• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.5
• /
• pp.482-488
• /
• 2014

This paper aims to analyze user's emotion automatically by analyzing Twitter, a representative social network service (SNS). In order to create sentiment analysis models by using machine learning techniques, sentiment labels that represent positive/negative emotions are required. However it is very expensive to obtain sentiment labels of tweets. So, in this paper, we propose a sentiment analysis model by using self-training technique in order to utilize "data without sentiment labels" as well as "data with sentiment labels". Self-training technique is that labels of "data without sentiment labels" is determined by utilizing "data with sentiment labels", and then updates models using together with "data with sentiment labels" and newly labeled data. This technique improves the sentiment analysis performance gradually. However, it has a problem that misclassifications of unlabeled data in an early stage affect the model updating through the whole learning process because labels of unlabeled data never changes once those are determined. Thus, labels of "data without sentiment labels" needs to be carefully determined. In this paper, in order to get high performance using self-training technique, we propose 3 policies for updating "data with sentiment labels" and conduct a comparative analysis. The first policy is to select data of which confidence is higher than a given threshold among newly labeled data. The second policy is to choose the same number of the positive and negative data in the newly labeled data in order to avoid the imbalanced class learning problem. The third policy is to choose newly labeled data less than a given maximum number in order to avoid the updates of large amount of data at a time for gradual model updates. Experiments are conducted using Stanford data set and the data set is classified into positive and negative. As a result, the learned model has a high performance than the learned models by using "data with sentiment labels" only and the self-training with a regular model update policy.

• The Journal of Korean society of community based occupational therapy
• /
• v.7 no.1
• /
• pp.59-70
• /
• 2017

Objective : The purpose of this study was to examine the effect of virtual reality-based remote rehabilitation on stroke patients systematically and to look for its effect and how to apply it domestically. Methods : In order to search data, EMBASE and CINAHL database were used. Relevant research used those terms of virtual reality, telerehabilitation, and stroke. A total of 10 studies satisfying the selection criteria was analyzed according to their qualitative level, general characteristics, and PICO method. Results : Based on the selected 10 studies, virtual reality-based telerehabilitation system was applied. Sensory and motor feedback was provided with inputting visual and auditory senses through a video in the home environment, and it stimulated changes in the client's nervous system. Tools to measure the results were upper extremity function, balance and gait, activities of daily living, etc. Those virtual reality-based telerehabilitation method had an effect on upper extremity function and ability of sense of balance in all studies, and on the activities of daily living partially. Telerehabilitation service to make up environmental specificity improved satisfaction of client. That meaned the effect of the intervention to maintain the function. Conclusion : The virtual reality-based telerehabilitation system was applied to upper extremity function, sense of balance, and activities of daily living largely, and it showed that it helped to improve functions through intervention, supervision, and training of therapist in the home environment as well. This study suggests the basis and possibility of clinical application on virtual-reality based telerehabilitation. Additional research is needed to diverse virtual reality intervention methods and the effect of telerehabilitation in the future.

• Journal of Korean Society for Geospatial Information Science
• /
• v.24 no.1
• /
• pp.43-50
• /
• 2016

Urbanization in Korea has increased significantly and subsequently, various facilities have been concentrated in urban areas at high speed in accordance with a growing urban population. Accordingly, damages have occurred due to a variety of disasters. In particular, fire damage among the social disasters caused the most severe damage in urban areas along with traffic accidents. 44,432 cases of fire occurred in 2015 in Korea. Due to these accidents, 253 were killed and property damage of 4,50 billion won was generated. However, despite the efforts to reduce a variety of damage, fire danger still remains high. In this regard, this study collected fire data, generated from 2007 to 2014 through the Jinju Fire Department and the National Fire Data System(NFDS) and calculated fire risk by analyzing the clustering of fire cases and facilities in Jinju-si based on the current DB of facilities, offered by the Ministry of Government Administration and Home Affairs. As a result, the risk ratings of fire occurrence were classified as four stages under the standards of the US Society of Fire Protection Engineers(SEPE). Business facilities, entertainment facilities, and automobile facilities were classified as the highest A grade, detached houses, Apartment houses, education facilities, sales facilities, accommodation, set of facilities, medical facilities, industrial facilities, and life service facilities were classified as U grade, and other facilities were classified as EU grade. Finally, hazardous production facilities were classified as BEU grade, the lowest grade. In addition, in the case of setting the standard with loss of life, the highest risk facility was the hazardous production facilities, while in the case of setting the standard with property damage, a set of facilities and industrial facilities showed the highest risk. In this regard, this study is expected to be effectively utilized to establish the fire reduction measures against facilities, distributed in urban space by calculating risk grades regarding the generation frequency, casualties, and property damage, through the classification of fire, occurred in the city, according to the facilities.

• Journal of Intelligence and Information Systems
• /
• v.16 no.3
• /
• pp.147-161
• /
• 2010

As broadcasting and communication are converged recently, communication is jointed to TV. TV viewing has brought about many changes. The IPTV (Internet Protocol Television) provides information service, movie contents, broadcast, etc. through internet with live programs + VOD (Video on demand) jointed. Using communication network, it becomes an issue of new business. In addition, new technical issues have been created by imaging technology for the service, networking technology without video cuts, security technologies to protect copyright, etc. Through this IPTV network, users can watch their desired programs when they want. However, IPTV has difficulties in search approach, menu approach, or finding programs. Menu approach spends a lot of time in approaching programs desired. Search approach can't be found when title, genre, name of actors, etc. are not known. In addition, inserting letters through remote control have problems. However, the bigger problem is that many times users are not usually ware of the services they use. Thus, to resolve difficulties when selecting VOD service in IPTV, a personalized service is recommended, which enhance users' satisfaction and use your time, efficiently. This paper provides appropriate programs which are fit to individuals not to save time in order to solve IPTV's shortcomings through filtering and recommendation-related system. The proposed recommendation system collects TV program information, the user's preferred program genres and detailed genre, channel, watching program, and information on viewing time based on individual records of watching IPTV. To look for these kinds of similarities, similarities can be compared by using ontology for TV programs. The reason to use these is because the distance of program can be measured by the similarity comparison. TV program ontology we are using is one extracted from TV-Anytime metadata which represents semantic nature. Also, ontology expresses the contents and features in figures. Through world net, vocabulary similarity is determined. All the words described on the programs are expanded into upper and lower classes for word similarity decision. The average of described key words was measured. The criterion of distance calculated ties similar programs through K-medoids dividing method. K-medoids dividing method is a dividing way to divide classified groups into ones with similar characteristics. This K-medoids method sets K-unit representative objects. Here, distance from representative object sets temporary distance and colonize it. Through algorithm, when the initial n-unit objects are tried to be divided into K-units. The optimal object must be found through repeated trials after selecting representative object temporarily. Through this course, similar programs must be colonized. Selecting programs through group analysis, weight should be given to the recommendation. The way to provide weight with recommendation is as the follows. When each group recommends programs, similar programs near representative objects will be recommended to users. The formula to calculate the distance is same as measure similar distance. It will be a basic figure which determines the rankings of recommended programs. Weight is used to calculate the number of watching lists. As the more programs are, the higher weight will be loaded. This is defined as cluster weight. Through this, sub-TV programs which are representative of the groups must be selected. The final TV programs ranks must be determined. However, the group-representative TV programs include errors. Therefore, weights must be added to TV program viewing preference. They must determine the finalranks.Based on this, our customers prefer proposed to recommend contents. So, based on the proposed method this paper suggested, experiment was carried out in controlled environment. Through experiment, the superiority of the proposed method is shown, compared to existing ways.

• Korean Journal of Materials Research
• /
• v.9 no.3
• /
• pp.274-281
• /
• 1999

Usually sputtering and electroless plating methods were used for manufacturing metal-alloy thin film magnetic memory devices. Since electroless plating method has many merits in mass production and product variety com­pared to sputtering method, many researches about electroless plating have been performed in the United State of America and Japan. However, electroless plating method has not been studied frequently in Korea. In these respects the purpose of this research is manufacturing Co-Mn-P alloy thin film on the corning glass 2948 by electroless plating method using sodium hypophosphite as a reductant, and analyzing deposition rate, alloy composition, microstructure, and magnetic characteristics at various pH's and temperatures. For Co-P alloy thin film, the reductive deposition reaction 0$\alpha$urred only in basic condition, not in acidic condition. The deposition rate increased as the pH and temperature increased, and the optimum condition was found at the pH of 10 and the temperature of $80^{\circ}C$. Also magnetic charac­teristics was found to be most excellent at the pH of 9 and the temperature of $70^{\circ}C$, resulting in the coercive force of 8700e and the squareness of 0.78. At this condition, the contents of P was 2.54% and the thickness of the film was $0.216\mu\textrm{m}$. For crystal orientation, we could not observe fcc for $\beta$-Co. On the other hand,(1010), (0002), (1011) orientation of hcp for a-Co was observed. We could confirm the formation of longitudinal magnetization from dominant (1010) and (1011) orientation of Co-P alloy. For Co-Mn-P alloy deposition, coercive force was about 1000e more than that of Co P alloy, but squareness had no difference. For crystal orientation, (l01O) and (lOll) orientation of $\alpha$-Co was dominant as same as that of Co- P alloy. Likewise we could confirm the formation of longitudinal magnetization.

• Asia pacific journal of information systems
• /
• v.24 no.4
• /
• pp.611-635
• /
• 2014

Information systems (IS) have become ubiquitous and changed every aspect of how people live their lives. While some IS have been successfully adopted and widely used, others have failed to be adopted and crowded out in spite of remarkable progress in technologies. Both the technology acceptance model (TAM) and the IS Success Model (ISSM), among many others, have contributed to explain the reasons of success as well as failure in IS adoption and usage. While the TAM suggests that intention to use and perceived usefulness lead to actual IS usage, the ISSM indicates that information quality, system quality, and service quality affect IS usage and user satisfaction. Upon literature review, however, we found a significant void in theoretical development and its applications that employ either of the two models, and we raise research questions. First of all, in spite of the causal relationship between intention to use and actual usage, in most previous studies, only intention to use was employed as a dependent variable without overt explaining its relationship with actual usage. Moreover, even in a few studies that employed actual IS usage as a dependent variable, the degree of actual usage was measured based on users' perceptual responses to survey questionnaires. However, the measurement of actual usage based on survey responses might not be 'actual' usage in a strict sense that responders' perception may be distorted due to their selective perceptions or stereotypes. By the same token, the degree of system quality that IS users perceive might not be 'real' quality as well. This study seeks to fill this void by measuring the variables of actual usage and system quality using 'fact' data such as system logs and specifications of users' information and communications technology (ICT) devices. More specifically, we propose an integrated research model that bring together the TAM and the ISSM. The integrated model is composed of both the variables that are to be measured using fact as well as survey data. By employing the integrated model, we expect to reveal the difference between real and perceived degree of system quality, and to investigate the relationship between the perception-based measure of intention to use and the fact-based measure of actual usage. Furthermore, we also aim to add empirical findings on the general research question: what factors influence actual IS usage and how? In order to address the research question and to examine the research model, we selected a mobile campus application (MCA). We collected both fact data and survey data. For fact data, we retrieved them from the system logs such information as menu usage counts, user's device performance, display size, and operating system revision version number. At the same time, we conducted a survey among university students who use an MCA, and collected 180 valid responses. A partial least square (PLS) method was employed to validate our research model. Among nine hypotheses developed, we found five were supported while four were not. In detail, the relationships between (1) perceived system quality and perceived usefulness, (2) perceived system quality and perceived intention to use, (3) perceived usefulness and perceived intention to use, (4) quality of device platform and actual IS usage, and (5) perceived intention to use and actual IS usage were found to be significant. In comparison, the relationships between (1) quality of device platform and perceived system quality, (2) quality of device platform and perceived usefulness, (3) quality of device platform and perceived intention to use, and (4) perceived system quality and actual IS usage were not significant. The results of the study reveal notable differences from those of previous studies. First, although perceived intention to use shows a positive effect on actual IS usage, its explanatory power is very weak ($R^2$=0.064). Second, fact-based system quality (quality of user's device platform) shows a direct impact on actual IS usage without the mediating role of intention to use. Lastly, the relationships between perceived system quality (perception-based system quality) and other constructs show completely different results from those between quality of device platform (fact-based system quality) and other constructs. In the post-hoc analysis, IS users' past behavior was additionally included in the research model to further investigate the cause of such a low explanatory power of actual IS usage. The results show that past IS usage has a strong positive effect on current IS usage while intention to use does not have, implying that IS usage has already become a habitual behavior. This study provides the following several implications. First, we verify that fact-based data (i.e., system logs of real usage records) are more likely to reflect IS users' actual usage than perception-based data. In addition, by identifying the direct impact of quality of device platform on actual IS usage (without any mediating roles of attitude or intention), this study triggers further research on other potential factors that may directly influence actual IS usage. Furthermore, the results of the study provide practical strategic implications that organizations equipped with high-quality systems may directly expect high level of system usage.

• Korean Journal of Remote Sensing
• /
• v.37 no.6_2
• /
• pp.1849-1858
• /
• 2021

We analyzed the monthly and annual trends of the meteorological factors(wind speeds and directions and air temperatures) measured at an automated synoptic observation system (ASOS) and fine particle (PM₁₀ and PM_2.5) concentrations measured at the air quality monitoring systems(AQMSs) in Suwon. In addition, we investigated how the fine particle concentrations were related to the meteorological factors as well as urban morphological parameters (fractions of building volume and road area). We calculated the total volume of buildings and the total area of the roads in the area of 2 km × 2 km centered at each AQMS using the geographic information system and environmental geographic information system. The analysis of the meteorological factors showed that the dominant wind directions at the ASOS were westerly and northwesterly and that the average wind speed was strong in Spring. The measured fine particle concentrations were low in Summer and early Autumn (July to September) and high in Spring and Winter. In 2020, the annual mean fine particle concentration was lowest at most AQMSs. The fine particle concentrations were negatively and weakly correlated with the measured wind speeds and air temperatures (the correlation between PM_2.5 concentrations and air temperatures was relatively strong). In Suwon city, at least for 6 AQMSs except for the RAQMS 131116 and AQMS 131118, the PM₁₀ concentrations were affected mainly by the transport from outside rather than primary emission from mobile sources or wind speed decrease caused by buildings and, in the case of PM_2.5, vise versa.

• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.197-217
• /
• 2018

Music is one of the most creative act that can express human sentiment with sound. Also, since music invoke people's sentiment to get empathized with it easily, it can either encourage or discourage people's sentiment with music what they are listening. Thus, sentiment is the primary factor when it comes to searching or recommending music to people. Regard to the music recommendation system, there are still lack of recommendation systems that are based on customer sentiment. An algorithm's that were used in previous music recommendation systems are mostly user based, for example, user's play history and playlists etc. Based on play history or playlists between multiple users, distance between music were calculated refer to basic information such as genre, singer, beat etc. It can filter out similar music to the users as a recommendation system. However those methodology have limitations like filter bubble. For example, if user listen to rock music only, it would be hard to get hip-hop or R&B music which have similar sentiment as a recommendation. In this study, we have focused on sentiment of music itself, and finally developed methodology of defining new index for music recommendation system. Concretely, we are proposing "SWEMS" index and using this index, we also extracted "Sentiment Pattern" for each music which was used for this research. Using this "SWEMS" index and "Sentiment Pattern", we expect that it can be used for a variety of purposes not only the music recommendation system but also as an algorithm which used for buildup predicting model etc. In this study, we had to develop the music recommendation system based on emotional adjectives which people generally feel when they listening to music. For that reason, it was necessary to collect a large amount of emotional adjectives as we can. Emotional adjectives were collected via previous study which is related to them. Also more emotional adjectives has collected via social metrics and qualitative interview. Finally, we could collect 134 individual adjectives. Through several steps, the collected adjectives were selected as the final 60 adjectives. Based on the final adjectives, music survey has taken as each item to evaluated the sentiment of a song. Surveys were taken by expert panels who like to listen to music. During the survey, all survey questions were based on emotional adjectives, no other information were collected. The music which evaluated from the previous step is divided into popular and unpopular songs, and the most relevant variables were derived from the popularity of music. The derived variables were reclassified through factor analysis and assigned a weight to the adjectives which belongs to the factor. We define the extracted factors as "SWEMS" index, which describes sentiment score of music in numeric value. In this study, we attempted to apply Case Based Reasoning method to implement an algorithm. Compare to other methodology, we used Case Based Reasoning because it shows similar problem solving method as what human do. Using "SWEMS" index of each music, an algorithm will be implemented based on the Euclidean distance to recommend a song similar to the emotion value which given by the factor for each music. Also, using "SWEMS" index, we can also draw "Sentiment Pattern" for each song. In this study, we found that the song which gives a similar emotion shows similar "Sentiment Pattern" each other. Through "Sentiment Pattern", we could also suggest a new group of music, which is different from the previous format of genre. This research would help people to quantify qualitative data. Also the algorithms can be used to quantify the content itself, which would help users to search the similar content more quickly.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.14 no.1
• /
• pp.101-116
• /
• 2019

Technology-based start-up is important in that it encourages innovation, facilitates the development of new products and services, and contributes to job creation. Technology-based start-up activates entrepreneurship when appropriate support is provided within the ecosystem. Thus, understanding the technology-based start-up ecosystem is crucial. The purpose of this study is as follows. First, in Herrmann et al.'s(2015) study, we compare and analyze the ecosystem of each country by selecting representative regions such as Silicon Valley, Tel Aviv, London and Singapore which have the highest ranking in the start-up ecosystem. Second, we try to deeply understand the start-up ecosystem based on in-depth interviews with various stakeholders such as VC investors, start-ups, support organizations, and professors related to the Korean start-up ecosystem. Finally, based on the results of the study, we suggest development and activation of Korean technology-based start-up ecosystem. As a result, the Seoul start-up ecosystem showed a positive evaluation of government support compared to other advanced countries. In addition, it was confirmed that the ratio of tele-work and start-up company working experience of employees was higher than other countries. On the other hand, in Seoul, It was confirmed that overseas market performance, human resource diversity, attracting investment, hiring technological engineers, and the ratio of female entrepreneurs were lower than those of overseas advanced countries. In addition, according to the results of the interview analysis, Seoul was able to find that start-up ecosystems such as individual angel investors, accelerators, support institution, and media are developing thanks to the government's market-oriented policy support. However, in order for this development to continue, it is necessary to improve the continuous investment system, expansion of diversity, investment return system, and accessibility to the global market. A discussion on this issue is presented.

• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.51-66
• /
• 2018

As AI (Artificial Intelligence) technologies have been swiftly evolved, a lot of products and services are under development in various fields for better users' experience. On this technology advance, negative effects of AI technologies also have been discussed actively while there exists positive expectation on them at the same time. For instance, many social issues such as trolley dilemma and system security issues are being debated, whereas autonomous vehicles based on artificial intelligence have had attention in terms of stability increase. Therefore, it needs to check and analyse major social issues on artificial intelligence for their development and societal acceptance. In this paper, multi-categorical sentiment analysis is conducted over online public opinion on artificial intelligence after identifying the trending topics related to artificial intelligence for two years from January 2016 to December 2017, which include the event, match between Lee Sedol and AlphaGo. Using the largest web portal in South Korea, online news, news headlines and news comments were crawled. Considering the importance of trending topics, online public opinion was analysed into seven multiple sentimental categories comprised of anger, dislike, fear, happiness, neutrality, sadness, and surprise by topics, not only two simple positive or negative sentiment. As a result, it was found that the top sentiment is "happiness" in most events and yet sentiments on each keyword are different. In addition, when the research period was divided into four periods, the first half of 2016, the second half of the year, the first half of 2017, and the second half of the year, it is confirmed that the sentiment of 'anger' decreases as goes by time. Based on the results of this analysis, it is possible to grasp various topics and trends currently discussed on artificial intelligence, and it can be used to prepare countermeasures. We hope that we can improve to measure public opinion more precisely in the future by integrating empathy level of news comments.