• Annual Conference on Human and Language Technology
• /
• 2009.10a
• /
• pp.155-159
• /
• 2009

본 논문은 한국어 문서 감정분류를 위한 중요한 어휘 자원인 감정자질(Sentiment Feature)의 의미지향성(Semantic Orientation) 추정을 위해 일반적인 특성과 영역(Domain) 의존적인 특성을 반영하여 한국어 문서 감정분류(Sentiment Classification)의 성능 향상을 얻을 수 있는 기법을 제안한다. 감정자질의 의미지 향성은 검색 엔진을 통해 추출한 각 감정 자질의 스니핏(Snippet)과 실험 말뭉치를 이용하여 추정할 수 있다. 검색 엔진을 통해 추출된 스니핏은 감정자질의 일반적인 특성을 반영하며, 실험 말뭉치는 분류하고자 하는 영역 의존적인 특성을 반영한다. 이렇게 얻어진 감정자질의 의미지향성 수치는 각 문장의 감정강도를 추정하기 위해 이용되며, 문장의 감정 강도의 값을 TF-IDF 가중치 기법에 접목하여 감정자질의 가중치를 책정한다. 최종적으로 학습 과정에서 긍정 문서에서는 긍정 감정자질, 부정 문서에서는 부정 감정자질을 대상으로 추가 가중치를 부여하여 학습하였다. 본 논문에서는 문서 분류에 뛰어난 성능을 보여주는 지지 벡터 기계(Support Vector Machine)를 사용하여 제안한 방법의 성능을 평가한다. 평가 결과, 일반적인 정보 검색에서 사용하는 내용어(Content Word) 기반의 자질을 사용한 경우보다 3.1%의 성능향상을 보였다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.1
• /
• pp.106-111
• /
• 2011

Video-based detection and tracking of moving objects has been widely used in real-time monitoring systems and a videoconferencing. Also, because object motion tracking can be expanded to Human-computer interface and Human-robot interface, Moving object tracking technology is one of the important key technologies. If we can track a specified object in an environment of multiple moving objects, then there will be a variety of applications. In this paper, we introduce a specified object motion tracking using particle filter. The results of experiments show that particle filter can achieve good performance in single object motion tracking and a specified object motion tracking in an environment of multiple moving objects.

• Journal of Power Electronics
• /
• v.11 no.6
• /
• pp.837-845
• /
• 2011

This paper proposes phase current reconstruction techniques for two-phase two-leg and two-phase four-leg inverters using a single current sensor. In the proposed methods, one phase current is sampled simultaneously with a particular branch current by using only one current sensor, and then current reconstruction algorithms are applied to extract the information on two phase currents from the sensor output. The sampled current information is periodically updated at the peak and the valley of the triangular carrier waveform in each switching cycle of pulse-width modulation (PWM). The voltage vector spaces where the phase currents can be reconstructed are evaluated. Compared to the existing method using two individual current sensors in two phases, the proposed schemes can save implementation cost since it is possible to remove one current sensor. In addition, the proposed methods are free from gain discrepancy issues between two current sensors. Simulations and experiments show excellent current reconstruction performance of the proposed methods.

• ETRI Journal
• /
• v.28 no.3
• /
• pp.320-328
• /
• 2006

Using biometrics to verify a person's identity has several advantages over the present practice of personal identification numbers (PINs) and passwords. To gain maximum security in a verification system using biometrics, the computation of the verification as well as the storing of the biometric pattern has to take place in a smart card. However, there is an open issue of integrating biometrics into a smart card because of its limited resources (processing power and memory space). In this paper, we propose a speaker verification algorithm using a support vector machine (SVM) with a very few features, and implemented it on a 32-bit smart card. The proposed algorithm can reduce the required memory space by a factor of more than 100 and can be executed in real-time. Also, we propose a hardware design for the algorithm on a field-programmable gate array (FPGA)-based platform. Based on the experimental results, our SVM solution can provide superior performance over typical speaker verification solutions. Furthermore, our FPGA-based solution can achieve a speed-up of 50 times over a software-based solution.

• Smart Structures and Systems
• /
• v.13 no.5
• /
• pp.849-868
• /
• 2014

An indirect approach is explored for structural health bridge monitoring allowing for wide, yet cost-effective, bridge stock coverage. The detection capability of the approach is tested in a laboratory setting for three different reversible proxy types of damage scenarios: changes in the support conditions (rotational restraint), additional damping, and an added mass at the midspan. A set of frequency features is used in conjunction with a support vector machine classifier on data measured from a passing vehicle at the wheel and suspension levels, and directly from the bridge structure for comparison. For each type of damage, four levels of severity were explored. The results show that for each damage type, the classification accuracy based on data measured from the passing vehicle is, on average, as good as or better than the classification accuracy based on data measured from the bridge. Classification accuracy showed a steady trend for low (1-1.75 m/s) and high vehicle speeds (2-2.75 m/s), with a decrease of about 7% for the latter. These results show promise towards a highly mobile structural health bridge monitoring system for wide and cost-effective bridge stock coverage.

• Journal of the Korea Society of Computer and Information
• /
• v.12 no.5
• /
• pp.121-129
• /
• 2007

Scalarization is a process that a parallel construct like an array statement of Fortran 90 or FORALL of HPF is converted into sequential loops that maintain the correct semantics. Most compilers of HPF, recognized as a standard data parallel language, convert a HPF program into a Fortran 77 program inserted message passing primitives. During scalariztion, a parallel construct FORALL should be translated into Fortran 77 DO loops maintaining the semantics of FORALL. In this paper, we propose a scalarization algorithm which converts a FORALL construct into a DO loop with improved performance. For this, we define and use a relation distance vector to keep necessary dependence informations. Then we evaluate execution times of the codes generated by our method and by PARADIGM compiler method for various array sizes.

• Journal of IKEEE
• /
• v.16 no.4
• /
• pp.382-388
• /
• 2012

An H.264/AVC fast motion estimation methodology is presented in this paper. Advanced SIMD based NEON which is one of the parallel processing methods is supported under the ARM Cortex-A9 dual-core platform. NEON is applied to a full search technique with one of the various motion estimation methods and SAD operation count of each macroblock is reduced to 1/4. Pixel values of the corresponding macroblock are assigned to eight 16-bit NEON registers and Intrinsic function in NEON architecture carried out 128 bits arithmetic operations at the same time. In this way, the exact motion vector with the minimum SAD value among the calculated SAD values can be designated. Experimental results show that performance gets improved 30% above average in accordance with the size of image and macroblock.

• Journal of the Korea Society of Computer and Information
• /
• v.12 no.1 s.45
• /
• pp.261-267
• /
• 2007

The research about Intelligence Transport Systems(ITS) is actively studied for the traffic problem solution recently. Also, the various methods to detect vehicles moving in the roads are studied. This research using image processing technology is to give the drivers the road information quickly by developing Vehicle Detection System that detects through traffics. Purpose or this research is developing efficient algorithm to facilitate hardware composition. We use morphology method to extract corner points in the images captured by CCD camera. Also, the proposed algorithm detects vehicle's moving area by using motion vectors between corner points. The experiments of the proposed algorithm whose processing time was shortened show good results in vehicle detection on the live road images.

• Journal of the Korea Society of Computer and Information
• /
• v.8 no.3
• /
• pp.87-93
• /
• 2003

The purpose of this research is to develop a virtual reality system which enables to actually experience the virtual reality through the visual sense of human. TSS was applied in tracing the movement of moving picture in this research. By applying TSS, it was possible to calculate multiple motion vectors from moving picture, and then camera's motion parameters were obtained by utilizing the relationship between the motion vectors. For the purpose of experiencing the virtual reality by synchronizing the camera's accelerated velocity and the simulator's movements, the relationship between the value of camera's accelerated velocity and the simulator's movements was analyzed and its result was applied to the neutral network training. It has been proved that the proposed virtual reality immersion system in this dissertation can dynamically control the movements of moving picture and can also operate the simulator quite similarly to the real movements of moving picture.

• Journal of the Korea Society of Computer and Information
• /
• v.4 no.3
• /
• pp.28-34
• /
• 1999

In this paper. we propose the method of Scene Change Detection for video sequence using the DC components and the moving vectors in the Macro Blocks in the DCT blocks. The proposed method detects the Scene Change which would not be related with the specific sequences in the compressed MPEG domain. To do this. we define new metrics for Scene Change Detection using the features of picture component and detect the exact Scene Change point of B-pictures using the characteristics of B-picture's sharp response for the moving vectors. In brief, we will detect the cut point using I-picture and the gradual scene changes such as dissolve, fade, wipe, etc. As a results, our proposed method shows good test results for the various MPEG sequences.