• The Journal of Information Systems
• /
• v.25 no.4
• /
• pp.23-36
• /
• 2016

Purpose Recently, many researchers have paid much attention to the Artificial Intelligence fields of GVGP, PCG. The paper suggests that the improved MCTS algorithm to apply for the framework can generate better AI agent. Design/methodology/approach As noted, the MCTS generate magnificent performance without an advanced training and in turn, fit applying to the field of GVGP which does not need prior knowledge. The improved and modified MCTS shows that the survival rate is increased interestingly and the search can be done in a significant way. The study was done with 2 different sets. Findings The results showed that the 10 training set which was not given any prior knowledge and the other training set which played a role as validation set generated better performance than the existed MCTS algorithm. Besed upon the results, the further study was suggested.

• Korean Journal of Applied Biomechanics
• /
• v.32 no.3
• /
• pp.69-79
• /
• 2022

Objective: The purpose of this study is to analyze trends related to sports and artificial intelligence (AI) to understand the trends and how they change according to time, and to establish methods to apply AI in sports. Both macro and micro perspectives related to sports utilization of AI were analyzed. Method: In this study, after analyzing and discussing various information related to the use of artificial intelligence in the sports through a search of academic journals, papers, books, and websites published recently at nationally and internationally, the application plan of artificial intelligence in the sports field was presented. Results: 1) Motion analysis technology using artificial intelligence is effective in sports where posture is important, and if it provides systematic feedback and training methods, it can help improve performance. 2) The introduction of a sports referee judgment system using artificial intelligence is expected to improve performance by restoring factual judgment and objective fairness in sports games. 3) Artificial intelligence will provide coaching staff and players with a variety of information to help improve performance through systematic coaching and improving feedback and enhanced training methods. 4) It is judged that artificial intelligence-related to sports ethics, sports ICT, sports marketing, sports prediction, etc. We think that based on the current AI research trends will have a positive impact on all sports-related areas, helping to revitalize sports. Conclusion: Motion analysis technology using artificial intelligence, sports referee judgment system, coaching using artificial intelligence, and artificial intelligence are judged to have a positive effect on all sports-related areas and help revitalize sports.

• ETRI Journal
• /
• v.46 no.1
• /
• pp.48-58
• /
• 2024

This paper presents the development of language tutoring systems for nonnative speakers by leveraging advanced end-to-end automatic speech recognition (ASR) and proficiency evaluation. Given the frequent errors in non-native speech, high-performance spontaneous speech recognition must be applied. Our systems accurately evaluate pronunciation and speaking fluency and provide feedback on errors by relying on precise transcriptions. End-to-end ASR is implemented and enhanced by using diverse non-native speaker speech data for model training. For performance enhancement, we combine semisupervised and transfer learning techniques using labeled and unlabeled speech data. Automatic proficiency evaluation is performed by a model trained to maximize the statistical correlation between the fluency score manually determined by a human expert and a calculated fluency score. We developed an English tutoring system for Korean elementary students called EBS AI Peng-Talk and a Korean tutoring system for foreigners called KSI Korean AI Tutor. Both systems were deployed by South Korean government agencies.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.5
• /
• pp.697-706
• /
• 2023

This study examines the history of string quartet performances and analyzes contemporary integrated performances to propose a new performance paradigm for future audiences. It examines past developments and audience interactions, and how modern classical performance can gain a competitive edge internationally through tech integration. Building on this foundation, a future vision is proposed for Korean string quartet performances, drawing from novel performances that are interconnected with their historical context. The study concludes that modern string quartets necessitate innovative and original performance directions that can be achieved through various technological integrations.

• Journal of the Korean Society of Radiology
• /
• v.85 no.4
• /
• pp.705-713
• /
• 2024

This article discusses studies and real-world experiences related to the clinical application of artificial intelligence-based computer-aided detection (AI-CAD) software (LuCAS-plus, Monitor Corporation) in detecting pulmonary nodules. During clinical trials for lung cancer screening, AI-CAD exhibited performance comparable to that of medical professionals in terms of sensitivity and specificity. Studies revealed that applying AI-CAD for diagnosing pulmonary metastases led to high detection rates. The use of a nodule matching algorithm in diagnosing pulmonary metastases significantly reduced false non-metastasis results. In clinical settings, implementing AI-CAD enhanced the efficiency of pulmonary nodule detection, saving time and effort during CT reading. Overall, AI-CAD is expected to offer substantial support for lung cancer screening and the interpretation of chest CT scans for malignant tumor surveillance.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.692-695
• /
• 2024

With the recent advancements in artificial intelligence (AI), the performance of deep learning-based audio deepfake technology has significantly improved. This technology has been exploited for criminal activities, leading to various cases of victimization. To prevent such illicit outcomes, this paper proposes a deep learning-based audio deepfake detection model. In this study, we propose CoNSIST, an improved audio deepfake detection model, which incorporates three additional components into the graph-based end-to-end model AASIST: (i) Squeeze and Excitation, (ii) Positional Encoding, and (iii) Reformulated HS-GAL, This incorporation is expected to enable more effective feature extraction, elimination of unnecessary operations, and consideration of more diverse information, thereby improving the performance of the original AASIST. The results of multiple experiments indicate that CoNSIST has enhanced the performance of audio deepfake detection compared to existing models.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.5
• /
• pp.707-719
• /
• 2023

In the Fourth Industrial Revolution era, AI technologies, such as Chat GPT, have moved beyond assisting to actively analyzing data and providing solutions. This research assessed Chat GPT's e-service quality's influence on perceived value, innovativeness, and subsequent learning outcomes. Findings revealed that while ease of use and responsiveness weren't significant, safety and reliability were positively related to perceived value and innovativeness. A negative correlation was found between trustworthiness and perceived value. Users who saw Chat GPT as valuable and innovative experienced enhanced learning. The study emphasizes the need for guidelines in deploying Chat GPT academically. Given Chat GPT's recent introduction, further nuanced research is necessary.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.4
• /
• pp.57-64
• /
• 2024

The introduction of Smart Factories has transformed manufacturing towards more objective and efficient line management. However, most companies are not effectively utilizing the vast amount of sensor data collected every second. This study aims to use this data to predict product quality and manage production processes efficiently. Due to security issues, specific sensor data could not be verified, so semiconductor process-related training data from the "SAMSUNG SDS Brightics AI" site was used. Data preprocessing, including removing missing values, outliers, scaling, and feature elimination, was crucial for optimal sensor data. Oversampling was used to balance the imbalanced training dataset. The SVM (rbf) model achieved high performance (Accuracy: 97.07%, GM: 96.61%), surpassing the MLP model implemented by "SAMSUNG SDS Brightics AI". This research can be applied to various topics, such as predicting component lifecycles and process conditions.

• Korean Journal of Weed Science
• /
• v.18 no.2
• /
• pp.106-115
• /
• 1998

This study was conducted to investigate the effect of oxadiazon, molinate, thiobencarb before seeding on control of red rice and barnyardgrass in water-seeded rice. High application rate plot among oxadiazon treatment plots could observe phytotoxicity symptoms depending on field conditions, but these injury recovered gradually with time. Molinate and thiobencarb application plots at the concentration of 225~400, 210~420g ai/l0a respectively were not observed phytotoxicity. Control of red rice was different according to kinds of herbicides and application rates. Oxadiazon showed higher control performance at the concentration of more than 60g ai/10a. Control effect of molinate and thiobencarb against red rice was enhanced with the increase of application rate, and both herbicides showed satisfactory effect at more than 300g ai/10a. Control of barnyardgrass showed up to 90~100% in all tested herbicides. There was no significant yield reduction by oxadiazon, molinate, and thiobencarb application before seeding in all tested field. In the pot experiment, crop injury, seedling stand, and early growth were more advantageous at time of drainge after one day after seeding than flooding until rooting.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.171-187
• /
• 2023

When a person's face is recognized through a recording device such as a low-pixel surveillance camera, it is difficult to capture the face due to low image quality. In situations where it is difficult to recognize a person's face, problems such as not being able to identify a criminal suspect or a missing person may occur. Existing studies on face recognition used refined datasets, so the performance could not be measured in various environments. Therefore, to solve the problem of poor face recognition performance in low-quality images, this paper proposes a method to generate high-quality images by performing image quality improvement on low-quality facial images considering various environments, and then improve the performance of facial feature point detection. To confirm the practical applicability of the proposed architecture, an experiment was conducted by selecting a data set in which people appear relatively small in the entire image. In addition, by choosing a facial image dataset considering the mask-wearing situation, the possibility of expanding to real problems was explored. As a result of measuring the performance of the feature point detection model by improving the image quality of the face image, it was confirmed that the face detection after improvement was enhanced by an average of 3.47 times in the case of images without a mask and 9.92 times in the case of wearing a mask. It was confirmed that the RMSE for facial feature points decreased by an average of 8.49 times when wearing a mask and by an average of 2.02 times when not wearing a mask. Therefore, it was possible to verify the applicability of the proposed method by increasing the recognition rate for facial images captured in low quality through image quality improvement.