• Journal of Broadcast Engineering
• /
• v.27 no.1
• /
• pp.44-55
• /
• 2022

In order to automatically provide information on fruits in agricultural related broadcasting contents, instance image segmentation of target fruits is required. In addition, the information on the 3D pose of the corresponding fruit may be meaningfully used. This paper represents research that provides information about tomatoes in video content. A large amount of data is required to learn the instance segmentation, but it is difficult to obtain sufficient training data. Therefore, the training data is generated through a data augmentation technique based on a small amount of real images. Compared to the result using only the real images, it is shown that the detection performance is improved as a result of learning through the synthesized image created by separating the foreground and background. As a result of learning augmented images using images created using conventional image pre-processing techniques, it was shown that higher performance was obtained than synthetic images in which foreground and background were separated. To estimate the pose from the result of object detection, a point cloud was obtained using an RGB-D camera. Then, cylinder fitting based on least square minimization is performed, and the tomato pose is estimated through the axial direction of the cylinder. We show that the results of detection, instance image segmentation, and cylinder fitting of a target object effectively through various experiments.

• Journal of the Korean Society for information Management
• /
• v.40 no.2
• /
• pp.183-209
• /
• 2023

The purpose of this study is to evaluate the Dublin Core metadata generated by ChatGPT using book covers, title pages, and colophons from a collection of books. To achieve this, we collected book covers, title pages, and colophons from 90 books and inputted them into ChatGPT to generate Dublin Core metadata. The performance was evaluated in terms of completeness and accuracy. The overall results showed a satisfactory level of completeness at 0.87 and accuracy at 0.71. Among the individual elements, Title, Creator, Publisher, Date, Identifier, Rights, and Language exhibited higher performance. Subject and Description elements showed relatively lower performance in terms of completeness and accuracy, but it confirmed the generation capability known as the inherent strength of ChatGPT. On the other hand, books in the sections of social sciences and technology of DDC showed slightly lower accuracy in the Contributor element. This was attributed to ChatGPT's attribution extraction errors, omissions in the original bibliographic description contents for metadata, and the language composition of the training data used by ChatGPT.

• Journal of Cadastre & Land InformatiX
• /
• v.53 no.1
• /
• pp.47-63
• /
• 2023

The Seoul Metropolitan Government is building and operating digital twin-based urban spatial information to solve various problems in the city and provide public services. Two essential factors to ensure the stable utilization of spatial information for the implementation of such a digital twin city are the latest and quality of the data. However, it is time-consuming and costly to maintain continuous updating of high-quality urban spatial information. To overcome this problem, we studied efficient urban spatial information construction technology and the operation, management, and update procedures of construction data. First, we demonstrated and applied automatic 3D building construction technology centered on point clouds using the latest hybrid sensors, confirmed that it is possible to automatically construct high-quality building models using high-density airborne lidar results, and established an efficient data management plan. By applying differentiated production methods by region, supporting detection of urban change areas through Seoul spatial feature identifiers, and producing international standard data by level, we strengthened the utilization of urban spatial information. We believe that this study can serve as a good precedent for local governments and related organizations that are considering activating urban spatial information based on digital twins, and we expect that discussions on the construction and management of spatial information as infrastructure information for city-level digital twin implementation will continue.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.3
• /
• pp.731-736
• /
• 2023

Recently, the medical field has been applying mandatory Electronic Medical Records (EMRs) and Electronic Health Records (EHRs) systems that computerize and manage medical records, and distributing them throughout the entire medical industry to utilize patients' past medical records for additional medical procedures. However, the conversations between medical professionals and patients that occur during general medical consultations and counseling sessions are not separately recorded or stored, so additional important patient information cannot be efficiently utilized. Therefore, we propose an electronic medical record system that uses speech recognition and natural language processing deep learning to store conversations between medical professionals and patients in text form, automatically extracts and summarizes important medical consultation information, and generates electronic medical records. The system acquires text information through the recognition process of medical professionals and patients' medical consultation content. The acquired text is then divided into multiple sentences, and the importance of multiple keywords included in the generated sentences is calculated. Based on the calculated importance, the system ranks multiple sentences and summarizes them to create the final electronic medical record data. The proposed system's performance is verified to be excellent through quantitative analysis.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.4
• /
• pp.21-29
• /
• 2023

In this paper, we propose an AI-based system for automatically classifying industry and occupation codes in the population census. The accurate classification of industry and occupation codes is crucial for informing policy decisions, allocating resources, and conducting research. However, this task has traditionally been performed by human coders, which is time-consuming, resource-intensive, and prone to errors. Our system represents a significant improvement over the existing rule-based system used by the statistics agency, which relies on user-entered data for code classification. In this paper, we trained and evaluated several models, and developed an ensemble model that achieved an 86.76% match accuracy in industry and 81.84% in occupation, outperforming the best individual model. Additionally, we propose process improvement work based on the classification probability results of the model. Our proposed method utilizes an ensemble model that combines transfer learning techniques with pre-trained models. In this paper, we demonstrate the potential for AI-based systems to improve the accuracy and efficiency of population census data classification. By automating this process with AI, we can achieve more accurate and consistent results while reducing the workload on agency staff.

• The Journal of Society for e-Business Studies
• /
• v.27 no.2
• /
• pp.205-218
• /
• 2022

Recently, digital transformation in manufacturing has been accelerating. It results in that the data collection technologies from the shop-floor is becoming important. These approaches focus primarily on obtaining specific manufacturing data using various sensors and communication technologies. In order to expand the channel of field data collection, this study proposes a method to automatically collect manufacturing data based on vision-based artificial intelligence. This is to analyze real-time image information with the object detection and tracking technologies and to obtain manufacturing data. The research team collects object motion information for each frame by applying YOLO (You Only Look Once) and DeepSORT as object detection and tracking algorithms. Thereafter, the motion information is converted into two pieces of manufacturing data (production performance and time) through post-processing. A dynamically moving factory model is created to obtain training data for deep learning. In addition, operating scenarios are proposed to reproduce the shop-floor situation in the real world. The operating scenario assumes a flow-shop consisting of six facilities. As a result of collecting manufacturing data according to the operating scenarios, the accuracy was 96.3%.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.7
• /
• pp.295-302
• /
• 2023

Software requirements written in natural language may have different meanings from the stakeholders' viewpoint. When designing an architecture based on quality attributes, it is necessary to accurately classify quality attribute requirements because the efficient design is possible only when appropriate architectural tactics for each quality attribute are selected. As a result, although many natural language processing models have been studied for the classification of requirements, which is a high-cost task, few topics improve classification performance with the imbalanced quality attribute datasets. In this study, we first show that the classification model can automatically classify the Korean requirement dataset through experiments. Based on these results, we explain that data augmentation through EDA(Easy Data Augmentation) techniques and undersampling strategies can improve the imbalance of quality attribute datasets, and show that they are effective in classifying requirements. The results improved by 5.24%p on F1-score, indicating that handling imbalanced data helps classify Korean requirements of classification models. Furthermore, detailed experiments of EDA illustrate operations that help improve classification performance.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.6
• /
• pp.719-729
• /
• 2017

Recently, the field of agriculture has been gaining a new leap with the integration of ICT technology in agriculture. In particular, smart farms, which incorporate the Internet of Things (IoT) technology in agriculture, are in the spotlight. Smart farm technology collects and analyzes information such as temperature and humidity of the environment where crops are cultivated in real time using sensors to automatically control the devices necessary for harvesting crops in the control device, Environment. Although smart farm technology is paying attention as if it can solve everything, most of the research focuses only on increasing crop yields. This paper focuses on the development of a system architecture that can harvest high quality crops at the optimum stage rather than increase crop yields. In this paper, we have developed an architecture using apple trees as a sample and used the color information and weight information to predict the harvest time of apple trees. The simple board that collects color information and weight information and transmits it to the server side uses Arduino and adopts model-driven development (MDD) as development methodology. We have developed an architecture to provide services to PC users in the form of Web and to provide Smart Phone users with services in the form of hybrid apps. We also developed an architecture that uses beacon technology to provide orchestration information to users in real time.

• Korean Journal of Culture and Social Issue
• /
• v.24 no.1
• /
• pp.29-47
• /
• 2018

Do social situations have an impact on an individual's information processing and emotional experiences? Two studies were conducted to investigate relationships between self-reference effects, emotional experiences and social information processing. Study 1 examined whether biases favoring self-related stimuli could occur automatically. Participants had to judge whether sequential geometric shape-label pairs matched or mismatched. The results showed that self-related stimuli are more rapidly processed than friends/others-related stimuli. In Study 2, the participants had to recall items which were presented with different instructions (either chosen by a friend or by the computer). Here we explored whether the self-reference effect is reduced in a social learning condition. When comparing the social learning condition (seated in pairs) with the nonsocial learning condition (seated alone), the participants recalled more self-related words in the nonsocial learning condition than in the social learning condition. Importantly, the automatic self-reference effect disappeared in the social learning condition. More friends-related words were recalled in the social condition than self-related words. In addition, while tasting chocolates, the participants judged them to be more likeable in the social condition than in the nonsocial condition. These results implicated that social processing can be useful for reducing the automatic self-reference effects and shared experiences are perceived more intensely than unshared experiences.

• Journal of IKEEE
• /
• v.27 no.4
• /
• pp.486-493
• /
• 2023

In this paper, we propose an automatic hand gesture area extraction and recognition technique using FMCW radar-based point cloud and LSTM. The proposed technique has the following originality compared to existing methods. First, unlike methods that use 2D images as input vectors such as existing range-dopplers, point cloud input vectors in the form of time series are intuitive input data that can recognize movement over time that occurs in front of the radar in the form of a coordinate system. Second, because the size of the input vector is small, the deep learning model used for recognition can also be designed lightly. The implementation process of the proposed technique is as follows. Using the distance, speed, and angle information measured by the FMCW radar, a point cloud containing x, y, z coordinate format and Doppler velocity information is utilized. For the gesture area, the hand gesture area is automatically extracted by identifying the start and end points of the gesture using the Doppler point obtained through speed information. The point cloud in the form of a time series corresponding to the viewpoint of the extracted gesture area is ultimately used for learning and recognition of the LSTM deep learning model used in this paper. To evaluate the objective reliability of the proposed technique, an experiment calculating MAE with other deep learning models and an experiment calculating recognition rate with existing techniques were performed and compared. As a result of the experiment, the MAE value of the time series point cloud input vector + LSTM deep learning model was calculated to be 0.262 and the recognition rate was 97.5%. The lower the MAE and the higher the recognition rate, the better the results, proving the efficiency of the technique proposed in this paper.