Vol. 51, No. 2,
Feb. 2024
Digital Library
An Efficient Algorithm for Diversified Top-k Subgraph Querying
http://doi.org/10.5626/JOK.2024.51.2.103
Subgraph matching is a core and important problem in graph analysis. The subgraph matching problem is to find all embeddings of the query graph in the data graph. However, the output results from previously proposed algorithms often overlap with each other, and thus interesting results are often missed. For this purpose, the diversified top-k subgraph querying problem is proposed. The diversified top-k subgraph querying problem is to find k embeddings that have the highest coverage among embeddings of the query graph in the data graph. In this paper, we present an algorithm for the diversified top-k subgraph querying problem and demonstrate that it finds diversified top-k results efficiently compared to existing algorithms.
Storage Trie Optimization Based on Ethereum Transaction Data
http://doi.org/10.5626/JOK.2024.51.2.110
Interest in blockchain has grown with the increased usage of Ethereum, thus the blockchain state data has exploded, making it difficult for users to participate in the network. In this paper, we propose a method of optimizing the storage trie, which accounts for a significant portion of state data, based on pas transaction data of real Ethereum. By deleting storage trie that never appeared during 1 million blocks from a massive 14 million block storage tire, we reduced the storage space by 19.6%, which is 10.8GB. Based on the research results of this paper, it is expected that we can propose a more effective storage trie optimization based on data.
Overcoming a Zone Reclaiming Overhead with Partial-Zone Reclaiming
Inho Song, Wonjin Lee, Jaedong Lee, Seehwan Yoo, Jongmoo Choi
http://doi.org/10.5626/JOK.2024.51.2.115
Solid State Drive (SSD) suffers unpredictable IO latency and space amplification due to the traditional block interface. Zoned Namespace, which is a more flash friendly interface, replaced the block interface bringing reliable IO latency and increasing both the capacity and lifespan of SSDs. The benefit of the zone interface is not free. A Zoned Namespace (ZNS) SSD delegates the garbage collection and data placement responsibility to the host, which requires host-level garbage collection called "zone reclaiming". At the same time, ZNS SSD exposes a larger zone to the host to exploit the device parallelism. The increased number of blocks to a zone gives high parallelism; however, the overhead of the zone reclaiming process becomes high with the increased size of the zone. Eventually, the host neither expects predictable latency nor optimal performance due to the background process. This paper tackles the overhead of the zone reclaiming process by introducing "Partial Zone Reclaiming" method. Partial zone reclaiming delays the ongoing reclaiming process and handles the host request that is on the fly. In our experiment, partial zone reclaiming not only improved the host request latency by up to 8% on average, but also reduced zone reclaiming time by up to 41%.
Improved Recall of Plant Disease Detection Model using Image Super Resolution
Hyeonggyeong Kim, Chaesung Lim, Seungmin Tak
http://doi.org/10.5626/JOK.2024.51.2.125
Early identification and diagnosis of plant disease is very important because plant diseases have a great impact on yield. Currently, research on developing and advancing models for diagnosing plant diseases and pests using artificial intelligence is being actively conducted. However, even if the model showed good performance during verification, the performance deteriorates when the resolution of the input image is low during operation. If disease control is delayed because of delayed diseases diagnosis due to low resolution, the entire crop is affected by the diseases resulting in a decrease in yield. The purpose of this study was to improve the reproducibility of the model by utilizing super-resolution that increases the resolution of the image. BICUBIC, SRCNN, and SRGAN were used as super-resolution algorithms. After x4 scale super-resolution of test images with 64×64, 128×128, and 192×192 resolutions, they were directly input into the trained YOLOv5 model. As a result, the recall improved by 34% in SRGAN, 30% in SRCNN, and 19% in BICUBIC.
A Hybrid Deep Learning Model for Real-Time Forecasting Fire Temperature in Underground Utility Tunnel Based on Residual CNN-LSTM
http://doi.org/10.5626/JOK.2024.51.2.131
Underground utility tunnels (UUTs) play major roles in sustaining the life of citizens and industries with regard to carrying electricity, telecommunication, water supply pipes. Fire is one of the most commonly common disasters in underground facilities, which can be prevented through proper management. This paper proposes a hybrid deep learning model named Residual CNN-LSTM to predict fire temperatures. Scenarios of underground facility fire outbreaks were created and fire temperature data was collected using FDS software. In the experiment, we analyzed the appropriate depth of residual learning of the proposed model and compared the performance to other predictive models. The results showed that RMSE, MAE and MAPE of Residual CNN-LSTM are each 0.061529, 0.053851, 6.007076 respectively, making Residual CNN-LSTM far superior to other models in terms of its predictive performance.
Proposal of An Intent Classification Method Using Text Augmentation Techniques and Transfer Learning
Huiwon Lee, Sungho Park, Chaewon Lee, Seunghyun Lee, Kangbae Lee
http://doi.org/10.5626/JOK.2024.51.2.141
Intent classification is the first step of task-directed chatbots and is an important phase in performance improvement. However, task-oriented chatbots are limited by a lack of data for specific domains. The purpose of this study is to solve the problem of data limitation by utilizing text augmentation techniques and transfer learning. Previously, studies using transfer learning and text augmentation techniques existed, but it was difficult to find studies applicable to various domains. This study proposes a text augmentation technique and transfer learning method applicable to various domains. For the experiment, less than 10,000, 20,000, and 30,000 data were constructed according to the ratio of actual utterance intentions in 8 domains. As a result of the experiment, although differences existed depending on the domain, it was confirmed that the method proposed in this study was excellent for all 8 domains. It was confirmed that the accuracy for the 8 domains improved by 10%, 3.4%, and 1.9%, respectively on average with the decreasing size of the training data, and the F1-Score improved by 30%, 12%, and 7.5%, respectively on average.
UnityPGTA: A Unity Platformer Game Testing Automation Tool Using Reinforcement Learning
Se-chan Park, Deock Yeop Kim, Woo Jin Lee
http://doi.org/10.5626/JOK.2024.51.2.149
The cost of game testing in the video game industry is significant, accounting for nearly half of the expenses. Research efforts are underway to automate testing processes to reduce testing costs. However, existing research on test automation often involves manual tasks such as script writing, which is costly and labor-intensive. Additionally, implementations using virtual environments like VGDL and GVG-AI pose challenges when applied to real game testing. In this paper, we propose a tool for automating game testing with the aim of system fault detection, focusing on a Unity platformer game. The proposed tool is based on a commercial game engine, autonomously analyzing the game without human intervention to establish an automated game testing environment. We compare and analyze the error detection results of the proposed tool with a random baseline model using open-source games, demonstrating the tool"s effectiveness in performing automated game analysis and testing environment setup, ultimately reducing testing costs and improving quality and stability.
Explainable Artificial Intelligence in Molecular Graph Classification
Yeongyeong Son, Yewon Shin, Sunyoung Kwon
http://doi.org/10.5626/JOK.2024.51.2.157
With the advancement of artificial intelligence (AI), there is a growing need for explainable artificial intelligence (XAI). Recently, Graph neural network-based XAI research has been actively conducted, but it mainly focuses on generic graphs. Due to the distinctive characteristics relying on the chemical properties of molecular graphs, we emphasize the necessity for research to investigate whether existing XAI techniques can provide interpretability in molecular graphs. In this paper, we employ existing XAI techniques to molecular graphs and assess them quantitatively and qualitatively to see their interpretability. Furthermore, we examine the outcomes after standardizing the significance ratio of essential features, highlighting the significance of sparsity as one of the XAI evaluation metrics.
SBERT-PRO: Predicate Oriented Sentence Embedding Model for Intent and Event Detection
Dongryul Ko, Jeayun Lee, Dahee Lee, Yuri Son, Sangmin Kim, Jaeeun Jang, Munhyeong Kim, Sanghyun Park, Jaieun Kim
http://doi.org/10.5626/JOK.2024.51.2.165
Intent detection is a crucial task in conversational systems for understanding user intentions. Additionally, event detection is vital for identifying important events within various texts, including news articles, social media posts, and reports. Among diverse approaches, the sentence embedding similarity-based method has been widely adopted to solve open-domain classification tasks. However, conventional embedding models tend to focus on specific keywords within a sentence and are not suitable for tasks that require a high-level semantic understanding of a sentence as opposed to a narrow focus on specific details within a sentence. This limitation becomes particularly evident in tasks such as intent detection, which requires a broader understanding of the intention of a sentence, and event detection, which requires an emphasis on actual events within a sentence. In this paper, we construct a training dataset suitable for intent and event detection using entity attribute information and entity relation information. Our approach is inspired by the significance of emphasizing the embedding of predicates, which unfold the content of a sentence, as opposed to focusing on entity attributes within a sentence. Furthermore, we suggest an adaptive learning strategy for the existing sentence embedding model and demonstrate that our proposed model, SBERT-PRO (PRedicate Oriented), outperforms conventional models
Ray Tracing-based Real-time Collision Detection Using Bounding Mesh of Polygonal Model
Seokyoung Koh, Youngwook Kim, Insung Ihm
http://doi.org/10.5626/JOK.2024.51.2.173
For accurate real-time collision detection between two polygonal meshes, it is essential to check if each triangle of one polygonal mesh is intersected with the other polygonal mesh. However, because the number of triangles of large-size meshes easily increases, such a simple method often cannot achieve real-time detection. In this paper, we propose a GPU-assisted real-time collision detection technique where both a bounding mesh approximating a given large-size mesh and the GPU-assisted ray-tracing hardware are effectively exploited. In this method, the bounding mesh that intends to reduce the number of triangles participating in the triangle-object intersection is first intersected with the other mesh. In this way, it was possible to perform the collision detection operation within the reduced region with decreased numbers of triangles. In addition, we improved the performance of the collision detection process by exploiting the GPU-supported ray-tracing engine for accelerating the triangle-object intersection operation.
Optimization of EOG-Based Horizontal Gaze Tracking Lightweight Deep Learning Algorithm in a Virtual Environment
http://doi.org/10.5626/JOK.2024.51.2.184
This study presents an algorithm for real-time prediction of eye blinks with high accuracy and minimal parameters, utilizing a deep learning model. Previous eye-tracking algorithms relied on the assumption that the EOG(Electrooculography) signal from the pupil is linear with the angle [1,2]. However, the algorithm presented in this paper has an induction bias based on the data available. As a result, a lightweight deep learning network with layers like 1D CNN(Convolutional Neural Network) and residual block can make real-time prediction. In this study, we conducted an experiment using a device that could predicts eye movements, even while wearing an HMD(Head Mount Display) designed for virtual environments, via deep learning model predictions of eye blinks. Reconstruction of the eye using EOG data, as studied here, has the potential to yield realistic reconstructions. By researching up and down movements and extreme eye movements, the real-time nature of the avatar"s eyes may be utilized.
Search
Journal of KIISE
- ISSN : 2383-630X(Print)
- ISSN : 2383-6296(Electronic)
- KCI Accredited Journal
Editorial Office
- Tel. +82-2-588-9240
- Fax. +82-2-521-1352
- E-mail. chwoo@kiise.or.kr