• Journal of Information Processing Systems
• /
• v.11 no.1
• /
• pp.39-56
• /
• 2015

Continuous multi-interval prediction (CMIP) is used to continuously predict the trend of a data stream based on various intervals simultaneously. The continuous integrated hierarchical temporal memory (CIHTM) network performs well in CMIP. However, it is not suitable for CMIP in real-time mode, especially when the number of prediction intervals is increased. In this paper, we propose a real-time integrated hierarchical temporal memory (RIHTM) network by introducing a new type of node, which is called a Zeta1FirstSpecializedQueueNode (ZFSQNode), for the real-time continuous multi-interval prediction (RCMIP) of data streams. The ZFSQNode is constructed by using a specialized circular queue (sQUEUE) together with the modules of original hierarchical temporal memory (HTM) nodes. By using a simple structure and the easy operation characteristics of the sQUEUE, entire prediction operations are integrated in the ZFSQNode. In particular, we employed only one ZFSQNode in each level of the RIHTM network during the prediction stage to generate different intervals of prediction results. The RIHTM network efficiently reduces the response time. Our performance evaluation showed that the RIHTM was satisfied to continuously predict the trend of data streams with multi-intervals in the real-time mode.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.4
• /
• pp.463-468
• /
• 2011

Context prediction methods have been developed in two ways - one is a prediction for discrete context and the other is for continuous context. As most of the prediction methods have been used with prediction algorithms in specific domains suitable to the environment and characteristics of contexts, it is difficult to conduct a prediction for a user's context which is based on various environments and characteristics. This study suggests a context prediction method available for both discrete and continuous contexts without being limited to the characteristics of a specific domain or context. For this, we conducted a context prediction based on sequence matching by generating sequences from contexts in consideration of association rules between context attributes and by applying variable weights according to each context attribute. Simulations for discrete and continuous contexts were conducted to evaluate proposed methods and the results showed that the methods produced a similar performance to existing prediction methods with a prediction accuracy of 80.12% in discrete context and 81.43% in continuous context.

• KIPS Transactions on Computer and Communication Systems
• /
• v.1 no.1
• /
• pp.11-20
• /
• 2012

Stream data shows a sequence of values changing continuously over time. Due to the nature of stream data, its trend is continuously changing according to various time intervals. Therefore the prediction of stream data must be carried out simultaneously with respect to multiple intervals, i.e. Continuous Multiple Prediction(CMP). In this paper, we propose a Continuous Integrated Hierarchical Temporal Memory (CIHTM) network for CMP based on the Hierarchical Temporal Memory (HTM) model which is a neocortex leraning algorithm. To develop the CIHTM network, we created three kinds of new modules: Shift Vector Senor, Spatio-Temporal Classifier and Multiple Integrator. And also we developed learning and inferencing algorithm of CIHTM network.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.13 no.9
• /
• pp.836-844
• /
• 2001

For the radiant floor heating system, the possibility of suboptimal prediction control was investigated by computer simulation and experiment. For this study, TRANSYS program was used and an experimental facility consisting of two rooms (3$\times$4.4$\times$2.8m) was built. The facility enabled simultaneous comparison of two different control strategies which implemented in a separate room. Results showed that outdoor air temperature prediction control was superior to the conventional outdoor air temperature compensation control for radiant floor heating system. However, more research for fine prediction of outside air temperature was required in the future.

• Earthquakes and Structures
• /
• v.22 no.6
• /
• pp.609-623
• /
• 2022

To study the empirical seismic fragility of a reinforced concrete girder bridge, based on the theory of numerical analysis and probability modelling, a regression fragility method of a rapid fragility prediction model (Gaussian first-order regression probability model) considering empirical seismic damage is proposed. A total of 1,069 reinforced concrete girder bridges of 22 highways were used to verify the model, and the vulnerability function, plane, surface and curve model of reinforced concrete girder bridges (simple supported girder bridges and continuous girder bridges) considering the number of samples in multiple intensity regions were established. The new empirical seismic damage probability matrix and curve models of observation frequency and damage exceeding probability are developed in multiple intensity regions. A comparative vulnerability analysis between simple supported girder bridges and continuous girder bridges is provided. Depending on the theory of the regional mean seismic damage index matrix model, the empirical seismic damage prediction probability matrix is embedded in the multidimensional mean seismic damage index matrix model, and the regional rapid prediction matrix and curve of reinforced concrete girder bridges, simple supported girder bridges and continuous girder bridges in multiple intensity regions based on mean seismic damage index parameters are developed. The established multidimensional group bridge vulnerability model can be used to quantify and predict the fragility of bridges in multiple intensity regions and the fragility assessment of regional group reinforced concrete girder bridges in the future.

• Journal of Korea Multimedia Society
• /
• v.14 no.9
• /
• pp.1152-1164
• /
• 2011

Stock price is stream data to change continuously. The characteristics of these data, stock trends according to flow of time intervals may differ. therefore, stock price should be continuously prediction when the price is updated. In this paper, we propose the new prediction system that continuously predicts the stock price according to the predefined time intervals for the selected stock item using HTM model. We first present a preprocessor which normalizes the stock data and passes its result to the stream sensor. We next present a stream sensor which efficiently processes the continuous input. In addition, we devise a storage node which stores the prediction results for each level and passes it to next upper level and present the HTM network for prediction using these nodes. We show experimented our system using the actual stock price and shows its performance.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.19 no.5
• /
• pp.1182-1189
• /
• 1995

Several methods have been developed to predict the creep rupture time of the steam pipes in thermal power plant. However, existing creep life prediction methods give very conservative value at operating stress of power plant and creep rupture strain cannot be well estimated. Therefore, in this study, creep rupture time and strain prediction method accounting for material damage and grain boundary sliding is newly proposed and compared with the existing experimental data. The creep damage evolves by continuous cavity nucleation and constrained cavity growth. The results showed good correlation between the theoretically predicted creep rupture time and the experimental data. And creep rupture strain may be well estimated by using the proposed method.

• Journal of KSNVE
• /
• v.7 no.6
• /
• pp.1001-1006
• /
• 1997

Railroad noise is one of the main causes of environmental impact. Whenever a new railroad line is planned or a housing project near an existing railroad is proposed, an estimate of the relevant noise levels is usually required. For this, it is necessary to quantify those paramters that affect the railroad noise. This paper presents an accurate prediction of railroad noise.

• Journal of Korea Foundry Society
• /
• v.11 no.1
• /
• pp.44-53
• /
• 1991

The proper feeding conditions for thin Al-Alloy (AA336, JIS AC8A) castings in permanent mold were investigated to eliminate microshrinkage porosity. 5mm-thick plates (200mm long, 60mm wide) were cast with increasing padding taper from 0 to 5% under different conditions : (1) constant mold temperature of $350^{\circ}C$, (2) continuous production with uniform mold thickness (10mm), (3) continuous production with a negative taper of 2.5% in mold thickness (thickness decreasing in direction to riser). The test casting were machined off to the midplane and the shrinkage porosity was examined visually. The critical padding taper which can just eliminate the shrinkage porosity was determined for each condition, i.e. : (1) 4.5% at the constant mold temperature, (2) 3.5% for continuous production with the uniform mold thickness (3) 1.5% for continuous production with the taper in mold thickness. A computer simulation by a finite difference analysis program was applied to the test casting. The liquid fraction gradient (LFG) and the temperature gradient divided by the square root of the cooling rate (G /SR) were calculated at the end of solidification and compared with the shrinkage porosity area in the castings. For the case of constant mold temperature, LFG is a better parameter to predict shrinkage porosity than G /SR and its critical value is around 11%/cm. But for the case of continuous production, neither LFG nor G /SR could be a reliable parameter. The experimental results about the critical padding taper are of practical interest for designing permanent molds and castings. The computer simulation results stimulate further research to be directed on the prediction of centerline microshrinkage porosity in continuous production.

• Nuclear Engineering and Technology
• /
• v.56 no.6
• /
• pp.2343-2351
• /
• 2024

Accurately predicting the thermal hydraulic parameters of a transient reactor core under different working conditions is the first step toward reactor safety. Mass flow rate and temperature are important parameters of core thermal hydraulics, which have often been modeled as time series prediction problems. This study aims to achieve accurate and continuous prediction of core thermal hydraulic parameters under instantaneous conditions, as well as test the feasibility of a newly constructed gated recurrent unit (GRU) model based on the soft attention mechanism for core parameter predictions. Herein, the China Experimental Fast Reactor (CEFR) is used as the research object, and CEFR 1/2 core was taken as subject to carry out continuous predictive analysis of thermal parameters under transient conditions., while the subchannel analysis code named SUBCHANFLOW is used to generate the time series of core thermal-hydraulic parameters. The GRU model is used to predict the mass flow and temperature time series of the core. The results show that compared to the adaptive radial basis function neural network, the GRU network model produces better prediction results. The average relative error for temperature is less than 0.5 % when the step size is 3, and the prediction effect is better within 15 s. The average relative error of mass flow rate is less than 5 % when the step size is 10, and the prediction effect is better in the subsequent 12 s. The GRU model not only shows a higher prediction accuracy, but also captures the trends of the dynamic time series, which is useful for maintaining reactor safety and preventing nuclear power plant accidents. Furthermore, it can provide long-term continuous predictions under transient reactor conditions, which is useful for engineering applications and improving reactor safety.