• KIEE International Transaction on Systems and Control
• /
• v.2D no.2
• /
• pp.125-134
• /
• 2002

This paper proposes a method for identifying temporal pattern clusters to predict events in time series. Instead of predicting future values of the time series, the proposed method forecasts specific events that may be arbitrarily defined by the user. The prediction is defined by an event characterization function, which is the target of prediction. The events are predicted when the time series belong to temporal pattern clusters. To identify the optimal temporal pattern clusters, fuzzy goal programming is formulated to combine multiple objectives and solved by an adaptive differential evolution technique that can overcome the sensitivity problem of control parameters in conventional differential evolution. To evaluate the prediction method, five test examples are considered. The adaptive differential evolution is also tested for twelve optimization problems.

• International Journal of Computer Science & Network Security
• /
• v.22 no.10
• /
• pp.177-182
• /
• 2022

Technology is progressing with every passing day and the enormous usage of electricity is becoming a necessity. One of the techniques to enjoy the assistances in a smart home is the efficiency to manage the electric energy. When electric energy is managed in an appropriate way, it drastically saves sufficient power even to be spent during hard time as when hit by natural calamities. To accomplish this, prediction of energy consumption plays a very important role. This proposed prediction model Coherent Weighted K-Means Clustering ARIMA (CWKMCA) enhances the weighted k-means clustering technique by adding weights to the cluster points. Forecasting is done using the ARIMA model based on the centroid of the clusters produced. The dataset for this proposed work is taken from the Pecan Project in Texas, USA. The level of accuracy of this model is compared with the traditional ARIMA model and the Weighted K-Means Clustering ARIMA Model. When predicting,errors such as RMSE, MAPE, AIC and AICC are analysed, the results of this suggested work reveal lower values than the ARIMA and Weighted K-Means Clustering ARIMA models. This model also has a greater loglikelihood, demonstrating that this model outperforms the ARIMA model for time series forecasting.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.54 no.6
• /
• pp.390-395
• /
• 2005

Sunspots are dark areas that grow and decay on the lowest level of the sun that is visible from the Earth. Shot-term predictions of solar activity are essential to help plan missions and to design satellites that will survive for their useful lifetimes. This paper presents a parallel-structure fuzzy system(PSFS) for prediction of sunspot number time series. The PSFS consists of a multiple number of component fuzzy systems connected in parallel. Each component fuzzy system in the PSFS predicts future data independently based on its past time series data with different embedding dimension and time delay. An embedding dimension determines the number of inputs of each component fuzzy system and a time delay decides the interval of inputs of the time series. According to the embedding dimension and the time delay, the component fuzzy system takes various input-output pairs. The PSFS determines the final predicted value as an average of all the outputs of the component fuzzy systems in order to reduce error accumulation effect.

• Industrial Engineering and Management Systems
• /
• v.9 no.2
• /
• pp.131-140
• /
• 2010

Biclustering is a method of finding meaningful subsets of objects and attributes simultaneously, which may not be detected by traditional clustering methods. It is popularly used for the analysis of microarray data representing the expression levels of genes by conditions. Usually, biclustering algorithms do not consider a sequential relation between attributes. For time series data, however, bicluster solutions should keep the time sequence. This paper proposes a new biclustering algorithm for time series data by modifying the plaid model. The proposed algorithm introduces a parameter controlling an interval between two selected time points. Also, the pruning step preventing an over-fitting problem is modified so as to eliminate only starting or ending points. Results from artificial data sets show that the proposed method is more suitable for the extraction of biclusters from time series data sets. Moreover, by using the proposed method, we find some interesting observations from real-world time-course microarray data sets and apartment price data sets in metropolitan areas.

• Journal of Internet Computing and Services
• /
• v.24 no.2
• /
• pp.57-66
• /
• 2023

Currently, a new energy system is emerging that implements consumption reduction by improving energy efficiency. Accordingly, as smart grids spread, the rate system by timing is expanding. The rate system by timing is a rate system that applies different rates by season/hour to pay according to usage. In this study, external factors such as temperature/day/time/season are considered and the time series prediction model, LSTM, is used to predict energy power usage data. Based on this energy usage prediction model, energy usage charges are reduced by analyzing usage patterns for each device and transferring power energy from the maximum load time to the light load time. In order to analyze the usage pattern for each device, a clustering technique is used to learn and classify the usage pattern of the device by time. In summary, this study predicts usage and usage fees based on the user's power data usage, analyzes usage patterns by device, and provides customized demand transfer services based on analysis, resulting in cost reduction for users.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.5
• /
• pp.9-14
• /
• 2018

For an efficient management of electricity market and power systems, accurate forecasts for electricity demand are essential. Since there are many factors, either known or unknown, determining the realized loads, it is difficult to forecast the demands with the past time series only. In this paper we perform a cluster analysis on electricity demand data collected from Jan. 2000 to Dec. 2017. Our purpose of clustering on electricity demand data is that each cluster is expected to consist of data whose latent variables are same or similar values. Then, if properly clustered, it is possible to develop an accurate forecasting model for each cluster separately. To validate the feasibility of this approach for building better forecasting models, we clustered data with t-SNE. To apply t-SNE to time series data effectively, we adopt the dynamic time warping as a similarity measure. From the result of experiments, we found that several clusters are well observed and each cluster can be interpreted as a mix of well-known factors such as trends, seasonality and holiday effects and other unknown factors. These findings can motivate the approaches which build forecasting models with respect to each cluster independently.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.2
• /
• pp.58-65
• /
• 1997

A new automatic classification method with high and stable accuracy for time-series image data is presented in this paper. This method is based on prior condition that a classified map of the target area already exists, or at least one of the time-series image data had been classified. The classified map is used as a reference map to specify training areas of classification categories. The new automatic classification method consists of five steps, i.e., extraction of training data using reference map, detection of changed pixels based upon the homogeneity of training data, clustering of changed pixels, reconstruction of training data, and classification as like maximum likelihood classifier. In order to evaluate the performance of this method qualitatively, four time-series Landsat TM image data were classified by using this method and a conventional method which needs a skilled operator. As a results, we could get classified maps with high reliability and fast throughput, without a skilled operator.

• The Korean Journal of Applied Statistics
• /
• v.29 no.1
• /
• pp.1-12
• /
• 2016

Contrasted with the standard linear ARMA models, financial time series exhibits non-standard features such as fat-tails, non-normality, volatility clustering and asymmetries which are usually referred to as "stylized facts" in financial time series context (Terasvirta, 2009). We are accordingly led to ad hoc models (apart from ARMA) to accommodate stylized facts (Andersen et al., 2009). The paper aims to give a contemporary overview on financial and special time series models based on the recent literature and on the author's publications. Various models are illustrated including asymmetric models, integer valued models, multivariate models and high frequency models. Selected statistical issues on the models are discussed, bringing some perspectives to the future works in this area.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.6
• /
• pp.1957-1980
• /
• 2021

The significant aim of this research has always been to evaluate the mechanism for efficient and inherently aware usage of vitality in-home devices, thus improving the information of smart metering systems with regard to the usage of selected homes and the time of use. Advances in information processing are commonly used to quantify gigantic building activity data steps to boost the activity efficiency of the building energy systems. Here, some smart data mining models are offered to measure, and predict the time series for energy in order to expose different ephemeral principles for using energy. Such considerations illustrate the use of machines in relation to time, such as day hour, time of day, week, month and year relationships within a family unit, which are key components in gathering and separating the effect of consumers behaviors in the use of energy and their pattern of energy prediction. It is necessary to determine the multiple relations through the usage of different appliances from simultaneous information flows. In comparison, specific relations among interval-based instances where multiple appliances use continue for certain duration are difficult to determine. In order to resolve these difficulties, an unsupervised energy time-series data clustering and a frequent pattern mining study as well as a deep learning technique for estimating energy use were presented. A broad test using true data sets that are rich in smart meter data were conducted. The exact results of the appliance designs that were recognized by the proposed model were filled out by Deep Convolutional Neural Networks (CNN) and Recurrent Neural Networks (LSTM and GRU) at each stage, with consolidated accuracy of 94.79%, 97.99%, 99.61%, for 25%, 50%, and 75%, respectively.

• Structural Monitoring and Maintenance
• /
• v.7 no.2
• /
• pp.149-166
• /
• 2020

This paper presents the results of an experimental investigation on a vibration-based damage identification framework for a steel girder type and a truss bridge based on acceleration responses to operational loading. The method relies on sensor clustering-based time-series analysis of the operational acceleration response of the bridge to the passage of a moving vehicle. The results are presented in terms of Damage Features from each sensor, which are obtained by comparing the actual acceleration response from the sensors to the predicted response from the time-series model. The damage in the bridge is detected by observing the change in damage features of the bridge as structural changes occur in the bridge. The relative severity of the damage can also be quantitatively assessed by observing the magnitude of the changes in the damage features. The experimental results show the potential usefulness of the proposed method for future applications on condition assessment of real-life bridge infrastructures.