• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.402-405
• /
• 2023

본 연구의 목적은 발생한 거래에 대해 적합한 회계 계정을 선택하는 예측 모델을 생성하는 것이다. 이를 통해 단기적으로 보조 수단으로 활용하여 회계 전표 승인에 대한 소요 시간을 단축하거나, 장기적으로 손익계산서가 일정 오차율 이내에서 자동으로 빠르게 작성됨으로써 재무 정보의 적시성을 올려주고, 기업의 실적을 나타냄에 있어 개별 담당자의 주관이 개입될 여지가 줄어든다는 면에서 재무 정보의 객관성을 올려줄 것으로 기대한다. 제안하는 모델은 비용 전표 이력의 적요를 자연어 처리하고 학습한 모델을 통해 1 차(공시용) 비용 계정을 분류한다. 분류 결과를 범위로 활용하는 기계 학습을 활용하여 좀 더 세밀한 범위의 2 차(관리용) 비용 계정을 분류하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.924-925
• /
• 2023

본 연구는 최근 기계학습 모델의 복잡성 증가와 '블랙 박스'로 인식된 머신러닝 모델의 해석 문제에 주목하였다. 이를 해결하기 위해, AutoML 기술을 사용하여 효율적으로 최적의 모델을 탐색하고, XAI 기법을 도입하여 모델의 예측 과정에 대한 투명성을 확보하려 하였다. XAI 기법을 도입한 방식은 전통적인 방법에 비해 뛰어난 해석력을 제공하며, 사용자가 머신러닝 모델의 예측 근거와 그 타당성을 명확히 이해할 수 있음을 확인하였다.

• Journal of Intelligence and Information Systems
• /
• v.8 no.2
• /
• pp.205-227
• /
• 2002

Our study is focused on a multiple-agent system to provide efficient collaborative work by automating the conference calling process with the help of intelligent agents. Automating the meeting scheduling requires a careful consideration of the individual official schedule as well as the privacy and personal preferences. Therefore, the automation of conference calling needs the distributed processing task where a separate calendar management process is associated for increasing the reliability and inherent parallelism. This paper describes in detail the design and implementation issues of a multiple-agent system for conference calling that allows the convener and participants to minimize their efforts in creating a meeting. Our system is based on the client-sewer model. In the sewer side, a scheduling agent, a negotiating agent, a personal information managing agent, a group information managing agent, a session managing agent, and a coordinating agent are operating. In the client side, an interface agent, a media agent, and a collaborating agent are operating. Agents use a standardized knowledge manipulation language to communicate amongst themselves. Communicating through a standardized knowledge manipulation language allows the system to overcome heterogeneity which is one of the most important problems in communication among agents for distributed collaborative computing. The agents of our system propose the dates on which as many participants as possible are available to attend the conference using the forward chaining algorithm and the back propagation network algorithm.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10a
• /
• pp.438-441
• /
• 1996

Spinal deformity is a serious disease especially for teenagers and it is desirable for school children to be checked possible spinal deformity by moire photographic inspection method. The moire images of children's backs are visually inspected by doctors, which may cause misjudge because of a large amount of data they have to examine. A technique is proposed in this paper for automating this inspection by computer. Two characteristic axes, a potential symmetry axis approximating the human middle line and a principal axis representing the direction of a moire pattern are employed. Two principal axes are extracted locally on a back and their gradients against the potential symmetry axis are calculated. These gradients compose a 2D feature space and a linear discriminant function (LDF) is defined there which separates normal cases from suspicious cases. The LDF defined by 40 training, data was employed in the experiment to examine 40 test data and 77.5% of them were classified correctly. This amounts to 88.8% if the training data is included.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.433-437
• /
• 2003

Quantitative Feedback Theory (QFT) is one of effective methods of robust controller design. In QFT design we can considers the phase information of the perturbed plant so it is less conservative than $H_{\infty}$ and ${\mu}$-synthesis methods and as be shown, it is more transparent than the sensitivity reduction methods mentioned . In this paper we want to overcome the major drawback of QFT method which is lack of an automatic method for loop-shaping step of the method so we focus on the following problem: Given a nominal plant and QFT bounds, synthesize a controller that achieves closed-loop stability and satisfies the QFT boundaries. The usual approach to this problem involves loop-shaping in the frequency domain by manipulating the poles and zeros of the nominal loop transfer function. This process now aided by recently developed computer aided design tools proceeds by trial and error and its success often depends heavily on the experience of the loop-shaper. Thus for the novice and First time QFT user, there is a genuine need for an automatic loop-shaping tool to generate a first-cut solution. Clearly such an automatic process must involve some sort of optimization, and while recent results on convex optimization have found fruitful applications in other areas of control theory we have tried to use LMI theory for automating the loop-shaping step of QFT design.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.44 no.11
• /
• pp.56-64
• /
• 2007

We developed the first automatic design system targeting a promising hybrid CMOS-Nanoelectronics Architecture called CMOL. The CMOL architecture uses NOR gates to implement combinational logic. In this hybrid CMOS-nanoelectronics architecture, logical functions and the interconnections share the nanoelectronics hardware resource. Towards automating the CMOL physical design process, we developed a model for the CMOL architecture, formulated the placement and routing problems for the CMOL architecture subject to the unique CMOL specific constraints, and solved it by combining a placement algorithm with a gate assignment algorithm in a loop. We validated the proposed approach by implementing several industrial strength designs.

• International Journal of Internet, Broadcasting and Communication
• /
• v.12 no.1
• /
• pp.130-136
• /
• 2020

There are many problems that occur currently in agriculture industries. The problems such as unexpected of changing weather condition, lack of labor, dry soil were some of the reasons that may cause the growth of the plants. Condition of the weather in local area is inconsistent due to the global warming effect thus affecting the production of the crops. Furthermore, the loss of farm labor to urban manufacturing jobs is also the problem in this industry. Besides, the condition for the plant like air humidity, air temperature, air quality index, and soil moisture are not being recorded automatically which is more reason for the need of implementation system to monitor the data for future research and development of agriculture industry. As of this, we aim to provide a solution by developing IoT-based platform along with the irrigation for increasing crop quality and productivity in agriculture field. We aim to develop a smart garden system environment which the system is able to auto-monitoring the humidity and temperature of surroundings, air quality and soil moisture. The system also has the capability of automating the irrigation process by analyzing the moisture of soil and the climate condition (like raining). Besides, we aim to develop user-friendly system interface to monitor the data collected from the respective sensor. We adopt an open source hardware to implementation and evaluate this research.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.25 no.5
• /
• pp.1067-1075
• /
• 2015

With the recent increase of the number of mobile game users, the side effects such as the manipulation of game points, levels and game speed and payment fraud are emerging. Especially, the emulators which make it possible for mobile applications to run on PC is a great threat to mobile game security since debugging specific game application or automating the game playing can be done easier with them. Therefore, we research the efficient ways to detect widely used Android Emulators such as BlueStacks, GenyMotion, Andy, YouWave and ARC Welder from the perspective of client(app), game server and network to reduce threat to mobile game security.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.48 no.12
• /
• pp.1554-1563
• /
• 1999

This paper presents the design of high speed processor for a sequence logic control using field programmable gate array(FPGA). The sequence logic controller is widely used for automating a variety of industrial plants. The FPGA designed by VHDL consists of program and data memory interface block, input and output block, instruction fetch and decoder block, register and ALU block, program counter block, debug control block respectively. Dedicated clock inputs in the FPGA were used for high speed execution, and also the program memory was separated from the data memory for high speed execution of the sequence instructions at 40 MHz clock. Therefore it was possible that sequence instructions could be operated at the same time during the instruction fetch cycle. In order to reduce the instruction decoding time and the interface time of the data memory interface, an instruction code size was implemented by 16 bits or 32 bits respectively. And the real time debug operation was implemented for easy debugging the designed processor. This FPGA was synthesized by pASIC 2 SpDE and Synplify-Lite synthesis tool of Quick Logic company. The final simulation for worst cases was successfully performed under a Verilog HDL simulation environment. And the FPGA programmed for an 84 pin PLCC package was applied to sequence control system with inputs and outputs of 256 points. The designed processor for the sequence logic was compared with the control system using the DSP(TM320C32-40MHz) and conventional PLC system. The designed processor for the sequence logic showed good performance.

• Journal of KIBIM
• /
• v.3 no.3
• /
• pp.29-38
• /
• 2013

Domestic construction industry is larger in size, and its shape is more complex. As a result, collaboration and information management tasks are difficult to manage in a way that conventional 2D-based exchange of information. BIM technology was introduced as a solution for this. But BIM only provides a very limited set of features such as Constructability review, clash detection in reality. and duplication of work and a lot of iterations occurs in BIM process. Thus, it takes quite a lot time to work. We studied how to improve the work efficiency by connecting API to business processes. Using the API in the integration process by automating repetitive tasks, reduce a significant amount of work time Using API (Automation, Optimization, Interoperability, Analysis) can solve the task problem that does not solved by the basic features, If we make good use of the combined API will be improved productivity.