• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.10
• /
• pp.1453-1461
• /
• 2022

The accuracy of peripheral object recognition algorithms using 3D data sensors such as LiDAR in autonomous vehicles has been increasing through many studies, but this requires high performance hardware and complex structures. This object recognition algorithm acts as a large load on the main processor of an autonomous vehicle that requires performing and managing many processors while driving. To reduce this load and simultaneously exploit the advantages of 3D sensor data, we propose 2D data-based recognition using the ROI generated by extracting physical properties from 3D sensor data. In the environment where the brightness value was reduced by 50% in the basic image, it showed 5.3% higher accuracy and 28.57% lower performance time than the existing 2D-based model. Instead of having a 2.46 percent lower accuracy than the 3D-based model in the base image, it has a 6.25 percent reduction in performance time.

• ETRI Journal
• /
• v.29 no.2
• /
• pp.179-188
• /
• 2007

We propose a multi-strategic concept-spotting approach for robust spoken language understanding of conversational Korean in a hostile recognition environment such as in-car navigation and telebanking services. Our concept-spotting method adopts a partial semantic understanding strategy within a given specific domain since the method tries to directly extract predefined meaning representation slot values from spoken language inputs. In spite of partial understanding, we can efficiently acquire the necessary information to compose interesting applications because the meaning representation slots are properly designed for specific domain-oriented understanding tasks. We also propose a multi-strategic method based on this concept-spotting approach such as a voting method. We present experiments conducted to verify the feasibility of these methods using a variety of spoken Korean data.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2016.07a
• /
• pp.51-54
• /
• 2016

In computer vision especially in image processing, it has become popular to apply deep convolutional networks for supervised learning. Convolutional networks have shown a state of the art results in classification, object recognition, detection as well as semantic segmentation. However, supervised learning has two major disadvantages. One is it requires huge amount of labeled data to get high accuracy, the second one is to train so much data takes quite a bit long time. On the other hand, unsupervised learning can handle these problems more cheaper way. In this paper we show efficient way to learn features for classification in an unsupervised way. The network trained layer-wise, used backpropagation and our network learns features from unlabeled data. Our approach shows better results on Caltech-256 and STL-10 dataset.

• Journal of the Korea Computer Industry Society
• /
• v.5 no.1
• /
• pp.65-76
• /
• 2004

In this paper, we observe the differences between linguistic and computational aspect in the automatic processing of languages which are dominant representation method for information in the Internet. For efficient information retrieval, information extraction and machine translation from the massive documents, we investigate analysis units for morphology analysis, syntactic analysis and semantic analysis. and propose the syntactic longest analysis unit rather than morphological unit based on linguistics. Also, by evaluating with massive documents, we show that the proposed analysis units can be used for the constraint which can reduce the ambiguity occurring in the language processing.

• Proceedings of the Korean Society for Cognitive Science Conference
• /
• 2002.05a
• /
• pp.157-162
• /
• 2002

본 연구는 영어 단어 재인 과정에서 나타나는 한국인의 어휘 수준과 의미 수준 양상을 알아보기 위해 실시되었다 이를 위해 본 연구에서는 세 종류의 실험을 시행하였는데, 첫 번째 실험에서는 한국어 처리 기제와 영어 처리 기제의 독립 여부를 알아보기 위하여 한국어로는 여러 의미를 갖지만 영어로는 한 가지 의미만을 가지는 영어단어를 점화 자극으로 하고, 한국어와는 관련된 의미를 갖지만 영어와는 무관련한 한국어 단어를 목표 자극으로 사용하여(예, bridge-팔)언어간 의미 점화 어휘판단 과제를 시행하였다. 두 번째 실험에서는 비교적 개념 구조가 한국어와 영어에서 유사하다고 생각되어지는 외래어를 자극으로 사용하여 언어간(예, elevator-승강기), 언어 내(예, 엘리베이터-승강기) 어휘판단과제를 실시하였다. 연구 결과 첫 번째 실험에서는 유의미한 점화효과가 나타나지 않았고, 두 번째 실험에서는 언어간에는 SOA에 따라서 결과가 달랐고, 언어 내에는 촉진적 점화효과가 나타났다 이러한 결과는 영어의 일반 어휘에 대한 의미 표상 체계는 독립적으로 존재하였고, 외래어와 같이 특수한 어휘에 대해서는 다른 표상 체계를 갖고 있는 것으로 나타났다

• Proceedings of the IEEK Conference
• /
• 1998.06a
• /
• pp.665-668
• /
• 1998

본 논문에서는 초저속 동영상 부호화에 관한 것으로, 움직임 추정 효율을 개선하기 위해 분할된 영역별로 움직임 정보를 추정하여 부호화를 수행할 뿐만 아니라 분할된 영역중 의미있는 부분을 선택적으로 부호화할 수 있는 영역분할 기반 영상부호화 기법에 관한 것이다. 첫째로, 움직임 추정은 분할된 영역 정보를 이용한 가변 탐색 영역 설정을 통해 전역 탐색 움직임 추정시 소모되는 많은 연산량을 줄이고, 둘째로, 움직임 추정 후 추정된 움직임 정보를 이용해 영역의 재분할 과정을 통해 분할된 영역별로 움직임 정보를 부호화 함으로써 개선된 부호화 효율을 보이며, 셋째로, 분할된 영역 중 얼굴과 같은 의미를 갖는 영역을 선택적으로 부호화하고 전송하기 위한 인식 기법을 제안하고자 한다.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.41 no.4
• /
• pp.433-441
• /
• 1992

This paper describes an algorithm that can efficiently analyze the ECG signal using frame knowledge representation technique. Input to the analysis process is a set of significant points which have been extracted from an original sampled signal(lead II) by the syntactic peak recognition algorithm. The hierarchical property of ECG signal is represented by hierarchical AND/OR graph. The semantic information and constraints of the ECG signal are desctibed by frame. As the control mechanism for labeling points, the search mechanism with the mixed paradigms of data-driven and model driven hypothesis formation, scoring function, hypothesis modification network and instance inheritance are used. We used the CSE database in order to evaluate the performance of the proposed algorithm.

• ETRI Journal
• /
• v.38 no.3
• /
• pp.487-493
• /
• 2016

Two new methods are proposed for an unsupervised adaptation of a language model (LM) with a single sentence for automatic transcription tasks. At the training phase, training documents are clustered by a method known as Latent Dirichlet allocation (LDA), and then a domain-specific LM is trained for each cluster. At the test phase, an adapted LM is presented as a linear mixture of the now trained domain-specific LMs. Unlike previous adaptation methods, the proposed methods fully utilize a trained LDA model for the estimation of weight values, which are then to be assigned to the now trained domain-specific LMs; therefore, the clustering and weight-estimation algorithms of the trained LDA model are reliable. For the continuous speech recognition benchmark tests, the proposed methods outperform other unsupervised LM adaptation methods based on latent semantic analysis, non-negative matrix factorization, and LDA with n-gram counting.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2006.05a
• /
• pp.219-225
• /
• 2006

This paper studies on the visibility of dashboard in forklift. As part of the real setting devised for this study, 1. Important evaluation by males experience in forklift driving, 2. Icon cognition experiment, 3. Gage cognition experiment, subjects were asked to estimate the important evaluation, sketched to icon and gage position on the screen. Subjective evaluations were carried out by semantic differential method, sketch method, sketch method, then analyzed by consistency test, frequency rate and T-test. I gather the results concerning the relationship between consistent answers and cognition rates of dashboard understand the conditions which create a desired instrument panel.

• Journal of Computing Science and Engineering
• /
• v.3 no.3
• /
• pp.143-164
• /
• 2009

This article surveys recent research in the area of language modeling (sometimes called statistical language modeling) approaches to information retrieval. Language modeling is a formal probabilistic retrieval framework with roots in speech recognition and natural language processing. The underlying assumption of language modeling is that human language generation is a random process; the goal is to model that process via a generative statistical model. In this article, we discuss current research in the application of language modeling to information retrieval, the role of semantics in the language modeling framework, cluster-based language models, use of language modeling for XML retrieval and future trends.