Vol. 49, No. 9,
Sep. 2022
Digital Library
Automatic Generation of Secure Communication Code in Model-based Software Development Framework
Jaewoo Son, Jangryul Kim, EunJin Jeong, Soonhoi Ha
http://doi.org/10.5626/JOK.2022.49.9.669
With the development of the Internet of Things (IoT), the importance of communication and security is growing, as the connection between embedded platforms becomes common. The model-based software development methodology, one of the methods of developing embedded software, is effective for software development on different platforms, by automatically generating code suitable for the platform from a platform-independent model. This is useful in distributed embedded systems by also generating remote communication code, but there are no studies on automatic secure communication code generation. In this paper, we propose a method for automatically applying security on communication, in a model-based software development framework. The efficiency and validity of the proposed method were verified through the implementation of examples, that require communication between different platforms with various encryption methods.
Automatic Classification of Pneumonia Based on Ensemble Deep Learning Model Using Intensity Normalization and Multiscale Lung-Focused Patches on Chest X-Ray Images
Yoon Jo Kim, Jinseo An, Helen Hong
http://doi.org/10.5626/JOK.2022.49.9.677
It is difficult to classify normal and pneumonia in pediatric chest X-ray (CXR) images due to irregular intensity values. In addition, deep learning model has a limitation in that it can misclassify CXR by incorrectly focusing on the outer part of the lung. This study proposed an automatic classification of pneumonia based on ensemble deep learning model using three intensity normalizations and multiscale lung-focused patches on CXR images. First, to correct for irregular intensity values in internal lungs, three intensity normalization methods were performed respectively. Second, to focus on internal lungs, regions of interest were extracted by segmenting lung regions. Third, multiscale lung-focused patches were extracted to train the characterization of pneumonia. Finally, ensemble modeling with attention module was performed to improve the classification performance. In the experiment, the method using large patches of CLAHE images showed an accuracy of 92%, which was 5% higher than that of original images. Furthermore, the proposed method using an ensemble of large and middle patches showed the best performance with an accuracy of 93%.
KorSciQA 2.0: Question Answering Dataset for Machine Reading Comprehension of Korean Papers in Science & Technology Domain
Hyesoo Kong, Hwamook Yoon, Mihwan Hyun, Hyejin Lee, Jaewook Seol
http://doi.org/10.5626/JOK.2022.49.9.686
Recently, the performance of the Machine Reading Comprehension(MRC) system has been increased through various open-ended Question Answering(QA) task, and challenging QA task which has to comprehensively understand multiple text paragraphs and make discrete inferences is being released to train more intelligent MRC systems. However, due to the absence of a QA dataset for complex reasoning to understand academic information in Korean, MRC research on academic papers has been limited. In this paper, we constructed a QA dataset, KorSciQA 2.0, for the full text including abstracts of Korean academic papers and divided the difficulty level into general, easy, and hard for discriminative MRC systems. A methodology, process, and system for constructing KorSciQA 2.0 were proposed. We conducted MRC performance evaluation experiments and when fine-tuning based on the KorSciBERT model, which is a Korean-based BERT model for science and technology domains, the F1 score was 80.76%, showing the highest performance.
Proposal of a Graph Based Chat Message Analysis Model for Messenger User Verification
http://doi.org/10.5626/JOK.2022.49.9.696
As crimes and accidents through messengers increase, the necessity of verifying messenger users is emerging. In this study, two graph-based messenger user verification models that apply the traditional author verification problem to chat text were proposed. First, the graph random walk model builds an n-gram transition graph with a previous chat message and verifies the user by learning the characteristic of traversing the transition graph with a message whose author is unknown. The results showed an accuracy of 86% in 10,000 chat conversations. Second, the graph volume model verified the user using the characteristic that the size of the transition graph increased over time and achieved an accuracy of 87% in 1,000 chat conversations. When the density of the chat messages was calculated based on the transmission time, both graph models could guarantee more than 80% accuracy when the chat density was 15 or more.
Super Resolution-based Robust Image Inpainting for Large-scale Missing Regions
Jieun Lee, SeungWon Jung, Jonghwa Shim, Eenjun Hwang
http://doi.org/10.5626/JOK.2022.49.9.708
Image inpainting is a method of filling missing regions of an image with plausible imagery. Even though the performance of recent inpainting methods has been significantly improved owing to the introduction of deep learning, unnatural results can be obtained when an input image has a large-scale missing region, contains a complex scene, or is a high-resolution image. In this study, we propose a super resolution-based two-stage image inpainting method, motivated by the point that inpainting performance in low-resolution images is better than in high-resolution images. In the first step, we convert a high-resolution image into a low-resolution image and then perform image inpainting, which results in the initial output image. In the next step, the initial output image becomes the final output image, with the same resolution as the original input image using the super resolution model. To verify the effectiveness of the proposed method, we conducted quantitative and qualitative evaluations using the high-resolution Urban100 dataset. Furthermore, we analyzed the inpainting performance depending on the size of the missing region and demonstrated that the proposed method could generate satisfactory results in a free-form mask.
Swarm Reconnaissance Drone System for Efficient Object Detection
SungTae Moon, Jihoon Jeon, Yongwoo Kim
http://doi.org/10.5626/JOK.2022.49.9.715
With the recent development in drone technology, drones are being used in numerous industries such as cultural performances, logistics delivery, and traffic monitoring. In particular, as drones are used in reconnaissance fields such as the search for missing people and intruder detection, efficient mission performance has become possible. For effective reconnaissance, it is necessary to quickly monitor a large area and find a target in real-time. However, the current system cannot obtain real-time reconnaissance results because it is difficult to process inside the drone due to its performance limitations. In addition, it is difficult to conduct integrated commands and share information because it is judged based on the images obtained individually from the drone. This paper proposes a pruning algorithm and active swarm reconnaissance system for object detection based on stitched drone images. Using four drones, the proposed system verifies the real-time object detection and swarm operation system.
Comparison of BERT-based Model Performance in CBCA Criteria Classification
Junho Shin, Jungsoo Shin, Eunkyung Jo, Yeohoon Yoon, Jaehee Jung
http://doi.org/10.5626/JOK.2022.49.9.727
In the case of child sex crimes, the victim"s statement plays a critical role in determining the existence or innocence of the case, so the Supreme Prosecutors" Office classifies the statement into a total of 19 criteria according to Criteria-Based Content Analysis (CBCA), a victim"s statement analysis technique. However, this may differ in criteria classification according to the subjective opinion of the statement analyst. Thus, in this paper, two major classification methods were applied and analyzed to present an criteria classification model using BERT and RoBERTa. The two methods comprise of a method of classifying the entire criterion at the same time, as well as method of dividing it into four groups, and then classifying the criteria within the group secondarily. The experiment classified statements into 16 criteria of CBCA and performed comparative analysis using several pre-trained models. As a result of the classification, the former classification method performed better than the latter classification method in 13 of the total 16 criteria, and the latter method was effective in three criteria with a relatively insufficient number of training data. Additionally, the RoBERTa-based model performed better than the BERT-based model in 15 of the 16 criteria, and the BERT model, which was pre-trained using only Korean conversational colloquial language, classified the remaining one criterion uniquely. This paper shows that the proposed model, which was pre-trained using interactive colloquial data is effective in classifying children"s statement sentences.
Movie Summarization Based on Emotion Dynamics and Multimodal Information
Myungji Lee, Hongseok Kwon, WonKee Lee, Jong-Hyeok Lee
http://doi.org/10.5626/JOK.2022.49.9.735
Movie summarization is the task of summarizing a full-length movie by creating a short video summary containing its most informative scenes. This paper proposes an automatic movie summarization model that comprehensively considers the three main elements of the movie: characters, plot, and video information for movie summary. To accurately identify major events on the movie plot, we propose a Transformer-based architecture that uses the movie script"s dialogue information and the main characters" emotion dynamics information as model training features, and then combines the script and video information. Through experiments, the proposed method is shown to be helpful in increasing the accuracy of identifying major events in movies and consequently improves the quality of movie summaries.
Optimizing Homomorphic Compiler HedgeHog for DNN Model based on CKKS Homomorphic Encryption Scheme
Dongkwon Lee, Gyejin Lee, Suchan Kim, Woosung Song, Dohyung Lee, Hoon Kim, Seunghan Jo, Kyuyeon Park, Kwangkeun Yi
http://doi.org/10.5626/JOK.2022.49.9.743
We present a new state-of-the-art optimizing homomorphic compiler HedgeHog based on high-level input language. Although homomorphic encryption enables safe and secure third party computation, it is hard to build high-performance HE applications without expertise. Homomorphic compiler lowers this hurdle, but most of the existing compilers are based on HE scheme that does not support real number computation and a few compilers based on the CKKS HE scheme that supports real number computation uses low-level input language. We present an optimizing compiler HedgeHog whose input language supports high-level DNN operators. In addition to its ease of use, compiled HE code shows a maximum of 22% more of speedup than the existing state-of-the-art compiler.
A Decision Support System for Situation Management based on the Variability of Disaster Situations
Hyesun Lee, Sun-Wha Lim, Eun Joo Kim, Soyoung Park, Kang Bok Lee, Sang Gi Hong
http://doi.org/10.5626/JOK.2022.49.9.755
With increasing frequency and extent of disasters, the importance of prompt and accurate situation management is also increasing. Existing methods to support situation management decision-making can be applied only to specific situation management tasks in limited circumstances, making it difficult to support customized decision-making according to disaster situations. To address this problem, this paper proposed a variability-based situation management decision support method considering characteristics of disaster situations. The proposed method was based on the software product line engineering concept, constructing core information that could be configured by considering variabilities of disaster situation characteristics, thus providing situation management information from the core information according to disaster situations. This method could increase work efficiency by supporting systematic decision-making step by step based on the situation management work process according to the disaster situation. It could increase the speed and accuracy of decision-making by supporting decision-making automation. The feasibility of the method was validated by applying the method to situation management scenarios for different disaster situations.
Knowledge Graph Embedding with Entity Type Constraints
Seunghwan Kong, Chanyoung Chung, Suheon Ju, Joyce Jiyoung Whang
http://doi.org/10.5626/JOK.2022.49.9.773
Knowledge graph embedding represents entities and relationships in the feature space by utilizing the structural properties of the graph. Most knowledge graph embedding models rely only on the structural information to generate embeddings. However, some real-world knowledge graphs include additional information such as entity types. In this paper, we propose a knowledge graph embedding model by designing a loss function that reflects not only the structure of a knowledge graph but also the entity-type information. In addition, from the observation that certain type constraints exist on triplets based on their relations, we present a negative sampling technique considering the type constraints. We create the SMC data set, a knowledge graph with entity-type restrictions to evaluate our model. Experimental results show that our model outperforms the other baseline models.
VNF Anomaly Detection Method based on Unsupervised Machine Learning
Seondong Heo, Seunghoon Jeong, Hosang Yun
http://doi.org/10.5626/JOK.2022.49.9.780
By applying virtualization technology to telecommunication networks, it is possible to reduce hardware dependencies and provide flexible control and management to the operators. In addition, since Capital Expenditure (CAPEX) and Operating Expenditure (OPEX) can be reduced by utilizing the technology, modern telco operators and service providers are using Software-Defined Networking(SDN) and Network Function Virtualization (NFV) technology to provide services more efficiently. As SDN and NFV are widely used, cyber attacks on Vitualized Network Functions (VNF) that degrade the quality of service or cause service denial are increasing. In this study, we propose a VNF anomaly detection method based on unsupervised machine learning techniques that models the steady states of VNFs and detects abnormal states caused by cyber attacks.
AoI based Data Freshness Improvement Possibility Analysis for Industrial Automation Systems
Gukcheol Choi, Junhwan Huh, Yunseob Kim, Donghyun Kim, Jongdeok Kim
http://doi.org/10.5626/JOK.2022.49.9.788
Recently, industrial automation systems have been used with various equipment and industrial protocols to provide high-level process automation. When performing real-time status information update in a network composed of various protocols, transmission delay can occur if the data processing speed of each protocol is not considered when transmitting and receiving data between heterogeneous protocols. Transmission delay causes problems with monitoring and controlling based on the old state information. Therefore, it is important to update the status information at appropriate intervals so that the destination system receives fresh information. In this paper, we analyze the problem caused by the difference in the data processing speed of each protocol during heterogeneous EtherCAT and OPC UA protocol communication using AoI (Age of Information), a metric of data freshness, and then we propose a method to find an appropriate update cycle.
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