• 한국컴퓨터정보학회논문지
• /
• 제23권1호
• /
• pp.17-24
• /
• 2018

With improvement of speech recognition and natural language processing, dialog systems are recently adapted to various service domains. It became possible to get desirable services by conversation through the dialog system, but it is still necessary to improve separate modules, such as domain detection, intention detection, named entity recognition, and out-of-domain detection, in order to achieve stable service offer. When it misclassifies an in-domain sentence of conversation as out-of-domain, it will result in poor customer satisfaction and finally lost business. As there have been relatively small number of studies related to the out-of-domain detection, in this paper, we introduce a new method using a hierarchical Dirichlet process and demonstrate the effectiveness of it by experimental results on Korean dataset.

• Quantitative Bio-Science
• /
• 제37권2호
• /
• pp.81-89
• /
• 2018

It is commonplace that high false detection rates interfere with immediate vision-based fire monitoring system. To circumvent this challenge, we propose a fire detection algorithm that can accommodate color variations of RGB in temporal domain, aiming at reducing false detection rates. Despite interrupting images (e.g., background noise and sudden intervention), the proposed method is proved robust in capturing distinguishable features of fire in temporal domain. In numerical studies, we carried out extensive real data experiments related to fire detection using 24 video sequences, implicating that the propose algorithm is found outstanding as an effective decision rule for fire detection (e.g., false detection rate <10%).

• 융합정보논문지
• /
• 제9권9호
• /
• pp.1-12
• /
• 2019

대화시스템은 인간과 컴퓨터 사이의 새로운 의사소통 수단으로 떠오르고 있다. 대화시스템은 인간의 음성을 입력으로 취하여, 적절한 음성 답변 또는 서비스를 제공하게 된다. 아마존 에코, 네이버 웨이브 등과 같은 대화시스템 제품들이 등장하고 있음에도 불구하고, 이 대화시스템들은 공통적으로 미지원 도메인을 제대로 처리하지 못한다는 문제점을 안고 있다. 이와 관련한 몇몇 연구들이 있었지만, 이 문제를 풀기 위한 더욱 많은 연구가 진행될 필요가 있다. 이 논문에서는, 미지원 도메인 검출과 관련한 기존 연구들에 대하여 3가지 관점, 즉 데이터, 자질, 방법에 대한 관점으로 요약한 정보를 제공한다. 데이터셋이 부족하다는 점으로 인해 타 연구분야에 비해 적은 연구가 수행되어왔으므로, 앞으로 가장 시급한 연구 주제는 대화시스템의 미지원 도메인 검출을 위한 공개용 데이터셋을 구축하고 배포하는 것이다.

• 전기학회논문지P
• /
• 제58권2호
• /
• pp.136-141
• /
• 2009

An AC generator is an important components in producing a electric power and so it requires highly reliable protection relays to minimize the possibility of demage occurring under fault conditions. Conventionally, a DFT based RDR has been used for protecting the generator stator winding. However, when DFTs based on Fourier analysis are used, it has been pointed out that defects can occur during the process of transforming a time domain signal into a frequency domain one which can lead to loss of time domain information. This paper proposes the internal fault detection and fault type discrimination for the stator winding by applying the detailed coefficients by Daubechies Wavelet Transform to overcome the defects in the DFT process. For the case studies reported in the paper, a model system was established for the simulations utilizing the ATP, and this verified the effectiveness of the proposed technique through various off-line tests carried out on the collected data. The propose method is shown to be able to rapidly identify internal fault and did not operate a miss-operation for all the external fault tested.

• Smart Structures and Systems
• /
• 제6권7호
• /
• pp.811-833
• /
• 2010

Vibration control and health monitoring of building structures have been actively investigated in recent years but treated separately according to the primary objective pursued. This paper presents a general approach in the time domain for integrating vibration control and health monitoring of a building structure to accommodate various types of control devices and on-line damage detection. The concept of the time-domain approach for integrated vibration control and health monitoring is first introduced. A parameter identification scheme is then developed to identify structural stiffness parameters and update the structural analytical model. Based on the updated analytical model, vibration control of the building using semi-active friction dampers against earthquake excitation is carried out. By assuming that the building suffers certain damage after extreme event or long service and by using the previously identified original structural parameters, a damage detection scheme is finally proposed and used for damage detection. The feasibility of the proposed approach is demonstrated through detailed numerical examples and extensive parameter studies.

• Asia pacific journal of information systems
• /
• 제31권3호
• /
• pp.335-357
• /
• 2021

As reproduction of images can be done with ease, copy detection has increasingly become important. In the duplication process, image modifications are likely to occur and some alterations are deliberate and can be viewed as attacks. A wide range of copy detection techniques has been proposed. In our study, content-based copy detection, which basically applies DCT-based features for images, namely, pixel values, edges, texture information and frequency-domain component distribution, is employed. Experiments are carried out to evaluate robustness and sensitivity of DCT-based features from attacks. As different types of DCT-based features hold different pieces of information, how features and attacks are related can be shown in their robustness and sensitivity. Rather than searching for proper features, use of robustness and sensitivity is proposed here to realize how the attacked features have changed when an image attack occurs. The experiments show that, out of ten attacks, the neural networks are able to detect seven attacks namely, Gaussian noise, S&P noise, Gamma correction (high), blurring, resizing (big), compression and rotation with mostly related to their sensitive features.

• 전기학회논문지P
• /
• 제57권4호
• /
• pp.377-382
• /
• 2008

For stator winding protection of AC generator, KCL(Kirchhoff's Current Law) is widely applied. Actually a CRDR(Current Ratio Differential Relay) based on DFT(Discrete Fourier Transform) has been used for protecting generator. It has been pointed out that defects can occur during the process of transforming a time domain signal into a frequency domain one which can lead to loss of time domain information. Wavelets techniques are proposed for the analysis of power system transients. This paper introduces an algorithm to choose a suitable Mother Wave1et for generator stator fault detection. For optimal selection, we analyzed db(Daubechies), sym(Symlets), and coif(Coiflects) of Mother Wavelet. And we compared with performance of the choice algorithm using detail coefficients energy and RMS(root mean square) error. It can be improved the reliability of the conventional DFT based CRDR. The feasibility and effectiveness of the proposed scheme is proved with simulation using collected data obtained from ATP (Alternative Transient Program) package.

• 정보처리학회논문지B
• /
• 제11B권3호
• /
• pp.353-360
• /
• 2004

최근까지 MPEG으로 압축된 영상의 장면전환점 검출에 관한 연구가 많이 진행되어왔다. 그러나 대체로 디코딩 과정을 거친 후 픽셀단위의 비교를 통해 장면전환점을 검출하는 경우가 많았다. 이 경우 디코딩 과정에서의 많은 계산에 의해 실시간 적용에 부적합하게 된다. 최근에는 압축영역에서의 정보만을 이용해 장면전환점을 검출하는 연구가 많이 진행되고 있으며, 본 논문에서는 압축영역에서 장면전환점을 검출하면서도 보다 빠르고 정확한 검출이 이루어지도록 I픽처 단위의 블록과 P픽처 단위의 내부블록으로 나눈 후 I블록별 검사를 통해 장면전환이 검출된 블록에 대해서 P블록별 검사를 수행하고 최종적으로 B적처까지의 검사를 통해 정확한 장면전환점을 찾는 순차접근법을 제안한다. 순차 접근법은 대부분의 처리가 압축영역에서 이루어지고 또한 블록단위의 결사를 하므로 불필요한 픽처들의 검사과정을 줄여서 보다 빠른 장면전환점 검출이 가능하다 순차접근법은 빠른 처리속도와 함께 정확한 검색이 가능하도록 최적의 알고리즘을 사용하고 있다.

• 한국음향학회지
• /
• 제28권8호
• /
• pp.822-831
• /
• 2009

애자는 송전선 시스템에서 전기적으로나 기계적으로 매우 중요한 소자이다. 송전선 시스템에 설치된 이후 애자의 열화 등에 의해 고장이 난 애자를 찾아내기 위해 애자로 부터의 방사 소음을 측정하여 분석하였다. 대상으로 한 제품은 2종류의 현수 애자, COS, 2종류의 Line Poster, 피뢰기이며, 이들 제품의 정상 상태와 고장 상태의 방사 소음을 각각 측정하여 시간 파형, 주파수 스펙트럼, 피크 검출의 결과를 서로 비교하여 그 차이점을 제시하였다. 또한, 이를 바탕으로 방사 소음으로부터 고장 상태의 애자의 검출의 가능성 및 그 방법을 제시하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권9호
• /
• pp.2927-2941
• /
• 2022

The primary task of machine fault diagnosis is to judge whether the current state is normal or damaged, so it is a typical binary classification problem with mutual exclusion. Mutually exclusive events and out-of-domain detection have one thing in common: there are two types of data and no intersection. We proposed a fusion model method to improve the accuracy of machine fault diagnosis, which is based on the mutual exclusivity of events and the commonality of out-of-distribution detection, and finally generalized to all binary classification problems. It is reported that the performance of a convolutional neural network (CNN) will decrease as the recognition type increases, so the variational auto-encoder (VAE) is used as the primary model. Two VAE models are used to train the machine's normal and fault sound data. Two reconstruction probabilities will be obtained during the test. The smaller value is transformed into a correction value of another value according to the mutually exclusive characteristics. Finally, the classification result is obtained according to the fusion algorithm. Filtering normal data features from fault data features is proposed, which shields the interference and makes the fault features more prominent. We confirm that good performance improvements have been achieved in the machine fault detection data set, and the results are better than most mainstream models.