• Journal of KIISE:Computer Systems and Theory
• /
• v.37 no.6
• /
• pp.354-367
• /
• 2010

There are many methods for analyzing patterns in time series data. Although stock data represents a time series, there are few studies on stock pattern analysis and prediction. Since people believe that stock price changes randomly we cannot predict stock prices using a scientific method. In this paper, we measured the degree of the randomness of stock prices using Kolmogorov complexity, and we showed that there is a strong correlation between the degree and the accuracy of stock price prediction using our semi-global alignment method. We transformed the stock price data to quantized string sequences. Then we measured randomness of stock prices using Kolmogorov complexity of the string sequences. We use KOSPI 690 stock data during 28 years for our experiments and to evaluate our methodology. When a high Kolmogorov complexity, the stock price cannot be predicted, when a low complexity, the stock price can be predicted, but the prediction ratio of stock price changes of interest to investors, is 12% prediction ratio for short-term predictions and a 54% prediction ratio for long-term predictions.

• Proceedings of the Korea Contents Association Conference
• /
• 2007.11a
• /
• pp.903-907
• /
• 2007

The aim of this paper is to help learners develop algorithmic thinking skill to solve a problem using LAMS and to draw their interest in learning through various learning activities to solve it. LAMS has the advantages of easy teaching contents' design and implementation and of an offer of sequential learning under various learning environments. The designed contents were applied to elementary school students' learning and a questionnaire survey was conducted. They showed positive responses, on the one hand, they hoped that various kinds of learning would be provided including not only data sorting but also technical contents related to computer. For further study, it is necessary to revise and supplement conceptual principals or contents of computer education in elementary and junior high schools.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2017.04a
• /
• pp.150-150
• /
• 2017

조립라인에서 볼트의 수량을 정확하게 검출하는 장치는 작업속도의 향상 및 불량발생을 줄이기 위해 필요한 것이다. 현재 조립에 필요한 수량을 작업자의 시각에 의해 파악하고 있기 때문에 작업시간이 증가되고 있으며 특히 조립 과정 중 작업자의 실수로 볼트가 제품의 내부에 침투하여 제품의 소음, 성능저하 및 수명단축을 초래하고 있다. 본 연구에서는 작업자의 편의성 및 조립속도 향상을 위해 볼트를 감지하여 자동으로 수량을 검출하는 장치를 개발하였다. 볼트의 특성에 따라 볼트 선별부의 치수를 수정하면 되도록 하였다. 조립라인의 생산성을 향상시키기 위한 설계는 Auto CAD를 이용하였다. 조립라인의 공간 효율 증가를 위하여 볼트 수량 검출기의 가로${\times}$세로의 크기를 최소로 하여 $220{\times}360{\times}1170mm$로 설계하였다. 받침대는 $60{\times}60$ 프로파일을 이용하였고 다른 구성 부품은 SUS304 재질을 가공하여 조립하였다. 실험은 실험구 마다 100회 측정하여 평균값을 나타냈으며, 소수점은 시스템에 영향이 없기 때문에 절사하였다. Test 19-27 구간이 배출부가 가장 적게 구동하는 것으로 나타났다. 정렬부의 각도가 10, $15^{\circ}$의 경우는 볼트와 배출부의 마찰력이 증가하여 구동횟수가 증가한 것으로 판단된다. $20^{\circ}$이상의 각도에서는 볼트가 배출부에 안착하기 전에 하강하기 때문에 반복횟수가 증가한 것으로 판단된다. 따라서 최적의 정렬부 각도는 $20^{\circ}$로 나타났다. 볼트의 지름이 3, 5, $7{\phi}$ 일 때 정렬부의 각도에 따른 정렬부의 반복횟수에 대한 결과 값을 한 결과 $20^{\circ}$에서 정렬부의 구동횟수가 가장 적은 것 으로 나타났다. 정렬부의 각도가 큰 경우 구동에 의한 볼트와의 운동에너지의 증가로 반복횟수가 증가한 것으로 판단된다.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.11
• /
• pp.411-418
• /
• 2022

Incorrectly loaded containers can easily knock down by strong winds. Container collapse accidents can lead to material damage and paralysis of the port system. In this paper, We propose a deep learning-based container loading state and accident risk detection technique. Using Darknet-based YOLO, the container load status identifies in real-time through corner casting on the top and bottom of the container, and the risk of accidents notifies the manager. We present criteria for classifying container alignment states and select efficient learning algorithms based on inference speed, classification accuracy, detection accuracy, and FPS in real embedded devices in the same environment. The study found that YOLOv4 had a weaker inference speed and performance of FPS than YOLOv3, but showed strong performance in classification accuracy and detection accuracy.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.127-146
• /
• 2022

Recently, as word embedding has shown excellent performance in various tasks of deep learning-based natural language processing, researches on the advancement and application of word, sentence, and document embedding are being actively conducted. Among them, cross-language transfer, which enables semantic exchange between different languages, is growing simultaneously with the development of embedding models. Academia's interests in vector alignment are growing with the expectation that it can be applied to various embedding-based analysis. In particular, vector alignment is expected to be applied to mapping between specialized domains and generalized domains. In other words, it is expected that it will be possible to map the vocabulary of specialized fields such as R&D, medicine, and law into the space of the pre-trained language model learned with huge volume of general-purpose documents, or provide a clue for mapping vocabulary between mutually different specialized fields. However, since linear-based vector alignment which has been mainly studied in academia basically assumes statistical linearity, it tends to simplify the vector space. This essentially assumes that different types of vector spaces are geometrically similar, which yields a limitation that it causes inevitable distortion in the alignment process. To overcome this limitation, we propose a deep learning-based vector alignment methodology that effectively learns the nonlinearity of data. The proposed methodology consists of sequential learning of a skip-connected autoencoder and a regression model to align the specialized word embedding expressed in each space to the general embedding space. Finally, through the inference of the two trained models, the specialized vocabulary can be aligned in the general space. To verify the performance of the proposed methodology, an experiment was performed on a total of 77,578 documents in the field of 'health care' among national R&D tasks performed from 2011 to 2020. As a result, it was confirmed that the proposed methodology showed superior performance in terms of cosine similarity compared to the existing linear vector alignment.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• v.10 no.2
• /
• pp.268-272
• /
• 2005

• Bulletin of the Korean Space Science Society
• /
• 2008.04a
• /
• pp.29.1-29.1
• /
• 2008

• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06a
• /
• pp.74-75
• /
• 2008

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2009.06a
• /
• pp.803-804
• /
• 2009

• Proceedings of the IEEK Conference
• /
• 2000.11c
• /
• pp.93-96
• /
• 2000

In this paper, we propose an efficient database system for video retrieval. Using the color spaces, it shows results of user's request. Each color space used following user's selection. We suggest adaptive three color systems for database. Experimental results based on a video database containing 331 shots are included.