- Log In/Sign Up
- P-ISSN1738-6764
- E-ISSN2093-7504
- KCI
ISSN : 1738-6764
Vol.15 No.4
Abstract
As the recent developments of artificial intelligence, particularly machine-learning, impact every aspect of society, they are also increasingly influencing creative fields manifested as new artistic tools and inspirational sources. However, as more artists integrate the technology into their creative works, the issues of diversity and fairness are also emerging in the AI-based creative practice. The data dependency of machine-learning algorithms can amplify the social injustice existing in the real world. In this paper, we present an interactive visualization system for raising the awareness of the diversity and fairness issues. Rather than resorting to education, campaign, or laws on those issues, we have developed a web & ML-based interactive data visualization system. By providing the interactive visual experience on the issues in interesting ways as the form of web content which anyone can access from anywhere, we strive to raise the public awareness of the issues and alleviate the important ethical problems. In this paper, we present the process of developing the ML-based interactive visualization system and discuss the results of this project. The proposed approach can be applied to other areas requiring attention to the issues.
Abstract
This paper presents a solution of the ‘Quick, Draw! Doodle Recognition Challenge’ hosted by Google. Doodles are drawings comprised of concrete representational meaning or abstract lines creatively expressed by individuals. In this challenge, a doodle is presented as a sequence of sketches. From the view of at the sketch level, to learn the pattern of strokes representing a doodle, we propose a sequential model stacked with multiple convolution layers and Long Short-Term Memory (LSTM) cells following the attention mechanism [15]. From the view at the image level, we use multiple models pre-trained on ImageNet to recognize the doodle. Finally, an ensemble and a post-processing method using the minimum cost flow algorithm are introduced to combine multiple models in achieving better results. In this challenge, our solutions garnered 11th place among 1,316 teams. Our performance was 0.95037 MAP@3, only 0.4% lower than the winner. It demonstrates that our method is very competitive. The source code for this competition is published at: https://github.com/ngxbac/Kaggle-QuickDraw.
Abstract
The efficient implementation of various physical actions of agents to respond to dynamically changing situations is essential for the simulation of realistic agents and activities in a cyber world. To achieve a maximum diversity of actions and immediate responsiveness to abrupt changes in situations, we have developed an animation technique in which complex actions are recursively constructed by reusing a set of primitive motions, and agents are designed to react in real-time to abrupt ambient changes by computationally satisfying kinematic constraints on body parts with respect to their goals. Our reusing scheme is extended to visualize the procedure of realistic intricate situations involving many concurring events. Our approach based on motion reuse and recursive assembly has clear advantages in motion variability and action diversity with respect to authoring scalability and motion responsiveness compared to conventional monolithic (static) animation techniques. This diversity also serves to accommodate the characteristic unpredictability of events concurring in a situation due to inherent non-determinism of associated conditions. To demonstrate the viability of our approach, we implement several composite and parallel actions in a dynamically changing example situation involving events that were originally independent until coincidentally inter-coupled therein.
Abstract
In this paper, we propose an advanced Minimum Mean Square Error (MMSE) channel estimation method for IEEE 802.11p/Wireless Access in Vehicular Environments (WAVE) systems. To improve the performance of MMSE method, we apply the Weighted Sum using Update Matrix (WSUM) scheme to the step of calculating the instantaneously estimated channel and then, a time domain selectively averaging method is applied after the WSUM scheme. Based on that, the accuracy of instantaneously estimated channel increases and then, the accuracy of auto covariance matrix also increases. Consequently, we can achieve the performance gain over the conventional MMSE method. Through simulations based on the IEEE 802.11p standard, it is confirmed that the proposed scheme can outperform the existing channel estimation schemes.
Abstract
This is an integrative review paper of Augmented Reality (AR)/Virtual Reality (VR) simulation programs in the mental health area including the analysis of the general characteristics, contents, and the impact of the interventions studies. The keywords used to search the studies were “AR/VR” and “medical/nursing students”. The author and a postdoctoral research fellow searched four electronic databases: Web of Science, PubMed, EmBase, and CINHA, and as a result nine studies met the inclusion criteria. Among the selected studies AR/VR simulation programs in the mental health area for healthcare professionals were found to be effective in clinical skills as well as for the interpersonal relationship and the stigma of mentally ill patients. Providing an opportunity to experience a safe and effective tool is important when educating health professionals and AR/VR simulation programs are safe and effective. Thus, standardized AR/VR simulation programs are needed to be developed for health professionals.
Abstract
This study is designed to examine antecedents and consequences of mobile advertising avoidance. However, to date, research on mobile advertising avoidance has been scarce. Thus, this study makes significant contributions by addressing understudied areas in mobile advertising. Study results show that the perceived mobile advertising risk is positively related to mobile advertising avoidance. This study found that the perceived trust in mobile advertising is negatively linked to mobile advertising avoidance. The study results show that the perceived Internet users’ data privacy concerns is positively linked to mobile advertising avoidance. Finally, study results suggest that mobile advertising avoidance is positively linked to intention to delete the ad.
Abstract
Baotu Spring Park, a must-visit place in Jinan, China, has been rated as the country’s highest-level scenic spot by the Chinese government. However, social media that highly reflects public opinions tends to express a lower evaluation of Baotu Spring Park. Thus, this paper employs service design thinking methods to identify the problems of Baotu Spring Park and provide solutions from the perspective of visitors. Based on desk research, tourist behavior tracking, contextual interviews, and a customer journey map, it was found that the service gap of Baotu Spring Park lacks a unified and effective instruction system. Also, the activities, parking, and high-quality tourist souvenirs are deficient, and there is no online information delivery platform. Finally, five suggestions are made,- respectively:,- redesign the sign system, enhance the participation of tourists, redesign the tourist souvenirs and display space, offer parking areas and shuttle buses, as well as set up a dedicated application.
Abstract
In recent years, emotion recognition has been an interesting and challenging topic. Compared to facial expressions and speech modality, gesture-based emotion recognition has not received much attention with only a few efforts using traditional hand-crafted methods. These approaches require major computational costs and do not offer many opportunities for improvement as most of the science community is conducting their research based on the deep learning technique. In this paper, we propose an end-to-end deep learning approach for classifying emotions based on bodily gestures. In particular, the informative keyframes are first extracted from raw videos as input for the 3D-CNN deep network. The 3D-CNN exploits the short-term spatiotemporal information of gesture features from selected keyframes, and the convolutional LSTM networks learn the long-term feature from the features results of 3D-CNN. The experimental results on the FABO dataset exceed most of the traditional methods results and achieve state-of-the-art results for the deep learning-based technique for gesture-based emotion recognition.
Abstract
Social media is a massive dataset in which individuals' thoughts are freely recorded. So there have been a variety of efforts to analyze it and to understand the social phenomenon. In this study, Twitter was used to define the moments when negative perceptions of the Korean Meteorological Administration (KMA) were displayed and the reasons people were dissatisfied with the KMA. Machine learning methods were used for sentiment analysis to automatically train the implied awareness on Twitter which mentioned the KMA July-October 2011-2014. The trained models were used to validate sentiments on Twitter 2015–2016, and the frequency of negative sentiments was compared with the satisfaction of forecast users. It was found that the frequency of the negative sentiments increased before satisfaction decreased sharply. And the tweet keywords and the news headlines were qualitatively compared to analyze the cause of negative sentiments. As a result, it was revealed that the individual caused the increase in the monthly negative sentiments increase in 2016. This study represents the value of sentiment analysis that can complement user satisfaction surveys. Also, combining Twitter and news headlines provided the idea of analyzing the causes of dissatisfaction that are difficult to identify with only satisfaction surveys. The results contribute to improving user satisfaction with weather services by efficiently managing changes in satisfaction.
Abstract
This study examined the overall relationship between information privacy concern, need for uniqueness (NFU), and disclosure behavior to explain the personal factors that drive data-sharing on Facebook. The results of an online survey conducted with 222 Facebook users show that among diverse data that social media users disclose online, four distinct factors are identified: basic personal data, private data, personal opinions, and personal photos. In general, there is a negative relationship between privacy concern and a positive relationship between the NFU and the willingness to self-disclose information. Overall, the NFU was a better predictor of willingness to disclose information than privacy concern, gender, or age. While privacy concern has been identified as an influential factor when users evaluate social networking sites, the findings of this study contribute to the literature by demonstrating that an individual’s need to manifest individualization on social media overrides privacy concerns.
Abstract
The purpose of this study was to investigate the key factors that influence consumers’ preference for mobile payment in China. China has been quietly experiencing a third technological revolution that has markedly changed the way of life for its people. We used the structural equation modeling with 573 Chinese people to investigate the mobile-payment system in China based on the technology acceptance model. We found that factors such as value of service, security, convenience, and perceived usefulness have an impact on consumer satisfaction, and that satisfaction supports consumer purchasing. Also, it is possible to conclude that this proven instrument will assist researchers to further develop and refine mobile-payment research models.
Abstract
This study examines the impact of online collaborative English language learning to enhance learner motivation and classroom engagement in university English instruction. The role of learner motivation and classroom engagement has gained much attention under the premises of current constructivist framework of English as a foreign language education. To promote learner motivation and classroom interaction in English instruction, participants in this study engaged in integrative English learning activities through online group collaboration and peer-tutoring. They exchanged productive peer response and shared their learning experiences throughout the integrative English learning activities. Digital technology played an integral role in motivating the learning process of the participants. Data for this study were gathered through an online questionnaire survey and semi-structured interviews. The data were analyzed based on the ARCS motivational model of instructional design to identify the motivational aspects of integrative English learning activities. This study reveals that participants of this study regarded online collaborative English learning activities as the positive and motivating learning experience. The online collaborative English reading instruction had positive effect on improving EFL university students’ learning performance. Participants of this study also identified affective and metacognitive benefits of online collaborative EFL learning activities for learner motivation and classroom engagement. This study reveals that the social networking platform in online group collaboration played a crucial role for the participants in understanding the integration of online group collaboration as the positive and effective language learning strategy. This study may have implications in suggesting the effective instructional design for promoting learner motivation and classroom interaction in EFL education.
Abstract
EMI (English as a Medium of Instruction) classes are now accepted policy at Korean universities, yet students often struggle with required academic English writings. The present study examined an EMI class that used direct instruction and access to online assistive English writing software. From preliminary analysis, 26 students expressed interest in how an EMI academic writing class could facilitate improved English writing skills. Study participants completed a survey on self-efficacy and learning needs and assignments for an EMI academic writing class. To establish inter-rater reliability, three trained raters assessed the written essays of students prior to and after instructional intervention. Fleiss’ Kappas statistics showed moderate reliability. Students’ opinions on the use of online software were also analysed. Paired t-test was run on the quality of students’ pre- and post-instruction assignments, and there was significant difference in the rated scores. Self-efficacy was found to have moderate positive association with improved post-essay writing scores.
Abstract
With the development of AI (artificial intelligence), animation digital publishing has been integrated with intellectualization. This paper adopts the theory of the global value chain, and analyzes the basic structure of the animation publishing value chain. Then focuses on the analysis of digital technology and artificial intelligence technology to play an active role in the topic selection and content customization of animation digital publishing products, optimization of publishing platforms, and user experience of publishing products. Finally, it proposes the use of artificial intelligence data analysis and deep learning technology. The purpose of this paper is to realize the upgrading of animation digital publishing, product upgrading, industrial chain upgrading, and identify some promotion methods for the value chain, such as copyright protection.
Abstract
It has been reported that large amounts of information on agri-foods were delivered to consumers through television and social networks, and the information may influence consumers’ behavior. The purpose of this paper was first to analyze relations of social network service and broadcasting program on paprika consumption in the aspect of amounts to purchase and identify potential factors that can promote paprika consumption; second, to develop prediction models of paprika consumption by using structured and unstructured big data. By using data 2010-2017, cross-correlation and time-series prediction algorithms (autoregressive exogenous model and vector error correction model), statistically significant correlations between paprika consumption and television programs/shows and blogs mentioning paprika and diet were identified with lagged times. When paprika and diet related data were added for prediction, these data improved the model predictability. This is the first report to predict paprika consumption by using structured and unstructured data.