• Journal of Animal Science and Technology
• /
• v.44 no.3
• /
• pp.327-340
• /
• 2002

This study was conducted to investigate the effects of domestic clay minerals on feed efficiency, meat quantity, meat quality and economic traits in 24 head of Hanwoo steers(166.1kg in body weight) for 540 days from six to 24 months in age. Feeding trial was conducted with 4 treatment(six heads/treatment) which were T1(Control), T2(Control+Kaolinite), T3(Control+Bentonite), T4(Control+Illite). The results obtained are summarized as follows; The range of average daily gains were 0.682 to 0.713, 0.669 to 0.714, 0.690 to 0.840 and 0.699 to 0.756kg in growing, fattening, finishing and over-all period, respectively, and the gains were high in T1 for growing and fattening period but in clay mineral groups for finishing and over-all period, especially it was high in Illite and Bentonite groups. Concentrates and TDN intakes per unit of kg gains were lower in clay mineral groups than in control and was lower especially in Bentonite groups. In carcass characteristics, dressed carcass and fresh meat and retailed cut percent were not apparently difference by treatments, and yield index was 69.3, 68.9, 68.8 and 68.6 in T3, T2, T4 and T1, respectively. Marbling scores were 5.1, 4.6, 4.4 and 3.3 in T3, T2, T4 and T1, respectively, and the range of shear force by treatment was from 3.51 to 6.02kg/cm2. and were improved with significant difference(P<0.05) in clay mineral groups than in control. Also in palatability traits, panel test scores of juiciness, tenderness and flavor were improved in clay mineral feeding groups, especially the flavor was improved with highly significant difference(P<0.01) in clay mineral groups than in control. In total fatty acid contents, the rate of SFA(saturated fatty acid) in longissimus muscle of beef was higher in the order of T2, T3, T1 and T4 while the rate of MUFA(monounsaturated fatty acid) was high in the order of T4, T3, T1 and T2. The content of oleic acid which is major influential factor at the flavor of beef was higher in Illite groups than in any other groups. In composition of amino acids in longissimus muscles of beef, the rate of essential amino acids was high in the order of T1, T2, T3 and T4. and the rate of amino acids in clay mineral groups was smaller than in control.In chemical component in Gom-Tang(soup of bone) made by Hanwoo steer’s leg-bone, the ranges of crude protein, ether extract, and crude ash was 0.81 to 1.24, 0.17 to 0.35 and 0.07 to 0.09%, respectively. In mineral composition, the ranges of Ca, P, Na and Mg was 14.01 to 15.77, 11.45 to 16.40, 37.92 to 49.99 and 0.26 to 0.46ppm, respectively. Chemical composition were not apparently different but mineral composition was increased in clay mineral groups than in control. Income by treatments was 967,096 to 1,524,055 Won per head for 540 days and income of clay mineral groups in comparison with control’s increased by 23.7 to 57.6 percent, and especially it was higher in bentonite and(or) Illite groups than others. According to the above results it may be concluded that clay mineral to growing-fattening Hanwoo steers can be improved the meat quantity, meat quality and income. Especially the effect of bentonite and illite is large and can be recommended for usage to improve animal performance as feed additives of growing-fattening Hanwoo steers.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.20 no.1
• /
• pp.41-51
• /
• 1987

This study was carried out to prepare powdered smoked-dried mackerel which can be used as a soup base, and to examine storage stability and the taste compounds of Products. Raw mackerel are filleted, toiled for 10 minutes and pressed to remove lipids, and then soaked in extract solution of skipjack meat. This soaked mackerel are smoked 3 times to $10-12\%$ moisture content at $80^{\circ}C$ for 8 hours. And the smoked-dried mackerel were pulverized to 50 mesh. Finally, the powdered smoked-dried mackerel were packed in a laminated film $bag(PET/Al\;foil/CPP:\;5{\mu}m/15{\mu}m/70{\mu}m,\;15\times17cm)$ with air(product C), nitrogen(product N) and oxygen absorber(product O), and then stored at room temperature for 100 days. The moisture and crude lipid content of powdered smoked-dried mackerel was $11.3-12.3\%,\;12\%$, respectively, and water activity is 0.52-0.56. And these values showed little changes during storage. The pH, VBN and amino nitrogen content increased slowly during storage. Hydrophilic and lipophilic brown pigment formation showed a tendency of increase in product(C) and showed little change in product(N) and (O). The TBA value, peroxide value and carbonyl value of product(N) and (O) were lower than those of product (C). The major fatty acids of products were 16:0, 18:1, 22:6, 18:0 and 20:5, and polyenoic acids decreased, while saturated and monoenoic acids increased during processing and storage of products. The IMP content in products were 420.2-454.2 mg/100 g and decreased slightly with storage period. And major non-volatile organic acids in products were lactic acid, succinic acid and $\alpha-ketoglutaric$ acid. In free amino acids and related compounds, major ones are histidine, alanine, hydroxyproline, lysine, glutamic acid and anserine, which occupied $80.8\%$ of total free amino acids. The taste compounds of powdered smoked-dried mackerel were free amino acids and related compounds (1,279.4 mg/100 g), non-volatile organic acids(948.1 mg/100 g), nucleotides and their related compounds (672.8 mg/100 g), total creatinine(430.4 ntg/100 g), tetaine(86.6 mg/100 g) and small amount of TMAO. The extraction condition of powdered smoked-dried mackerel in preparing soup stock is appropriate at $100^{\circ}C$ for 1 minute. Judging from the results of taste and sensory evaluation, it is concluded that the powdered smoked-dried mackerel can be used as natural flavoring substance in preparing soups and broth.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.97-117
• /
• 2020

Product evaluation criteria is an indicator describing attributes or values of products, which enable users or manufacturers measure and understand the products. When companies analyze their products or compare them with competitors, appropriate criteria must be selected for objective evaluation. The criteria should show the features of products that consumers considered when they purchased, used and evaluated the products. However, current evaluation criteria do not reflect different consumers' opinion from product to product. Previous studies tried to used online reviews from e-commerce sites that reflect consumer opinions to extract the features and topics of products and use them as evaluation criteria. However, there is still a limit that they produce irrelevant criteria to products due to extracted or improper words are not refined. To overcome this limitation, this research suggests LDA-k-NN model which extracts possible criteria words from online reviews by using LDA and refines them with k-nearest neighbor. Proposed approach starts with preparation phase, which is constructed with 6 steps. At first, it collects review data from e-commerce websites. Most e-commerce websites classify their selling items by high-level, middle-level, and low-level categories. Review data for preparation phase are gathered from each middle-level category and collapsed later, which is to present single high-level category. Next, nouns, adjectives, adverbs, and verbs are extracted from reviews by getting part of speech information using morpheme analysis module. After preprocessing, words per each topic from review are shown with LDA and only nouns in topic words are chosen as potential words for criteria. Then, words are tagged based on possibility of criteria for each middle-level category. Next, every tagged word is vectorized by pre-trained word embedding model. Finally, k-nearest neighbor case-based approach is used to classify each word with tags. After setting up preparation phase, criteria extraction phase is conducted with low-level categories. This phase starts with crawling reviews in the corresponding low-level category. Same preprocessing as preparation phase is conducted using morpheme analysis module and LDA. Possible criteria words are extracted by getting nouns from the data and vectorized by pre-trained word embedding model. Finally, evaluation criteria are extracted by refining possible criteria words using k-nearest neighbor approach and reference proportion of each word in the words set. To evaluate the performance of the proposed model, an experiment was conducted with review on '11st', one of the biggest e-commerce companies in Korea. Review data were from 'Electronics/Digital' section, one of high-level categories in 11st. For performance evaluation of suggested model, three other models were used for comparing with the suggested model; actual criteria of 11st, a model that extracts nouns by morpheme analysis module and refines them according to word frequency, and a model that extracts nouns from LDA topics and refines them by word frequency. The performance evaluation was set to predict evaluation criteria of 10 low-level categories with the suggested model and 3 models above. Criteria words extracted from each model were combined into a single words set and it was used for survey questionnaires. In the survey, respondents chose every item they consider as appropriate criteria for each category. Each model got its score when chosen words were extracted from that model. The suggested model had higher scores than other models in 8 out of 10 low-level categories. By conducting paired t-tests on scores of each model, we confirmed that the suggested model shows better performance in 26 tests out of 30. In addition, the suggested model was the best model in terms of accuracy. This research proposes evaluation criteria extracting method that combines topic extraction using LDA and refinement with k-nearest neighbor approach. This method overcomes the limits of previous dictionary-based models and frequency-based refinement models. This study can contribute to improve review analysis for deriving business insights in e-commerce market.

• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.161-177
• /
• 2019

In this paper, we study the performance improvement of the answer extraction in Question-Answering system by using sentence dependency parsing result. The Question-Answering (QA) system consists of query analysis, which is a method of analyzing the user's query, and answer extraction, which is a method to extract appropriate answers in the document. And various studies have been conducted on two methods. In order to improve the performance of answer extraction, it is necessary to accurately reflect the grammatical information of sentences. In Korean, because word order structure is free and omission of sentence components is frequent, dependency parsing is a good way to analyze Korean syntax. Therefore, in this study, we improved the performance of the answer extraction by adding the features generated by dependency parsing analysis to the inputs of the answer extraction model (Bidirectional LSTM-CRF). The process of generating the dependency graph embedding consists of the steps of generating the dependency graph from the dependency parsing result and learning the embedding of the graph. In this study, we compared the performance of the answer extraction model when inputting basic word features generated without the dependency parsing and the performance of the model when inputting the addition of the Eojeol tag feature and dependency graph embedding feature. Since dependency parsing is performed on a basic unit of an Eojeol, which is a component of sentences separated by a space, the tag information of the Eojeol can be obtained as a result of the dependency parsing. The Eojeol tag feature means the tag information of the Eojeol. The process of generating the dependency graph embedding consists of the steps of generating the dependency graph from the dependency parsing result and learning the embedding of the graph. From the dependency parsing result, a graph is generated from the Eojeol to the node, the dependency between the Eojeol to the edge, and the Eojeol tag to the node label. In this process, an undirected graph is generated or a directed graph is generated according to whether or not the dependency relation direction is considered. To obtain the embedding of the graph, we used Graph2Vec, which is a method of finding the embedding of the graph by the subgraphs constituting a graph. We can specify the maximum path length between nodes in the process of finding subgraphs of a graph. If the maximum path length between nodes is 1, graph embedding is generated only by direct dependency between Eojeol, and graph embedding is generated including indirect dependencies as the maximum path length between nodes becomes larger. In the experiment, the maximum path length between nodes is adjusted differently from 1 to 3 depending on whether direction of dependency is considered or not, and the performance of answer extraction is measured. Experimental results show that both Eojeol tag feature and dependency graph embedding feature improve the performance of answer extraction. In particular, considering the direction of the dependency relation and extracting the dependency graph generated with the maximum path length of 1 in the subgraph extraction process in Graph2Vec as the input of the model, the highest answer extraction performance was shown. As a result of these experiments, we concluded that it is better to take into account the direction of dependence and to consider only the direct connection rather than the indirect dependence between the words. The significance of this study is as follows. First, we improved the performance of answer extraction by adding features using dependency parsing results, taking into account the characteristics of Korean, which is free of word order structure and omission of sentence components. Second, we generated feature of dependency parsing result by learning - based graph embedding method without defining the pattern of dependency between Eojeol. Future research directions are as follows. In this study, the features generated as a result of the dependency parsing are applied only to the answer extraction model in order to grasp the meaning. However, in the future, if the performance is confirmed by applying the features to various natural language processing models such as sentiment analysis or name entity recognition, the validity of the features can be verified more accurately.