• Title/Summary/Keyword: Standard addition

Search Result 4,528, Processing Time 0.035 seconds

A Study on Market Size Estimation Method by Product Group Using Word2Vec Algorithm (Word2Vec을 활용한 제품군별 시장규모 추정 방법에 관한 연구)

  • Jung, Ye Lim;Kim, Ji Hui;Yoo, Hyoung Sun
    • Journal of Intelligence and Information Systems
    • /
    • v.26 no.1
    • /
    • pp.1-21
    • /
    • 2020
  • With the rapid development of artificial intelligence technology, various techniques have been developed to extract meaningful information from unstructured text data which constitutes a large portion of big data. Over the past decades, text mining technologies have been utilized in various industries for practical applications. In the field of business intelligence, it has been employed to discover new market and/or technology opportunities and support rational decision making of business participants. The market information such as market size, market growth rate, and market share is essential for setting companies' business strategies. There has been a continuous demand in various fields for specific product level-market information. However, the information has been generally provided at industry level or broad categories based on classification standards, making it difficult to obtain specific and proper information. In this regard, we propose a new methodology that can estimate the market sizes of product groups at more detailed levels than that of previously offered. We applied Word2Vec algorithm, a neural network based semantic word embedding model, to enable automatic market size estimation from individual companies' product information in a bottom-up manner. The overall process is as follows: First, the data related to product information is collected, refined, and restructured into suitable form for applying Word2Vec model. Next, the preprocessed data is embedded into vector space by Word2Vec and then the product groups are derived by extracting similar products names based on cosine similarity calculation. Finally, the sales data on the extracted products is summated to estimate the market size of the product groups. As an experimental data, text data of product names from Statistics Korea's microdata (345,103 cases) were mapped in multidimensional vector space by Word2Vec training. We performed parameters optimization for training and then applied vector dimension of 300 and window size of 15 as optimized parameters for further experiments. We employed index words of Korean Standard Industry Classification (KSIC) as a product name dataset to more efficiently cluster product groups. The product names which are similar to KSIC indexes were extracted based on cosine similarity. The market size of extracted products as one product category was calculated from individual companies' sales data. The market sizes of 11,654 specific product lines were automatically estimated by the proposed model. For the performance verification, the results were compared with actual market size of some items. The Pearson's correlation coefficient was 0.513. Our approach has several advantages differing from the previous studies. First, text mining and machine learning techniques were applied for the first time on market size estimation, overcoming the limitations of traditional sampling based- or multiple assumption required-methods. In addition, the level of market category can be easily and efficiently adjusted according to the purpose of information use by changing cosine similarity threshold. Furthermore, it has a high potential of practical applications since it can resolve unmet needs for detailed market size information in public and private sectors. Specifically, it can be utilized in technology evaluation and technology commercialization support program conducted by governmental institutions, as well as business strategies consulting and market analysis report publishing by private firms. The limitation of our study is that the presented model needs to be improved in terms of accuracy and reliability. The semantic-based word embedding module can be advanced by giving a proper order in the preprocessed dataset or by combining another algorithm such as Jaccard similarity with Word2Vec. Also, the methods of product group clustering can be changed to other types of unsupervised machine learning algorithm. Our group is currently working on subsequent studies and we expect that it can further improve the performance of the conceptually proposed basic model in this study.

Performance State and Improvement Countermeasure of Primary Health Care Posts (보건진료소(保健診療所)와 업무실태(業務實態)와 개선방안(改善方案))

  • Park, Young-Hee;Kam, Sin;Han, Chang-Hyun;Cha, Byung-Jun;Kim, Tae-Woong;Gie, Jung-Aie;Kim, Byong-Guk
    • Journal of agricultural medicine and community health
    • /
    • v.25 no.2
    • /
    • pp.353-377
    • /
    • 2000
  • This study was performed to investigate the performance state and improvement countermeasure of Primary Health care Posts(PHPs). The operation reports of PHPs(1996 330 PHPs, 1999 313 PHPs) located in Kyongsangbuk-Do and data collected by self-administered questionnaire survey of 280 community health practitioners(CHPs) were analyzed. The major results were as follows: Population per PHP in 1999 decreased in number compared with 1996. But population of the aged increased in number. The performance status of PHP in 1999 increased compared with 1996. A hundred forty one community health practitioners(50.4%) replied that the fiscal standing of PHP was good. Only 1.4% replied that the fiscal standing of PHP was difficult. For the degree of satisfaction in affairs, overall of community health practitioners felt proud. The degree of cooperation between PHP and public health institutions was high and the degree of cooperation of between PHP and private medical institutions was high. The degree of cooperation between PHP and Health Center was significantly different by age of CHP, the service period of CHP, and CHP's service period at present PHP. Over seventy percent of CHPs replied that they had cooperative relationship with operation council, village health workers, community organization. CHPs who drew up the paper on PHP's health activity plan were 96.4 % and only 11.4% of CHPs participated drawing up the report on the second community health plan. CHPs who grasped the blood pressure and smoking status of residents over 70% were 88.2%, 63.9% respectively and the grasp rate of blood pressure fur residents were significantly different according to age and educational level of CHP. CHPs received job education in addition continuous job education arid participated on research program in last 3 years were 27.5%, respectively. CHPs performed the return health program for residents in last 3years were 65.4%. Over 95% of CHPs replied that PHPs might be necessary and 53.9% of CHPs replied that the role of PHPs should be increased. CHPS indicated that major reasons of FHPs lockout were lack of understanding for PHP and administrative convenience, CHPs were officials in special government service governors intention of self-governing body. CHPs suggested number of population in health need such as the aged and patients with chronic disease, opinion of residents, population size, traffic situation and network in order as evaluation criteria for PHP and suggested results of health performance, degree of relationship with residents, results of medical examination anti treatment, ability for administration and affairs in order as evaluation criteria for CHP. CHPs replied that the important countermeasures for PHPs under standard were affairs improvement of PHPs and shifting of location to health weakness area in city. Over 50% of CHPs indicated that the most important thing for improvement of PHPs was affairs adjustment of CLIP. And CHPs suggested that health programs carried out in priority at PHP were management of diabetes mellitus and hypertention. home visiting health care, health care for the aged. The Affairs of BLIP should be adjusted to satisfy community health need and health programs such as management of diabetes mellitus and hypertention, home visiting health care, health care for the aged should be activated in order that PHPs become organization reflecting value system of primary health care.

  • PDF

CAS 500-1/2 Image Utilization Technology and System Development: Achievement and Contribution (국토위성정보 활용기술 및 운영시스템 개발: 성과 및 의의)

  • Yoon, Sung-Joo;Son, Jonghwan;Park, Hyeongjun;Seo, Junghoon;Lee, Yoojin;Ban, Seunghwan;Choi, Jae-Seung;Kim, Byung-Guk;Lee, Hyun jik;Lee, Kyu-sung;Kweon, Ki-Eok;Lee, Kye-Dong;Jung, Hyung-sup;Choung, Yun-Jae;Choi, Hyun;Koo, Daesung;Choi, Myungjin;Shin, Yunsoo;Choi, Jaewan;Eo, Yang-Dam;Jeong, Jong-chul;Han, Youkyung;Oh, Jaehong;Rhee, Sooahm;Chang, Eunmi;Kim, Taejung
    • Korean Journal of Remote Sensing
    • /
    • v.36 no.5_2
    • /
    • pp.867-879
    • /
    • 2020
  • As the era of space technology utilization is approaching, the launch of CAS (Compact Advanced Satellite) 500-1/2 satellites is scheduled during 2021 for acquisition of high-resolution images. Accordingly, the increase of image usability and processing efficiency has been emphasized as key design concepts of the CAS 500-1/2 ground station. In this regard, "CAS 500-1/2 Image Acquisition and Utilization Technology Development" project has been carried out to develop core technologies and processing systems for CAS 500-1/2 data collecting, processing, managing and distributing. In this paper, we introduce the results of the above project. We developed an operation system to generate precision images automatically with GCP (Ground Control Point) chip DB (Database) and DEM (Digital Elevation Model) DB over the entire Korean peninsula. We also developed the system to produce ortho-rectified images indexed to 1:5,000 map grids, and hence set a foundation for ARD (Analysis Ready Data)system. In addition, we linked various application software to the operation system and systematically produce mosaic images, DSM (Digital Surface Model)/DTM (Digital Terrain Model), spatial feature thematic map, and change detection thematic map. The major contribution of the developed system and technologies includes that precision images are to be automatically generated using GCP chip DB for the first time in Korea and the various utilization product technologies incorporated into the operation system of a satellite ground station. The developed operation system has been installed on Korea Land Observation Satellite Information Center of the NGII (National Geographic Information Institute). We expect the system to contribute greatly to the center's work and provide a standard for future ground station systems of earth observation satellites.

A Study on the Problems and Resolutions of Provisions in Korean Commercial Law related to the Aircraft Operator's Liability of Compensation for Damages to the Third Party (항공기운항자의 지상 제3자 손해배상책임에 관한 상법 항공운송편 규정의 문제점 및 개선방안)

  • Kim, Ji-Hoon
    • The Korean Journal of Air & Space Law and Policy
    • /
    • v.29 no.2
    • /
    • pp.3-54
    • /
    • 2014
  • The Republic of Korea enacted the Air Transport Act in Commercial Law which was entered into force in November, 2011. The Air Transport Act in Korean Commercial Law was established to regulate domestic carriage by air and damages to the third party which occur within the territorial area caused by aircraft operations. There are some problems to be reformed in the Provisions of Korean Commercial Law for the aircraft operator's liability of compensation for damages to the third party caused by aircraft operation as follows. First, the aircraft operator's liability of compensation for damages needs to be improved because it is too low to compensate adequately to the third party damaged owing to the aircraft operation. Therefore, the standard of classifying per aircraft weight is required to be detailed from the current 4-tier into 10-tier and the total limited amount of liability is also in need of being increased to the maximum 7-hundred-million SDR. In addition, the limited amount of liability to the personal damage is necessary to be risen from the present 125,000 SDR to 625,000 SDR according to the recent rate of prices increase. This is the most desirable way to improve the current provisions given the ordinary insurance coverage per one aircraft accident and various specifications of recent aircraft in order to compensate the damaged appropriately. Second, the aircraft operator shall be liable without fault to damages caused by terrorism such as hijacking, attacking an aircraft and utilizing it as means of attack like the 9 11 disaster according to the present Air Transport Act in Korean Commercial Law. Some argue that it is too harsh to aircraft operators and irrational, but given they have also some legal duties of preventing terrorism and in respect of helping the third party damaged, it does not look too harsh or irrational. However, it should be amended into exempting aircraft operator's liability when the terrorism using of an aircraft by well-organized terrorists group happens like 9 11 disaster in view of balancing the interest between the aircraft operator and the third party damaged. Third, considering the large scale of the damage caused by the aircraft operation usually aircraft accident, it is likely that many people damaged can be faced with a financial crisis, and the provision of advance payment for air carrier's liability of compensation also needs to be applied to the case of aircraft operator's liability. Fourth, the aircraft operator now shall be liable to the damages which occur in land or water except air according to the current Air Transport Act of Korean Commercial Law. However, because the damages related to the aircraft operation in air caused by another aircraft operation are not different from those in land or water. Therefore, the term of 'on the surface' should be eliminated in the term of 'third parties on the surface' in order to make the damages by the aircraft operation in air caused by another aircraft operation compensable by Air Transport Act of Korean Commercial Law. It is desired that the Air Transport Act in Commercial Law including the clauses related to the aircraft operator's liability of compensation for damages to the third party be developed continually through the resolutions about its problems mentioned above for compensating the third party damaged appropriately and balancing the interest between the damaged and the aircraft operator.

Essay on Form and Function Design (디자인의 형태와 기능에 관한 연구)

  • 이재국
    • Archives of design research
    • /
    • v.2 no.1
    • /
    • pp.63-97
    • /
    • 1989
  • There is nothing more important than the form and function in design, because every design product can be done on the basis of them. Form and Function are already existed before the word of design has been appeared and all the natural and man-made things' basic organization is based on their organic relations. The organic relations is the source of vitality which identifies the subsistance of all the objects and the evolution of living creatures has been changed their appearances by the natural law and order. Design is no exception. Design is a man-made organic thing which is developed its own way according to the purposed aim and given situations. If so, what is the ultimate goal of design. It is without saying that the goal is to make every effort to contribute to the -human beings most desirable life by the designer who is devoting himself to their convenience and well-being. Therefore, the designer can be called the man of rich life practitioner. This word implies a lot of meanings since the essence of design is improving the guality of life by the man-made things which are created by the designer. Also, the things are existed through the relations between form and function, and the things can keep their value when they are answered to the right purpose. In design, thus, it is to be a main concern how to create valuable things and to use them in the right way, and the subject of study is focused on the designer's outlook of value and uk relations between form and function. Christopher Alexander mentioned the importance of form as follows. The ultimate object of design is form. Every design problem begins with an effort to achieve fittness between the form and its context. The form is the solution to the problem: the context defmes the problem. In other words, when we speak of design, the real object of discussion is not form alone, but the ensemble comprising the form and its context. Good fit is a desirable property of this ensemble which relates to some particular division of the ensemble into form and context. Max Bill mainatined how important form is in design. Form represents a self-contained concept, and its embodiment in an object results in that object becoming a work of art. Futhermore, this explains why we use form so freguently in a comparative sense for determining whether one thing is less or more beautiful than another, and why the ideal of absolute beauty is always the standard by which we appraise form, and through form, art itself. Hence form has became synonymous with beauty. On the other hand, Laszlo Moholy-Nagy stated the importance of function as follows. Function means the task an object is designed to fulfill the task instrument is shaping the form. Unfortunately, this principle was not appreciated at the same time but through the endeavors of Frank Lloyd Wright and of the Bauhaus group and its many collegues in Europe, the idea of functionalism became the keynote of the twenites. Functionalism soon became a cheap slogan, however, and its original meaning blurred. It is neccessary to reexamine it in the light of present circumstances. Charles William Eliot expressed his idea on the relations between function and beauty. Beauty often results chiefly from fittness: indeed it is easy to manitain that nothing is fair except what is fit its uses or functions. If the function of the product of a machine be useful and valuable, an the machine be eminently fit for its function, it conspicuously has the beauty of fittness. A locomotive or a steamship has the same sort of beauty, derived from the supreme fittness for its function. As functions vary, so will those beauty..vary. However, it is impossible to study form and function in separate beings. Function can't be existed without form, and without function, form is nothing. In other words, form is a function's container, and function is content in form. It can be said that, therefore, the form and function are indispensable and commensal individuals which have coetemal relations. From the different point of view, sometimes, one is more emphasized than the other, but in this case, the logic is only accepted on the assumption of recognizing the importance of the other's entity. The fact can be proved what Frank Hoyd wright said that form and function are one. In spite of that, the form and function should be considered as independent indivisuals, because they are too important to be treated just as the simple single one. Form and function have flexible properties to the context. In other words, the context plays a role as the barometer to define the form and function, also which implies every meaning of surroun'||'&'||'not;dings. Thus, design is formed under the influence of situations. Situations are dynamic, like the design process itself, in which fixed focus can be cripping. Moreover, situations control over making the good design. Judging from the respect, I defined the good design in my thesis An Analytic Research on Desigh Ethic, "good design is to solve the problem by the most proper way in the situations." Situations are changeable, and so is design. There is no progress without change, but change is not neccessarily progress. It is highly desirable that there changes be beneficial to mankind. Our main problem is to be able to discriminate between that which should be discarded and that which should be kept, built upon, and improved. Form and Function are no exception. The practical function gives birth to the inevitable form and the $$\mu$ti-classified function is delivered to the varieties of form. All of these are depended upon changeable situations. That is precisely the situations of "situation de'||'&'||'not;sign", the concept of moving from the design of things to the design of the circumstances in which things are used. From this point of view, the core of form and function is depended upon how the designer can manage it efficiently in given situations. That is to say that the creativity designer plays an important role to fulfill the purpose. Generally speaking, creativity is the organization of a concept in response to a human need-a solution that is both satisfying and innovative. In order to meet human needs, creative design activities require a special intuitive insight which is set into motion by purposeful imagination. Therefore, creativity is the most essential quality of every designer. In addition, designers share with other creative people a compulsive ingenuity and a passion for imaginative solutions which will meet their criteria for excellence. Ultimately, it is said that the form and function is the matter which belongs to the desire of creative designers who constantly try to bring new thing into being to create new things. In accordance with that the main puppose of this thesis is to catch every meaning of the form and function and to close analyze their relations for the promotion of understanding and devising practical application to gradual progression in design. The thesis is composed of four parts: Introduction, Form, Function and Conclusion. Introduction, the purpose and background of the research are presented. In Chapter I, orgin of form, perception of form, and classification of form are studied. In Chapter II, generation of function, development of function, and diversification of function are considered. Conclusion, some concluding words are mentioned.ioned.

  • PDF

A Study on the Morphological Structure of Sasul-Sijo (사설시조의 형태구조 연구)

  • Won, Yong-Moon
    • Sijohaknonchong
    • /
    • v.23
    • /
    • pp.161-188
    • /
    • 2005
  • The purpose of this study was to delve into the morphological types of Sijo in an effort to determine the morphological structure of Sasul-sijo, and it's also attempted to present standard about how to discriminate Pyong-si, Eos-sijo and Sasul-sijo from one another from a morphological standpoint. It's suggested that Si with tee Jangs, six verses and 12 stanzas or more, with three Jangs, seven verses and 14 stanzas or more, and with three Jangs, eight verses and 16 stanzas or more should respectively be called Pyong-sijo, Eos-sijo and Sasul-sijo. After what Sijo was and what's not were discussed, how to distinguish Eos-sijo from Sasul-sijo was described, and finally, the structure of Sasul-sijo was presented. As for Sijo and non-Sijo, the types of works that consisted of tee Jangs, like Sijo, yet didn't suit its framework and Yuljo and were written in Chinese characters were regarded as non-Sijo. Concerning discrimination between Eos-si and Sasul-sijo, the type of Sijo that included one more or higher number of verse(s) and two more or higher number of stanzas in one of three Jangs was defined as Eos-sijo, and the type of Sijo that involved two more or higher number of verses and four more or higher number of stanzas in one of three Jangs was called Sasul-sijo. In other words, Eos-sijo contained one more verse in one of tee Jangs, and Sasul-sijo included one more Jang in one tee Jangs. The sort of Sijo that contained one more Jang in one of three Jangs could be viewed as Sasul-sijo. Regarding the structure of Sasul-si, there should be three Jangs, eight verses and 16 stanzas in one piece of Sasul-sijo. Any type of Sijo that contained two more or higher number of verses and four more or higher number of stanzas could be called Sasul-sijo. Such an addition of verse and stanza could done in various ways. The examples were (1) adding stanzas the first Jang, 2) adding stanzas to the second Jang, (3) adding stanzas to the final Jang, (4) adding stanzas to both the first and Second Jangs, (5) adding stanzas to th the second and final Jangs, and (6) adding stanzas to all the first, second and third Jangs at the same time. Besides, there was an extremely broad gap between the numbers of verse and stanza in Sasul-sijo, which ranged from a low of eight stanzas to a high of 87 ones in one of three Jangs.

  • PDF

Clinical Study of Corrosive Esophagitis (부식성 식도염에 관한 임상적 고찰)

  • 이원상;정승규;최홍식;김상기;김광문;홍원표
    • Proceedings of the KOR-BRONCHOESO Conference
    • /
    • 1981.05a
    • /
    • pp.6-7
    • /
    • 1981
  • With the improvement of living standard and educational level of the people, there is an increasing awareness about the dangers of toxic substances and lethal drugs. In addition to the above, the governmental control of these substances has led to a progressive decrease in the accidents with corrosive substances. However there are still sporadic incidences of suicidal attempts with the substances due to the unbalance between the cultural development in society and individual emotion. The problem is explained by the fact that there is a variety of corrosive agents easily available to the people due to the considerable industrial development and industrialization. Salzen(1920), Bokey(1924) were pioneers on the subject of the corrosive esophagitis and esophageal stenosis by dilatation method. Since then there had been a continuing improvement on the subject with researches on various acid(Pitkin, 1935, Carmody, 1936) and alkali (Tree, 1942, Tucker, 1951) corrosive agents, and the use of steroid (Spain, 1950) and antibiotics. Recently, early esophagoscopic examination is emphasized on the purpose of determining the way of the treatment in corrosive esophagitis patients. In order to find the effective treatment of such patients in future, the authors selected 96 corrosive esophagitis patients who were admitted and treated at the ENT department of Severance hospital from 1971 to March, 1981 to attempt a clinical study. 1. Sex incidence……male: female=1 : 1.7, Age incidence……21-30 years age group; 38 cases (39.6%). 2. Suicidal attempt……80 cases(83.3%), Accidental ingestion……16 cases (16.7%). Among those who ingested the substance accidentally, children below ten years were most numerous with nine patients. 3. Incidence acetic acid……41 cases(41.8%), lye…20 cases (20.4%), HCI……17 cases (17.3%). There was a trend of rapid rise in the incidence of acidic corrosive agents especially acetic acid. 4. Lavage……57 cases (81.1%). 5. Nasogastric tube insertion……80 cases (83.3%), No insertion……16 cases(16.7%), late admittance……10 cases, failure…4 cases, other……2 cases. 6. Tracheostomy……17 cases(17.7%), respiratory problems(75.0%), mental problems (25.0%). 7. Early endoscopy……11 cases(11.5%), within 48 hours……6 cases (54.4%). Endoscopic results; moderate mucosal ulceration…8 cases (72.7%), mild mucosal erythema……2 cases (18.2%), severe mucosal ulceration……1 cases (9.1%) and among those who took early endoscopic examination; 6 patients were confirmed mild lesion and so they were discharged after endoscopy. Average period of admittance in the cases of nasogastric tube insertion was 4 weeks. 8. Nasogastric tube indwelling period……average 11.6 days, recently our treatment trend in the corrosive esophagitis patients with nasogastric tube indwelling is determined according to the finding of early endoscopy. 9. The No. of patients who didn't given and delayed administration of steroid……7 cases(48.9%): causes; kind of drug(acid, unknown)……12 cases, late admittance……11 cases, mild case…9 cases, contraindication……7 cases, other …8 cases. 10. Management of stricture; bougienage……7 cases, feeding gastrostomy……6 cases, other surgical management……4 cases. 11. Complication……27 cases(28.1%); cardio-pulmonary……10 cases, visceral rupture……8 cases, massive bleeding……6 cases, renal failure……4 cases, other…2 cases, expire and moribund discharge…8 cases. 12. No. of follow-up case……23 cases; esophageal stricture……13 cases and site of stricture; hypopharynx……1 case, mid third of esophagus…5 cases, upper third of esophagus…3 cases, lower third of esophagus……3 cases pylorus……1 case, diffuse esophageal stenosis……1 case.

  • PDF

KNU Korean Sentiment Lexicon: Bi-LSTM-based Method for Building a Korean Sentiment Lexicon (Bi-LSTM 기반의 한국어 감성사전 구축 방안)

  • Park, Sang-Min;Na, Chul-Won;Choi, Min-Seong;Lee, Da-Hee;On, Byung-Won
    • Journal of Intelligence and Information Systems
    • /
    • v.24 no.4
    • /
    • pp.219-240
    • /
    • 2018
  • Sentiment analysis, which is one of the text mining techniques, is a method for extracting subjective content embedded in text documents. Recently, the sentiment analysis methods have been widely used in many fields. As good examples, data-driven surveys are based on analyzing the subjectivity of text data posted by users and market researches are conducted by analyzing users' review posts to quantify users' reputation on a target product. The basic method of sentiment analysis is to use sentiment dictionary (or lexicon), a list of sentiment vocabularies with positive, neutral, or negative semantics. In general, the meaning of many sentiment words is likely to be different across domains. For example, a sentiment word, 'sad' indicates negative meaning in many fields but a movie. In order to perform accurate sentiment analysis, we need to build the sentiment dictionary for a given domain. However, such a method of building the sentiment lexicon is time-consuming and various sentiment vocabularies are not included without the use of general-purpose sentiment lexicon. In order to address this problem, several studies have been carried out to construct the sentiment lexicon suitable for a specific domain based on 'OPEN HANGUL' and 'SentiWordNet', which are general-purpose sentiment lexicons. However, OPEN HANGUL is no longer being serviced and SentiWordNet does not work well because of language difference in the process of converting Korean word into English word. There are restrictions on the use of such general-purpose sentiment lexicons as seed data for building the sentiment lexicon for a specific domain. In this article, we construct 'KNU Korean Sentiment Lexicon (KNU-KSL)', a new general-purpose Korean sentiment dictionary that is more advanced than existing general-purpose lexicons. The proposed dictionary, which is a list of domain-independent sentiment words such as 'thank you', 'worthy', and 'impressed', is built to quickly construct the sentiment dictionary for a target domain. Especially, it constructs sentiment vocabularies by analyzing the glosses contained in Standard Korean Language Dictionary (SKLD) by the following procedures: First, we propose a sentiment classification model based on Bidirectional Long Short-Term Memory (Bi-LSTM). Second, the proposed deep learning model automatically classifies each of glosses to either positive or negative meaning. Third, positive words and phrases are extracted from the glosses classified as positive meaning, while negative words and phrases are extracted from the glosses classified as negative meaning. Our experimental results show that the average accuracy of the proposed sentiment classification model is up to 89.45%. In addition, the sentiment dictionary is more extended using various external sources including SentiWordNet, SenticNet, Emotional Verbs, and Sentiment Lexicon 0603. Furthermore, we add sentiment information about frequently used coined words and emoticons that are used mainly on the Web. The KNU-KSL contains a total of 14,843 sentiment vocabularies, each of which is one of 1-grams, 2-grams, phrases, and sentence patterns. Unlike existing sentiment dictionaries, it is composed of words that are not affected by particular domains. The recent trend on sentiment analysis is to use deep learning technique without sentiment dictionaries. The importance of developing sentiment dictionaries is declined gradually. However, one of recent studies shows that the words in the sentiment dictionary can be used as features of deep learning models, resulting in the sentiment analysis performed with higher accuracy (Teng, Z., 2016). This result indicates that the sentiment dictionary is used not only for sentiment analysis but also as features of deep learning models for improving accuracy. The proposed dictionary can be used as a basic data for constructing the sentiment lexicon of a particular domain and as features of deep learning models. It is also useful to automatically and quickly build large training sets for deep learning models.

A Deep Learning Based Approach to Recognizing Accompanying Status of Smartphone Users Using Multimodal Data (스마트폰 다종 데이터를 활용한 딥러닝 기반의 사용자 동행 상태 인식)

  • Kim, Kilho;Choi, Sangwoo;Chae, Moon-jung;Park, Heewoong;Lee, Jaehong;Park, Jonghun
    • Journal of Intelligence and Information Systems
    • /
    • v.25 no.1
    • /
    • pp.163-177
    • /
    • 2019
  • As smartphones are getting widely used, human activity recognition (HAR) tasks for recognizing personal activities of smartphone users with multimodal data have been actively studied recently. The research area is expanding from the recognition of the simple body movement of an individual user to the recognition of low-level behavior and high-level behavior. However, HAR tasks for recognizing interaction behavior with other people, such as whether the user is accompanying or communicating with someone else, have gotten less attention so far. And previous research for recognizing interaction behavior has usually depended on audio, Bluetooth, and Wi-Fi sensors, which are vulnerable to privacy issues and require much time to collect enough data. Whereas physical sensors including accelerometer, magnetic field and gyroscope sensors are less vulnerable to privacy issues and can collect a large amount of data within a short time. In this paper, a method for detecting accompanying status based on deep learning model by only using multimodal physical sensor data, such as an accelerometer, magnetic field and gyroscope, was proposed. The accompanying status was defined as a redefinition of a part of the user interaction behavior, including whether the user is accompanying with an acquaintance at a close distance and the user is actively communicating with the acquaintance. A framework based on convolutional neural networks (CNN) and long short-term memory (LSTM) recurrent networks for classifying accompanying and conversation was proposed. First, a data preprocessing method which consists of time synchronization of multimodal data from different physical sensors, data normalization and sequence data generation was introduced. We applied the nearest interpolation to synchronize the time of collected data from different sensors. Normalization was performed for each x, y, z axis value of the sensor data, and the sequence data was generated according to the sliding window method. Then, the sequence data became the input for CNN, where feature maps representing local dependencies of the original sequence are extracted. The CNN consisted of 3 convolutional layers and did not have a pooling layer to maintain the temporal information of the sequence data. Next, LSTM recurrent networks received the feature maps, learned long-term dependencies from them and extracted features. The LSTM recurrent networks consisted of two layers, each with 128 cells. Finally, the extracted features were used for classification by softmax classifier. The loss function of the model was cross entropy function and the weights of the model were randomly initialized on a normal distribution with an average of 0 and a standard deviation of 0.1. The model was trained using adaptive moment estimation (ADAM) optimization algorithm and the mini batch size was set to 128. We applied dropout to input values of the LSTM recurrent networks to prevent overfitting. The initial learning rate was set to 0.001, and it decreased exponentially by 0.99 at the end of each epoch training. An Android smartphone application was developed and released to collect data. We collected smartphone data for a total of 18 subjects. Using the data, the model classified accompanying and conversation by 98.74% and 98.83% accuracy each. Both the F1 score and accuracy of the model were higher than the F1 score and accuracy of the majority vote classifier, support vector machine, and deep recurrent neural network. In the future research, we will focus on more rigorous multimodal sensor data synchronization methods that minimize the time stamp differences. In addition, we will further study transfer learning method that enables transfer of trained models tailored to the training data to the evaluation data that follows a different distribution. It is expected that a model capable of exhibiting robust recognition performance against changes in data that is not considered in the model learning stage will be obtained.

Discussion on the Necessity of the Study on the Principle of 'How to Mark an Era in Almanac Method of Tiāntǐlì(天體曆)' Formed until Han dynasty (한대(漢代) 이전에 형성된 천체력(天體曆) 기년(紀年) 원리 고찰의 필요성에 대한 소론(小論))

  • Seo, Jeong-Hwa
    • (The)Study of the Eastern Classic
    • /
    • no.72
    • /
    • pp.365-400
    • /
    • 2018
  • The signs of $G{\bar{a}}nzh{\bar{i}}$(干支: the sexagesimal calendar system) almanac, which marked each year, month, day and time with 60 ordinal number marks made by combining 10 $Ti{\bar{a}}ng{\bar{a}}ns$(天干: the decimal notation to mark date) and 12 $D{\grave{i}}zh{\bar{i}}s$(地支 : the duodecimal notation to mark date), were used not only as the sign of the factors affecting the occurrence of a disease and treatment in the area of traditional oriental medicine, but also as the indicator of prejudging fortunes in different areas of future prediction techniques.(for instance, astrology, the theory of divination based on topography, four pillars of destiny and etc.) While theories of many future predictive technologies with this $G{\bar{a}}nzh{\bar{i}}$(干支) almanac signs as the standard had been established in many ways by Han dynasty, it is difficult to find almanac discussion later on the fundamental theory of 'how it works like that'. As for the method to mark the era of $Ti{\bar{a}}nt{\check{i}}l{\grave{i}}$(天體曆: a calendar made with the sidereal period of Jupiter and the Sun), which determines the name of a year depending on where $Su{\grave{i}}x{\bar{i}}ng$(歲星: Jupiter) is among the '12 positions of zodiac', there are three main ways of $$Su{\grave{i}}x{\bar{i}}ng-J{\grave{i}}ni{\acute{a}}nf{\check{a}}$$(歲星紀年法: the way to mark an era by the location of Jupiter on the celestial sphere), $$T{\grave{a}}isu{\grave{i}}-J{\grave{i}}ni{\acute{a}}nf{\check{a}}$$ (太歲紀年法: the way to mark an era by the location facing the location of Jupiter on the celestial sphere) and $$G{\bar{a}}nzh{\bar{i}}-J{\grave{i}}ni{\acute{a}}nf{\check{a}}$$(干支紀年法: the way to mark an era with Ganzhi marks). Regarding $$G{\bar{a}}nzh{\bar{i}}-J{\grave{i}}ni{\acute{a}}nf{\check{a}}$$(干支紀年法), which is actually the same way to mark an era as $$T{\grave{a}}isu{\grave{i}}-J{\grave{i}}ni{\acute{a}}nf{\check{a}}$$(太歲紀年法) with the only difference in the name, there are more than three ways, and one of them has continued to be used in China, Korea and so on since Han dynasty. The name of year of $G{\bar{a}}nzh{\bar{i}}$(干支) this year, 2018, has become $W{\grave{u}}-X{\bar{u}}$(戊戌) just by 'accident'. Therefore, in this discussion, the need to realize this situation was emphasized in different areas of traditional techniques of future prediction in which distinct theories have been established with the $G{\bar{a}}nzh{\bar{i}}$(干支) mark of year, month, day and time. Because of the 1 sidereal period of Jupiter, which is a little bit shorter than 12 years, once about one thousand years, 'the location of Jupiter on the zodiac' and 'the name of a year of 12 $D{\grave{i}}zh{\bar{i}}s$(地支) marks' accord with each other just for about 85 years, and it has been verified that recent dozens of years are the very period. In addition, appropriate methods of observing the the twenty-eight lunar mansions were elucidated. As $G{\bar{a}}nzh{\bar{i}}$(干支) almanac is related to the theoretical foundation of traditional medical practice as well as various techniques of future prediction, in-depth study on the fundamental theory of ancient $Ti{\bar{a}}nt{\check{i}}l{\grave{i}}$(天體曆) cannot be neglected for the succession and development of traditional oriental study and culture, too.