• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.9
• /
• pp.433-440
• /
• 2016

Railway point machines act as actuators that provide different routes to trains by driving switchblades from the current position to the opposite one. Since point failure can significantly affect railway operations with potentially disastrous consequences, early stress detection of point machine is critical for monitoring and managing the condition of rail infrastructure. In this paper, we propose a stress detection method for point machine in railway condition monitoring systems using sound data. The system enables extracting sound feature vector subset from audio data with reduced feature dimensions using feature subset selection, and employs support vector machines (SVMs) for early detection of stress anomalies. Experimental results show that the system enables cost-effective detection of stress using a low-cost microphone, with accuracy exceeding 98%.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.37 no.5
• /
• pp.66-76
• /
• 2000

This paper describes design and implementation of caption-processing ASIC(Application Specific Integrated Circuits) for OSD(On Screen Display) of karaoke system. The OSD of conventional karaoke system was implemented by a general purpose DSP, however this paper suggest a design to save hardware resources. The ASIC receives commands and data of graphic and caption from host processor, and then modifies the data to have various graphic effects. The design has been done by schematic and VHDL coding. The design was verified by logic simulation and FPGA emulation on the real system. The chip was fabricated with 0.8${\mu}{\textrm}{m}$ CMOS SOG, and worked properly at the karaoke system.

• Journal of KIISE:Software and Applications
• /
• v.31 no.2
• /
• pp.164-172
• /
• 2004

For a local search algorithm to find a bettor quality solution it is required to generate and evaluate a sufficiently large number of candidate solutions as neighbors at each iteration, demanding quite an amount of CPU time. This paper presents a method of selectively generating only good-looking candidate neighbors, so that the number of neighbors can be kept low to improve the efficiency of search. In our method, a newly generated candidate solution is probabilistically selected to become a neighbor based on the quality estimation determined heuristically by a very simple evaluation of the generated candidate. Experimental results on the problem of load balancing for production scheduling have shown that our candidate selection method outperforms other random or greedy selection methods in terms of solution quality given the same amount of CPU time.

• Journal of Advanced Navigation Technology
• /
• v.26 no.5
• /
• pp.319-324
• /
• 2022

If radio interference occurs or there is no navigation device, radio navigation of high-speed moving object becomes impossible. Nevertheless, if there are multiple ground stations and precise range measurement between the high-speed moving object and the ground station can be secured, it is possible to estimate the position of moving object. This paper proposes a position estimation method using high-precision TDOA measurement generated using TLM signal. In the proposed method, a common error of moving object is removed using the TDOA measurements. The measurements is generated based on TLM signal including SOQPSK PN symbol capable of precise timing synchronization. Therefore, since precise timing synchronization of the system has been performed, the timing error between ground stations has a very small value. This improved the position estimation performance by increasing the accuracy of the measured values. The proposed method is verified through software-based simulation, and the performance of estimated position satisfies the target performance.

• Journal of Advanced Navigation Technology
• /
• v.27 no.1
• /
• pp.146-153
• /
• 2023

In accordance with the industrial convergence regulation sandbox decision promoted by the Ministry of Trade, Industry and Energy, the "machine tool sharing service in the factory" applied for by MyMaker Co., Ltd., an industry-academia cooperation company, was granted a demonstration exception. While implementing this, in a situation where the ordering service part had to be developed as software, the company's domain problems were identified and analyzed, procedures were established, and a system was designed that met the related requirements. As a joint research and development project to solve the difficulties of the LINC+ industry, the order-to-order system was finally developed for shared factory services. In accordance with the procedure and requirements analysis, the planning, design, prototyping, and implementation production stages were carried out. Finally, it was confirmed that the final development contents were well implemented according to the requirements, and the resolution of the difficulties was confirmed through functional verification demonstrations.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.8
• /
• pp.333-340
• /
• 2023

Efficient prediction of corporate bankruptcy is an important part of making appropriate lending decisions for financial institutions and reducing loan default rates. In many studies, classification models using artificial intelligence technology have been used. In the financial industry, even if the performance of the new predictive models is excellent, it should be accompanied by an intuitive explanation of the basis on which the result was determined. Recently, the US, EU, and South Korea have commonly presented the right to request explanations of algorithms, so transparency in the use of AI in the financial sector must be secured. In this paper, an artificial intelligence-based interpretable classification prediction model was proposed using corporate bankruptcy data that was open to the outside world. First, data preprocessing, 5-fold cross-validation, etc. were performed, and classification performance was compared through optimization of 10 supervised learning classification models such as logistic regression, SVM, XGBoost, and LightGBM. As a result, LightGBM was confirmed as the best performance model, and SHAP, an explainable artificial intelligence technique, was applied to provide a post-explanation of the bankruptcy prediction process.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.2
• /
• pp.62-69
• /
• 2022

An electrocardiogram (ECG) is one of the most important biosignals, and in particular, continuous ECG monitoring is very important in patients with arrhythmia. There are many different types of arrhythmia (sinus node, sinus tachycardia, atrial premature beat (APB), and ventricular fibrillation) depending on the cause, and continuous ECG monitoring during daily life is very important for early diagnosis of arrhythmias and setting treatment directions. The ECG signal of arrhythmia patients is very unstable, and it is difficult to detect the R-peak point, which is a key feature for automatic arrhythmias detection. In this study, we develped a continuous measuring Holter ECG monitoring device and software for analysis and confirmed the utility of R-peak of the ECG signal with MIT-BIH arrhythmia database. In future studies, it needs the validation of algorithms and clinical data for morphological classification and prediction of arrhythmias due to various etiologies.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.27-27
• /
• 2021

세굴은 유체와 유사의 상호작용으로 발생하는 중요한 자연 현상 중 하나로, 구조 및 지반 붕괴, 홍수, 생태계 파괴 등의 문제를 야기할 수 있다. 이러한 세굴 현상을 예측하기 위해 많은 수치적 연구가 진행되어왔지만, 대부분의 연구가 기존 격자기반방법인 유한체적법 (FVM)과 개별요소법 (DEM)이 연성된 모델을 이용하였고, 이는 격자 의존도로 인한 정확도와 효율성의 문제점을 보였다. 해결책으로 입자기반 유체해석 방법인 약압축성 SPH (WCSPH)와 개별요소법의 결합모델을 이용한 모의가 연구되어 왔지만, 단순 밀도차를 활용한 유체해석방법이 압력의 불안정성을 야기하여 유사의 운동에도 영향을 주는 결과를 보였다. 또한, 개별요소법의 특성상 모의 입자의 크기를 실제 실험 입자의 크기와 동일하게 설정하면서 입자수가 지나치게 증가해 계산의 효율성이 현저히 낮아지게 되었고, 이로 인해 실제 자연 지형에 적용하는데 어려움을 보여주었다. 본 연구에서는 향상된 세굴 수치모의해석을 위해 반복법을 통해 안정적인 유체 압력을 계산하는 비압축성 SPH (ISPH)와 개별요소법을 연성한 ISPH-DEM 모델을 사용하였다. 또한, 계산속도 향상을 위해 하나의 입자가 다수의 작은 입자의 움직임을 대표하는 Coarse-grained 방법을 적용하여 기존 모델을 개선하였다. 개선된 모델을 NFLOW ISPH PURPLE 소프트웨어를 이용하여 세굴 현상을 수치 모의하였고 실험 결과와 검증을 진행한 결과, 세굴의 깊이, 너비, 형상 등을 비교하였을 때 약 10% 이내의 오차를 보였고, Coarse-grained 방법을 통한 입자 수 감소로 최소 13배 증가된 해석 속도를 보였다. 이를 통해 본 연구에서 제시된 모델이 실제 자연 지형에서의 적용가능성을 확인할 수 있었다.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.10
• /
• pp.117-127
• /
• 2012

Identifying user requirements efficiently and reflecting them on the existing system is very important in a rapidly changing web and mobile environments. This study proposes the strategies to refining requirements and to prioritizing those refined requirements for changing of web and mobile application based on user requirements (e.g. mobile application comments, Q&A, reported information as discomfort factors). In order to refining the user requirements, those requirements are grouped by using the advancement of the software business of the Forum of standardization and the existing configuration-based programs. Then, we mapped them onto the PIECES framework to identifying whether the refined requirements are correctly reflected to the system in a way of valid and pure. To determine the priority of refined requirements, first, relative weights are given to software structure, requirements and categories of PIECES. Second, integration points on each requirement are counted to obtain the relative value of partial and overall score of a set of software structural requirements. In order to verifying the possibility and proving the effectiveness of proposing technique in this study, survey was conducted on changing requirements of mobile application which have been serviced at S University by targeting 15 people of work-related stakeholders.

• KIPS Transactions on Computer and Communication Systems
• /
• v.8 no.9
• /
• pp.209-216
• /
• 2019

Publish-subscribe communication model is popular for various type of distributed applications because of its loosely coupled style connections. Among the various architecture style for publish-subscribe system, peer-to-peer architecture has been used for the mission critical application domain since it provides high scalability and real-timeness. On the other hand, to utilize the bandwidth of given networks, message filtering is frequently used to reduce the number of messages on the system. Even if P2P provides superior scalability, it is hard to apply filtering to the its messaging system because the filtering process should be done on the peer-side in P2P architecture that are usually done on the broker server in conventional pub/sub architecture. In this paper, we propose a hierarchical subscription management structure as well as message forwarding scheme for efficient data dissemination. Our proposed scheme reduces the number of received messages by filter-out un-wanted messages and offloading the message dissemination work to other subscribers to enhance the messaging throughput.