• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.9
• /
• pp.4814-4832
• /
• 2019

Plagiarism detection is increasingly exploiting text alignment. Text alignment involves extracting the plagiarism passages in a pair of the suspicious document and its source document. The heuristics have achieved excellent performance in text alignment. However, the further improvements of the heuristic methods mainly depends more on the experiences of experts, which makes the heuristics lack of the abilities for continuous improvements. To address this problem, machine learning maybe a proper way. Considering the position relations and the context of text segments pairs, we formalize the text alignment task as a problem of sequence labeling, improving the current methods at the model level. Especially, this paper proposes to use the probabilistic graphical model to tag the observed sequence of pairs of text segments. Hence we present the sequence labeling approach for text alignment in plagiarism detection based on Conditional Random Fields. The proposed approach is evaluated on the PAN@CLEF 2012 artificial high obfuscation plagiarism corpus and the simulated paraphrase plagiarism corpus, and compared with the methods achieved the best performance in PAN@CLEF 2012, 2013 and 2014. Experimental results demonstrate that the proposed approach significantly outperforms the state of the art methods.

• Journal of the Korea Safety Management & Science
• /
• v.13 no.2
• /
• pp.147-155
• /
• 2011

For an effective energy management in intelligent buildings it is necessary to gather information about position/absence of people and the level of population. In this paper the smart occupancy detection system based on the active RFID is developed to satisfy such a demand. The performance of the developed system is tested and verified through various experiments. Furthermore the feasibility test of the active RFID tag is performed to verify whether it can be used as a location-based occupancy sensor. The developed core technology can be also applied to other fields such as security, healthcare, smart home, etc.

• Journal of Microbiology
• /
• v.42 no.2
• /
• pp.126-132
• /
• 2004

A single chain variable fragment (scFv) specific towards B. pseudomallei exotoxin had previously been generated from an existing hybridoma cell line (6E6AF83B) and cloned into the phage display vector pComb3H. In this study, the scFv was subcloned into the pComb3X vector to facilitate the detection and purification of expressed antibodies. Detection was facilitated by the presence of a hemagglutinin (HA) tag, and purification was facilitated by the presence of a histidine tag. The culture was grown at 30$^{\circ}C$ until log phase was achieved and then induced with 1 mM IPTG in the absence of any additional carbon source. Induction was continued at 30$^{\circ}C$ for five h. The scFv was discerned by dual processes-direct enzyme-linked immunosorbent assays (ELISA), and Western blotting. When compared to E. coli strains ER2537 and HB2151, scFv expression was observed to be highest in the E. coli strain Topl0F'. The expressed scFv protein was purified via nickel-mediated affinity chromatography and results indicated that two proteins a 52 kDa protein, and a 30 kDa protein were co-purified. These antibodies, when blotted against immobilized exotoxin, exhibited significant specificity towards the exotoxin, com-pared to other B. pseudomallei antigens. Thus, these antibodies should serve as suitable reagents for future affinity purification of the exotoxin.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.7 no.3
• /
• pp.373-378
• /
• 2006

One of the biggest problems that should be solved in present RFID systems is a reduction of identification efficiency by the collision of singals between different tags. As the number of tags, which should be identified, increases over the size of allocated round, more slots experiences the collision between them. It can causes generation of tag collision assigning the fixed round size and so, allocated round size should be regulated properly. This paper proposes the algorithm which can reduce collision between tags, and allocate specific round size dynamically for efficient tag identification. After each round is finished, the reader allocates the round size dynamically using the collision information of the slot. All collision informations of the slot consists of the number of slots which came into conflict, tags which were realized properly without any conflictions and empty slots. We used slotted aloha algorithm as the collision detection algorithm and finally, checked that this could be used very usefully when this algorithm which was proposed effectively could not know how many number of tags were exisisted through the simulation in advance.

• Journal of Environmental Science International
• /
• v.29 no.9
• /
• pp.885-905
• /
• 2020

This study described the characteristics of the upstream migration of salmon (Chum salmon, Oncorhynchus keta) along Yeon-gok Stream in the eastern coastal region of Korea from October 24 to November 9, 2018 using radio tag and data storage tag loggers for the detection of the locations of tagged salmon and measurement of water temperature. Tracking experiments were conducted and classified into four types (case 1 to case 4) depending on the release time and the number of salmon tracked. Experiments from case 1 to case 3 were classified depending on the number of salmon tracked into cases in which a single tagged salmon was tracked (case 1), a pair of tagged salmon was tracked (case 2), and salmon were tracked by different sex ratios (case 3). Experiments from cases 1 to 3 were conducted between 10 AM and 1 PM, and case 4 was conducted after 3:30 PM. Salmon moved and spawned in the downstream region of the Yeon-gok, where water temperature is higher than in other rivers and salmon return in Canada, Russia, Japan, and the U.S.A. Most of the radio-tagged salmon swam in deep and shaded areas during the day but actively moved upstream close to sunset, regardless of the release time. Females showed relatively more active movements than males during upstream migration.

• Development and Reproduction
• /
• v.18 no.4
• /
• pp.275-286
• /
• 2014

To successful molecular breeding, identification and functional characterization of breeding related genes and development of molecular breeding techniques using DNA markers are essential. Although the development of a useful marker is difficult in the aspect of time, cost and effort, many markers are being developed to be used in molecular breeding and developed markers have been used in many fields. Single nucleotide polymorphisms (SNPs) markers were widely used for genomic research and breeding, but has hardly been validated for screening functional genes in olive flounder. We identified single nucleotide polymorphisms (SNPs) from expressed sequence tag (EST) database in olive flounder; out of a total 4,327 ESTs, 693 contigs and 514 SNPs were detected in total EST, and these substitutions include 297 transitions and 217 transversions. As a result, 144 SNP markers were developed on the basis of 514 SNP to selection of useful gene region, and then applied to each of eight wild and culture olive flounder (total 16 samples). In our experimental result, only 32 markers had detected polymorphism in sample, also identified 21 transitions and 11 transversions, whereas indel was not detected in polymorphic SNPs. Heterozygosity of wild and cultured olive flounder using the 32 SNP markers is 0.34 and 0.29, respectively. In conclusion, we identified SNP and polymorphism in olive flounder using newly designed marker, it supports that developed markers are suitable for SNP detection and diversity analysis in olive flounder. The outcome of this study can be basic data for researches for immunity gene and characteristic with SNP.

• Korean Journal of Cognitive Science
• /
• v.12 no.3
• /
• pp.19-28
• /
• 2001

In this paper, we describe an algorithm for transliterated foreign word extraction in Korean language. In the proposed method we reformulate the transliterated foreign word extraction problem as a syllable-tagging problem such that each syllable is tagged with a transliterated foreign syllable tag or a pure Korean syllable tag. Syllable sequences of Korean strings ale modeled by Hidden Markov Model whose state represents a character with binary marking to indicate whether the character forms a Korean word or not. The proposed method extracts a transliterated foreign word with high recall rate and precision rate. Moreover, our method shows good performance even with small-sized training corpora.

• KSBB Journal
• /
• v.25 no.2
• /
• pp.199-204
• /
• 2010

We generated the feasibility of DNA separation in free-solution using genetically engineered repetitive polypeptides as drag-tags. Two different-sized repetitive polypeptides were designed, expressed in E. coli, and purified. They were conjugated to a fluorescently labeled DNA (100 base), and the electrophoretic mobilities of these conjugate molecules were analyzed on a microchip. The results of these studies indicate that genetically engineered repetitive polypeptide is a prominent candidate for rapid and high-throughput genetic mutation detection, such as SNP analysis.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06b
• /
• pp.55-57
• /
• 2006

본 논문에서는 컬러코드를 이용하여 증강현실 시스템에 사용 가능한 태그를 탐지하는 알고리즘을 설계하고 차단 현상에 강인한 알고리즘을 제안하였다. 기존의 ARToolkit에서 태그의 일부분이 사용자 또는 다른 물체에 의해 가려지게 될 경우 증강되었던 객체가 순간 사라져 버리는 불안정성 (Instability) 문제를 해결하기 위한 방법에 초점을 맞춘다. 불안정성의 문제는 이미지 안에 태그가 존재하지만 해당하는 객체를 증강시키지 못하는 False Negative 에러와 태그가 존재하지 않는 곳에 잘못된 객체를 증강시키는 False Positive 에러로 분류 될 수 있다. 제안된 탐지 알고리즘으로 특정 컬러 영역을 분리하여 모서리 여부를 판별하고 모서리인 경우 가려진 꼭지점의 위치를 추출하여 태그가 차단에 의하여 가려졌을 때에도 객체를 안정적으로 증강시킬 수 있다. 기존 AR 시스템들의 태그를 가지고 Daylight 65, Illuminant A. CWF, TL84의 4가지의 표준 조명하에 컬러코드 4종류, ARToolkit 태그 4개, ARTag 4개를 이용하여 실험을 진행하여 차단 현상이 발생하면 전혀 객체를 증강시킬 수 없었던 ARToolkit에서도 DayLight65의 경우 50%의 False Negative. False Positive rate을 보여 기존 증강현실 시스템에서 보였던 불안정성 문제를 개선하였다.

• International Journal of Computer Science & Network Security
• /
• v.21 no.7
• /
• pp.182-190
• /
• 2021

Deep learning is an advanced technology for large-scale data analysis, with numerous promising cases like image processing, object detection and significantly more. It becomes customarily to use transfer learning and fine-tune a pre-trained CNN model for most image recognition tasks. Having people taking photos and tag themselves provides a valuable resource of in-data. However, these tags and labels might be noisy as people who annotate these images might not be experts. This paper aims to explore the impact of noisy labels on fine-tuning pre-trained CNN models. Such effect is measured on a food recognition task using Food101 as a benchmark. Four pre-trained CNN models are included in this study: InceptionV3, VGG19, MobileNetV2 and DenseNet121. Symmetric label noise will be added with different ratios. In all cases, models based on DenseNet121 outperformed the other models. When noisy labels were introduced to the data, the performance of all models degraded almost linearly with the amount of added noise.