• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.27 no.6
• /
• pp.1419-1429
• /
• 2017

Recently, environment based authentication technique had proposed reinforced authentication, which generating statistical model per user after user login history classifies into account takeover or legitimate login. But reinforced authentication is likely to be attacked if user was not attacked in past. To improve this problem in this paper, we propose unconsciousness authentication technique that generates 2-Class user model, which trains user's environmental information and others' one using machine learning algorithms. To evaluate performance of proposed technique, we performed evasion attacks: non-knowledge attacker that does not know any information about user, and sophisticated attacker that only knows one information about user. Experimental results against non-knowledge attacker show that precision and recall of Class 0 were measured as 1.0 and 0.998 respectively, and experimental results against sophisticated attacker show that precision and recall of Class 0 were measured as 0.948 and 0.998 respectively.

• Journal of Intelligence and Information Systems
• /
• v.13 no.4
• /
• pp.91-104
• /
• 2007

Ontology matching technique is one of the most important techniques in the Semantic Web as well as in other areas. Ontology matching algorithm takes two ontologies as input, and finds out the matching relations between the two ontologies by using some parameters in the matching process. Ontology matching is very useful in various areas such as the integration of large-scale ontologies, the implementation of intelligent unified search, and the share of domain knowledge for various applications. In general cases, the performance of ontology matching is estimated by measuring the matching results such as precision and recall regardless of the requirements that came from the matching environment. Therefore, most research focuses on controlling parameters for the optimization of precision and recall separately. In this paper, we focused on the harmony of precision and recall rather than independent performance of each. The purpose of this paper is to propose a methodology that determines parameters for the desired ratio of precision and recall that is appropriate for the requirements of the matching environment.

• Journal of the Korean Society for Library and Information Science
• /
• v.44 no.1
• /
• pp.117-135
• /
• 2010

We designed a structured folksonomy system in which queries can be expanded through tag control; equivalent, synonym or related tags are bound together, in order to improve the retrieval efficiency (recall and precision) of image data. Then, we evaluated the proposed system by comparing it to a tag-based system without tag control in terms of recall, precision, and user satisfaction. Furthermore, we also investigated which query expansion method is the most efficient in terms of retrieval performance. The experimental results showed that the recall, precision, and user satisfaction rates of the proposed system are statistically higher than the rates of the tag-based system, respectively. On the other hand, there are significant differences among the precision rates of query expansion methods but there are no significant differences among their recall rates. The proposed system can be utilized as a guide on how to effectively index and retrieve the digital content of digital library systems in the Library 2.0 era.

• Annual Conference of KIPS
• /
• 2022.11a
• /
• pp.478-480
• /
• 2022

This paper studies human activity image classification using deep transfer learning techniques focused on the inception convolutional neural networks (InceptionV3) model. For this, we used UFC-101 public datasets containing a group of students' behaviors in mathematics classrooms at a school in Thailand. The video dataset contains Play Sitar, Tai Chi, Walking with Dog, and Student Study (our dataset) classes. The experiment was conducted in three phases. First, it extracts an image frame from the video, and a tag is labeled on the frame. Second, it loads the dataset into the inception V3 with transfer learning for image classification of four classes. Lastly, we evaluate the model's accuracy using precision, recall, F1-Score, and confusion matrix. The outcomes of the classifications for the public and our dataset are 1) Play Sitar (precision = 1.0, recall = 1.0, F1 = 1.0), 2), Tai Chi (precision = 1.0, recall = 1.0, F1 = 1.0), 3) Walking with Dog (precision = 1.0, recall = 1.0, F1 = 1.0), and 4) Student Study (precision = 1.0, recall = 1.0, F1 = 1.0), respectively. The results show that the overall accuracy of the classification rate is 100% which states the model is more powerful for learning UCF-101 and our dataset with higher accuracy.

• Asia Marketing Journal
• /
• v.15 no.3
• /
• pp.117-139
• /
• 2013

Research on purchase intention had showed remarkable progress in contributing to the theory of consumer behavior. Despite the popularity of academic discussions on various issues influencing purchase intention, the mediating role of brand recall and brand attitude on purchase intention, in particular advergames, has not yet been well explored, especially in developing economies such as Malaysia. Furthermore, the influence of self-brand congruity, entertainment and brand placement acceptance as antecedents to brand recall and brand attitude are expected to add value to the brand recall, brand attitude and purchase intention relationships. This paper aims to investigate the impact of the mediating role of brand recall and brand attitude on purchase intention in advergames among Malaysian gamers. The antecedents towards brand recall and brand attitude are also examined to measure their influence on purchase intention. A total of 350 Malaysian gamers were interviewed through online survey in this study. The results showed that brand recall and brand attitude mediate the relationship between self-brand congruity, entertainment and brand placement acceptance with purchase intention. Also, entertainment and brand placement acceptance were found to have a significant relationship with brand recall. As expected, brand recall and brand attitude showed a positive relationship with consumer purchase intention in advergames. It was found that self-brand congruity has a significant influence on brand attitude and purchase intention. When users see the brand which matches with them, they tend to act positively toward the brand exposed in the game. This is consistent with Escalas and Bettman (2005) who suggested that the greater the congruity, the more positive the consumer's attitude toward the brand in question. This leads to game usage and purchase (Davis and Lang, 2013). In the advergaming context, the entertainment value in advergames is very important to determine the level of enjoyment and pleasure experienced by gamers during game-playing. Therefore, the more entertaining the ads, the more it will be remembered and the greater the positive behavior of the consumer towards the advergames - this ultimately stimulates their intention to purchase the brand. This study shows the effect of brand placement on brand recall and brand attitude and also purchase intention. Brand placements might not work in games due to the interactivity involved in game-playing as people could be distracted from noticing the brand placements (Yang et al., 2006). However, the significant influence of brand placements found in this study may provide major promise for advertisers. Game players may or may not explicitly remember the brands they see in the games, but these placements may influence their brand recall and brand attitude and could therefore influence later decisions (Yang et al., 2006). In this study, it was found that self-brand congruity was not significantly related with brand recall. The reason for this could be attributed to the fact that this study examined gamers who are highly involved in the interactive medium of games which force them to focus on game play rather than advertisements; the level of recognition to remember the brand exposed in the game is low and contributes to the "mismatch" between the gamers and the said brand. The present study contributes to the existing literature of the antecedents of brand recall and brand attitude in advergames. This study contributes to the role of brand recall and brand attitude as mediators in purchase behavior theory. Academically, the relationship between brand recall and brand attitude is well known in advergaming research, but their impact as important mediators on purchase intention add new understanding in the interactive communication literature. Their mediating role may provide new insights on how they facilitate the effects of self-brand congruity, entertainment and brand placement on purchase intention. Besides that, the studies on the influence of self-brand congruity on brand recall and brand attitude and also consumer intention to purchase had not well-investigated in advergames. This study contributes to fill those gaps in advergames literature. For practitioners, this study could suggest the use of illustrative or demonstrative placements of new products to help customers remember new brands, and the use of associative placements for existing products to increase consumers' purchase intention (Ho et al., 2011). To advertisers, this study may provide useful information to improve their current advertising strategies in games, for instance, by considering game players' congruity, entertainment value and brand placement factors.

• Science of Emotion and Sensibility
• /
• v.11 no.2
• /
• pp.257-270
• /
• 2008

Three experiments were carried out in order to determine whether users have longer using time, better recall of product information, and flow in an aesthetically appealing product (media player) in products offering good usability. For the experiment, fourteen emotional words were employed which were made up of 8 aesthetic and 6 usability words. In a preliminary experiment, the subjects freely used three media players and selected emotional words by a 7-point likert scale to distinguish a group of similar usability value and another group contrary to the other in aesthetic and usability value. (N=18) In the main experiment, it was hypothesized that users use more and have more flow and recalled information in the case of the aesthetically appealing product. Therefore, in the main experiment, we measured how much time subjects spent using the product and asked them to make an assumption regarding the time spent by the group that has the same usability value. We then examined the time they spent and the gap between the actual and estimated time. We also calculated the amount of menu information recalled via a questionnaire. In the last experiment, we selected the group of products contrary to each other in aesthetic and usability value and assessed the differences in using time, recall of product information, and flow. (N=18) The empirical results provide evidence that aesthetically appealing products are associated with greater flow and recall of product information than other products, thus supporting the hypothesis. In addition, it was found that there is a positive correlation between the aesthetically appealing product and flow index as well as with recalled information.

• Journal of Information Processing Systems
• /
• v.11 no.3
• /
• pp.450-464
• /
• 2015

In linguistics, stemming is the operation of reducing words to their more general form, which is called the 'stem'. Stemming is an important step in information retrieval systems, natural language processing, and text mining. Information retrieval systems are evaluated by metrics like precision and recall and the fundamental superiority of an information retrieval system over another one is measured by them. Stemmers decrease the indexed file, increase the speed of information retrieval systems, and improve the performance of these systems by boosting precision and recall. There are few Persian stemmers and most of them work based on morphological rules. In this paper we carefully study Persian stemmers, which are classified into three main classes: structural stemmers, lookup table stemmers, and statistical stemmers. We describe the algorithms of each class carefully and present the weaknesses and strengths of each Persian stemmer. We also propose some metrics to compare and evaluate each stemmer by them.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.24 no.4
• /
• pp.217-238
• /
• 2013

We investigated how combining different types of images with written text affects the comprehension of health related information. The types of images were picture, photograph, and X-ray. 47 four year college students were recruited for the experiment. The independent variables in this study included information presentation format, vividness of image, and the degree of awareness for the disease. The dependent variables were recognition and recall for information. The results showed that the information with images in recognition and recall had higher score than information with written text only. In regard to the effect of different kinds of images on comprehension of health information, information with picture had higher score than the information with photograph and X-ray. The vividness of image were found to work as a negative factor on the recognition of information. Finally, the degree of awareness of disease also failed to have any significant effect on subjects' recall and recognition. This research has implications for the contents design of health related website.

• Korean Journal of Child Studies
• /
• v.14 no.1
• /
• pp.153-166
• /
• 1993

The purpose of the present study was to examine age differences in children's recall for information about aggression, prosociability, and social withdrawal of others and to investigate the impact of likeability on children's recall for social behavioral information. The subjects were 160 children, 20 boys and 20 girls each at 6, 8, 10, and 12 years of age. The subjects listened to descriptions of the social behavior of a hypothetical boy and girl and subsequently reported their recollections. These descriptions were drawn from Bukowski's(1990) stydy, the Pupil Evaluation Inventory, and the Pittsburgh Adjustment Scales. The data were analyzed with 2-way ANOVA, paired T-test, and correlation. Differences across the age levels were found in the number of behaviors correctly recalled for the behavioral descriptions of aggression, prosociability, and social withdrawal. Descriptions of aggressive behavior was recalled more when children listened to a hypothetical boy than to a hypothetical girl. Additional analyses revealed that at 6 years of age, children recalled more descriptions of aggressive and prosocial behavior than of withdrawal and at 10 and 12 years of age, children recalled more descriptions of withdrawal behavior than of aggressive and prosocial behaviors. The more negative the children's affective evaluations of the withdrawal behavior, the better they recalled the withdrawal behavior.

• The Journal of Information Systems
• /
• v.18 no.3
• /
• pp.111-134
• /
• 2009

Today many owners of Web sites are looking to user's satisfaction survey as a key means of measuring the usability of a Web site. While it is preferred for it simplicity and ease of use, this survey method is not without potential risks. This paper focuses on showing that the existing practice of questionnaire-based usability measurement is subject to human recall errors, and that such flaws can be reduced when the questionnaire survey is followed by the users hands-on experience of the site. An empirical study was conducted, and the results indicate that the above speculation holds true. Even if respondents felt highly confident about their responses on a recall survey, a hands-on experience with a focal Web site increased the extent to which the respondents were satisfied with the shopping mall site. This indicates that a user's perception of the quality of a Web site may be distorted or lost as time goes by. In addition, the findings have shown that the use of the verbal protocol analysis method can reveal critical information that can help track the root causes of Web site usability problems, thereby helping to develop site enhancement strategies. The paper concludes with directions for future research.