• 스마트미디어저널
• /
• 제11권3호
• /
• pp.31-38
• /
• 2022

문서 추출 요약 연구에서는 문장 간 관계를 기반으로 중요한 문장을 선택하는 다양한 방법들이 제안되었다. 문장의 도합유사도를 이용한 한국어 문서 요약에서는 문장의 도합유사도를 문장 정보량으로 보고, 이를 기준으로 중요한 문장을 선택하여 요약문을 추출하였다. 그러나 이는 각 문장이 전체 문서에 기여하는 다양한 중요도를 고려하지 못한다는 문제가 있다. 이에 본 연구에서는 문장의 정량적 정보량과 의미적 정보량을 기반으로 중요한 문장을 선택하여 요약문을 제공하는 문서 추출 요약 방법을 제안한다. 실험 결과, 추출 문장 일치도는 58.56%, ROUGE 점수가 34로 비교 연구보다 우수한 성능을 보였으며, 딥러닝 기반 방법과 비교해 추출 방법은 가볍지만 성능은 유사하였다. 이를 통해 문장 간 의미적 유사성을 기반으로 정보를 압축해 나가는 방식이 문서 추출 요약에서 중요한 접근 방법임을 확인하였다. 또한 빠르게 추출된 요약문을 기반으로 문서 생성요약단계를 효과적으로 수행할 수 있으리라 기대한다.

• 제어로봇시스템학회논문지
• /
• 제17권3호
• /
• pp.277-282
• /
• 2011

This paper describes a sensor fusion-based semantic map building which can improve the capabilities of a mobile robot in various domains including localization, path-planning and mapping. To build a semantic map, various environmental information, such as doors and cliff areas, should be extracted autonomously. Therefore, we propose a method to detect doors, cliff areas and robust visual features using a laser scanner and a vision sensor. The GHT (General Hough Transform) based recognition of door handles and the geometrical features of a door are used to detect doors. To detect the cliff area and robust visual features, the tilting laser scanner and SIFT features are used, respectively. The proposed method was verified by various experiments and showed that the robot could build a semantic map autonomously in various indoor environments.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권3호
• /
• pp.1722-1741
• /
• 2017

Intrusion detection techniques based on virtual machine introspection (VMI) provide high temper-resistance in comparison with traditional in-host anti-virus tools. However, the presence of semantic gap also leads to the performance and compatibility problems. In order to map raw bits of hardware to meaningful information of virtual machine, detailed knowledge of different guest OS is required. In this work, we present VDSM, a lightweight and general approach based on driver separation mechanism: divide semantic view reconstruction into online driver of view generation and offline driver of semantics extraction. We have developed a prototype of VDSM and used it to do intrusion detection on 13 operation systems. The evaluation results show VDSM is effective and practical with a small performance overhead.

• 한국언어정보학회:학술대회논문집
• /
• 한국언어정보학회 2007년도 정기학술대회
• /
• pp.76-85
• /
• 2007

This paper addresses a task of opinion extraction from given documents and its positive/negative classification. We propose a sentence classification method using a notion of syntactic piece. Syntactic piece is a minimum unit of structure, and is used as an alternative processing unit of n-gram and whole tree structure. We compute its semantic orientation, and classify opinion sentences into positive or negative. We have conducted an experiment on more than 5000 opinion sentences of multiple domains, and have proven that our approach attains high performance at 91% precision.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권8호
• /
• pp.1996-2015
• /
• 2023

High-definition (HD) maps can provide precise road information that enables an autonomous driving system to effectively navigate a vehicle. Recent research has focused on leveraging semantic segmentation to achieve automatic annotation of HD maps. However, the existing methods suffer from low recognition accuracy in automatic driving scenarios, leading to inefficient annotation processes. In this paper, we propose a novel semantic segmentation method for automatic HD map annotation. Our approach introduces a new encoder, known as the convolutional transformer hybrid encoder, to enhance the model's feature extraction capabilities. Additionally, we propose a multi-level fusion module that enables the model to aggregate different levels of detail and semantic information. Furthermore, we present a novel decoupled boundary joint decoder to improve the model's ability to handle the boundary between categories. To evaluate our method, we conducted experiments using the Bird's Eye View point cloud images dataset and Cityscapes dataset. Comparative analysis against stateof-the-art methods demonstrates that our model achieves the highest performance. Specifically, our model achieves an mIoU of 56.26%, surpassing the results of SegFormer with an mIoU of 1.47%. This innovative promises to significantly enhance the efficiency of HD map automatic annotation.

• 한국컴퓨터정보학회논문지
• /
• 제26권1호
• /
• pp.163-170
• /
• 2021

빅데이터가 여러 분야에서 다양하게 접목됨에 따라 빅데이터 시장이 하드웨어로부터 시작해서 서비스 소프트웨어 부문으로 확장되고 있다. 특히 빅데이터 의미 파악 및 이해 능력, 분석 결과 등 총체적이고 직관적인 시각화를 위하여 애플리케이션을 제공하는 거대 플랫폼 시장으로 확대되고 있다. 그 중에서 SNS(Social Network Service) 등과 같은 소셜 미디어를 활용한 빅데이터 추출 및 분석에 대한 수요가 기업 뿐만 아니라 개인에 이르기까지 매우 활발히 진행되고 있다. 그러나 이처럼 사용자 트렌드 분석과 마케팅을 위한 소셜 미디어 데이터의 수집 및 분석에 대한 많은 수요에도 불구하고, 다양한 소셜 미디어 서비스 인터페이스의 이질성으로 인한 동적 연동의 어려움과 소프트웨어 플랫폼 구축 및 운영의 복잡성을 해결하기 위한 연구가 미흡한 상태이다. 따라서 본 논문에서는 소셜 미디어 데이터의 수집에서 추출 및 분류에 이르는 과정을 하나로 통합하여 운영할 수 있는 프레임워크를 개발하는 방법에 대해 제시한다. 제시된 프레임워크는 이질적인 소셜 미디어 데이터 수집 채널의 문제를 어댑터 패턴을 통해 해결하고, 의미 연관성 기반 추출 기법과 주제 연관성 기반 분류 기법을 통해 소셜 토픽 추출과 분류의 정확성을 높였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권3호
• /
• pp.771-791
• /
• 2022

Protein-protein interaction (PPI) extraction from original text is important for revealing the molecular mechanism of biological processes. With the rapid growth of biomedical literature, manually extracting PPI has become more time-consuming and laborious. Therefore, the automatic PPI extraction from the raw literature through natural language processing technology has attracted the attention of the majority of researchers. We propose a PPI extraction model based on the large pre-trained language model and adversarial training. It enhances the learning of semantic and syntactic features using BioBERT pre-trained weights, which are built on large-scale domain corpora, and adversarial perturbations are applied to the embedding layer to improve the robustness of the model. Experimental results showed that the proposed model achieved the highest F1 scores (83.93% and 90.31%) on two corpora with large sample sizes, namely, AIMed and BioInfer, respectively, compared with the previous method. It also achieved comparable performance on three corpora with small sample sizes, namely, HPRD50, IEPA, and LLL.

• ETRI Journal
• /
• 제33권5호
• /
• pp.720-730
• /
• 2011

Opinion mining involves the analysis of customer opinions using product reviews and provides meaningful information including the polarity of the opinions. In opinion mining, feature extraction is important since the customers do not normally express their product opinions holistically but separately according to its individual features. However, previous research on feature-based opinion mining has not had good results due to drawbacks, such as selecting a feature considering only syntactical grammar information or treating features with similar meanings as different. To solve these problems, this paper proposes an enhanced feature extraction and refinement method called FEROM that effectively extracts correct features from review data by exploiting both grammatical properties and semantic characteristics of feature words and refines the features by recognizing and merging similar ones. A series of experiments performed on actual online review data demonstrated that FEROM is highly effective at extracting and refining features for analyzing customer review data and eventually contributes to accurate and functional opinion mining.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권8호
• /
• pp.3806-3825
• /
• 2016

This paper brings out a neoteric frame of reference for visual semantic based 3d video search and retrieval applications. Newfangled 3D retrieval application spotlight on shape analysis like object matching, classification and retrieval not only sticking up entirely with video retrieval. In this ambit, we delve into 3D-CBVR (Content Based Video Retrieval) concept for the first time. For this purpose we intent to hitch on BOVW and Mapreduce in 3D framework. Here, we tried to coalesce shape, color and texture for feature extraction. For this purpose, we have used combination of geometric & topological features for shape and 3D co-occurrence matrix for color and texture. After thriving extraction of local descriptors, TB-PCT (Threshold Based- Predictive Clustering Tree) algorithm is used to generate visual codebook. Further, matching is performed using soft weighting scheme with L₂ distance function. As a final step, retrieved results are ranked according to the Index value and produce results .In order to handle prodigious amount of data and Efficacious retrieval, we have incorporated HDFS in our Intellection. Using 3D video dataset, we fiture the performance of our proposed system which can pan out that the proposed work gives meticulous result and also reduce the time intricacy.

• 디지털융복합연구
• /
• 제11권9호
• /
• pp.147-151
• /
• 2013

질의 키워드의 출현 빈도수가 높은 문서를 검색하면 키워드의 의미가 다양하여 정확한 정보를 인지하지 못하며, 기존 검색 시스템의 온톨로지 구성만으로는 검색된 문서들이 사용자의 요구에 부합되지 않는 문제점을 가진다. 본 연구에서는 시맨틱 웹 기술을 기반으로 인사관리에서 인선에 필요한 다양한 개념들과 지식으로 구성된 인선 온톨로지와 인선 규칙들을 구축하고 이들을 지원하는 인선 절차와 인선 결과의 적합성을 확인할 수 있는 시스템을 제안한다. 또한, 이를 기반으로 비모수적 상관 계수를 이용하여 음성 정보를 추출하는 방법을 사용하여 평균 SNR이 0.752dB 감소됨을 보임으로써 제안한 방법의 우수성을 확인하였다.