• 한국항행학회논문지
• /
• 제12권5호
• /
• pp.502-508
• /
• 2008

인터넷의 급속한 확산과 대량 정보의 이동은 문서요약을 더욱 필요 하고 있다. 본 논문은 비음수 행렬 인수분해로 얻어진 비음수 의미 가변 행렬과 의미특징의 포괄적 중요도를 이용하여 문장을 추출하여서 포괄적 문서요약을 하는 새로운 방법을 제안하였다. 제안된 방법은 인간의 인식 과정과 유사한 비음수 제약을 사용한다. 이 결과 주제의 군집방법이나 잠재의미분석을 사용한 비지도 학습방법에 비해 더욱 의미 있는 문장을 선택하여 문서를 요약할 수 있다. 실험결과 제안방법이 다른 방법들에 비하여 좋은 성능을 보인다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제12권4호
• /
• pp.277-284
• /
• 2012

Named entity recognition (NER) technique can play a crucial role in extracting information from the web. While NER systems with relatively high performances have been developed based on careful manipulation of terms with a statistical model, term mismatches often degrade the performance of such systems because the strings of all the candidate entities are not known a priori. Despite the importance of lexical-level term mismatches for NER systems, however, most NER approaches developed to date utilize only the term string itself and simple term-level features, and do not exploit the semantic features of terms which can handle the variations of terms effectively. As a solution to this problem, here we propose to match the semantic concepts of term units in restaurant named entities (NEs), where these units are automatically generated from multiple resolutions of a semantic tree. As a test experiment, we applied our restaurant NER scheme to 49,153 nouns in Korean restaurant web pages. Our scheme achieved an average accuracy of 87.89% when applied to test data, which was considerably better than the 78.70% accuracy obtained using the baseline system.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제35권4호
• /
• pp.255-264
• /
• 2008

본 논문은 K-means과 비음수 행렬 분해(NMF)를 이용하여 주제기반의 다중문서를 요약하는 새로운 방법을 제안하였다. 제안방법은 비음수 행렬 분해를 이용하여 가중치가 부여된 용어-문장 행렬을 희소(Sparse)한 비음수 의미특징 행렬과 비음수 변수 행렬로 분해함으로써 직관적으로 이해할 수 있는 형태의 의미적 특징을 추출할 수 있고, 주제와 의미특징간의 유사도에 가중치를 부여하여 유사도는 높으나 실제 의미 없는 문장이 추출되는 것을 막는다. 또한 K-means 군집을 이용하여 문장에 포함된 노이즈를 제거함으로써 문서의 의미가 요약에 편향되게 반영하는 것을 피할 수 있고, 추출된 문장에 부여된 순위순서대로 정렬하여 보여 줌으로써 응집성을 높인다. 실험 결과 제안방법이 다른 방법에 비하여 좋은 성능을 보인다.

• 한국멀티미디어학회논문지
• /
• 제21권12호
• /
• pp.1425-1430
• /
• 2018

In this paper, we propose a CNN based deep learning algorithm for semantic segmentation of images. In order to improve the accuracy of semantic segmentation, we combined pixel level object classification and image level object classification. The image level object classification is used to accurately detect the characteristics of an image, and the pixel level object classification is used to indicate which object area is included in each pixel. The proposed network structure consists of three parts in total. A part for extracting the features of the image, a part for outputting the final result in the resolution size of the original image, and a part for performing the image level object classification. Loss functions exist for image level and pixel level classification, respectively. Image-level object classification uses KL-Divergence and pixel level object classification uses cross-entropy. In addition, it combines the layer of the resolution of the network extracting the features and the network of the resolution to secure the position information of the lost feature and the information of the boundary of the object due to the pooling operation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권1호
• /
• pp.245-265
• /
• 2022

In response to problems such as insufficient extraction information, low detection accuracy, and frequent misdetection in the field of Thangka image defects, this paper proposes a YOLOv5 prediction algorithm fused with the attention mechanism. Firstly, the Backbone network is used for feature extraction, and the attention mechanism is fused to represent different features, so that the network can fully extract the texture and semantic features of the defect area. The extracted features are then weighted and fused, so as to reduce the loss of information. Next, the weighted fused features are transferred to the Neck network, the semantic features and texture features of different layers are fused by FPN, and the defect target is located more accurately by PAN. In the detection network, the CIOU loss function is used to replace the GIOU loss function to locate the image defect area quickly and accurately, generate the bounding box, and predict the defect category. The results show that compared with the original network, YOLOv5-SE and YOLOv5-CBAM achieve an improvement of 8.95% and 12.87% in detection accuracy respectively. The improved networks can identify the location and category of defects more accurately, and greatly improve the accuracy of defect detection of Thangka images.

• Journal of information and communication convergence engineering
• /
• 제22권1호
• /
• pp.56-63
• /
• 2024

Despite the rapid strides in content-based image retrieval, a notable disparity persists between the visual features of images and the semantic features discerned by humans. Hence, image retrieval based on the association of semantic similarities recognized by humans with visual similarities is a difficult task for most image-retrieval systems. Our study endeavors to bridge this gap by refining image semantics, aligning them more closely with human perception. Deep learning techniques are used to semantically classify images and retrieve those that are semantically similar to personalized images. Moreover, we introduce a keyword-based image retrieval, enabling automatic labeling of images in mobile environments. The proposed approach can improve the performance of a mobile device with limited resources and bandwidth by performing retrieval based on the visual features and keywords of the image on the mobile device.

• 한국IT서비스학회지
• /
• 제10권3호
• /
• pp.189-201
• /
• 2011

Feature models are widely used to model commonalities and variabilities among products during software product line development. Feature configurations are generated by selecting the features to be included in individual products. Automated tools to identify errors or inconsistencies in the feature models and configurations are essential to successful software product line engineering. This paper proposes a verification technique and tool based on semantic web technologies such as OWL, SWRL and Protege API. This approach checks the feature model and configuration based on predefined rules and provides information on existence of errors as well as the kinds of those errors. This approach is extensible due to ease of rule modification and may be easily applied to other environments because semantic web technologies can be easily integrated with other programming environments. This paper demonstrates how various semantic web-related technologies can support automatic verification of one kind of software development artifact, the feature model.

• 한국군사과학기술학회지
• /
• 제25권6호
• /
• pp.606-616
• /
• 2022

Semantic segmentation in autonomous driving for unstructured environments is challenging due to the presence of uneven terrains, unstructured class boundaries, irregular features and strong textures. Current off-road datasets exhibit difficulties like class imbalance and understanding of varying environmental topography. To overcome these issues, we propose a deep learning framework for semantic segmentation that involves a pooled class semantic segmentation with five classes. The evaluation of the framework is carried out on two off-road driving datasets, RUGD and TAS500. The results show that our proposed method achieves high accuracy and real-time performance.

• 인문언어
• /
• 제6권
• /
• pp.321-357
• /
• 2004

In this article the structure of modern Russian humor is analyzed on the basis of some theories: bi-sociation theory (Koestler 1964), semantic script theory of verbal humor, using the concept of semantic presupposition, pragmatic felicity condition (Searle 1969; Levinson 1983) and grammatical rules (Chomsky 1965). Up to now the listed former theories were not examined and less analyzed by the semantic structure in the study of the structure of Russian humor(HcaeBa 1969; 3 $a_{OPHOB}$ 1991; 1992). Kreps (1981), who analyzed the works of Zoschenko, presented 21 types of humor, using the term 'humoreme'(Kpenc 1981, 36-37). These types are the list of the available means of humor that work not in the base of semantic criteria, but in the base of means of literary rhetoric. Kreps presented types of humor means, such as contradiction, antonymic substitution, macaronic speech and correlation of humoremes in the various types of humor. Apart from Kreps, Manakov (MaHaKOB 1986, 61-79) also studied these problems. He also set the system of the basic types of humor. Manakov introduced the linguistic means of humor of some Russian writers: Gogol, Tchechov. The means that Manakov showed with detailed examples, are trope, epithet, comic comparison, comic metaphor, comic periphrasis, euphemism, pun, zeugma, comic toponym, comic onomatopoeia, mania of foreign vocabulary, folk etymology, dialect etc. But these studies don't explain why these means make the works humorous. An, B.p tried to answer this question (안병팔 1997 a; b). An B.p. explains contexts of humor through the Release theory, the Superiority theory and the Incongruity theory. An, B.p. explained the process of deviation from the grammatical norms through morpho-syntactic and lexical means. But in these studies the humor was not analyzed by the semantic criteria. In order to linguistically evaluate various means of humor formation, it is necessary to elicit its deep structure, which makes it possible to research the formation and interpretation of humor. For this purpose this article, being based on the Incongruity theory, defined the structure of humor as negation of presupposition. Of course the former traditional studies also well shared the concept of 'contradiction' and 'contrast' of humor structure, but they didn't explain the structure by semantic differential features. This study, analyzing the works of' Zadornov, M., tried to note that through the negation of semantic presupposition the structure of contradiction is formed with semantic differential features on the semantic, syntactic or lexical dimensions.

• 정보과학회 논문지
• /
• 제44권12호
• /
• pp.1282-1289
• /
• 2017

최근 심층 컨볼루션 신경망을 활용한 이미지 분할과 물체 위치감지 연구가 활발히 진행되고 있다. 특히 네트워크의 최상위 단에서 추출한 특징 지도뿐만 아니라, 중간 은닉 층들에서 추출한 특징 지도를 활용하면 더욱 정확한 물체 감지를 수행할 수 있고 이에 대한 연구 또한 활발하게 진행되고 있다. 이에 밝혀진 경험적 특성 중 하나로 중간 은닉 층마다 추출되는 특징 지도는 각기 다른 특성을 가지고 있다는 것이다. 그러나 모델이 깊어질수록 가능한 중간 연결과 이용할 수 있는 중간 층 특징 지도가 많아지는 반면, 어떠한 중간 층 연결이 물체 분할에 더욱 효과적일지에 대한 연구는 미비한 상황이다. 또한 중간층 연결 방식 및 중간층의 특징 지도에 대한 정확한 분석 또한 부족한 상황이다. 따라서 본 연구에서 최신 깊은 신경망에서 중간층 연결의 특성을 파악하고, 어떠한 중간 층 연결이 물체 감지에 최적의 성능을 보이는지, 그리고 중간 층 연결마다 특징은 어떠한지 밝혀내고자 한다. 그리고 이전 방식에 비해 더 깊은 신경망을 활용하는 물체 분할의 방법과 중간 연결의 방향을 제시한다.