• The Journal of the Convergence on Culture Technology
• /
• v.8 no.5
• /
• pp.735-740
• /
• 2022

The construction is the industry with the highest fatalities, and the fatalities has not decreased despite various institutional improvements. Accordingly, real-time safety management by applying artificial intelligence (AI) to CCTV images is emerging. Although some research on worker detection by applying AI to images of construction sites is being conducted, there are limitations in performance expression due to problems such as complex background due to the nature of the construction industry. In this study, the YOLO model and the OpenPose model were fused to improve the performance of worker detection and posture estimation to improve the detection performance of workers in various complex conditions. This is expected to be highly useful in terms of unsafe behavior and health management of workers in the future.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.4
• /
• pp.210-219
• /
• 2023

The decline in the rural populace and an aging workforce have led to fatalities due to worsening environments and hazards within vinyl greenhouses. Therefore, it is necessary to automate crop cultivation and disease detection system in greenhouses to prevent labor loss. In this paper, an object detection-based model is used to detect diseased crop in greenhouses. In addition, the system proposed configures the environment of the artificial intelligence model in the cloud to ensure stability. The system captures images taken inside the vinyl greenhouse and stores them in a database, and then downloads the images to the cloud to perform inference based on Yolo-v4 for detection, generating JSON files for the results. Analyze this file and send it to the database for storage. From the experimental results, it was confirmed that disease detection through object detection showed high performance in real environments like vinyl greenhouses. It was also verified that efficient monitoring is possible through the database

• The Journal of the Korea Contents Association
• /
• v.22 no.5
• /
• pp.491-502
• /
• 2022

Voice technology allows consumers to make purchases through smart devices, and the interest in voice-driven conversational commerce has significantly expanded. In this study, we explored the continuance use intention of voice commerce, and the adoption of a value-attitude-behavior model. An online survey was conducted on 360 individuals who used an artificial intelligence assistant device in a voice commerce environment. We used Amos 23.0 and SPSS 25.0 for descriptive, confirmatory, and structural equation modeling analyses. These results indicated that functional value was the highest influencing variable on satisfaction of voice commerce, while social, emotional, and epistemic values significantly influenced it as well. Additionally, satisfaction of voice commerce significantly influenced the continuance use intention of voice commerce. These findings could help us understand the characteristics of voice commerce users and the diversity value in voice commerce environment.

• Journal of the Korean Institute of Gas
• /
• v.27 no.2
• /
• pp.49-56
• /
• 2023

As AI (Artificial Intelligence)-related technologies are highly developed due to the 4th industrial revolution, cases of applying AI in various fields are increasing. The main reason is that there are practical limits to direct processing and analysis of exponentially increasing data as information and communication technology develops, and the risk of human error can be reduced by applying new technologies. In this study, after collecting the data received from the 'remote potential measurement terminal (T/B, Test Box)' and the output of the 'remote rectifier' at that time, AI was trained. AI learning data was obtained through data augmentation through regression analysis of the initially collected data, and the learning model applied the value-based Q-Learning model among deep reinforcement learning (DRL) algorithms. did The AI that has completed data learning is put into the actual city gas supply area, and based on the received remote T/B data, it is verified that the AI responds appropriately, and through this, AI can be used as a suitable means for electricity management in the future. want to verify.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.277-280
• /
• 2021

Recently as various contents are mass produced based on high accessibility, the media contents market is more active. Users want to find content that suits their taste, and each platform is competing for personalized recommendations for content. For an efficient recommendation system, high-quality metadata is required. Existing platforms take a method in which the user directly inputs the metadata of an image. This will waste time and money processing large amounts of data. In this paper, for media hyperpersonalization recommendation, keyframes are extracted based on the YCrCb color model of the video based on movie trailers, movie genres are distinguished through supervised learning of artificial intelligence and In the future, we would like to propose a utilization plan for generating metadata.

• The Journal of Bigdata
• /
• v.7 no.1
• /
• pp.49-61
• /
• 2022

In sports, the proportion of data analysis in team management such as team strategy planning and marketing is increasing. In KBO(Korea Baseball Organization) league, in particular, plans such as recruiting players and fostering players are established to devise team strategies for the next year, such as FA and trade, at the end of a season. For these reasons, it is very important to predict players' performance for the next year. In this study, the target was limited to only the batter and tried to find out how to predict whether the performance of the next year will improve. As a standard record for rising and falling, OPS(On-Base Plus Slugging), which is easy to calculate and has a high relationship with team score, was used. In this study, 40 years of regular season data from 1982 to 2021 were used as data, and 11 machine learning classification models were used as experimental methods. Predicting the rise and fall of OPS, RBF SVM, Neural Net, Gaussian Process, and AdaBoost were more accurate than other classification models, and age did not significantly affect accuracy.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.3
• /
• pp.571-580
• /
• 2022

Marine deposited waste is a major cause of problems such as a lot of damage and an increase in the estimated amount of garbage due to abandoned fishing grounds caused by ghost fishing. In this paper, we implement a real-time marine deposited waste detection artificial intelligence system to understand the actual conditions of waste fishing gear usage, distribution, loss, and recovery, and study methods for performance improvement. The system was implemented using the yolov5 model, which is an excellent performance model for real-time object detection, and the 'data screening process' and 'class segmentation' method of learning data were applied as performance improvement methods. In conclusion, the object detection results of datasets that do screen unnecessary data or do not subdivide similar items according to characteristics and uses are better than the object recognition results of unscreened datasets and datasets in which classes are subdivided.

• Smart Media Journal
• /
• v.11 no.7
• /
• pp.61-69
• /
• 2022

In the learned machine learning, the performance of machine learning degrades at the same time as drift occurs in terms of learning models and learning data over time. As a solution to this problem, I would like to propose the concept and evaluation method of ML drift to determine the re-learning period of machine learning. An XAI test and an XAI test of an apple image were performed according to strawberry and clarity. In the case of strawberries, the change in the XAI analysis of ML models according to the clarity value was insignificant, and in the case of XAI of apple image, apples normally classified objects and heat map areas, but in the case of apple flowers and buds, the results were insignificant compared to strawberries and apples. This is expected to be caused by the lack of learning images of apple flowers and buds, and more apple flowers and buds will be studied and tested in the future.

• The Journal of the Korea Contents Association
• /
• v.22 no.8
• /
• pp.33-43
• /
• 2022

Labeled graphs are used to represent entities, their relationships, and their structures in real data such as knowledge graphs and protein interactions. With the rapid development of IT and the explosive increase in data, there has been a need for a subgraph matching technology to provide information that the user is interested in. In this paper, we propose an approximate Top-k labeled subgraph matching scheme that considers the semantic similarity of labels and the difference in graph structure. The proposed scheme utilizes a learning model using FastText in order to consider the semantic similarity of a label. In addition, the label similarity graph(LSG) is used for approximate subgraph matching by calculating similarity values between labels in advance. Through the LSG, we can resolve the limitations of the existing schemes that subgraph expansion is possible only if the labels match exactly. It supports structural similarity for a query graph by performing searches up to 2-hop. Based on the similarity value, we provide k subgraph matching results. We conduct various performance evaluations in order to show the superiority of the proposed scheme.

• Journal of IKEEE
• /
• v.27 no.4
• /
• pp.518-523
• /
• 2023

The diagnosis of Inter Turn Short Circuits (ITSC) in induction motors is critical due to the escalating severity of faults resulting from even minor disruptions in the stator windings. However, diagnosing ITSC presents significant challenges due to similarities in noise and losses shared with 3-phase induction motors. Although artificial intelligence techniques have been explored for efficient diagnosis, practical applications heavily rely on model-based methods, necessitating further research to enhance diagnostic performance. This study proposed a diagnostic method applied the Clarke Transformation approach, focusing solely on current components while disregarding changes in rotating flux. Experimental results conducted over a 30-minute period, encompassing both normal and ITSC conditions, demonstrate the effectiveness of the proposed approach, with FAR(False Accept Rates) of 0.2% for normal-to-ITSC FRR(False Rejection Rates) and 0.26% for ITSC-to-normal FRR. These findings underscore the efficacy of the proposed approach.