• Title/Summary/Keyword: Time Pattern

Search Result 7,033, Processing Time 0.047 seconds

A Study on the Optimal Trading Frequency Pattern and Forecasting Timing in Real Time Stock Trading Using Deep Learning: Focused on KOSDAQ (딥러닝을 활용한 실시간 주식거래에서의 매매 빈도 패턴과 예측 시점에 관한 연구: KOSDAQ 시장을 중심으로)

  • Song, Hyun-Jung;Lee, Suk-Jun
    • The Journal of Information Systems
    • /
    • v.27 no.3
    • /
    • pp.123-140
    • /
    • 2018
  • Purpose The purpose of this study is to explore the optimal trading frequency which is useful for stock price prediction by using deep learning for charting image data. We also want to identify the appropriate time for accurate forecasting of stock price when performing pattern analysis. Design/methodology/approach In order to find the optimal trading frequency patterns and forecast timings, this study is performed as follows. First, stock price data is collected using OpenAPI provided by Daishin Securities, and candle chart images are created by data frequency and forecasting time. Second, the patterns are generated by the charting images and the learning is performed using the CNN. Finally, we find the optimal trading frequency patterns and forecasting timings. Findings According to the experiment results, this study confirmed that when the 10 minute frequency data is judged to be a decline pattern at previous 1 tick, the accuracy of predicting the market frequency pattern at which the market decreasing is 76%, which is determined by the optimal frequency pattern. In addition, we confirmed that forecasting of the sales frequency pattern at previous 1 tick shows higher accuracy than previous 2 tick and 3 tick.

A Study on the Metallic ion Migration Phenomena of PCB (PCB의 금속 이온 마이그레이션 현상에 관한 연구)

  • Hong Won Sik;Kang Bo-Chul;Song Byeong Suk;Kim Kwang-Bae
    • Korean Journal of Materials Research
    • /
    • v.15 no.1
    • /
    • pp.54-60
    • /
    • 2005
  • Recently a lots of problems have observed in high densified and high integrated electronic components. One of them is ion migration phenomena, which induce the electrical short of electrical circuit. ion migration phenomena has been observed in the field of exposing the specific environment and using for a long tin e. This study was evaluated the generation time of ion migration and was investigated properly test method through water drop test and high temperature high humidity test. Also we observed direct causes and confirmed generation mechanism of dendritic growth as we reproduced the ion migration phenomena. We utilized PCB(printed circuit board) having a comb pattern as follows 0.5, 1.0, 2.0 mm pattern distance. Cu, SnPb and Au were electroplated on the comb pattern. 6.5 V and 15 V were applied in the comb pattern and then we measured the electrical short time causing by ion migration. In these results, we examined a difference of ion migration time depending on pattern materials, applied voltage and pattern spacing of PCB conductor.

Analysis of Urban Distribution Pattern with Satellite Imagery

  • Roh, Young-Hee;Jeong, Jae-Joon
    • Proceedings of the KSRS Conference
    • /
    • 2007.10a
    • /
    • pp.616-619
    • /
    • 2007
  • Nowadays, urbanized area expands its boundary, and distribution of urbanized area is gradually transformed into more complicated pattern. In Korea, SMA(Seoul Metropolitan Area) has outstanding urbanized area since 1950s. But it is ambiguous whether urban distribution is clustered or dispersed. This study aims to show the way in which expansion of urbanized area impacts on spatial distribution pattern of urbanized area. We use quadrat analysis, nearest-neighbor analysis and fractal analysis to know distribution pattern of urbanized area in time-series urban growth. The quadrat analysis indicates that distribution pattern of urbanized area is clustered but the cohesion is gradually weakened. And the nearest-neighbor analysis shows that point patterns are changed that urbanized area distribution pattern is progressively changed from clustered pattern into dispersed pattern. The fractal dimension analysis shows that 1972's distribution dimension is 1.428 and 2000's dimension is 1.777. Therefore, as time goes by, the complexity of urbanized area is more increased through the years. As a result, we can show that the cohesion of the urbanized area is weakened and complicated.

  • PDF

A Study on the Basic Pattern of Men's Casual Jacket (남성 캐주얼 재킷 원형 개발에 관한 연구)

  • Kim, Mi-Jung;Jo, Jin-Suk
    • Journal of the Korean Society of Clothing and Textiles
    • /
    • v.30 no.2 s.150
    • /
    • pp.207-220
    • /
    • 2006
  • The purpose of the study is to develop the basic pattern of casual jacket for men aged between 25 and 34. Compared to the tailored jackets, casual jackets are designed much more diverse form depending on the target customer, price range and moreover fashion trend. Therefore in order to reduce the cost and time of developing new style, pattern draft from the basic pattern is better approach rather than develop each style form the measurements every time. For men's casual jacket pattern draft, the basic pattern of fit and comfort was developed through following research procedures. 173 men were surveyed about their habit of buying and wearing of casual jackets. MDs and pattern designers of 10 casual wear brands for men were interviewed. As a starting point, 3 different basic patterns were selected. 2 patterns were from the 2 interviewed brands and the last one was the pattern of ESMOD. The 3 patterns were studied by means of comparing measurements and general styling. As a results it was found that the pattern of S brand is featuring I silhouette, the pattern of K brand is featuring H silhouette and the pattern of ESMOD is featuring Y silhouette. The results of wearing test showed that the pattern of S brand is the best among the three. They were to add ease around the chest line and waist line, to relocate the waist line and the break point, to increase the jacket length and upper arm width. The improved pattern was made of polyester for the wearing test. The wearing test showed developed pattern was improved significantly. To verify the use of developed basic pattern, two buttoned single jacket was made.

Perfect Reconstruction in Sub-Nyquist Nonuniform Sampling of Signals with Known upper Time-frequency Boundary (비 균일 표본화 신호의 완전 복구에 관한 연구)

  • 이희영;정현권
    • Proceedings of the IEEK Conference
    • /
    • 2002.06e
    • /
    • pp.9-12
    • /
    • 2002
  • The problem of sub-Nyquist nonuniform sampling for the perfect reconstruction of signals with time-varying spectral contents is studied. The signals are assumed to have a known instantaneous bandwidth in time-frequency domain. As the function of time, the nonuniform sampling pattern of a given signal, that is, the instantaneous sampling frequency is determined by the observation of instantaneous bandwidth based on time-frequency analysis. The proposed sampling pattern guarantees the perfect reconstruction of nonuniform sampled signals under Nyquist-sampling rate in average.

  • PDF

Pattern recognition of time series data based on the chaotic feature extracrtion (카오스 특징 추출에 의한 시계열 신호의 패턴인식)

  • 이호섭;공성곤
    • Proceedings of the Korean Institute of Intelligent Systems Conference
    • /
    • 1996.10a
    • /
    • pp.294-297
    • /
    • 1996
  • This paper proposes the method to recognize of time series data based on the chaotic feature extraction. Features extract from time series data using the chaotic time series data analysis and the pattern recognition process is using a neural network classifier. In experiment, EEG(electroencephalograph) signals are extracted features by correlation dimension and Lyapunov experiments, and these features are classified by multilayer perceptron neural networks. Proposed chaotic feature extraction enhances recognition results from chaotic time series data.

  • PDF

Analysis of Diffusion Pattern in New Product and Services Based on Two-pieces Bass Model (신제품 및 서비스에 있어 이분조각 Bass모형에 의한 확산 패턴 분석)

  • Hong, Seok-Kee;Hong, Jung-Sik
    • IE interfaces
    • /
    • v.23 no.4
    • /
    • pp.337-348
    • /
    • 2010
  • The Bass model is the most widely used model in research of new product diffusion because it presents a nice explanation on the diffusion process of new products. However, it has a limitation that its performance of fitness is lower as the available data become less and also, the diffusion curve is bell-shape and so, it can not represent the various diffusion patterns. Recently, a two-pieces Bass model is developed and applied to analyze diffusion of 10 products. The results are encouraging in terms of fitness. However, diffusion pattern is not dealt with in the paper. In this paper, analysis of diffusion pattern is in depth addressed in two-pieces Bass model. It is shown that the diffusion curves are divided into 3 types with respect to the peak adoption rate and each type is divided into 2 types further. Takeoff time of a diffusion process is analyzed by using the inflection point and regime-change time where it represents the point that imitation and innovation parameters change. Empirical studies for 68 products(28 domestic products and 40 USA products) are performed to analyze the diffusion pattern. Findings are that diffusion patterns of all products except 1 USA product show type I and regime-change time becomes shorter as the introduction time of the product is later in domestic products and regime-change time can be regarded as a takeoff time in 47% of total 68 products.

A Study on the Design for Pattern Generator Circuit (Pattern generator 회로 설계에 관한 연구)

  • 노영동;김준식
    • Proceedings of the Korea Institute of Convergence Signal Processing
    • /
    • 2003.06a
    • /
    • pp.262-267
    • /
    • 2003
  • At process of production according to development of accumulation degree of semi-conductor element, because functional mistake examination time required increases, is becoming big obstacle factor in cost-cutting. Studied pattern generator that generate pattern and address that is bundle enemy to process these controversial point effectively.

  • PDF

Study of Temporal Data Mining for Transformer Load Pattern Analysis (변압기 부하패턴 분석을 위한 시간 데이터마이닝 연구)

  • Shin, Jin-Ho;Yi, Bong-Jae;Kim, Young-Il;Lee, Heon-Gyu;Ryu, Keun-Ho
    • The Transactions of The Korean Institute of Electrical Engineers
    • /
    • v.57 no.11
    • /
    • pp.1916-1921
    • /
    • 2008
  • This paper presents the temporal classification method based on data mining techniques for discovering knowledge from measured load patterns of distribution transformers. Since the power load patterns have time-varying characteristics and very different patterns according to the hour, time, day and week and so on, it gives rise to the uninformative results if only traditional data mining is used. Therefore, we propose a temporal classification rule for analyzing and forecasting transformer load patterns. The main tasks include the load pattern mining framework and the calendar-based expression using temporal association rule and 3-dimensional cube mining to discover load patterns in multiple time granularities.

ANALYSIS OF LANDUSE PATTERN OF RIVER BOUNDARY USING TIME-SERIES AERIAL IMAGE

  • Lee, Geun-Sang;Chae, Hyo-Sok;Lee, Hyun-Seok;Hwang, Eui-Ho
    • Proceedings of the KSRS Conference
    • /
    • v.2
    • /
    • pp.764-767
    • /
    • 2006
  • It can be important framework data to monitor the change of land-use pattern of river boundary in design and management of river. This study analyzed the change of land-use pattern of Gab- and Yudeung River using time-series aerial images. To do this, we carried out radiation and geometric correction of image, and estimated land-use changes in inland and floodplain. As the analysis of inland, the ratio of residential, commercial, industrial, educational and public area, that is urbanized element, increases, but that of agricultural area shows a decline on the basis of 1990. Also, Minimum Distance Method, which is a kind of supervised classification method, is applied to extract water-body and sand bar layer in floodplain. As the analysis of land-use, the ratio of level-upped riverside land and water-body increases, but that of sand bar decreases. These time-series land use information can be important decision making data to evaluate the urbanization of river boundary, and especially it gives us goodness in river development project such as the composition of ecological habitat.

  • PDF