http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Company Name Discrimination in Tweets using Topic Signatures Extracted from News Corpus
Hong, Beomseok,Kim, Yanggon,Lee, Sang Ho Korean Institute of Information Scientists and Eng 2016 Journal of Computing Science and Engineering Vol.10 No.4
It is impossible for any human being to analyze the more than 500 million tweets that are generated per day. Lexical ambiguities on Twitter make it difficult to retrieve the desired data and relevant topics. Most of the solutions for the word sense disambiguation problem rely on knowledge base systems. Unfortunately, it is expensive and time-consuming to manually create a knowledge base system, resulting in a knowledge acquisition bottleneck. To solve the knowledge-acquisition bottleneck, a topic signature is used to disambiguate words. In this paper, we evaluate the effectiveness of various features of newspapers on the topic signature extraction for word sense discrimination in tweets. Based on our results, topic signatures obtained from a snippet feature exhibit higher accuracy in discriminating company names than those from the article body. We conclude that topic signatures extracted from news articles improve the accuracy of word sense discrimination in the automated analysis of tweets.
Company Name Discrimination in Tweets using Topic Signatures Extracted from News Corpus
Beomseok Hong,Yanggon Kim,Sang Ho Lee 한국정보과학회 2016 Journal of Computing Science and Engineering Vol.10 No.4
It is impossible for any human being to analyze the more than 500 million tweets that are generated per day. Lexical ambiguities on Twitter make it difficult to retrieve the desired data and relevant topics. Most of the solutions for the word sense disambiguation problem rely on knowledge base systems. Unfortunately, it is expensive and time-consuming to manually create a knowledge base system, resulting in a knowledge acquisition bottleneck. To solve the knowledge-acquisition bottleneck, a topic signature is used to disambiguate words. In this paper, we evaluate the effectiveness of various features of newspapers on the topic signature extraction for word sense discrimination in tweets. Based on our results, topic signatures obtained from a snippet feature exhibit higher accuracy in discriminating company names than those from the article body. We conclude that topic signatures extracted from news articles improve the accuracy of word sense discrimination in the automated analysis of tweets.
IoT-Based Smart Garbage System for Efficient Food Waste Management
Hong, Insung,Park, Sunghoi,Lee, Beomseok,Lee, Jaekeun,Jeong, Daebeom,Park, Sehyun Hindawi Publishing Corporation 2014 The Scientific World Journal Vol.2014 No.-
<P>Owing to a paradigm shift toward Internet of Things (IoT), researches into IoT services have been conducted in a wide range of fields. As a major application field of IoT, waste management has become one such issue. The absence of efficient waste management has caused serious environmental problems and cost issues. Therefore, in this paper, an IoT-based smart garbage system (SGS) is proposed to reduce the amount of food waste. In an SGS, battery-based smart garbage bins (SGBs) exchange information with each other using wireless mesh networks, and a router and server collect and analyze the information for service provisioning. Furthermore, the SGS includes various IoT techniques considering user convenience and increases the battery lifetime through two types of energy-efficient operations of the SGBs: stand-alone operation and cooperation-based operation. The proposed SGS had been operated as a pilot project in Gangnam district, Seoul, Republic of Korea, for a one-year period. The experiment showed that the average amount of food waste could be reduced by 33%.</P>
Park, Jinsung,Suh, Beomseok,Shin, Dong Wook,Hong, Jun Hyuk,Ahn, Hanjong Korean Cancer Association 2016 Cancer Research and Treatment Vol.48 No.3
<P><B>Purpose</B></P><P>We investigated changing patterns of primary treatment in Korean men with prostate cancer (PC) and impact of sociodemographic factors on treatment choice from a nationwide cohort over 10 years.</P><P><B>Materials and Methods</B></P><P>We conducted a cohort study of a 2% nationwide random sample of Korean National Health Insurance. A total of 1,382 patients who had undergone active treatments for newly diagnosed PC between 2003 and 2013 were included. Time trends in primary treatment of PC, including radical surgery, radiation therapy (RT), and androgen deprivation therapy (ADT) were analyzed.</P><P><B>Results</B></P><P>Total number of patients undergoing active treatments increased significantly (162%). Surgery cases showed the most significant increase, from 22.4% in 2003 to 45.4% in 2013, while the relative proportion of ADT showed a tendency to decrease from 60.3% in 2003 to 45.4% in 2013, and the relative proportion of RT was variable over 10 years (from 7.2% to 18.4%). While treatment patterns differed significantly according to age (p < 0.001) and income classes (p=0.014), there were differences in primary treatment according to residential area. In multinomial logistic regression analysis, older patients showed significant association with ADT or RT compared to surgery, while patients with higher income showed significant association with surgery.</P><P><B>Conclusion</B></P><P>Treatment pattern in Korean PC patients has changed remarkably over the last 10 years. Sociodemographic factors do affect the primary treatment choice. Our results will be valuable in overviewing changing patterns of primary treatment in Korean PC patients and planning future health policy for PC.</P>
Artificial Intelligence in Health Care: Current Applications and Issues
박찬우,서성욱,Kang Noeul,Ko BeomSeok,Choi Byung Wook,Park ChangMin,Chang Dong Kyung,김휘영,Kim Hyunchul,이현나,Jang Jinhee,Ye Jong Chul,Jeon Jong Hong,Seo Joon Beom,Kim Kwang Joon,Jung Kyu-Hwan,Kim Namkug,Paek Se 대한의학회 2020 Journal of Korean medical science Vol.35 No.42
In recent years, artificial intelligence (AI) technologies have greatly advanced and become a reality in many areas of our daily lives. In the health care field, numerous efforts are being made to implement the AI technology for practical medical treatments. With the rapid developments in machine learning algorithms and improvements in hardware performances, the AI technology is expected to play an important role in effectively analyzing and utilizing extensive amounts of health and medical data. However, the AI technology has various unique characteristics that are different from the existing health care technologies. Subsequently, there are a number of areas that need to be supplemented within the current health care system for the AI to be utilized more effectively and frequently in health care. In addition, the number of medical practitioners and public that accept AI in the health care is still low; moreover, there are various concerns regarding the safety and reliability of AI technology implementations. Therefore, this paper aims to introduce the current research and application status of AI technology in health care and discuss the issues that need to be resolved.
Zang, Yunxiang,Lim, Myungho,Park, Beomseok,Hong, Seungbeom,Kim, Doohwan Korean Society for Molecular Biology 2008 Molecules and cells Vol.25 No.2
Indole glucosinolates (IG) play important roles in plant defense, plant-insect interactions, and stress responses in plants. In an attempt to metabolically engineer the IG pathway flux in Chinese cabbage, three important Arabidopsis cDNAs, CYP79B2, CYP79B3, and CYP83B1, were introduced into Chinese cabbage by Agrobacterium-mediated transformation. Overexpression of CYP79B3 or CYP83B1 did not affect IG accumulation levels, and overexpression of CYP79B2 or CYP79B3 prevented the transformed callus from being regenerated, displaying the phenotype of indole-3-acetic acid (IAA) overproduction. However, when CYP83B1 was overexpressed together with CYP79B2 and/or CYP79B3, the transformed calli were regenerated into whole plants that accumulated higher levels of glucobrassicin, 4-hydroxy glucobrassicin, and 4-methoxy glu-cobrassicin than wild-type controls. This result suggests that the flux in Chinese cabbage is predominantly channeled into IAA biosynthesis so that coordinate expression of the two consecutive enzymes is needed to divert the flux into IG biosynthesis. With regard to IG accumulation, overexpression of all three cDNAs was no better than overexpression of the two cDNAs. The content of neoglucobrassicin remained unchanged in all transgenic plants. Although glucobrassicin was most directly affected by overexpression of the transgenes, elevated levels of the parent IG, glucobrassicin, were not always accompanied by increases in 4-hydroxy and 4-methoxy glucobrassicin. However, one transgenic line producing about 8-fold increased glucobrassicin also accumulated at least 2.5 fold more 4-hydroxy and 4-methoxy glucobrassicin. This implies that a large glucobrassicin pool exceeding some threshold level drives the flux into the side chain modification pathway. Aliphatic glucosinolate content was not affected in any of the transgenic plants.