• The Journal of Bigdata
• /
• v.3 no.2
• /
• pp.59-70
• /
• 2018

In order to provide stable district heat supplying service to the certain limited residential area, it is the most important to forecast the short-term future demand more accurately and produce and supply heat in efficient way. However, it is very difficult to develop a universal heat demand forecasting model that can be applied to general situations because the factors affecting the heat consumption are very diverse and the consumption patterns are changed according to individual consumers and regional characteristics. In particular, considering all of the various variables that can affect heat demand does not help improve performance in terms of accuracy and versatility. Therefore, this study aims to develop a demand forecasting model using deep learning based on only limited information that can be acquired in real time. A demand forecasting model was developed by learning the artificial neural network of the Tensorflow using past data consisting only of the outdoor temperature of the area and date as input variables. The performance of the proposed model was evaluated by comparing the accuracy of demand predicted with the previous regression model. The proposed heat demand forecasting model in this research showed that it is possible to enhance the accuracy using only limited variables which can be secured in real time. For the demand forecasting in a certain region, the proposed model can be customized by adding some features which can reflect the regional characteristics.

• Korean Journal of Remote Sensing
• /
• v.35 no.2
• /
• pp.241-250
• /
• 2019

The current U.S. remote sensing act was made in 1992 and has been criticized for being outdated and inappropriate in view of the modern technological development. In order to enhance the American competitiveness and leadership in the world, President Trump announced Space Policy Directive (SPD) - 2 on May 24, which is designed to modernize the regulations related to commercial space activities including private remote sensing system operations. It should be noted that the regulatory reform efforts are made within broader terms of the National Security Strategy on Dec. 17, 2017, pursuing the enhancement of national security and economic prosperity as well. A legislative support in Congress has also been added to the Administration's efforts. The proposed regulatory reform on the licensing of commercial remote sensing system operations outlines the features of lessening administrative burden on applicants by simplifying the overall application process and of limiting the operations only when there is an impact upon the national security with clear and convincing evidence. But, due to a different regulatory system of each country, such a movement to expand an individual's freedom to explore and utilize outer space may result in an international dispute or a violation of international obligations, so there should be a merit in paying attention to the U.S. commercial remote sensing regulatory reform, and it is desirable to establish international norms as flexible and appropriate to the level of space technology and space industry.

• Phonetics and Speech Sciences
• /
• v.13 no.2
• /
• pp.77-90
• /
• 2021

This study is to develop a Korean version of nonword intervention by modifying and supplementing a Rapid syllable transition treatment (ReST) and to determine its effect by applying it to children with CAS. Ultimately, the purpose of this study is to investigate whether nonword interventions are effective for nonword production ability and generalization of real words. Single-subject research using the ABA design was performed for a child aged five years and six months with diagnostic features of CAS. The nonwords used in the interventions were made suitable for the individual child. The intervention was provided in one-hour sessions, twice a week for six weeks. In all cases, performance of the treated three-syllable nonwords improved, and untreated three-syllable words, four-syllable words, and nonwords showed a generalization effect. However, the generalization of treatment effects to words was smaller than for nonwords. The nonword intervention was effective in improving the subject's speech motor programming skills. As a result, transition errors due to impaired speech motor programming were greatly reduced, and the ability to produce untreated nonwords was greatly increased. However, there was a limit to the full improvement of strongly habitable word errors, which would be expected if a more intensive and repetitive intervention schedule was provided.

• Journal of Internet Computing and Services
• /
• v.21 no.6
• /
• pp.57-69
• /
• 2020

As more people share their opinions in online communities, such as Internet portals and social networking services, more opinions are manipulated for the benefit of particular individuals and groups. In particular, when manipulations occur for political purposes, they influence election results as well as government policies and the quality of life. This type of manipulation has targeted the general public, and their analysis and detection has also focused on such manipulation. However, to more efficiently spread propaganda, recent manipulations have targeted common interest groups(e.g., a group of those interested in real estate) and propagated information whose content and style are customized to those groups. This work characterizes such manipulations on common interest groups and proposes method to detect manipulations. To this end, we collected and analyzed opinions posted on 10 common interest groups before and after an election. As a result, we found that manipulations on common interest groups indeed occurred and were gradually increasing toward the election date. We also proposed a detection system that examines individual opinions, their authors, and their collaborators. Using the collected opinions, we demonstrated that the proposed system can accurately classify more than 90% of manipulated opinions and that many of these opinions were posted by multiple collaborators. We believe that regular audits of opinions using the proposed system can quickly isolate manipulations and decrease their impact. Moreover, the proposed features can be used to identify manipulations in domains other than politics.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.12
• /
• pp.268-277
• /
• 2020

This study emphasizes that the survival strategy of universities should be a co-evolution strategy based on ecological thinking. Therefore, the purpose of the research is to present a theoretical framework for dividing the university innovation ecosystem into four stages and building a co-evolution strategy for each step, as universities play a prominent role in regional innovation ecosystems. Thus, our research method focused on literature research, and the theoretical framework for the university innovation ecosystem used Moore's Enterprise Ecosystem Model (1996). The university's ecological innovation strategy is divided into four stages of development, and a step-by-step co-evolution strategy is presented. Findings are summarized as follows. The pioneering stage involves the creation of values of the university-led innovation ecosystem. The expansion stage focuses on the establishment of critical mass. The authority stage covers maintaining authority and bargaining power. The renewal stage features continuous performance improvement. In particular, this theoretical model of the university-regional innovation ecosystem is meaningful in that it provides a theoretical basis for enhancing the effectiveness of government financial support projects, and for individual universities, it provides a framework for strategies suitable for their ecosystem building process.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• v.48 no.5
• /
• pp.249-258
• /
• 2022

The specific muscular structure of the tongue greatly affects margin shrinkage and tumor invasion, making the optimal surgical margin controversial. This study investigated surgical margin correlated prognosis of TSCC (tongue squamous cell carcinoma) according to margin location and its value, and the histopathologic factors which are suggestive of tumor invasion. And we would like to propose defining of the surgical margin for TSCC via prognosis according to location and margin values. We reviewed 45 patients diagnosed with TSCC who visited Seoul National University Dental Hospital (SNUDH) (Seoul, Republic of Korea) from 2010 to 2019, who were managed by a single surgical team. Patient clinical and pathological data of patients were retrospectively reviewed, and in 36 out of 45 patients, the pathologic parameters including the worst pattern of invasion (WPOI) and tumor budding were investigated via diagnostic histopathology slide reading. When standardized with as 0.25 cm anterior margins, as 0.35 cm deep margin, there was no significant difference in disease specific survival (DSS) or loco-regional recurrence-free survival (LRFS). Additionally, there was a non-significant difference in DSS and LRFS at the nearest margin of 0.35 cm (P_DSS=0.276, P_LRFS=0.162). Aggressive WPOI and high tumor budding showed lower survival and recurrence-free survival, and there were significant differences in close margin and involved margin frequencies. In TSCC, the value and location of the surgical margin did not have a significant relationship with prognosis, but WPOI and tumor budding suggesting the pattern of muscle invasion affected survival and recurrence-free survival. WPOI and tumor budding should be considered when setting an optimal surgical margin.

• Journal of Internet Computing and Services
• /
• v.23 no.4
• /
• pp.35-43
• /
• 2022

Makeup is the most common way to improve a person's appearance. However, since makeup styles are very diverse, there are many time and cost problems for an individual to apply makeup directly to himself/herself.. Accordingly, the need for makeup automation is increasing. Makeup transfer is being studied for makeup automation. Makeup transfer is a field of applying makeup style to a face image without makeup. Makeup transfer can be divided into a traditional image processing-based method and a deep learning-based method. In particular, in deep learning-based methods, many studies based on Generative Adversarial Networks have been performed. However, both methods have disadvantages in that the resulting image is unnatural, the result of makeup conversion is not clear, and it is smeared or heavily influenced by the makeup style face image. In order to express the clear boundary of makeup and to alleviate the influence of makeup style facial images, this study divides the makeup area and calculates the loss function using HoG (Histogram of Gradient). HoG is a method of extracting image features through the size and directionality of edges present in the image. Through this, we propose a makeup transfer network that performs robust learning on edges.By comparing the image generated through the proposed model with the image generated through BeautyGAN used as the base model, it was confirmed that the performance of the model proposed in this study was superior, and the method of using facial information that can be additionally presented as a future study.

• Journal of the Korean Society for information Management
• /
• v.39 no.2
• /
• pp.203-232
• /
• 2022

Drug addiction or substance use disorder is continuously observed worldwide for its risks and prevalence. In this context, numerous studies have been conducted regarding this issue. However, bibliometric analysis related to drug addiction is insufficient. In particular, it is difficult to find research that utilizes a macro-level bibliographic approach that comprehensively reflects various characteristics related to drug addiction. In this study, to reflect the multidimensional features of drug addiction, research trends in drug addiction in social science, natural science, and multidisciplinary studies were compared and analyzed. This study collected drug addiction research articles from 2002 to 2021 by searching from the Web of Science, and classified academic disciplines based on SCI(E) and SSCI information. Author keyword co-occurrence analysis was also conducted, which provided confirmation that natural science mainly studied psychoactive substances and the reward system in the brain, while drug addiction studies reflecting demographic characteristics were conducted in the domain of social science. In the multidisciplinary field, all of the above topics were covered. Author co-citation analysis was also employed, which showed that there are superstars (i.e., authors who receive a rigorous amount of citation) in the field of natural science, while in the social science domain, authors were highly cited not only at the individual level but also at the institutional level.

• Journal of the Korean Society for Library and Information Science
• /
• v.57 no.1
• /
• pp.93-114
• /
• 2023

Information extraction can facilitate the intensive analysis of documents by providing semantic triples which consist of named entities and their relations recognized in the texts. However, most of the research so far has been carried out separately for named entity recognition and relation extraction as individual studies, and as a result, the effective performance evaluation of the entire information extraction systems was not performed properly. This paper introduces two models of end-to-end information extraction that can extract various entity names in clinical records and their relationships in the form of semantic triples, namely pipeline and joint models and compares their performances in depth. The pipeline model consists of an entity recognition sub-system based on bidirectional GRU-CRFs and a relation extraction module using multiple encoding scheme, whereas the joint model was implemented with a single bidirectional GRU-CRFs equipped with multi-head labeling method. In the experiments using i2b2/VA 2010, the performance of the pipeline model was 5.5% (F-measure) higher. In addition, through a comparative experiment with existing state-of-the-art systems using large-scale neural language models and manually constructed features, the objective performance level of the end-to-end models implemented in this paper could be identified properly.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.23-34
• /
• 2023

Wearable technology for military applications has received considerable attention as a means of personal status check and monitoring. Among many, an implementation to recognize specific motion states of a human is promising in that allows active management of troops by immediately collecting the operational status and movement status of individual soldiers. In this study, as an extension of military wearable application research, a new ankle wearable device is proposed that can glean the information of a soldier on the battlefield on which action he/she takes in which environment. Presuming a virtual situation, the soldier's upper limbs are easily exposed to uncertainties about circumstances. Therefore, a sensing module is attached to the ankle of the soldier that may always interact with the ground. The obtained data comprises 3-axis accelerations and 3-axis rotational velocities, which cannot be interpreted by hand-made algorithms. In this study, to discern the behavioral characteristics of a human using these dynamic data, a data-driven model is introduced; four features extracted from sliced data (minimum, maximum, mean, and standard deviation) are utilized as an input of the model to learn and classify eight primary military movements (Sitting, Standing, Walking, Running, Ascending, Descending, Low Crawl, and High Crawl). As a result, the proposed device could recognize a movement status of a solider with 95.16% accuracy in an arbitrary test situation. This research is meaningful since an effective way of motion recognition has been introduced that can be furtherly extended to various military applications by incorporating wearable technology and artificial intelligence.