• Proceedings of the Korean Society for Language and Information Conference
• /
• 2002.02a
• /
• pp.166-176
• /
• 2002

A homonym could be disambiguated by another words in the context as nouns, predicates used with the homonym. This paper using semantic information (co-occurrence data) obtained from definitions of part of speech (POS) tagged UMRD-S$^1$), In this research, we have analyzed the result of an experiment on a homonym disambiguation system based on statistical model, to which Bayes'theorem is applied, and suggested a model established of the weight of sense rate and the weight of distance to the adjacent words to improve the accuracy. The result of applying the homonym disambiguation system using semantic information to disambiguating homonyms appearing on the dictionary definition sentences showed average accuracy of 98.32% with regard to the most frequent 200 homonyms. We selected 49 (31 substantives and 18 predicates) out of the 200 homonyms that were used in the experiment, and performed an experiment on 50,703 sentences extracted from Sejong Project tagged corpus (i.e. a corpus of morphologically analyzed words) of 3.5 million words that includes one of the 49 homonyms. The result of experimenting by assigning the weight of sense rate(prior probability) and the weight of distance concerning the 5 words at the front/behind the homonym to be disambiguated showed better accuracy than disambiguation systems based on existing statistical models by 2.93%,

• Journal of radiological science and technology
• /
• v.40 no.2
• /
• pp.237-243
• /
• 2017

This study evaluated the applicability of computer-aided diagnosis by retrospective analysis of GLCM algorithm based on cytopathological diagnosis of normal and malignant nodules in thyroid ultrasound images. In the experiment, the recognition rate and ROC curve of thyroid malignant nodule were analyzed using 6 parameters of GLCM algorithm. Experimental results showed 97% energy, 93% contrast, 92% correlation, 92% homogeneity, 100% entropy and 100% variance. Statistical analysis showed that the area under the curve of each parameter was more than 0.947 (p = 0.001) in the ROC curve, which was significant in the recognition of thyroid malignant nodules. In the GLCM, the cut-off value of each parameter can be used to predict the disease through analysis of quantitative computer-aided diagnosis.

• Korean Journal of Remote Sensing
• /
• v.33 no.5_1
• /
• pp.537-546
• /
• 2017

This study aims to develop the floating debris detection algorithm using a Unmanned Aerial Vehicle (UAV) and multispectral sensors. In addition, the occurrence range of floating debris was estimated by applying the algorithm. An aerial photograph using an unmanned aerial vehicle was used to generate an orthoimage that can calculate the area. A spectrum survey of water, plants litter, polystyrene foam etc. was conducted. After obtaining spectroscopic characteristics of floating debris and water, the River Floating Debris (RFD) index was calculated. And we detected the floating debris through band combination of sensor using RFD. As a result of the RFD application, accumulation zone of floating debris was confirmed at three sites in the orthoimage. It was estimated that a lot of floating debris was accumulated at 0.82 ha ($8,200m^2$), which is corresponding to 3.6% including the accumulation zone.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2001.01a
• /
• pp.272-277
• /
• 2001

In this paper, we describe a new method for selecting information sources in a distributed environment. Recently, there has been much research on distributed information retrieval, that is information retrieval (IR) based on a multi-database model in which the existence of multiple sources is modeled explicitly. In distributed IR, a method is needed that would enable selecting appropriate sources for users\` queries. Most existing methods use statistical data such as document frequency. These methods may select inappropriate ate sources if a query contains polysemous words. In this paper, we describe an information-source selection method using two types of thesaurus. One is a thesaurus automatically constructed from documents in a source. The other is a hand-crafted general-purpose thesaurus(e.g. WordNet). Terms used in documents in a source differ from one another and the meanings of a term differ depending on th situation in which the term is used. The difference is a characteristic of the source. In our method, the meanings of a term are distinguished between by the relationship between the term and other terms, and the relationship appear in the co-occurrence-based thesaurus. In this paper, we describe an algorithm for evaluating a usefulness of a source for a query based on a thesaurus. For a practical application of our method, we have developed Papits, a multi-agent-based in formation sharing system. An experiment of selection shows that our method is effective for selecting appropriate sources.

• Journal of the Korea Computer Industry Society
• /
• v.2 no.12
• /
• pp.1581-1590
• /
• 2001

This paper asserted more developmental model of WSD(word sense disambiguation) than J. Hur(2000)'s WSD model. This model suggested an improved statistical homonym disambiguation Model based on Bayes Theory. This paper using semantic information(co-occurrence data) obtained from definitions of part of speech(POS) tagged UMRD-S(Ulsan university Machine Readable Dictionary(Semantic Tagged)). we extracted semantic features in the context as nouns, predicates and adverbs from the definitions in the korean dictionary. In this research, we make an experiment with the accuracy of WSD system about major nine homonym nouns and new seven homonym predicates supplementary. The inner experimental result showed average accuracy of 98.32% with regard to the most Nine homonym nouns and 99.53% for the Seven homonym predicates. An Addition, we save test on Korean Information Base and ETRI's POS tagged corpus. This external experimental result showed average accuracy of 84.42% with regard to the most Nine nouns over unsupervised learning sentences from Korean Information Base and ETRI Corpus, 70.81 ％ accuracy rate for the Seven predicates from Sejong Project phrase part tagging corpus (3.5 million phrases) too.

• The Plant Pathology Journal
• /
• v.20 no.4
• /
• pp.244-246
• /
• 2004

Sectors of rice blast fungus, Pyricularia grisea, frequently appeared on potato dextrose agar amended with edifenphos and iprobenfos. Thus, we assessed the sector-forming frequency of isolates of P. grisea and compared the fungicide sensitivity between wild types and sectors against the fungicides. The 905 isolates of the fungus were obtained from rice-growing locations in Korea from 1997-1998. When the isolates were grown on potato dextrose agar amended with minimal inhibitory concentrations of edifenphos (20 ${\mu}$g a.i./ml)and iprobenfos (55 ${\mu}$g a.i./ml), they produced sectors that overcame the effect of the fungicides. Among the 905 isolates tested, 9.0% produced sectors against edifenphos and 5.6%, against iprobenfos. Different sector-forming frequencies were also observed among the 11 locations of Korea. Sectors obtained from the fungicide-amended media generally grew more than their counterpart wild types grown on the media with either edifenphos or iprobenfos, regardless of their origins. In this study, greater relative growth of sectors over wild types of tested isolates can support the resistant characteristic of the fungus to survive against the fungicides. Therefore, the results indicate that the sectoring in rice blast fungus, P. grisea, may play a role in the occurrence of fungicide resistance.

• Proceedings of the Korean Society of Tribologists and Lubrication Engineers Conference
• /
• 2004.11a
• /
• pp.296-300
• /
• 2004

Currently. the study on structural ceramic helps to suggest the precise data of friction and wear in accordance with the various conditions in operations. Also, the study helps to predict effective operating conditions by monitoring the occurrence of wear transition. The studies in the Past were mainly concentrated in using identical materials. However, it is highly likely to have unqualified data from the differences of mechanical and chemical properties between ceramic materials. Thus, in this study, through conducting the ball-on-disk type wear testing, the different ceramic materials has been used to consider tribological characteristics between different ceramic materials. We conducted the wear test by using three kinds of specimen which are zirconia, alumina and silicon carbide against zirconia. We have changed the sliding velocity and the loading conditions in this test and found out that there is row friction coefficient and wear rate in the combination of zirconia and silicon carbide.

• Journal of Animal Science and Technology
• /
• v.54 no.6
• /
• pp.449-454
• /
• 2012

The present study was performed to investigate the effects of the plane of nutrition on growth performance and meat quality traits, especially marbling and PSE (pale, soft, and exudative), in finishing pigs. One hundred and four barrows and 102 gilts born to Yorkshire ${\times}$ Landrace dams and Duroc sires were randomly allocated to 16 pens at approximately 80-kg body weight, with 13 animals housed per pen except for two pens. Each eight pens received a diet containing either 3.4 Mcal ME/kg and 0.98% total lysine (high plane) or 3.1 Mcal ME/kg and 0.81% total lysine (medium plane). All animals were slaughtered at approximately 112 kg BW on an average, after which the Longissimus muscle (LM) was analyzed physicochemically. The ADG, ADFI, gain:feed as well as marbling score did not differ between the two dietary groups, whereas backfat thickness was greater in the high-plane group than in the medium-plane group (24.1 vs. 22.5 mm P<0.05). No LM exhibited PSE, i.e. $L^*$ (lightness) > 50, pH < 6.0 and drip loss > 5.0%, nor were these PSE-related variables influenced by the dietary treatment. Contents of crude protein and fat in LM did not differ between the two dietary groups. In conclusion, the present results suggest that growth performance and the occurrence of the PSE or 'watery' carcass are not influenced significantly by increasing the plane of nutrition in finishing pigs when the finisher is adequate nutritionally for supporting maximal lean growth. However, increasing the plane of nutrition is likely to result in an increase in fat deposition.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.7
• /
• pp.2633-2648
• /
• 2015

The problem of visual words' synonymy and ambiguity always exist in the conventional bag of visual words (BoVW) model based object category methods. Besides, the noisy visual words, so-called "visual stop-words" will degrade the semantic resolution of visual dictionary. In view of this, a novel bag of visual words method based on PLSA and chi-square model for object category is proposed. Firstly, Probabilistic Latent Semantic Analysis (PLSA) is used to analyze the semantic co-occurrence probability of visual words, infer the latent semantic topics in images, and get the latent topic distributions induced by the words. Secondly, the KL divergence is adopt to measure the semantic distance between visual words, which can get semantically related homoionym. Then, adaptive soft-assignment strategy is combined to realize the soft mapping between SIFT features and some homoionym. Finally, the chi-square model is introduced to eliminate the "visual stop-words" and reconstruct the visual vocabulary histograms. Moreover, SVM (Support Vector Machine) is applied to accomplish object classification. Experimental results indicated that the synonymy and ambiguity problems of visual words can be overcome effectively. The distinguish ability of visual semantic resolution as well as the object classification performance are substantially boosted compared with the traditional methods.

• Journal of the Korea Organic Resources Recycling Association
• /
• v.24 no.4
• /
• pp.49-57
• /
• 2016

In this study, a thermal hydrolysis technology was used to treat the poultry carcasses that were killed due to Avian Influenza (AI) occurrence, as well as to determine the possibility of fueling for the resultant products. Experimental results showed that the poultry carcasses were liquefied except for sand, and showed the optimum efficiency at $190^{\circ}C$ and operating time of 60 minutes. It has been shown that liquid products obtained after thermal hydrolysis has good conditions for fuel conversion since it had high carbon contents and calorific value, as well as low ash content. In addition, it was possible to operate the thermal hydrolysis facility by using only the waste heat generated in the combustion without injecting the auxiliary fuel, and the exhaust gas generated in the combustion has a small influence on the atmosphere.