• The KIPS Transactions:PartB
• /
• v.10B no.6
• /
• pp.687-694
• /
• 2003

According to the rapid increase of multimedia data quantity recently, various means of video data search has been desired. In order to process video data effectively, it is required that the content information of video data is loaded in database and semantic-based retrieval method can be available for various query of users. Currently existent contents-based video retrieval systems search by single method such as annotation-based or feature-based retrieval, and show low search efficiency and requires many efforts of system administrator or annotator form less perfect automatic processing. In this paper, we propose semantic-based video retrieval system which support semantic retrieval of various users by feature-based retrieval and annotation-based retrieval of massive video data. By user's fundamental query and selection of image for key frame that extracted from query, the agent gives the detail shape for annotation of extracted key frame. Also, key frame selected by user become query image and searches the most similar key frame through feature based retrieval method that propose. Therefore, we design the system that can heighten retrieval efficiency of video data through semantic-based retrieval.

• The KIPS Transactions:PartB
• /
• v.11B no.6
• /
• pp.701-708
• /
• 2004

Existing contents-based video retrieval systems search by using a single method such as annotation-based or feature-based retrieval. Hence, it not only shows low search efficiency, but also requires many efforts to provide system administrator or annotator with a perfect automatic processing. Tn this paper, we propose an agent-based, and automatic and unified semantics-based video retrieval system, which support various semantics-retrieval of the massive video data by integrating the feature-based retrieval and the annotation-based retrieval. The indexing agent embodies the semantics about annotation of extracted key frames by analyzing a fundamental query of a user and by selecting a key-frame image that is ed by a query. Also, a key frame selected by user takes a query image of the feature-based retrieval and the indexing agent searches and displays the most similar key-frame images after comparing query images with key frames in the database by using the color-multiple-partition histogram techniques. Furthermore, it is shown that the performance of the proposed system can be significantly improved.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.5
• /
• pp.11-18
• /
• 2008

One of important Issues in computer graphics field is to communicate among users in virtual world like secondlife. However, in 3D virtual world, users' needs to wish to build their own contents in 3D virtual space are rising, similarly, users produce own homepage and animation, and leave writing in notice board. In this paper, we tried to achieve this by introducing semantic annotation object concept, which is a kind of annotation method in 3D virtual world. User can retrieve an 3D object by searching corresponding annotation data. This method can build semantic 3D virtual world and enable users to search 3D objects by integrating 3D object and 2D semantic multimedia information. Also, through a comparison experiment with proposal system and general 3D virtual world. the performance of proposed system is evaluated.

• Animal Systematics, Evolution and Diversity
• /
• v.36 no.4
• /
• pp.336-346
• /
• 2020

Mitochondrial genome is an important molecule for systematic and evolutionary studies in metazoans. The development of next-generation sequencing (NGS) technique has rapidly increased the number of mitogenome sequences. The process of generating mitochondrial genome based on NGS includes different steps, from DNA preparation, sequencing, assembly, and annotation. Despite the effort to improve sequencing, assembly, and annotation methods of mitogenome, the low quality and/or quantity sequence in the final map can still be generated through the work. Therefore, it is necessary to check and curate mitochondrial genome sequence after annotation for proofreading and feedback. In this study, we introduce the pipeline for sequencing and curation for mitogenome based on NGS. For this purpose, two mitogenome sequences of Dermatobranchus otome were sequenced by Illumina Miseq system with different amount of raw read data. Generated reads were targeted for assembly and annotation with commonly used programs. As abnormal repeat regions present in the mitogenomes after annotation, primers covering these regions were designed and conventional PCR followed by Sanger sequencing were performed to curate the mitogenome sequences. The obtained sequences were used to replace the abnormal region. Following the replacement, each mitochondrial genome was compared with the other as well as the sequences of close species available on the Genbank for confirmation. After curation, two mitogenomes of D. otome showed a typically circular molecule with 14,559 bp in size and contained 13 protein-coding genes, 22 tRNA genes, two rRNA genes. The phylogenetic tree revealed a close relationship between D. otome and Tritonia diomea. The finding of this study indicated the importance of caution and curation for the generation of mitogenome from NGS.

• Journal of Life Science
• /
• v.16 no.3 s.76
• /
• pp.472-476
• /
• 2006

We have built a database server called HorseDB which contains the genome annotation information and biological information for horse from public database entries. The aims of HorseDB are the integration of biological information and horse genome data on genome scale using bioinformatic methods. To facilitate the extraction of useful information among collected horse genome and biological data, we developed a user-friendly interface system, HorseDB; an Integrated Horse Resource and web Service. The database is categorized by the general horse information data, a sequence annotation data, and a world-wide web analysis program interface. The database also provides an easy access for user to find out the useful information within horse genomes and support analyzed information, such as sequence alignment and gene annotation results. HorseDB can be accessed at http://www.primate.or.kr./horse.

• Journal of Korea Multimedia Society
• /
• v.9 no.1
• /
• pp.127-137
• /
• 2006

In order to process video data effectively, it is required that the content information of video data is loaded in database and semantic- based retrieval method can be available for various query of users. Currently existent contents-based video retrieval systems search by single method such as annotation-based or feature-based retrieval, and show low search efficiency and requires many efforts of system administrator or annotator form less perfect automatic processing. In this paper, we propose semantic-based video retrieval system which support semantic retrieval of various users by feature-based retrieval and annotation-based retrieval of massive video data. By user's fundamental query and selection of image for key frame that extracted from query, the automatic indexing agent gives the detail shape for annotation of extracted key frame. Also, key frame selected by user become query image and searches the most similar key frame through feature based retrieval method that propose. Therefore, we propose the system that can heighten retrieval efficiency of video data through semantic-based retrieval.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.8
• /
• pp.2031-2041
• /
• 1999

In this paper, we present the HVIS (Hybrid Video Information System) which bolsters up meaning retrieval of all the various users by integrating feature-based retrieval and annotation-based retrieval of unformatted formed and massive video data. HVIS divides a set of video into video document, sequence, scene and object to model the metadata and suggests the Two layered Hybrid Object-oriented Metadata Model(THOMM) which is composed of raw-data layer for physical video stream, metadata layer to support annotation-based retrieval, content-based retrieval, and similarity retrieval. Grounded on this model, we presents the video query language which make the annotation-based query, content-based query and similar query possible and Video Query Processor to process the query and query processing algorithm. Specially, We present the similarity expression to appear degree of similarity which considers interesting of user. The proposed system is implemented with Visual C++, ActiveX and ORACLE.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.04a
• /
• pp.85-88
• /
• 2007

본 연구에서는 베이지안 망 구조 학습에서, 학습 데이터의 특정 부분집합이 학습된 망의 각연결 구조(edge)의 형성에 기여하는 정도를 정량화하는 방법을 제안한다. 생물학 정보의 분석 등에 베이지안 망 학습을 이용하는 경우, 제안된 방법은 망의 각 연결 구조의 형성에 특정 군집 데이터가 기여하는 정도의 정량화가 가능하다. 제안된 방법의 유효성을 보이기 위해, 벤치마크 베이지안 망을 이용하여 제안된 방법이 망 연결 구조에 대한 데이터 군집별 기여도를 효과적으로 정량화 할 수 있음을 보인다.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.1
• /
• pp.124-131
• /
• 2024

Breast cancer classification using ultrasound, while widely employed, faces challenges due to its relatively low predictive value arising from significant overlap in characteristics between benign and malignant lesions, as well as operator-dependency. To alleviate these challenges and reduce dependency on radiologist interpretation, the implementation of automatic breast cancer classification in ultrasound image can be helpful. To deal with this problem, we propose a semi-supervised deep learning framework for breast cancer classification. In the proposed method, we could achieve reasonable performance utilizing less than 50% of the training data for supervised learning in comparison to when we utilized a 100% labeled dataset for training. Though it requires more modification, this methodology may be able to alleviate the time-consuming annotation burden on radiologists by reducing the number of annotation, contributing to a more efficient and effective breast cancer detection process in ultrasound images.

• Parasites, Hosts and Diseases
• /
• v.54 no.6
• /
• pp.751-758
• /
• 2016

This study aimed at constructing a draft genome of the adult female worm Toxocara canis using next-generation sequencing (NGS) and de novo assembly, as well as to find new genes after annotation using functional genomics tools. Using an NGS machine, we produced DNA read data of T. canis. The de novo assembly of the read data was performed using SOAPdenovo. RNA read data were assembled using Trinity. Structural annotation, homology search, functional annotation, classification of protein domains, and KEGG pathway analysis were carried out. Besides them, recently developed tools such as MAKER, PASA, Evidence Modeler, and Blast2GO were used. The scaffold DNA was obtained, the N50 was 108,950 bp, and the overall length was 341,776,187 bp. The N50 of the transcriptome was 940 bp, and its length was 53,046,952 bp. The GC content of the entire genome was 39.3%. The total number of genes was 20,178, and the total number of protein sequences was 22,358. Of the 22,358 protein sequences, 4,992 were newly observed in T. canis. Following proteins previously unknown were found: E3 ubiquitin-protein ligase cbl-b and antigen T-cell receptor, zeta chain for T-cell and B-cell regulation; endoprotease bli-4 for cuticle metabolism; mucin 12Ea and polymorphic mucin variant C6/1/40r2.1 for mucin production; tropomodulin-family protein and ryanodine receptor calcium release channels for muscle movement. We were able to find new hypothetical polypeptides sequences unique to T. canis, and the findings of this study are capable of serving as a basis for extending our biological understanding of T. canis.