Kwangyon Lee

Dr. Kwangyon Lee

Yonsei University
orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 September 2023 in Applied Sciences
Verified
Journal Article
Open access
PDF file
HJHaemin Jung
Haemin Jung
HPHeesung Park
Heesung Park
KLKwangyon Lee
Kwangyon Lee
Recommender systems play a crucial role in personalizing online user experiences by creating user profiles based on user–item interactions and preferences. Knowledge graphs (KGs) are intricate data structures that encapsulate semantic information, expressing users and items in a meaningful way. Although recent deep learning-based recommendation algorithms that embed KGs have demonstrated impressive performance, the richness of semantics and explainability embedded in the KGs are often lost due to the opaque nature of vector representations in deep neural networks. To address this issue, we propose a novel user profiling method for recommender systems that can encapsulate user preferences while preserving the original semantics of the KGs, using frequent subgraph mining. Our approach involves creating user profile vectors from a set of frequent subgraphs that contain information about user preferences and the strength of those preferences, measured by frequency. Subsequently, we trained a deep neural network model to learn the relationship between users and items, thereby facilitating effective recommendations using the neural network’s approximation ability. We evaluated our user profiling methodology on movie data and found that it demonstrated competitive performance, indicating that our approach can accurately represent user preferences while maintaining the semantics of the KGs. This work, therefore, presents a significant step towards creating more transparent and effective recommender systems that can be beneficial for a wide range of applications and readers interested in this field.

20 January 2021 in Applied Sciences
Verified
Journal Article
Open access
PDF file
KLKwangyon Lee
Kwangyon Lee
HJHaemin Jung
Haemin Jung
JHJune Hong
June Hong
WKWooju Kim
Wooju Kim
In many areas, vast amounts of information are rapidly accumulating in the form of ontology-based knowledge graphs, and the use of information in these forms of knowledge graphs is becoming increasingly important. This study proposes a novel method for efficiently learning frequent subgraphs (i.e., knowledge) from ontology-based graph data. An ontology-based large-scale graph is decomposed into small unit subgraphs, which are used as the unit to calculate the frequency of the subgraph. The frequent subgraphs are extracted through candidate generation and chunking processes. To verify the usefulness of the extracted frequent subgraphs, the methodology was applied to movie rating prediction. Using the frequent subgraphs as user profiles, the graph similarity between the rating graph and new item graph was calculated to predict the rating. The MovieLens dataset was used for the experiment, and a comparison showed that the proposed method outperformed other widely used recommendation methods. This study is meaningful in that it proposed an efficient method for extracting frequent subgraphs while maintaining semantic information and considering scalability in large-scale graphs. Furthermore, the proposed method can provide results that include semantic information to serve as a logical basis for rating prediction or recommendation, which existing methods are unable to provide.

1 January 2024 in Computers, Materials & Continua
Verified
Journal Article
Open access
HJHaemin Jung
Haemin Jung
HPHeesung Park
Heesung Park
HJHae Sun Jung
Hae Sun Jung
KLKwangyon Lee
Kwangyon Lee
The growing demand for energy-efficient solutions has led to increased interest in analyzing building facades, as buildings contribute significantly to energy consumption in urban environments. However, conventional image segmentation methods often struggle to capture fine details such as edges and contours, limiting their effectiveness in identifying areas prone to energy loss. To address this challenge, we propose a novel segmentation methodology that combines object-wise processing with a two-stage deep learning model, Cascade U-Net. Object-wise processing isolates components of the facade, such as walls and windows, for independent analysis, while Cascade U-Net incorporates contour information to enhance segmentation accuracy. The methodology involves four steps: object isolation, which crops and adjusts the image based on bounding boxes; contour extraction, which derives contours; image segmentation, which modifies and reuses contours as guide data in Cascade U-Net to segment areas; and segmentation synthesis, which integrates the results obtained for each object to produce the final segmentation map. Applied to a dataset of Korean building images, the proposed method significantly outperformed traditional models, demonstrating improved accuracy and the ability to preserve critical structural details. Furthermore, we applied this approach to classify window thermal loss in real-world scenarios using infrared images, showing its potential to identify windows vulnerable to energy loss. Notably, our Cascade U-Net, which builds upon the relatively lightweight U-Net architecture, also exhibited strong performance, reinforcing the practical value of this method. Our approach offers a practical solution for enhancing energy efficiency in buildings by providing more precise segmentation results.