Digital Library[ Search Result ]
Constructing a Korean Knowledge Graph Using Zero Anaphora Resolution and Dependency Parsing
Chaewon Lee, Kangbae Lee, Sungyeol Yu
http://doi.org/10.5626/JOK.2024.51.8.736
This study introduces a novel approach to creating a Korean-based knowledge graph by employing zero anaphora resolution, dependency parsing, and knowledge base extraction using ChatGPT. In order to overcome the limitations of conventional language models in handling the grammatical and morphological characteristics of Korean, this research incorporates prompt engineering techniques that combine zero anaphora resolution and dependency parsing. The main focus of this research is the 'Ko-Triple Extraction' method, which involves restoring omitted information in sentences and analyzing dependency structures to extract more sophisticated and accurate triple structures. The results demonstrate that this method greatly enhances the efficiency and accuracy of Korean text processing, and the validity of the triples has been confirmed through precision metrics. This study serves as fundamental research in the field of Korean text processing and suggests potential applications in various industries. Future research aims to apply this methodology to different industrial sectors and by expanding and connecting knowledge graph, generate valuable business insights. This approach is expected to contribute significantly make an important contribution not only to the advancement of natural language processing technologies but also to the effective of Korean in the field of artificial intelligence.
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.
A GCN-based Time-Series Data Anomaly Detection Method using Sensor-specific Time Lagged Cross Correlation
Kangwoo Lee, Yunyeong Kim, Sungwon Jung
http://doi.org/10.5626/JOK.2023.50.9.805
Anomaly detection of equipment through time series data is a very important because it can prevent further damage and contribute to productivity improvement. Although research studies on time series data anomaly detection are being actively conducted, but they have the following restrictions. First, unnecessary false alarms occur because correlations with other sensors are not considered. Second, although complete graph modeling and GAT have been applied to analyze the correlation of each sensor, this method requires a lot of time due to the increase in unnecessary operations. In this paper, we propose SC-GCNAD(Sensor-specific Correlation GCN Anomaly Detection) to address these problems. SC-GCNAD can analyze the exact correlation of each sensor by applying TLCC that reflects characteristics of time series data. It utilize GCN with excellent model expressiveness. As a result, SC-GCNAD can improve F1-Score by up to 6.37% and reduce analysis time by up to 95.31% compared to the baseline model.
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.
Systematic Development of Mobile IoT Device Power Management : Feature-based Variability Modeling and Asset Development
Hyesun Lee, Kang Bok Lee, Hyo-Chan Bang
Internet of Things (IoT) is an environment where various devices are connected to each other via a wired/wireless network and where the devices gather, process, exchange, and share information. Some of the most important types of IoT devices are mobile IoT devices such as smartphones. These devices provide various high-performance services to users but cannot be supplied with power all the time; therefore, power management appropriate to a given IoT environment is necessary. Power management of mobile IoT devices involves complex relationships between various entities such as application processors (APs), HW modules inside/outside AP, Operating System (OS), platforms, and applications; a method is therefore needed to systematically analyze and manage these relationships. In addition, variabilities related to power management such as various policies, operational environments, and algorithms need to be analyzed and applied to power management development. In this paper, engineering principles and a method based on them are presented in order to address these challenges and support systematic development of IoT device power management. Power management of connected helmet systems was used to validate the feasibility of the proposed method.
An R&E Model between University and High School for Information & Communication Technology Major Introduction and its Case Study
Since no course is offered in the area of professional ICT(Information & Communication Technology) in the high school curriculum, high school students do not have the opportunity to learn about the ICT engineering area and the possible career paths in the field. Due to this problem, high school students are not motivated to choose ICT majors at university level, and in turn, the ICT departments are struggling to recruit qualified students. In this paper, we present an R&E (research and education) model to mitigate this problem. We also present a case study on the program following the model offered by “H“ university in collaboration with a local high school. Through the program we provided high school students with design and development experiences to solve engineering problems related to the ICT area and tried to attract their attention to ICT majors. The participants of the R&E program were able to experience the systematic engineering design process, ICT tools, teamwork, and communication skills through problem solving procedures. Based on three years of observation and the survey, it was found that more than 76% of students were motivated highly by ICT and engineering majors via the program. The main contribution of the paper is that we have proposed and proved the R&E program model and applied the ICT R&E model to a program to attract qualified students to ICT majors.
Robust Anti Reverse Engineering Technique for Protecting Android Applications using the AES Algorithm
Classes.dex, which is the executable file for android operation system, has Java bite code format, so that anyone can analyze and modify its source codes by using reverse engineering. Due to this characteristic, many android applications using classes.dex as executable file have been illegally copied and distributed, causing damage to the developers and software industry. To tackle such ill-intended behavior, this paper proposes a technique to encrypt classes.dex file using an AES(Advanced Encryption Standard) encryption algorithm and decrypts the applications encrypted in such a manner in order to prevent reverse engineering of the applications. To reinforce the file against reverse engineering attack, hash values that are obtained from substituting a hash equation through the combination of salt values, are used for the keys for encrypting and decrypting classes.dex. The experiments demonstrated that the proposed technique is effective in preventing the illegal duplication of classes.dex-based android applications and reverse engineering attack. As a result, the proposed technique can protect the source of an application and also prevent the spreading of malicious codes due to repackaging attack.
Geometry Transformation in Spatial Domain Using Coefficient Changes in Frequency Domain toward Lightweight Image Encryption
Image data is mostly stored in compressed form because of its huge size. Therefore, a series of cumbersome procedures is required to apply a transformation to image data: decompression, extraction of spatial data, transformation and recompression. In this paper, we employ DCT(Discrete Cosine Transform) coefficients to change the spatial presentation of images. DCT is commonly used in still image compression standards such as JPEG and moving picture compression standards such as MPEG-2, MPEG-4, and H.264. In this paper, we derived mathematically the relationship between the geometry transformation in the spatial domain and coefficient changes in the DCT domain and verified it with images in the JPEG file format. Because of the efficiency of transformation in the frequency domain, our findings can be utilized for light-weight partial image encryption for privacy data protection or entertainment contents protection.
A Car Black Box Video Data Integrity Assurance Scheme Using Cyclic Data Block Chaining
Kang Yi, Kyung-Mi Kim, Yong Jun Cho
The integrity assurance of recorded video by car black boxes are necessary as the car black box is becoming more popular. In this paper, we propose a video data integrity assurance scheme reflecting the features of car black box. The proposed method can detect any kind of deletion, insertion, modification of frames by cyclic chaining using inter block relation. And, it provides the integrity assurance function consistently even in cases of file overwriting because of no more free space in storage, partial file data lost. And non-repudiation is supported. Experimental results with a car black box embedded system with A8 application processor show that our method has a feasible computational overhead to process full HD resoultion video at 30 frames per second in a real time.
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