• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.10
• /
• pp.1271-1279
• /
• 2020

Text region detection is a technology that detects text area in handwriting or printed documents. The detected text areas are digitized through a recognition step, which is used in various fields depending on the purpose of use. However, the detection result of the small text unit is not suitable for the industrial field. In addition, the border of tables in the document that it causes miss-detected results, which has an adverse effect on the recognition step. To solve the issues, we propose a method for detecting text region using the border information of the table. In order to utilize the border information of the table, the proposed method adjusts the flow of two decoders. Experimentally, we show improved performance using the table border pseudo label based on weak supervised learning.

• Journal of Broadcast Engineering
• /
• v.27 no.5
• /
• pp.694-702
• /
• 2022

This paper is the UX-based technology strategy research which is a solution to how conversational AI can be ethically evolved in the Metaverse environment. Since conversational AI influences people's on-offline decision-making factors through interaction with people, the Metaverse AI ethics must be reflected. In the machine learning process of conversational AI, cultural codes along with user's personal experience data must be included and considered to reduce the error value of user experience. Through this, the super-personalized Metaverse service can evolve ethically with social values. With above hypothesis as a result of the study, a conceptual model of a forward-looking perspective was developed and proposed by adding user experience data to the machine learning (ML) process for context-based interactive AI in the Metaverse service environment.

• Journal of Internet of Things and Convergence
• /
• v.8 no.1
• /
• pp.65-72
• /
• 2022

The Internet of Things (IoT) provides data convergence and sharing functions, and IoT technology is the most fundamental core technology in creating new services by convergence of various cutting-edge technologies. However, there are different classification systems for the Internet of Things, and when it is limited to the domestic public sector, it is difficult to properly grasp the current status of which devices are installed and operated with what share, and systematic data or research The results are very difficult to find. Therefore, in this study, the relevance of the classification system for IoT devices was analyzed according to reality based on sales, shipments, and growth rate, and based on this, the actual share of IoT devices among domestic public institutions was analyzed in detail. The derived detailed analysis results are expected to be efficiently utilized in the process of selecting IoT devices for research and analysis to advance information protection technology such as responding to malicious code attacks on IoT devices, analyzing incidents, and strengthening security vulnerabilities.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.11
• /
• pp.139-145
• /
• 2022

As products that consumers want become more diverse, the types of automation equipment are becoming more diverse and advanced to produce competitive products. In general, equipment is manufactured with built-in interface devices (HMI) for users so that operators can efficiently monitor and operate equipment quickly. Because HMI devices are connected to various industrial controllers, elements such as communication protocols of various controllers must be understood and set up in the design stage. Non-experts not only have difficulty choosing compatible items among various protocols, but also have limitations in integrating and operating on one device because screens and settings are statically assigned. This paper proposes a model that can scan information such as equipment ID and communication protocol with QR code using a mobile device, access industrial controller, and remotely operate the displayed equipment screen. The proposed model is expected to increase efficiency in inspection and management of automated equipment as it can easily set, monitor, and operate the communication environment of various automated equipment using one mobile device.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.158-160
• /
• 2022

Many office workers spend a lot of time performing repetitive office tasks in inefficient ways. We developed a user-friendly chatbot system based on Kakaotalk to automate repetitive tasks and used the chatbot in the real workplace. In the process of operating the chatbot, if several people use the chatbot at the same time, the server was down or could not respond. To address these issues, we performed code migration of programs used by chatbot back-end servers and tried several ways to improve server performance such as database redesign and load balancing. To determine how much each method affects performance improvement, we measured total request per second and average latency. After that, we proposed ways to improve the problems of using the chatbot in the work environment.

• Korean Chemical Engineering Research
• /
• v.61 no.2
• /
• pp.247-257
• /
• 2023

Precise counting of cell number stands in important position within clinical and research laboratories. Conventional methods such as hemocytometer, migration/invasion assay, or automated cell counters have limited in analytical time, cost, and accuracy., which needs an alternative way with time-efficient in-situ approach to broaden the application avenue. Here, we present simple coding-based cell counting method using image analysis tool, freely available image software (ImageJ). Firstly, we encapsulated RFP-expressing bacteria in a droplet using microfluidic device and automatically performed fluorescence image-based analysis for the quantification of cell numbers. Also, time-lapse images were captured for tracking the change of cell numbers in a droplet containing different concentrations of antibiotics. This study confirms that our approach is approximately 15 times faster and provides more accurate number of cells in a droplet than the external analysis program method. We envision that it can be used to the development of high-throughput image-based cell counting analysis.

• Convergence Security Journal
• /
• v.23 no.1
• /
• pp.45-54
• /
• 2023

Recently, with the development of the Internet of Things, research on protocols that can easily connect devices without a UI to the network has been steadily conducted. To this end, the Wi-Fi Alliance announced Wi-Fi Easy Connect, which can connect to a network using a QR code. However, since Wi-Fi Easy Connect requires a large amount of computation for safety, it is difficult to apply to low-power and miniaturized IoT devices. In addition, Wi-Fi Easy Connect considering scalability is designed to operate in a wired environment, but problems such as duplicate encryption occur because it does not consider a security environment like TLS. Therefore, in this paper, we analyze the Wi-Fi Easy Connect protocol and propose a protocol that can operate efficiently in the TLS environment. It was confirmed that the proposed protocol satisfies the existing security requirements and at the same time reduces about 67% of ECC scalar multiplication operations with a large amount of computation.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.9
• /
• pp.1-10
• /
• 2009

The field of the web service orchestration introduced to generate a valuable service by reusing single services. Recently, it suggests rule-based searching and composition by the AI (Artificial Intelligence) instead of simple searching or orchestration based on the IOPE(Input, Output, Precondition, Effect) to implement the Semantic web as the web service of the next generation. It introduce a AOP programming paradigm from existing object-oriented programming paradigm for more efficient modularization of software. In this paper, we design a dynamic web service orchestration and invocation scheme applying Aspect-Oriented Programming (AOP) and Reflection for Semantic web. The proposed scheme makes use of the Reflection technique to gather dynamically meta data and generates byte code by AOP to compose dynamically web services. As well as, our scheme shows how to execute composed web services through dynamic proxy objects generated by the Reflection. For performance evaluation of the proposed scheme, we experiment on search performance of composed web services with respect to business logic layer and user view layer.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.329-329
• /
• 2021

우리나라의 농촌유역은 일반적으로 상류의 농업용저수지와 하류의 배수장을 통해 홍수조절이 이루어지며, 각 농업수리구조물의 운영이 유역의 홍수 및 침수 발생에 큰 영향을 끼친다. 농촌유역의 홍수 대응 능력을 향상시키기 위해서는 농업수리구조물의 통합적 운영이 필요하나 현실에서 이를 시험 운영하기 위해서는 시간적·경제적으로 한계가 있다. 따라서 농촌유역 내 농업수리구조물을 연계한 통합 해석 시스템을 활용하여 다양한 구조물 운영 시나리오에 따른 홍수 위험을 예측하고 효율적인 대응 방안을 마련할 필요가 있다. 본 연구에서는 농업수리구조물을 연계한 홍수·침수 모의 시스템을 구축하기 위하여, 농촌유역에서 홍수·침수 모의를 위한 요소별 모듈을 구성하고, 각 모듈의 연계 기술을 개발하였다. 홍수·침수 해석 모듈은 농업용저수지 상류 유역에서부터 하류 하천 및 농경지까지 통합적으로 분석할 수 있도록 강우 분석 모듈, 강우-유출 모듈, 저수지 운영 모듈, 하천 수위 모듈, 농경지 배수 모듈의 5가지로 구성하였으며, 데이터베이스 모듈을 통해 기초자료를 저장하고 모듈 간의 입출력 과정을 처리하였다. 강우 분석, 강우-유출, 농경지 배수 모듈은 python 코드를 기반으로 자체적으로 구축하였으며, 기존의 모형 (FARD, HEC-HMS, GATE2018)들과 비교한 결과 거의 동일한 모의 결과를 나타냈다. 저수지 운영 모듈과 하천 수위 모듈은 각각 미 공병단의 HEC-5, HEC-RAS 모형을 CLI (Command Line Interface) 방식으로 외부 구동하도록 구성하였다. 전체 모듈 간의 연계에는 python 라이브러리인 Dask를 적용하여 대량의 데이터에 대한 병렬 처리 구조를 갖춤으로써 다양한 기상자료와 운영 시나리오에 따른 반복 작업을 효율적으로 수행하도록 구성하였다. 본 연구에서 개발한 홍수·침수 모의 요소별 모듈과 연계 기술을 기반으로, 농업수리구조물의 연계 운영을 통합적으로 모의함으로써 홍수 대비를 위한 효율적인 구조물 운영안을 도출할 수 있을 것으로 기대된다.

• Journal of Internet of Things and Convergence
• /
• v.9 no.6
• /
• pp.45-50
• /
• 2023

In software development, the elicitation and analysis of requirements is a crucial phase, and it involves considerable time and effort due to the involvement of various stakeholders. ChatGPT, having been trained on a diverse array of documents, is a large language model that possesses not only the ability to generate code and perform debugging but also the capability to be utilized in the domain of software analysis and design. This paper proposes a method of requirements engineering that leverages ChatGPT's capabilities for eliciting software requirements, analyzing them to align with system goals, and documenting them in the form of use cases. In software requirements engineering, it suggests that stakeholders, analysts, and ChatGPT should engage in a collaborative model. The process should involve using the outputs of ChatGPT as initial requirements, which are then reviewed and augmented by analysts and stakeholders. As ChatGPT's capability improves, it is anticipated that the accuracy of requirements elicitation and analysis will increase, leading to time and cost savings in the field of software requirements engineering.