A Real-Time Integrated Hierarchical Temporal Memory Network for the Real-Time Continuous Multi-Interval Prediction of Data Streams

( Hyun Syug Kang ) 한국정보처리학회 2015 Journal of information processing systems Vol.11 No.1

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.

Analysis of delay compensation in real-time dynamic hybrid testing with large integration time-step

Fei Zhu,Jin-Ting Wang,Feng Jin,Yao Gui,Meng-Xia Zhou 국제구조공학회 2014 Smart Structures and Systems, An International Jou Vol.14 No.6

With the sub-stepping technique, the numerical analysis in real-time dynamic hybrid testing is split into the response analysis and signal generation tasks. Two target computers that operate in real-time may be assigned to implement these two tasks, respectively, for fully extending the simulation scale of the numerical substructure. In this case, the integration time-step of solving the dynamic response of the numerical substructure can be dozens of times bigger than the sampling time-step of the controller. The time delay between the real and desired feedback forces becomes more striking, which challenges the well-developed delay compensation methods in real-time dynamic hybrid testing. This paper focuses on displacement prediction and force correction for delay compensation in the real-time dynamic hybrid testing with a large integration time-step. A new displacement prediction scheme is proposed based on recently-developed explicit integration algorithms and compared with several commonly-used prediction procedures. The evaluation of its prediction accuracy is carried out theoretically, numerically and experimentally. Results indicate that the accuracy and effectiveness of the proposed prediction method are of significance.

Artificial Neural Network-based Real Time Water Temperature Prediction in the Soyang River

Karpjoo Jeong(정갑주),Jonghyun Lee(이종현),Keun Young Lee(이근영),Bomchul Kim(김범철) 대한전기학회 2016 전기학회논문지 Vol.65 No.12

It is crucial to predict water temperature for aquatic ecosystem studies and management. In this paper, we first address challenging issues in predicting water temperature in a real time manner and propose a distributed computing model to address such issues. Then, we present an Artificial Neural Network (ANN)-based water temperature prediction model developed for the Soyang River and a cyberinfrastructure system called WT-Agabus to run such prediction models in an automated and real time manner. The ANN model is designed to use only weather forecast data (air temperature and rainfall) that can be obtained by invoking the weather forecasting system at Korea Meteorological Administration (KMA) and therefore can facilitate the automated and real time water temperature prediction. This paper also demonstrates how easily and efficiently the real time prediction can be implemented with the WT-Agabus prototype system.

An expanded Matrix Factorization model for real-time Web service QoS prediction

( Jinsheng Hao ),( Guoping Su ),( Xiaofeng Han ),( Wei Nie ) 한국인터넷정보학회 2021 KSII Transactions on Internet and Information Syst Vol.15 No.11

Real-time prediction of Web service of quality (QoS) provides more convenience for web services in cloud environment, but real-time QoS prediction faces severe challenges, especially under the cold-start situation. Existing literatures of real-time QoS predicting ignore that the QoS of a user/service is related to the QoS of other users/services. For example, users/services belonging to the same group of category will have similar QoS values. All of the methods ignore the group relationship because of the complexity of the model. Based on this, we propose a real-time Matrix Factorization based Clustering model (MFC), which uses category information as a new regularization term of the loss function. Specifically, in order to meet the real-time characteristic of the real-time prediction model, and to minimize the complexity of the model, we first map the QoS values of a large number of users/services to a lower-dimensional space by the PCA method, and then use the K-means algorithm calculates user/service category information, and use the average result to obtain a stable final clustering result. Extensive experiments on real-word datasets demonstrate that MFC outperforms other state-of-the-art prediction algorithms.

Analysis of delay compensation in real-time dynamic hybrid testing with large integration time-step

Zhu, Fei,Wang, Jin-Ting,Jin, Feng,Gui, Yao,Zhou, Meng-Xia Techno-Press 2014 Smart Structures and Systems, An International Jou Vol.14 No.6

With the sub-stepping technique, the numerical analysis in real-time dynamic hybrid testing is split into the response analysis and signal generation tasks. Two target computers that operate in real-time may be assigned to implement these two tasks, respectively, for fully extending the simulation scale of the numerical substructure. In this case, the integration time-step of solving the dynamic response of the numerical substructure can be dozens of times bigger than the sampling time-step of the controller. The time delay between the real and desired feedback forces becomes more striking, which challenges the well-developed delay compensation methods in real-time dynamic hybrid testing. This paper focuses on displacement prediction and force correction for delay compensation in the real-time dynamic hybrid testing with a large integration time-step. A new displacement prediction scheme is proposed based on recently-developed explicit integration algorithms and compared with several commonly-used prediction procedures. The evaluation of its prediction accuracy is carried out theoretically, numerically and experimentally. Results indicate that the accuracy and effectiveness of the proposed prediction method are of significance.

Real-Time Travel-Time Prediction Method Applying Multiple Traffic Observations

임성한,김영호,이청원 대한토목학회 2016 KSCE JOURNAL OF CIVIL ENGINEERING Vol.20 No.7

Various methods have been developed to predict automobile travel time, but they are often unreliable, especially when the travel time varies significantly during the transition between free flow and congested flow. This paper proposes a real-time travel-time prediction method. We apply a macroscopic traffic flow model with predicted boundary conditions and modify the scheme to calculate the traffic states to reflect the latest traffic conditions on a real-time basis. Our method uses traffic data from multiple observation systems, which is a crucial component for real-time application of the macroscopic traffic flow model that has not been previously applied to traffic flow models. The analysis of real traffic data collected from a section of the Korean Kyungbu Expressway shows that the proposed method outperforms other prediction methods, particularly during the transition between free flow and congested flow.

A Real-Time Integrated Hierarchical Temporal Memory Network for the Real-Time Continuous Multi-Interval Prediction of Data Streams

강현석 한국정보처리학회 2015 Journal of information processing systems Vol.11 No.1

Continuous multi-interval prediction (CMIP) is used to continuously predict the trend of a data stream basedon 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 thenumber of prediction intervals is increased. In this paper, we propose a real-time integrated hierarchicaltemporal memory (RIHTM) network by introducing a new type of node, which is called aZeta1FirstSpecializedQueueNode (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 simplestructure and the easy operation characteristics of the sQUEUE, entire prediction operations are integrated inthe ZFSQNode. In particular, we employed only one ZFSQNode in each level of the RIHTM network duringthe prediction stage to generate different intervals of prediction results. The RIHTM network efficientlyreduces the response time. Our performance evaluation showed that the RIHTM was satisfied to continuouslypredict the trend of data streams with multi-intervals in the real-time mode.

A Real-Time Integrated Hierarchical Temporal Memory Network for the Real-Time Continuous Multi-Interval Prediction of Data Streams

Kang, Hyun-Syug Korea Information Processing Society 2015 Journal of information processing systems Vol.11 No.1

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.

A real-time model based on least squares support vector machines and output bias update for the prediction of NOx emission from coal-fired power plant

Faisal Ahmed,Hyun Jun Cho,Jin-Kuk Kim,Noh Uk Seong,여영구 한국화학공학회 2015 Korean Journal of Chemical Engineering Vol.32 No.6

The accurate and reliable real-time estimation of NOx emission is indispensable for the implementation of successful control and optimization of NOx emission from a coal-fired power plant. We apply a real-time update scheme to least squares support vector machines (LSSVM) to build a real-time version for real-time prediction of NOx. Incorporation of LSSVM in the update scheme enhances its generalization ability for long-term predictions. The proposed real-time model based on LSSVM (LSSVM-scheme) is applied to NOx emission process data from a coal-fired power plant in Korea to compare the prediction performance of NOx emission with real-time model based on partial least squares (PLS-scheme). Prediction results show that LSSVM-scheme predicts robustly for a long passage of time with higher accuracy in comparison with PLS-scheme. We also present a user friendly and sophisticated graphical user interface to enhance the convenience to approach the features of real-time LSSVM-scheme.

Prediction Model of Real Estate ROI with the LSTM Model based on AI and Bigdata

Lee, Jeong-hyun,Kim, Hoo-bin,Shim, Gyo-eon The Institute of Internet 2022 International journal of advanced smart convergenc Vol.11 No.1

Across the world, 'housing' comprises a significant portion of wealth and assets. For this reason, fluctuations in real estate prices are highly sensitive issues to individual households. In Korea, housing prices have steadily increased over the years, and thus many Koreans view the real estate market as an effective channel for their investments. However, if one purchases a real estate property for the purpose of investing, then there are several risks involved when prices begin to fluctuate. The purpose of this study is to design a real estate price 'return rate' prediction model to help mitigate the risks involved with real estate investments and promote reasonable real estate purchases. Various approaches are explored to develop a model capable of predicting real estate prices based on an understanding of the immovability of the real estate market. This study employs the LSTM method, which is based on artificial intelligence and deep learning, to predict real estate prices and validate the model. LSTM networks are based on recurrent neural networks (RNN) but add cell states (which act as a type of conveyer belt) to the hidden states. LSTM networks are able to obtain cell states and hidden states in a recursive manner. Data on the actual trading prices of apartments in autonomous districts between January 2006 and December 2019 are collected from the Actual Trading Price Disclosure System of the Ministry of Land, Infrastructure and Transport (MOLIT). Additionally, basic data on apartments and commercial buildings are collected from the Public Data Portal and Seoul Metropolitan Government's data portal. The collected actual trading price data are scaled to monthly average trading amounts, and each data entry is pre-processed according to address to produce 168 data entries. An LSTM model for return rate prediction is prepared based on a time series dataset where the training period is set as April 2015~August 2017 (29 months), the validation period is set as September 2017~September 2018 (13 months), and the test period is set as December 2018~December 2019 (13 months). The results of the return rate prediction study are as follows. First, the model achieved a prediction similarity level of almost 76%. After collecting time series data and preparing the final prediction model, it was confirmed that 76% of models could be achieved. All in all, the results demonstrate the reliability of the LSTM-based model for return rate prediction.