 2015 International Journal of Hybrid Information Techno Vol.8 No.1

Opinion Target Extraction is one of the important tasks for text sentiment analysis, which has attracted much attention from many researchers. For this task, we proposed an M-Score algorithm utilized in the model which realized the domain-independent opinion target extraction function. This algorithm is derived from the Pointwise Mutual Information algorithm, but the difference is that it doesn’t need any manual seeds collection or any web searching engines, which reduces the manual participation and easy to be transplanted. This model starts with document preprocessing, effective opinion sentences extraction and candidate opinion target extraction by employing Conditional Random Fields Model with feature templates. Next, the M-Score algorithm is employed to extract seed set, and the bootstrapping approach is invoked to process the candidate opinion targets. Finally, the model uses word frequency and the Noun pruning algorithm to filter the opinion targets, and then obtains the final opinion targets for output. The experimental results show that the M-score method performs better than Pointwise Mutual Information algorithm in precision and recall.

Comparison of Efficacy of Propofol When Used with or without Remifentanil during Conscious Sedation with a Target-Controlled Infuser for Impacted Teeth Extraction

Sung, Juhan,Kim, Hyun-Jeong,Choi, Yoon Ji,Lee, Soo Eon,Seo, Kwang-Suk The Korean Dental Society of Anesthsiology 2014 Journal of Dental Anesthesia and Pain Medicine Vol.14 No.4

Background: Clinical use of propofol along with remifentanil for intravenous sedation is increasing in these days, but there are not enough researches to evaluate proper target concentration when these drugs are infused by using target controlled infusion (TCI) pump in dental treatment cases. In this study, we compared efficacy of TCI conscious sedation and target concentration of propofol when it used with or without remifentanil during conscious sedation with the help of a TCI for the surgical extraction of impacted teeth. Methods: After IRB approval, all the charts of patients who had undergone surgical extraction of impacted teeth under propofol TCI sedation for 6 months were selected and reviewed for this study. After reviewal of charts, we could divide patients in two groups. In one group (group 1), only propofol was selected for sedation and initial effect site concentration of propofol was $1{\mu}g/ml$ (n = 33), and in another group (group 2), both propofol and remifentanil was infused and initial effect site concentration of each drug was $0.6{\mu}g/ml$ and 1 ng/ml respectively (n = 25). For each group, average propofol target concentration was measured. In addition, we compared heart rate, respiratory rate, and systolic and diastolic blood pressure as well as oxygen saturation. Besides, BIS, sedation scores (OAAS/S), and subjective satisfaction scores were compared. Results: Between group 1 and 2, there were no significant differences in demographics (age, weight and height), and total sedation time. However, total infused dose and the effect site target concentration of propofol was $163.8{\pm}74.5mg$ and $1.13{\pm}0.21{\mu}g/ml$ in group 1, and $104.3{\pm}46.5mg$ and $0.72{\pm}0.26{\mu}g/ml$ in the group 2 with $1.02{\pm}0.21ng/l$ of the effect site target concentration of remifentanil, respectively. During sedation, there were no differences between overall vital sign, BIS and OAAS/S in 2 groups (P > 0.05). However, we figured out patients in group 2 had decreased pain sensation during sedation. Conclusions: Co-administration of propofol along with remifentanil via a TCI for the surgical extraction of impacted teeth may be safe and effective compared to propofol only administration.

Infrared Target Recognition using Heterogeneous Features with Multi-kernel Transfer Learning

( Xin Wang ),( Xin Zhang ),( Chen Ning ) 한국인터넷정보학회 2020 KSII Transactions on Internet and Information Syst Vol.14 No.9

Infrared pedestrian target recognition is a vital problem of significant interest in computer vision. In this work, a novel infrared pedestrian target recognition method that uses heterogeneous features with multi-kernel transfer learning is proposed. Firstly, to exploit the characteristics of infrared pedestrian targets fully, a novel multi-scale monogenic filtering-based completed local binary pattern descriptor, referred to as MSMF-CLBP, is designed to extract the texture information, and then an improved histogram of oriented gradient-fisher vector descriptor, referred to as HOG-FV, is proposed to extract the shape information. Second, to enrich the semantic content of feature expression, these two heterogeneous features are integrated to get more complete representation for infrared pedestrian targets. Third, to overcome the defects, such as poor generalization, scarcity of tagged infrared samples, distributional and semantic deviations between the training and testing samples, of the state-of-the-art classifiers, an effective multi-kernel transfer learning classifier called MK-TrAdaBoost is designed. Experimental results show that the proposed method outperforms many state-of-the-art recognition approaches for infrared pedestrian targets.

다중 신경회로망을 이용한 특징정보 융합과 적외선영상에서의 표적식별에의 응용

선선구,박현욱 대한전자공학회 2003 電子工學會論文誌-SP (Signal processing) Vol.38 No.2

전방 관측 적외선 영상에서 가려짐이 없는 표적과 부분적으로 가려진 표적을 식별하기 위해 국부적 표적 경계선에 대한 거리함수의 푸리에기술자와 다중의 다층 퍼셉트론을 사용한 특징정보 융합 방법을 제안한다. 표적을 배경으로부터 분리한 후에 표적 경계선의 중심을 기준으로 푸리에 기술자를 구해 전역적 특징으로 사용한다. 국부적인 형상 특징을 찾기 위해 표적 경계선을 분할하여 4개의 국부적 경계선을 만들고, 각 국부적 경계선에서 두 개의 극단점이 이루는 직선과 경계선 픽셀로부터 거리함수를 정의한다. 거리함수에 대한 푸리에 기술자를 국부적 형상특징으로 사용한다. 1개의 광역적 특징 백터와 4개의 국부적 특징 백터를 정의하고 다중의 다층 퍼셉트론을 사용하여 특징정보들을 융합함으로써 최종 표적식별 결과를 얻는다. 실험을 통해 기존의 특징벡터들에 의한 표적식별 방법과 비교하여 제안한 방법의 우수성을 입증한다. Distance Fourier descriptors of local target boundary and feature information fusion using multiple MLPs (Multilayer perceptrons) are proposed. They are used to identify nonoccluded and partially occluded targets in natural FLIR (forward-looking infrared) images. After segmenting a target, radial Fourier descriptors as global shape features are defined from the target boundary. A target boundary is partitioned into four local boundaries to extract local shape features. In a local boundary, a distance function is defined from boundary points and a line between two extreme points. Distance Fourier descriptors as local shape features are defined by using distance function. One global feature vector and four local feature vectors are used as input data for multiple MLPs to determine final identification result of the target. In the experiments, we show that the proposed method is superior to the traditional feature sets with respect to the identification performance.

Signal Feature Extraction of GMI Sensor in Longitudinally Excitated Amorphous Wire and Its Application in Target Detection

Xiusheng Duan,Jing Xiao 보안공학연구지원센터 2015 International Journal of Signal Processing, Image Vol.8 No.12

In order to expand the dynamic range of the GMI sensor in longitudinally excitated amorphous wire and improve its precision, waveforms of the GMI sensor are analyzed on the background of weak magnetic field measurement. Then three features extraction methods are studied in detail. According to the advantages and disadvantages of different methods, an improved method which combines the energy features of the wavelet decomposition and the amplitude features is proposed. First, fit the amplitude change ratio curve respectively with Gaussian function and polynomial function, which not only solves the problem of nonlinearity, but also improves the measurement accuracy. Considering the difference of signals’ in-pulse features at different positions, the ‘db5’ wavelet is introduced to decompose the signals. Then the BP neural network trained by the energy features of the wavelet is used to locate the target’s approximate position, as a result, the problem of multi-value is solved. At last, experiments of target detection in weak magnetic field prove that the method proposed is effective.

Precise Target Detection with Projection of Difference Map and Background Extraction

Byung-Gyu Kim,Kuk-Jin Song,Dong-Jo Park 한국과학기술원 인간친화 복지 로봇 시스템 연구센터 2001 International Journal of Assistive Robotics and Me Vol.2 No.2

  One of the basic processes of the target tracking system with imaging sensors is the segmentation that separates an object from the background in a given image. In this paper, a new technique for detecting the object in a given image sequence with the stationary background is suggested by using a gated difference image. By using the gated difference image, the gray level intensity of pixels in the difference image is projected and averaged on each axis. Then, the gate of the object is set by means of a mean value of pixels of the difference image in order to eliminate stains from the background. By putting a limit on the gate of the object in the segmentation process, stains which can be generated from the background are eliminated a priori. And the object is distinguished from the background by a simple background extraction. The proposed technique has been tested on several data.

MUSIC 알고리즘을 이용한 JEM 신호의 Chopping 주파수 추출

송원영,김형주,김성태,신인선,명로훈 한국전자파학회 2019 한국전자파학회논문지 Vol.30 No.3

Jet engine modulation(JEM) signals are widely used in the field of target recognition along with high-range resolution profile and inverse synthetic aperture radar because they provide specific information of the jet engine. To obtain the number of blades of the jet engine, the chopping frequency proportional to the number of blades must be extracted. In the conventional chopping frequency extraction method, an initial threshold value is defined and a method of detecting the chopping peak is used. However, this detection method takes time depending on the signal due to repetitive detection. Thus, in this study, we proposed to extract the chopping frequency using MUltiple SIgnal Classification(MUSIC) algorithm. We applied the MUSIC algorithm to a given JEM signal to find the chopping frequency and determine the blade number candidates. We also applied the MUSIC algorithm to other chopping frequency extractions to determine the score of the candidate groups. Unlike the conventional detection algorithm, which requires repetitive frequency detection, MUSIC algorithm quickly detects the accurate chopping frequency and reduces the calculation time.

모노스태틱 RCS와 바이스태틱 RCS의 표적 구분 성능 분석

이성준(Sung-Jun Lee),최인식(In-Sik Choi) 한국전자파학회 2010 한국전자파학회논문지 Vol.21 No.12

본 논문은 바이스태틱 RCS와 모노스태틱 RCS를 이용하여 각각 표적 구분 실험을 수행하고 그 성능을 비교분석하였다. 모노스태틱 및 바이스태틱 RCS로부터 특성을 추출하기 위하여 시간-주파수 영역 해석법인 STFT와 CWT를 이용하였으며, 다중 퍼셉트론 신경망을 구분기로 이용하였다. 실험 결과, 모노스태틱과 바이스태틱 RCS 모두 CWT가 STFT보다 더 나은 구분 성능을 보여주었다. 또한, STFT에서는 바이스태틱 RCS를 이용했을 때, CWT에서는 모노스태틱 RCS를 이용하였을 때 대체적으로 더 좋은 성능을 나타내었다. 결과적으로 본 논문을 통하여 바이스태틱 RCS도 모노스태틱 RCS처럼 표적 구분에 똑같이 적용할 수 있다는 것을 알 수 있었다. In this paper, we analyzed the performance of radar target classification using the monostatic and bistatic radar cross section(RCS) for four different wire targets. Short time Fourier transform(STFT) and continuous wavelet transform (CWT) were used for feature extraction from the monostatic RCS and the bistatic RCS of each target, and a multilayered perceptron(MLP) neural network was used as a classifier. Results show that CWT yields better performance than STFT for both the monostatic RCS and the bistatic RCS. And, when STFT was used, the performance of the bistatic RCS was slightly better than that of the monostatic RCS. However, when CWT was used, the performance of the monostatic RCS was slightly better than that of the bistatic RCS. Resultingly, it is proven that bistatic RCS is a good cadndidate for application to radar target classification in combination with a monostatic RCS.

약한 제트 엔진 변조 신호의 Spool Rate 추출을 위한 High-Pass Filtering 기반의 빠른 전처리 기법

송원영,김형주,김성태,신인선,명로훈 한국전자파학회 2019 한국전자파학회논문지 Vol.30 No.5

Jet engine modulation(JEM) signals are widely used for target recognition. These signals coming from a potentially hostile aircraft provide specific information about the jet engine. In order to obtain the number of blades, which is uniquely provided by the JEM signal, one must extract the spool rate, which is the rotation speed of the blades. In this paper, we propose an algorithm to extract the spool rate from a weak JEM signal. A criterion is developed to extract the spool rate from the JEM signal by analyzing the intensity of the JEM signal component. The weak signal is first subjected to a high-pass filtering-based process, which modifies it to facilitate spool rate extraction. We then apply a peak detection process and extract the spool rate. The technique is simpler than the existing CEMD or WD method, is accurate, and greatly reduces the time required

형태학적 연산에 기반한 해수면 온도 분포 추정 알고리즘

구은혜(Eun-Hye Gu),조웅호(Woong-Ho Cho),박길흠(Kil-Houm Park) 한국지능시스템학회 2012 한국지능시스템학회논문지 Vol.22 No.2

원거리의 표적을 탐지하기 위한 IRST시스템에서 표적은 배경영역에 포함된 많은 클러터로 인하여 검출이 매우 어렵다. 특히 해상환경에서 획득된 영상의 경우, 불균일한 해수면 온도 분포는 원거리에서 접근하는 소형 표적의 검출을 어렵게 하는 요인으로 작용한다. 이에 본 논문에서는 형태학적 연산을 기반으로 하는 불균일한 해수면 온도 분포를 추정하는 알고리즘을 제안한다. 정확한 해수면 온도 분포 추정을 위하여 상한 분포와 하한 분포로 나누어 추정하고, 추정된 결과의 평균값으로 최종 해수면 온도 분포를 도출한다. 또한 형태학적 연산을 적용함으로써 발생하는 서브샘플링 효과 문제를 해결하기 위하여 다앙한 크기의 구조요소를 이용하는 다중 가중치(multi-weight) 기법을 적용한다. 제안 방법의 타당성을 검증하기 위하여 다양한 환경에서 획득된 해수면 영상에 대한 해수면 온도 분포 추정 결과를 기존 알고리즘과 비교 검증하였다. Target detection is very difficult with complex clutters in IRST(Infrared Search and Track) system for a long distance target. Especially sea-clutter and ocean-surface with with non-uniform temperature distribution make it difficult to detect incoming targets in images obtained in sea environment. In this paper, we propese a nevel method based on morphological method for estimation of ocean surface with non-uniform temperature flow. In order to estimate the exact ocean surface temperature flow, we divided it into upper and lower bound flow. And after estimating it, the final ocean surface temperature flow is derived by a mean value of the estimated results. Also, we apply the munti-weighted technique with a variety of sizes of structure elements to overcome sub-sampling effect by using morphology method. Experimental results for ocean surface images acquired from many different environments are compared with results of existing method to verify the performance of the proposed methods.