• Journal of the Korea Society of Computer and Information
• /
• v.27 no.5
• /
• pp.37-45
• /
• 2022

As of 2020, about 500 hours of videos are uploaded to YouTube, a representative online video platform, per minute. As the number of users acquiring information through various uploaded videos is increasing, online video platforms are making efforts to provide better recommendation services. The currently used recommendation service recommends videos to users based on the user's viewing history, which is not a good way to recommend videos that deal with specific purposes and interests, such as educational videos. The recent recommendation system utilizes not only the user's viewing history but also the content features of the item. In this paper, we extract the content features of educational video for educational video recommendation based on YouTube, design a recommendation system using it, and implement it as a web application. By examining the satisfaction of users, recommendataion performance and convenience performance are shown as 85.36% and 87.80%.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.27 no.1
• /
• pp.27-33
• /
• 2023

Demands for eco-friendly food materials are increasing rapidly because of increased interest in well-being and health care, deterioration of air quality due to fine dust, and various soil and water pollution. Aquaponics is a system that can solve various problems such as economic activities, environmental problems, and safe food provision of the elderly population. However, techniques for deriving the optimal growth environment should be preceded. In this paper, we intend to design an intelligent plant growth measurement system that considers the characteristics of existing aquaponics. In particular, we would like to propose a module configuration plan for learning data and judgment systems when providing a uniform growth environment, focusing on designing systems suitable for production sites that do not have high-performance processing resources among intelligent aquaponics production management modules. It is believed that the proposed system can effectively perform deep learning with small analysis resources.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.1
• /
• pp.65-74
• /
• 2024

In recent years, image processing technology has played a critical role in the field of autonomous driving. Among them, image recognition technology is essential for the safety and performance of autonomous vehicles. Therefore, this paper aims to develop a hybrid image recognition system to enhance the safety and performance of autonomous vehicles. In this paper, various image recognition technologies are utilized to construct a system that recognizes and tracks objects in the vehicle's surroundings. Machine learning and deep learning algorithms are employed for this purpose, and objects are identified and classified in real-time through image processing and analysis. Furthermore, this study aims to fuse image processing technology with vehicle control systems to improve the safety and performance of autonomous vehicles. To achieve this, the identified object's information is transmitted to the vehicle control system to enable appropriate autonomous driving responses. The developed hybrid image recognition system in this paper is expected to significantly improve the safety and performance of autonomous vehicles. This is expected to accelerate the commercialization of autonomous vehicles.

• Journal of the Korea Safety Management & Science
• /
• v.25 no.3
• /
• pp.17-22
• /
• 2023

As the importance of artificial intelligence grows rapidly and emerges as a leader in technology, it is becoming an important variable in the next-generation industrial system along with the robot industry. In this study, a safety system was developed using deep learning technology to provide worker safety in a robot workplace environment. The implemented safety system has multiple cameras installed with various viewing directions to avoid blind spots caused by interference. Workers in various scenario situations were detected, and appropriate robot response scenarios were implemented according to the worker's risk level through IO communication. For human detection, the YOLO algorithm, which is widely used in object detection, was used, and a separate robot class was added and learned to compensate for the problem of misrecognizing the robot as a human. The performance of the implemented system was evaluated by operator detection performance by applying various operator scenarios, and it was confirmed that the safety system operated stably.

• Physical Therapy Rehabilitation Science
• /
• v.13 no.1
• /
• pp.106-112
• /
• 2024

Objective: This study aimed to evaluate the validity of a depth camera-based system for monitoring physical function, assessing its feasibility for accurately monitoring activities of daily living. Design: A cross-sectional study. Methods: Twenty-three participants were enlisted to perform fifteen activities of daily living within a living laboratory designed to simulate a home environment. Activities were monitored using a depth camera system capable of classifying actions into standing, sitting, and lying down, with a conventional video camera employed for activity recording. The duration of each activity, as measured by the system, was compared to direct observations made by a physical therapist which were analyzed using a motion analysis software. The association between these two measurement approaches was assessed through correlation analysis, coefficient of determination, intraclass correlation coefficient (ICC), and Bland-Altman plots. Results: Our findings indicated that standing activities exhibited the highest correlation (r=0.847) between the system measurements and physical therapist observations, followed by sitting (r=0.817) and lying down (r=0.734), which demonstrated lower correlations. However, the ICC and Bland-Altman plots revealed notable variances between the two measurement methods, particularly for activities involving lying down. Conclusions: In this study, the depth camera-based physical monitoring system showed promise feasibility in distinguishing standing, sitting, and lying down activities at home environments. However, the current study also underlined some necessities of enhancements in capturing lying down activities.

• International journal of advanced smart convergence
• /
• v.13 no.3
• /
• pp.101-108
• /
• 2024

This paper addresses the implementation of an on-device AI-based metal detection system using a Magneto-Impedance Sensor. Performing calculations on the AI device itself is essential, especially for unmanned aerial vehicles such as drones, where communication capabilities may be limited. Consequently, a system capable of analyzing data directly on the device is required. We propose a lightweight gated recurrent unit (GRU) model that can be operated on a drone. Additionally, we have implemented a real-time detection system on a CPU embedded system. The signals obtained from the Magneto-Impedance Sensor are processed in real-time by a Raspberry Pi 4 Model B. During the experiment, the drone flew freely at an altitude ranging from 1 to 10 meters in an open area where metal objects were placed. A total of 20,000,000 sequences of experimental data were acquired, with the data split into training, validation, and test sets in an 8:1:1 ratio. The results of the experiment demonstrated an accuracy of 94.5% and an inference time of 9.8 milliseconds. This study indicates that the proposed system is potentially applicable to unmanned metal detection drones.

• Phonetics and Speech Sciences
• /
• v.15 no.3
• /
• pp.75-82
• /
• 2023

Automatic speech recognition (ASR) has been revolutionized with deep learning-based approaches, among which self-supervised learning methods have proven to be particularly effective. In this study, we aim to enhance the performance of OpenAI's Whisper model, a multilingual ASR system on the Korean language. Whisper was pretrained on a large corpus (around 680,000 hours) of web speech data and has demonstrated strong recognition performance for major languages. However, it faces challenges in recognizing languages such as Korean, which is not major language while training. We address this issue by fine-tuning the Whisper model with an additional dataset comprising about 1,000 hours of Korean speech. We also compare its performance against a Transformer model that was trained from scratch using the same dataset. Our results indicate that fine-tuning the Whisper model significantly improved its Korean speech recognition capabilities in terms of character error rate (CER). Specifically, the performance improved with increasing model size. However, the Whisper model's performance on English deteriorated post fine-tuning, emphasizing the need for further research to develop robust multilingual models. Our study demonstrates the potential of utilizing a fine-tuned Whisper model for Korean ASR applications. Future work will focus on multilingual recognition and optimization for real-time inference.

• Journal of the Korea Society for Simulation
• /
• v.32 no.4
• /
• pp.19-26
• /
• 2023

The increase in the dropout rate of college students nationwide has a serious negative impact on universities and society as well as individual students. In order to proactive identify students at risk of dropout, this study built a decision tree, random forest, logistic regression, and deep learning-based dropout prediction model using academic data that can be easily obtained from each university's academic management system. Their performances were subsequently analyzed and compared. The analysis revealed that while the logistic regression-based prediction model exhibited the highest recall rate, its f-1 value and ROC-AUC (Receiver Operating Characteristic - Area Under the Curve) value were comparatively lower. On the other hand, the random forest-based prediction model demonstrated superior performance across all other metrics except recall value. In addition, in order to assess model performance over distinct prediction periods, we divided these periods into short-term (within one semester), medium-term (within two semesters), and long-term (within three semesters). The results underscored that the long-term prediction yielded the highest predictive efficacy. Through this study, each university is expected to be able to identify students who are expected to be dropped out early, reduce the dropout rate through intensive management, and further contribute to the stabilization of university finances.

• Journal of Intelligence and Information Systems
• /
• v.27 no.1
• /
• pp.103-128
• /
• 2021

Recently, investors' interest and the influence of stock-related information dissemination are being considered as significant factors that explain stock returns and volume. Besides, companies that develop, distribute, or utilize innovative new technologies such as artificial intelligence have a problem that it is difficult to accurately predict a company's future stock returns and volatility due to macro-environment and market uncertainty. Market uncertainty is recognized as an obstacle to the activation and spread of artificial intelligence technology, so research is needed to mitigate this. Hence, the purpose of this study is to propose a machine learning model that predicts the volatility of a company's stock price by using the internet search volume of artificial intelligence-related technology keywords as a measure of the interest of investors. To this end, for predicting the stock market, we using the VAR(Vector Auto Regression) and deep neural network LSTM (Long Short-Term Memory). And the stock price prediction performance using keyword search volume is compared according to the technology's social acceptance stage. In addition, we also conduct the analysis of sub-technology of artificial intelligence technology to examine the change in the search volume of detailed technology keywords according to the technology acceptance stage and the effect of interest in specific technology on the stock market forecast. To this end, in this study, the words artificial intelligence, deep learning, machine learning were selected as keywords. Next, we investigated how many keywords each week appeared in online documents for five years from January 1, 2015, to December 31, 2019. The stock price and transaction volume data of KOSDAQ listed companies were also collected and used for analysis. As a result, we found that the keyword search volume for artificial intelligence technology increased as the social acceptance of artificial intelligence technology increased. In particular, starting from AlphaGo Shock, the keyword search volume for artificial intelligence itself and detailed technologies such as machine learning and deep learning appeared to increase. Also, the keyword search volume for artificial intelligence technology increases as the social acceptance stage progresses. It showed high accuracy, and it was confirmed that the acceptance stages showing the best prediction performance were different for each keyword. As a result of stock price prediction based on keyword search volume for each social acceptance stage of artificial intelligence technologies classified in this study, the awareness stage's prediction accuracy was found to be the highest. The prediction accuracy was different according to the keywords used in the stock price prediction model for each social acceptance stage. Therefore, when constructing a stock price prediction model using technology keywords, it is necessary to consider social acceptance of the technology and sub-technology classification. The results of this study provide the following implications. First, to predict the return on investment for companies based on innovative technology, it is most important to capture the recognition stage in which public interest rapidly increases in social acceptance of the technology. Second, the change in keyword search volume and the accuracy of the prediction model varies according to the social acceptance of technology should be considered in developing a Decision Support System for investment such as the big data-based Robo-advisor recently introduced by the financial sector.

• Smart Media Journal
• /
• v.9 no.1
• /
• pp.38-44
• /
• 2020

Due to the high dependence on electric energy, electric fires make up a significant portion of fires in Korea. Electric arcs by short circuits or poor contact cause three of four electrical fires. An electric arc is a discharge phenomenon of electrical current between the insulators, which instantaneously produces high temperature. In order to reduce the fire due to electric arc, this study aims to predict the electric arc risk. We collected arc data from the arc detectors and converted into graphs based on temporal arc data. We used machine learning for training converted graph with different number of temporal arc data. To measure the performance of the learning model, we use the test data. In the results, when the number of temporal arc data was 20, the prediction rate was high as 86%.