• 제목/요약/키워드: Usefulness of Learning

검색결과 508건 처리시간 0.027초

Application of Support Vector Regression for Improving the Performance of the Emotion Prediction Model (감정예측모형의 성과개선을 위한 Support Vector Regression 응용)

  • Kim, Seongjin;Ryoo, Eunchung;Jung, Min Kyu;Kim, Jae Kyeong;Ahn, Hyunchul
    • Journal of Intelligence and Information Systems
    • /
    • 제18권3호
    • /
    • pp.185-202
    • /
    • 2012
  • .Since the value of information has been realized in the information society, the usage and collection of information has become important. A facial expression that contains thousands of information as an artistic painting can be described in thousands of words. Followed by the idea, there has recently been a number of attempts to provide customers and companies with an intelligent service, which enables the perception of human emotions through one's facial expressions. For example, MIT Media Lab, the leading organization in this research area, has developed the human emotion prediction model, and has applied their studies to the commercial business. In the academic area, a number of the conventional methods such as Multiple Regression Analysis (MRA) or Artificial Neural Networks (ANN) have been applied to predict human emotion in prior studies. However, MRA is generally criticized because of its low prediction accuracy. This is inevitable since MRA can only explain the linear relationship between the dependent variables and the independent variable. To mitigate the limitations of MRA, some studies like Jung and Kim (2012) have used ANN as the alternative, and they reported that ANN generated more accurate prediction than the statistical methods like MRA. However, it has also been criticized due to over fitting and the difficulty of the network design (e.g. setting the number of the layers and the number of the nodes in the hidden layers). Under this background, we propose a novel model using Support Vector Regression (SVR) in order to increase the prediction accuracy. SVR is an extensive version of Support Vector Machine (SVM) designated to solve the regression problems. The model produced by SVR only depends on a subset of the training data, because the cost function for building the model ignores any training data that is close (within a threshold ${\varepsilon}$) to the model prediction. Using SVR, we tried to build a model that can measure the level of arousal and valence from the facial features. To validate the usefulness of the proposed model, we collected the data of facial reactions when providing appropriate visual stimulating contents, and extracted the features from the data. Next, the steps of the preprocessing were taken to choose statistically significant variables. In total, 297 cases were used for the experiment. As the comparative models, we also applied MRA and ANN to the same data set. For SVR, we adopted '${\varepsilon}$-insensitive loss function', and 'grid search' technique to find the optimal values of the parameters like C, d, ${\sigma}^2$, and ${\varepsilon}$. In the case of ANN, we adopted a standard three-layer backpropagation network, which has a single hidden layer. The learning rate and momentum rate of ANN were set to 10%, and we used sigmoid function as the transfer function of hidden and output nodes. We performed the experiments repeatedly by varying the number of nodes in the hidden layer to n/2, n, 3n/2, and 2n, where n is the number of the input variables. The stopping condition for ANN was set to 50,000 learning events. And, we used MAE (Mean Absolute Error) as the measure for performance comparison. From the experiment, we found that SVR achieved the highest prediction accuracy for the hold-out data set compared to MRA and ANN. Regardless of the target variables (the level of arousal, or the level of positive / negative valence), SVR showed the best performance for the hold-out data set. ANN also outperformed MRA, however, it showed the considerably lower prediction accuracy than SVR for both target variables. The findings of our research are expected to be useful to the researchers or practitioners who are willing to build the models for recognizing human emotions.

The Critic on Mohism in the History of Korean Thoughts Centered on the Theory of Rejecting Heterodoxy (한국사상사에서의 묵가(墨家) 비판 - 벽리단론(闢異端論)의 전개 양상을 중심으로 -)

  • Yun, Muhak
    • The Journal of Korean Philosophical History
    • /
    • 제29호
    • /
    • pp.89-123
    • /
    • 2010
  • As above, as theoretical basis of critiques against School of Mohism, the researcher summarized the positions of the elder Confucian scholars including Meng Zi. In the body of text, taking it as promises, the researcher examined the critiques against Mo Tzu and School of Mohism as well focusing on the aspects and development of the theory of rejecting heterodoxy which had been introduced and strongly argued from the end of Goryeo kingdom to the late Joseon period. The summary of the body of this text is as follows: In the old literatures prior to Goryeo Kingdom, the researcher couldn't find any cases that either the School of Mohism or Mo Tzu including the Hundred Schools of Thought had been rejected explicitly. Having reached the end of Goryeo and the beginning of Joseon period, Meng Zi's viewpoints on the theory of rejecting heterodoxy had begun to emerge and come into play with the progress of accepting Neo-Confucianism, and, these critiques against Yang Zhu and Mo Tzu being given, the scholar-literati circle had started rejecting Buddhism and Lao Tzu. Basically the contents of the critiques against the School of Mohism in the early period of Joseon were in succession to Meng Zi's theory of rejecting heterodoxy and the views and thoughts of the elder Confucian scholars including Han Yu rather than any specific critiques against Mo Tzu' ideology itself. Until entering the middle of Joseon period, the critiques against the School of Mohism had been used as a tool to promote Confucianism in an affirmative manner, while arguing strongly against the viewpoint of Han Yu in the first place. Particularly, not only the original text of the Mo Tzu's writings were directly quoted, although it was partial, but also the contents of the critiques against the School of Mohism had been developed and stretched to the extent of their entire ideological system. Having approached to the late period of Joseon, the critiques against the School of Mohism had begun to be linked to those critiques against the study of state examination or of sentence patterns including Catholic Church, furthermore the critics raised their harsh tones against the irregularities of the society at large like the issue of corruptions of the government officials of those days instead, although they still had firmly stood on the ground of the theory of rejecting heterodoxy. Those scholars that belonged to the School of Practical Learning, in particular, said in justification of the School of Mohism arguing that the major ideologies of Mo Zi had usefulness in the real world, also they even evaluated that Meng Zi ' critiques against the School of Mohism were immoderate. To sum up, characteristics of scholars in the Joseon period to understand and critique the School of Mohism are that ideologies of Mo Tzu were mostly used as a tool for the sake of critiques against heresies in other sectors of society based mainly on Meng Zi's theory of rejecting heterodoxy, rather than opposing views against the ideologies or philosophies of the School of Mohism itself. Meanwhile, however, on the plus side, the critics praised Mo Tzu's individual efforts in order to put his ideology of peace into practice apart from the ideological system of the School of Mohism. Also, having reached the late period of Joseon, the researcher was able to have discovered the fact that the writings of Mo Tzu had been used as historical materials in order to ascertain historical truths of Confucian Scriptures, rather not having it regarded as an ideology text.

A study on the use of a Business Intelligence system : the role of explanations (비즈니스 인텔리전스 시스템의 활용 방안에 관한 연구: 설명 기능을 중심으로)

  • Kwon, YoungOk
    • Journal of Intelligence and Information Systems
    • /
    • 제20권4호
    • /
    • pp.155-169
    • /
    • 2014
  • With the rapid advances in technologies, organizations are more likely to depend on information systems in their decision-making processes. Business Intelligence (BI) systems, in particular, have become a mainstay in dealing with complex problems in an organization, partly because a variety of advanced computational methods from statistics, machine learning, and artificial intelligence can be applied to solve business problems such as demand forecasting. In addition to the ability to analyze past and present trends, these predictive analytics capabilities provide huge value to an organization's ability to respond to change in markets, business risks, and customer trends. While the performance effects of BI system use in organization settings have been studied, it has been little discussed on the use of predictive analytics technologies embedded in BI systems for forecasting tasks. Thus, this study aims to find important factors that can help to take advantage of the benefits of advanced technologies of a BI system. More generally, a BI system can be viewed as an advisor, defined as the one that formulates judgments or recommends alternatives and communicates these to the person in the role of the judge, and the information generated by the BI system as advice that a decision maker (judge) can follow. Thus, we refer to the findings from the advice-giving and advice-taking literature, focusing on the role of explanations of the system in users' advice taking. It has been shown that advice discounting could occur when an advisor's reasoning or evidence justifying the advisor's decision is not available. However, the majority of current BI systems merely provide a number, which may influence decision makers in accepting the advice and inferring the quality of advice. We in this study explore the following key factors that can influence users' advice taking within the setting of a BI system: explanations on how the box-office grosses are predicted, types of advisor, i.e., system (data mining technique) or human-based business advice mechanisms such as prediction markets (aggregated human advice) and human advisors (individual human expert advice), users' evaluations of the provided advice, and individual differences in decision-makers. Each subject performs the following four tasks, by going through a series of display screens on the computer. First, given the information of the given movie such as director and genre, the subjects are asked to predict the opening weekend box office of the movie. Second, in light of the information generated by an advisor, the subjects are asked to adjust their original predictions, if they desire to do so. Third, they are asked to evaluate the value of the given information (e.g., perceived usefulness, trust, satisfaction). Lastly, a short survey is conducted to identify individual differences that may affect advice-taking. The results from the experiment show that subjects are more likely to follow system-generated advice than human advice when the advice is provided with an explanation. When the subjects as system users think the information provided by the system is useful, they are also more likely to take the advice. In addition, individual differences affect advice-taking. The subjects with more expertise on advisors or that tend to agree with others adjust their predictions, following the advice. On the other hand, the subjects with more knowledge on movies are less affected by the advice and their final decisions are close to their original predictions. The advances in predictive analytics of a BI system demonstrate a great potential to support increasingly complex business decisions. This study shows how the designs of a BI system can play a role in influencing users' acceptance of the system-generated advice, and the findings provide valuable insights on how to leverage the advanced predictive analytics of the BI system in an organization's forecasting practices.

A Case Study on Students' Mathematical Concepts of Algebra, Connections and Attitudes toward Mathematics in a CAS Environment (CAS 그래핑 계산기를 활용한 수학 수업에 관한 사례 연구)

  • Park, Hui-Jeong;Kim, Kyung-Mi;Whang, Woo-Hyung
    • Communications of Mathematical Education
    • /
    • 제25권2호
    • /
    • pp.403-430
    • /
    • 2011
  • The purpose of the study was to investigate how the use of graphing calculators influence on forming students' mathematical concept of algebra, students' mathematical connection, and attitude toward mathematics. First, graphing calculators give instant feedback to students as they make students compare their written answers with the results, which helps students learn equations and linear inequalities for themselves. In respect of quadratic inequalities they help students to correct wrong concepts and understand fundamental concepts, and with regard to functions students can draw graphs more easily using graphing calculators, which means that the difficulty of drawing graphs can not be hindrance to student's learning functions. Moreover students could understand functions intuitively by using graphing calculators and explored math problems volunteerly. As a result, students were able to perceive faster the concepts of functions that they considered difficult and remain the concepts in their mind for a long time. Second, most of students could not think of connection among equations, equalities and functions. However, they could understand the connection among equations, equalities and functions more easily. Additionally students could focus on changing the real life into the algebraic expression by modeling without the fear of calculating, which made students relieve the burden of calculating and realize the usefulness of mathematics through the experience of solving the real-life problems. Third, we identified the change of six students' attitude through preliminary and an ex post facto attitude test. Five of six students came to have positive attitude toward mathematics, but only one student came to have negative attitude. However, all of the students showed positive attitude toward using graphing calculators in math class. That's because they could have more interest in mathematics by the strengthened and visualization of graphing calculators which helped them understand difficult algebraic concepts, which gave them a sense of achievement. Also, students could relieve the burden of calculating and have confidence. In a conclusion, using graphing calculators in algebra and function class has many advantages : formulating mathematics concepts, mathematical connection, and enhancing positive attitude toward mathematics. Therefore we need more research of the effect of using calculators, practical classroom materials, instruction models and assessment tools for graphing calculators. Lastly We need to make the classroom environment more adequate for using graphing calculators in math classes.

The Influence of Webtoon Usage Motivation and Theory of Planned Behavior on Intentions to Use Webtoon: Comparison between movie viewing, switching to paid content, and intention for buying character products (웹툰 이용동기와 계획행동이론 변인이 웹툰 관련 행동의도에 미치는 영향: 영화관람, 유료 콘텐츠 전환시 이용, 캐릭터 상품 구매의도의 비교)

  • Lee, Jeong Ki;Lee, You Jin;Kim, Byung Gue;Kim, Bo Mi;Choi, Sun Ryul;Koo, Ja Young;Koleva, Vanya Slavche
    • Korean Journal of Communication Studies
    • /
    • 제22권2호
    • /
    • pp.89-121
    • /
    • 2014
  • In order to suggest a strategy for continuous growth of webtoon, this article examined webtoon usage motivation and tried to make a prediction about culture content products and services connected with webtoon, including intention for viewing movies, based on webtoon; intention for switching to paid webtoon content, and intention for buying webtoon character products. From the point of view of Uses and Gratification Theory intentions for using webtoon and human sociocultural behavior intention are already predicted but with the usefulness of Theory of Planned Behavior Integrated Model this study extended the explanation power of prediction about webtoon related behavioral intention. Results found 5 motivational factors for webtoon usage i.e. 'seeking information', 'entertainment and access availability', 'webtoon genre characteristics', 'influence from a friend or acquaintance', and 'escapism and tension release'. Among them the ones that influenced the intention for viewing movies, based on webtoon, were found to be 'webtoon genre characteristics', 'escapism and tension release' and the 3 variables from Theory of Planned Behavior. 'Seeking information', 'entertainment and access availability', 'webtoon genre characteristics', and all the 3 variables from Theory of Planned Behavior were found to influence the intention for switching to paid webtoon content. The intention for buying webtoon based character products was affected by the motivational factors 'seeking information', 'escapism and tension release' and the behavior and subjective norms variables from Theory of Planned Behavior. Based on the uncommon results from the research several suggestions were made for the continuous growth of webtoon.

Usefulness of Data Mining in Criminal Investigation (데이터 마이닝의 범죄수사 적용 가능성)

  • Kim, Joon-Woo;Sohn, Joong-Kweon;Lee, Sang-Han
    • Journal of forensic and investigative science
    • /
    • 제1권2호
    • /
    • pp.5-19
    • /
    • 2006
  • Data mining is an information extraction activity to discover hidden facts contained in databases. Using a combination of machine learning, statistical analysis, modeling techniques and database technology, data mining finds patterns and subtle relationships in data and infers rules that allow the prediction of future results. Typical applications include market segmentation, customer profiling, fraud detection, evaluation of retail promotions, and credit risk analysis. Law enforcement agencies deal with mass data to investigate the crime and its amount is increasing due to the development of processing the data by using computer. Now new challenge to discover knowledge in that data is confronted to us. It can be applied in criminal investigation to find offenders by analysis of complex and relational data structures and free texts using their criminal records or statement texts. This study was aimed to evaluate possibile application of data mining and its limitation in practical criminal investigation. Clustering of the criminal cases will be possible in habitual crimes such as fraud and burglary when using data mining to identify the crime pattern. Neural network modelling, one of tools in data mining, can be applied to differentiating suspect's photograph or handwriting with that of convict or criminal profiling. A case study of in practical insurance fraud showed that data mining was useful in organized crimes such as gang, terrorism and money laundering. But the products of data mining in criminal investigation should be cautious for evaluating because data mining just offer a clue instead of conclusion. The legal regulation is needed to control the abuse of law enforcement agencies and to protect personal privacy or human rights.

  • PDF

Case Study on Science Drama in Elementary School (초등학교 과학 연극 수업 사례 연구)

  • Yoon, Hye-Gyoung;Na, Ji-Yeon;Jang, Byung-Ghi
    • Journal of The Korean Association For Science Education
    • /
    • 제24권5호
    • /
    • pp.902-915
    • /
    • 2004
  • Science drama can be an useful tool for understanding the nature of science, Science-Technology-Society relationship by providing indirect experiences to young students. Specific science concept and knowledge can also be learned with high interests. In this study, to explore the usefulness of science drama in elementary science lessons, two scripts of science drama and lesson plans were developed and implemented. Six step model for science drama lessons was also suggested. One was 'Manhattan Project' which dealt with social, ethical responsibility in using science & technology (science argument drama), and the other was 'Mom, My blood type is O' which explained the heredity of blood type (science concept drama). Two teachers were asked to write their journals during preparation and implementation of science drama lessons, and the lessons were observed by the researcher and video taped for analysis. Some students were interviewed just after the lessons by the teacher and all students were asked to write their impressions, change of their thought, what is leant etc. Overall responses of students and teachers on the two science drama lessons were very positive, 'Mom, My blood type is O' got more positive responses, and girls were more positive than boys. Some students anticipated another science drama even suggest topics for it. 'Mom, My blood type is O' was successful in making students (grade 3) understand the knowledge related with heredity of blood type (71% of the students got perfect answer). In 'Manhattan Project' students (grade 5) perceived more diverse location of responsibility after the lesson, but the danger and harmfulness of atomic power was embossed. This implied the need of more careful planning for the relevant learning activities before and after the play of science drama.Two teachers perceived the science drama as a new, useful tool for some subject which is hard to deal with by other teaching method. They were also satisfied with students' high interest and engagement during the science drama lessons but the extra time and effort for the lessons were pointed out as a main difficulties.

A Study on the Application of Outlier Analysis for Fraud Detection: Focused on Transactions of Auction Exception Agricultural Products (부정 탐지를 위한 이상치 분석 활용방안 연구 : 농수산 상장예외품목 거래를 대상으로)

  • Kim, Dongsung;Kim, Kitae;Kim, Jongwoo;Park, Steve
    • Journal of Intelligence and Information Systems
    • /
    • 제20권3호
    • /
    • pp.93-108
    • /
    • 2014
  • To support business decision making, interests and efforts to analyze and use transaction data in different perspectives are increasing. Such efforts are not only limited to customer management or marketing, but also used for monitoring and detecting fraud transactions. Fraud transactions are evolving into various patterns by taking advantage of information technology. To reflect the evolution of fraud transactions, there are many efforts on fraud detection methods and advanced application systems in order to improve the accuracy and ease of fraud detection. As a case of fraud detection, this study aims to provide effective fraud detection methods for auction exception agricultural products in the largest Korean agricultural wholesale market. Auction exception products policy exists to complement auction-based trades in agricultural wholesale market. That is, most trades on agricultural products are performed by auction; however, specific products are assigned as auction exception products when total volumes of products are relatively small, the number of wholesalers is small, or there are difficulties for wholesalers to purchase the products. However, auction exception products policy makes several problems on fairness and transparency of transaction, which requires help of fraud detection. In this study, to generate fraud detection rules, real huge agricultural products trade transaction data from 2008 to 2010 in the market are analyzed, which increase more than 1 million transactions and 1 billion US dollar in transaction volume. Agricultural transaction data has unique characteristics such as frequent changes in supply volumes and turbulent time-dependent changes in price. Since this was the first trial to identify fraud transactions in this domain, there was no training data set for supervised learning. So, fraud detection rules are generated using outlier detection approach. We assume that outlier transactions have more possibility of fraud transactions than normal transactions. The outlier transactions are identified to compare daily average unit price, weekly average unit price, and quarterly average unit price of product items. Also quarterly averages unit price of product items of the specific wholesalers are used to identify outlier transactions. The reliability of generated fraud detection rules are confirmed by domain experts. To determine whether a transaction is fraudulent or not, normal distribution and normalized Z-value concept are applied. That is, a unit price of a transaction is transformed to Z-value to calculate the occurrence probability when we approximate the distribution of unit prices to normal distribution. The modified Z-value of the unit price in the transaction is used rather than using the original Z-value of it. The reason is that in the case of auction exception agricultural products, Z-values are influenced by outlier fraud transactions themselves because the number of wholesalers is small. The modified Z-values are called Self-Eliminated Z-scores because they are calculated excluding the unit price of the specific transaction which is subject to check whether it is fraud transaction or not. To show the usefulness of the proposed approach, a prototype of fraud transaction detection system is developed using Delphi. The system consists of five main menus and related submenus. First functionalities of the system is to import transaction databases. Next important functions are to set up fraud detection parameters. By changing fraud detection parameters, system users can control the number of potential fraud transactions. Execution functions provide fraud detection results which are found based on fraud detection parameters. The potential fraud transactions can be viewed on screen or exported as files. The study is an initial trial to identify fraud transactions in Auction Exception Agricultural Products. There are still many remained research topics of the issue. First, the scope of analysis data was limited due to the availability of data. It is necessary to include more data on transactions, wholesalers, and producers to detect fraud transactions more accurately. Next, we need to extend the scope of fraud transaction detection to fishery products. Also there are many possibilities to apply different data mining techniques for fraud detection. For example, time series approach is a potential technique to apply the problem. Even though outlier transactions are detected based on unit prices of transactions, however it is possible to derive fraud detection rules based on transaction volumes.