• Journal of Intelligence and Information Systems
• /
• v.28 no.4
• /
• pp.251-273
• /
• 2022

Recently, research on applying text analysis to deep learning has steadily continued. In particular, researches have been actively conducted to understand the meaning of words and perform tasks such as summarization and sentiment classification through a pre-trained language model that learns large datasets. However, existing pre-trained language models show limitations in that they do not understand specific domains well. Therefore, in recent years, the flow of research has shifted toward creating a language model specialized for a particular domain. Domain-specific pre-trained language models allow the model to understand the knowledge of a particular domain better and reveal performance improvements on various tasks in the field. However, domain-specific further pre-training is expensive to acquire corpus data of the target domain. Furthermore, many cases have reported that performance improvement after further pre-training is insignificant in some domains. As such, it is difficult to decide to develop a domain-specific pre-trained language model, while it is not clear whether the performance will be improved dramatically. In this paper, we present a way to proactively check the expected performance improvement by further pre-training in a domain before actually performing further pre-training. Specifically, after selecting three domains, we measured the increase in classification accuracy through further pre-training in each domain. We also developed and presented new indicators to estimate the specificity of the domain based on the normalized frequency of the keywords used in each domain. Finally, we conducted classification using a pre-trained language model and a domain-specific pre-trained language model of three domains. As a result, we confirmed that the higher the domain specificity index, the higher the performance improvement through further pre-training.

• Ecology and Resilient Infrastructure
• /
• v.9 no.3
• /
• pp.183-193
• /
• 2022

The growth inhibitory effect of Microcystis aeruginosa according to the ultrasonic irradiation time was evaluated using a large algae sample volume (10 L) for various ultrasonic irradiation times (0.5, 1, 1.5, 2, 2.5 and 3 hr) at a laboratory scale. Based on the analysis of Chl-a and cell number of M. aerginosa, algae growth inhibition was observed with the decrease in Chl-a and cell number in all experimental groups after the ultrasonic irradiation. For the experimental group (T_B, T_C, T_D) with an ultrasonic irradiation time of less than 2 hours, rapid regrowth of algae was observed after growth inhibition, but the experimental group (T_E, T_F, T_G) with an irradiation time of more than 2 hours successfully inhibited algal growth lasting one or two more days. Based on the comparison of the recovery time to initial cell number the experimental group (T_B, T_C, T_D) took less than 20 days whereas the experimental group (T_E, T_F, T_G) took about 30 days. Correspondingly, the experimental group showed a high first order decay rate (𝜅) in proportion to the ultrasonic irradiation time during the growth inhibition period. Additionally, the specific growth rates (𝜇) during regrowth in the experimental group with irradiation time of more than 2 hours were relatively low compared to those in the experimental group with less than 2 hours. Therefore, ultrasonic irradiation for more than 2 hours is required for long-term (30 days) inhibition of algal growth in stagnant waters. However, the appropriate ultrasonic irradiation time for algae growth inhibition should be determined according to various field conditions such as the volume of stagnant water, water depth, flow rate, algae concentration, etc. Finally, damages to the algal cell surface and cell membrane were clearly observed, and both destruction and disturbance of gas vesicles of M. aeruginosa in the experimental group were discovered, indicating the growth inhibitory effect of Microcystis aeruginosa according to the ultrasonic irradiation time was confirmed.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.131-154
• /
• 2022

Recently, researches on unstructured data analysis have been actively conducted with the development of information and communication technology. In particular, topic modeling is a representative technique for discovering core topics from massive text data. In the early stages of topic modeling, most studies focused only on topic discovery. As the topic modeling field matured, studies on the change of the topic according to the change of time began to be carried out. Accordingly, interest in dynamic topic modeling that handle changes in keywords constituting the topic is also increasing. Dynamic topic modeling identifies major topics from the data of the initial period and manages the change and flow of topics in a way that utilizes topic information of the previous period to derive further topics in subsequent periods. However, it is very difficult to understand and interpret the results of dynamic topic modeling. The results of traditional dynamic topic modeling simply reveal changes in keywords and their rankings. However, this information is insufficient to represent how the meaning of the topic has changed. Therefore, in this study, we propose a method to visualize topics by period by reflecting the meaning of keywords in each topic. In addition, we propose a method that can intuitively interpret changes in topics and relationships between or among topics. The detailed method of visualizing topics by period is as follows. In the first step, dynamic topic modeling is implemented to derive the top keywords of each period and their weight from text data. In the second step, we derive vectors of top keywords of each topic from the pre-trained word embedding model. Then, we perform dimension reduction for the extracted vectors. Then, we formulate a semantic vector of each topic by calculating weight sum of keywords in each vector using topic weight of each keyword. In the third step, we visualize the semantic vector of each topic using matplotlib, and analyze the relationship between or among the topics based on the visualized result. The change of topic can be interpreted in the following manners. From the result of dynamic topic modeling, we identify rising top 5 keywords and descending top 5 keywords for each period to show the change of the topic. Existing many topic visualization studies usually visualize keywords of each topic, but our approach proposed in this study differs from previous studies in that it attempts to visualize each topic itself. To evaluate the practical applicability of the proposed methodology, we performed an experiment on 1,847 abstracts of artificial intelligence-related papers. The experiment was performed by dividing abstracts of artificial intelligence-related papers into three periods (2016-2017, 2018-2019, 2020-2021). We selected seven topics based on the consistency score, and utilized the pre-trained word embedding model of Word2vec trained with 'Wikipedia', an Internet encyclopedia. Based on the proposed methodology, we generated a semantic vector for each topic. Through this, by reflecting the meaning of keywords, we visualized and interpreted the themes by period. Through these experiments, we confirmed that the rising and descending of the topic weight of a keyword can be usefully used to interpret the semantic change of the corresponding topic and to grasp the relationship among topics. In this study, to overcome the limitations of dynamic topic modeling results, we used word embedding and dimension reduction techniques to visualize topics by era. The results of this study are meaningful in that they broadened the scope of topic understanding through the visualization of dynamic topic modeling results. In addition, the academic contribution can be acknowledged in that it laid the foundation for follow-up studies using various word embeddings and dimensionality reduction techniques to improve the performance of the proposed methodology.

• Journal of Popular Narrative
• /
• v.25 no.1
• /
• pp.429-462
• /
• 2019

This paper argues how the concept of melodrama can be articulated with the Affect Theory and Posthumanism in relation to animal or environment representation which have emerged as the new topics of the recent era. The argument will be made through the discussion of Agustin Zarzosa's book, Refiguring Melodrama in Film and Television: Captitve Affects, Elastic Sufferings, Vicarious Objects. Using a genealogical approach, the book revisits the notion of mode, affect, suffering (hysteria), and excess which have been dealt with in the existing studies of melodrama. In chapter one, he broadens the concept of melodrama as a mode into the means of redistribution of suffering across the whole society in the mechanism of the duo of evil and virtue. It is the opposition of Brooks's argument in which melodrama functions as the means of proving the distinction between evil and virtue. Chapter two focuses on the fact that melodrama is an elastic system of specification rather than a system of signification, with the perspective of Deleuzian metaphysics. Through the analysis of Home from the Hill (Vincente Minnelli, 1959), this chapter pays attention to an 'affect' generated by the encounters between the bodies and the Mise-en-Scène as a flow not of a meaning but of an affect. Chapter three argues that melodrama should reveal an unloved (woman's) suffering, opposing the discussion on the role of melodrama as the recovery of moral order. Safe (Todd Haynes, 1995), dealing with female suffering caused by the industrial and social environment, elaborates on the arguments on melodrama in relation to female hysteria with ecocritical standpoints. The rest of the two chapters discusses the role of melodrama for the limitation and extension of the notion of the human through 'animal' and 'posthuman' melodrama. It argues that the concept of melodrama as 'excess' and 'sacrifice' blurs the boundary between human and inhuman. In summary, although the author Zarzosa partly agrees with Peter Brook's notion of mode, affect and sufferings,he elaborates the concept of melodrama, by articulating philosophical arguments such as Deleuzianism, feminism, and posthumanism (Akira Lippit and Carry Wolf) with the melodrama. Thefore, Zarzosa challenges the concepts of melodrama led by Brooks, which had been canonical in the field.

• Journal of Popular Narrative
• /
• v.25 no.4
• /
• pp.191-221
• /
• 2019

This study aims to analyze the post-humanistic imagination that has emerged as a major academic thesis in Korean literature, especially novels. In particular, this paper focuses on Cho Ha-hyung's two novels Chimera's Morning(2004) and A Prefabricated Bodhi Tree(2008), published in the early 2000s, for intensive analysis. Post-humanism can be seen as an extension of post-modernism that tried to overcome the limitations of modernity and seek to establish a new world view. In particular, this thought pays attention to the comprehensive understanding of how the rapid development of science and technology, which has developed since the 20th century, has changed the view of humanity and human-centered civilization itself. At the concrete level, it is developing in the direction of constructing a new subject idea by reflecting and dismantling Western-, reason-, and male-centered power mechanisms that are the core of modern civilization. Cho attempts to discover and re-illuminate the surrounding figures, non-humans, and objects that were not noticed in the classic works written in the past. This ideological flow reflects the fact that the concept of human beings, which had been dominated by the humanities in recent years, has been completely changed, and the natural science and technology perspective is applied to the discourse field in various ways. From the point of view of post-humanism, objects that have not been classified as humans and objects that were considered inferior to humans should be included in human or comparable levels. These questions generate interdisciplinary research tasks by involving the large categories of philosophy, such as ontology, epistemology and empirical fields, as well as calling for the participation of the entire literature, science and social sciences. Against the backdrop of a disaster-hit world, Chimera's Morning and A Prefabricated Bodhi Tree depict human beings as variants transformed by bio-technology, and creatures made out of the artificial intelligence built by computer simulations. Post-humanistic ideas in Cho's novels provide a reflective opportunity to comprehensively reconsider the world's shape and human identity reproduced in the text, and to re-explore boundary lines and hierarchy order that distinguish between human and non-human.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.17 no.4
• /
• pp.87-100
• /
• 2022

Early start-up companies have an inherent limitation of lack of resources. Despite these limitations, in order to survive, the entrepreneur's personal ability to efficiently use limited resources is required. In the marketing field, various studies are needed to reduce the business failure rate through establishing growth strategies and innovation. Accordingly, it is necessary to apply the concept of entrepreneurial marketing, which has been researched and developed overseas for 30 years, to fit the domestic reality. According to the flow of this study, an empirical study should be preceded to clarify the influence relationship between entrepreneurial marketing orientation, marketing competency, and management performance, along with a theoretical theorem on entrepreneurial marketing that is suitable for early start-ups and small and medium-sized enterprises(SMEs) and can respond innovatively to changes. The establishment of entrepreneurial marketing orientation and the processes from which this concept leads to business performance through the organization's marketing capabilities and its effects will be empirically verified. For an empirical survey, a survey was conducted on founders of 220 companies, and path analysis using structural equations was used for hypothesis verification. The findings are as follows. First, it was found that the entrepreneurial marketing orientation had a positive effect on both the organization's marketing capabilities and management performance. Second, it was found that the organization's marketing capabilities also had a positive effect on management performance. Third, as a result of empirical analysis of the mediating effect of the organization's marketing capabilities on the relationship between entrepreneurial marketing orientation and management performance, it was found that marketing capabilities showed a greater mediating effect on non-financial performance than financial performance. On the other hand, it was confirmed that marketing performance had a stronger mediating effect on financial performance than non-financial performance. By confirming and presenting the concept and constituent factors of entrepreneurial marketing orientation of domestic start-ups, which were academic gaps for the purpose of this paper, the academic research is differentiated in that they were verified as six components of entrepreneurial marketing. The practical implications of the research results will be that the entrepreneurial marketing-oriented mindset of small and medium-sized companies will optimize market analysis capabilities, network with various stakeholders, and increase the organization's ability to demonstrate marketing capabilities.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.15 no.2
• /
• pp.51-61
• /
• 2010

Surface particulate organic carbon (POC) concentration was measured in the Northeastern Gulf of Mexico on 9 cruises from November 1997 to August 2000 to investigate the seasonal and spatial variability related to synchronous remote sensing data (Sea-viewing Wide Field-of-view Sensor (SeaWiFS), sea surface temperature (SST), sea surface height anomaly (SSHA), and sea surface wind (SSW)) and recorded river discharge data. Surface POC concentrations have higher values (>100 $mg/m^3$) on the inner shelf and near the Mississippi Delta, and decrease across the shelf and slope. The inter-annual variations of surface POC concentrations are relatively higher during 1997 and 1998 (El Nino) than during 1999 and 2000 (La Nina) in the study area. This phenomenon is directly related to the output of Mississippi River and other major rivers, which associated with global climate change such as ENSO events. Although highest river runoff into the northern Gulf of Mexico Coast occurs in early spring and lowest flow in late summer and fall, wide-range POC plumes are observed during the summer cruises and lower concentrations and narrow dispersion of POC during the spring and fall cruises. During the summer seasons, the river discharge remarkably decreases compared to the spring, but increasing temperature causes strong stratification of the water column and increasing buoyancy in near-surface waters. Low-density plumes containing higher POC concentrations extend out over the shelf and slope with spatial patterns and controlled by the Loop Current and eddies, which dominate offshore circulation. Although river discharge is normal or abnormal during the spring and fall seasons, increasing wind stress and decreasing temperature cause vertical mixing, with higher surface POC concentrations confined to the inner shelf.

• Korean Journal of Environmental Agriculture
• /
• v.38 no.4
• /
• pp.225-236
• /
• 2019

BACKGROUND: Hydroponics is one of the methods for evaluating plant production using the inorganic nutrient solutions, which is applied under the artificial light conditions of plant factory system. However, the application of the conventional inorganic nutrients for hydroponics caused several environmental problems: waste from culture mediums and high nitrate concentration in plants. Organic nutrients are generally irrigated as a supplementary fertilizer for plant growth promotion under field or greenhouse conditions. Hydroponic culture using organic nutrients derived from the agricultural by-products such as dumped stems, leaves or immature fruits is rarely considered in plant factory system. Effect of organic or conventional inorganic nutrient solutions on the growth and nutrient absorption pattern of green and red leaf lettuces was investigated in this experiment under fluorescent lamps (FL) and mixture Light-Emitting Diodes (LEDs). METHODS AND RESULTS: Single solution of tomatoes (TJ) and kales (K) deriving from agricultural by-products including leaves or stems and its mixed solution (mixture ration 1:1) with conventional inorganic Yamazaki (Y) were supplied for hydroponics under the plant factory system. The Yamazaki solution was considered as a control. 'Jeockchima' and 'Cheongchima' lettuce seedlings (Lactuca sativa L.) were used as plant materials. The seedlings which developed 2~3 true leaves were grown under the light qualities of FL and mixed LED lights of blue plus red plus white of 1:2:1 mixture in energy ratio for 35 days. Light intensity of the light sources was controlled at 180 μmol/㎡/s on the culture bed. The single and mixture nutrient solutions of organic and/or inorganic components which controlled at 1.5 dS/m EC and 5.8 pH were regularly irrigated by the deep flow technique (DFT) system on the culture gutters. Number of unfolded leaves of the seedlings grown under the single or mixed nutrient solutions were significantly increased compared to the conventional Y treatment. Leaf extension of 'Jeockchima' under the mixture LED radiation condition was not affected by Y and YK or YTJ mixture treatments. SPAD value in 'Jeockchima' leaves exposed by FL under the YK mixture medium was approximately 45 % higher than under conventional Y treatment. Otherwise, the maximum SPAD value in the leaves of 'Cheongchima' seedlings was shown in YK treatment under the mixture LED lights. NO₃-N contents in Y treatment treated with inorganic nutrient at the end of the experiment were up to 75% declined rather than increased over 60 % in the K and TJ organic treatment. CONCLUSION: Growth of the seedlings was affected by the mixture treatments of the organic and inorganic solutions, although similar or lower dry weight was recorded than in the inorganic treatment Y under the plant factory system. Treatment Y containing the highest NO₃-N content among the considered nutrients influenced growth increment of the seedlings comparing to the other nutrients. However effect of the higher NO₃-N content in the seedling growth was different according to the light qualities considered in the experiment as shown in leaf expansion, pigmentation or dry weight promotion under the single or mixed nutrients.

• Journal of Intelligence and Information Systems
• /
• v.23 no.1
• /
• pp.23-46
• /
• 2017

Although there have been cases of evaluating the value of specific companies or projects which have centralized on developed countries in North America and Europe from the early 2000s, the system and methodology for estimating the economic value of individual technologies or patents has been activated on and on. Of course, there exist several online systems that qualitatively evaluate the technology's grade or the patent rating of the technology to be evaluated, as in 'KTRS' of the KIBO and 'SMART 3.1' of the Korea Invention Promotion Association. However, a web-based technology valuation system, referred to as 'STAR-Value system' that calculates the quantitative values of the subject technology for various purposes such as business feasibility analysis, investment attraction, tax/litigation, etc., has been officially opened and recently spreading. In this study, we introduce the type of methodology and evaluation model, reference information supporting these theories, and how database associated are utilized, focusing various modules and frameworks embedded in STAR-Value system. In particular, there are six valuation methods, including the discounted cash flow method (DCF), which is a representative one based on the income approach that anticipates future economic income to be valued at present, and the relief-from-royalty method, which calculates the present value of royalties' where we consider the contribution of the subject technology towards the business value created as the royalty rate. We look at how models and related support information (technology life, corporate (business) financial information, discount rate, industrial technology factors, etc.) can be used and linked in a intelligent manner. Based on the classification of information such as International Patent Classification (IPC) or Korea Standard Industry Classification (KSIC) for technology to be evaluated, the STAR-Value system automatically returns meta data such as technology cycle time (TCT), sales growth rate and profitability data of similar company or industry sector, weighted average cost of capital (WACC), indices of industrial technology factors, etc., and apply adjustment factors to them, so that the result of technology value calculation has high reliability and objectivity. Furthermore, if the information on the potential market size of the target technology and the market share of the commercialization subject refers to data-driven information, or if the estimated value range of similar technologies by industry sector is provided from the evaluation cases which are already completed and accumulated in database, the STAR-Value is anticipated that it will enable to present highly accurate value range in real time by intelligently linking various support modules. Including the explanation of the various valuation models and relevant primary variables as presented in this paper, the STAR-Value system intends to utilize more systematically and in a data-driven way by supporting the optimal model selection guideline module, intelligent technology value range reasoning module, and similar company selection based market share prediction module, etc. In addition, the research on the development and intelligence of the web-based STAR-Value system is significant in that it widely spread the web-based system that can be used in the validation and application to practices of the theoretical feasibility of the technology valuation field, and it is expected that it could be utilized in various fields of technology commercialization.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.4 no.2
• /
• pp.45-53
• /
• 1984

This study was conducted to investigate characteristics of nonpoint pollutant discharges and concentrations in runoff from the urban and agricultural areas in Korea. The analytical parameters used for this study were COD, BOD and SS. This study was conducted during the period from May to August 1981. Nonpoint pollutant mass loadings from the urban area were influenced by the rainfall intensity and the duration of rainfall, and etc. The concentrations of pollutants in the first flush was higher as the discharges increased. It was, however, found that the concentrations of pollutants in the heavy storm runoff were decreased due to the dilution effect. When other rainfall followed a peak rainfall, the concentrations of pollutants were lower than expected, because the first flush conveyed the most of pollutants deposited on the combined sewers. However the concentrations were increased in proportion to the increased flow when a rainfall of higher intensity than the first flush was continued. Yearly area yield rates in kg/ha were estimated to be 690.5(489.9~1,328) of COD, 319.7(226.8~614.8) of BOD, and 831.2(589.7~1,598) of SS. Pollutant sources in agricultural area were of the domestic waste water, manure composting stack, and agricultural solid wastes and etc. In the paddy field, yearly area yield rates in kg/ha were estimated to be 623.4(21.7~114) of COD, 18.65(9.53~34.5) of BOD, and 91.9(46.3~171.8) of SS. In the crop land, however, yearly rates in kg/ha were estimated to be 91.9(46.3~171.8) of COD, 23.09(11.7~42.5) of BOD, and 23.09(11.4~43.4) of SS. Pollutant sources in the feedlot area were originating from the feces of cattle, the cleaning water, the wastes spilled from manure composting stack during rain. Yearly area yield rate in kg/ha was estimated to be 3.804(2,489~6,658) of COD, 2.047(464~2,900) of BOD, and 1.149 (729~1,442) of SS. Pollutant discharges in the forest area were resulted from the organic layer like leaves and others deposited on the surface. Yearly area yield rate in kg/ha was estimated to be 9.86(5.45~18.56) of COD, 3.48(1.67~7.54) of BOD, and 4.64(9.74~10.35) of SS.