The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Many time series database applications require processing and analyzing database sequences where the focus is on finding the patterns and trends in sequence data. In this paper, we propose a new approach based on the observation that finding sequential patterns in databases is somehow similar to searching for a phrase in the text. However instead of searching for sequence of letters usually from finite...
Network traffic feature is generally described as self-similarity in a time series of volume counts (e.g. of bytes or packets) view. What is omitted from this view of traffic is the content of packets. In this paper, we find the self-similarity also exists in traffic information through long-time statistics of the internet traffic data, coupled with a discussion of the underlying mathematical and...
On the basis of analyzing the newly time sequence research achievement nowadays, several definitions on seismological zone relativity are put forward in this paper for integrating the large amount of history earthquake source data and the experimental expert knowledge in seismological field. At the same time, the time sequence similarity-matching model of the relevant seismological zone is presented,...
This paper uses fuzzy clustering iteration method to cluster the data of many years rainfall, and then considers sensitiveness coefficient as the foundation of calculating weight, which affects the crop output by valid rainfall in each growth stage. On this base, by means of the principle and method of R/S analysis, this paper establishes the predicting model to research on time series data mining...
We propose a new type of editor which is able to handle a function in each cell of an excel like table: we present the complex data situation which consists in multiple multidimensional time series. New algorithms working in a multidimensional space of curves (such as a set of multiple time series) or on discrete distributions, without loss of information as it is the case with more classical encoding...
Independent component analysis (ICA) neural network is an important method for separating the mixed signal into independent components. However, the ICA neural networks can produce complicated dynamical behavior under certain conditions, such as the periodic oscillation, bifurcation and chaos. This paper introduces the chaos control of a class of ICA learning algorithm, Hyvarinen and Oja's ICA namely,...
Open ended robotic discovery aims at enabling robots to autonomously design and execute sophisticated experiments for gaining conceptual insight about real world. Such experiments are planned activities rather than innate motor commands and thus each single experiment results in a multivariate time series. In such a scenario, reducing the number of features in order to allow a symbolic learner to...
In order to have fault diagnosis for centrifugal compressor correctly, the times series analysis with neural network was carried out for it. The theory model of time series analysis method was put forward firstly, and the autoregressive coefficients diagnosis method was discussed then. And the neural network diagnosis method with AR coefficients was put forward at last. And the fault diagnosis results...
In this paper, an algorithm of position related channel character extraction and match localization based on ray-tracing is presented. Firstly the radio propagation of beacons is simulated and the time series for location is produced by using ray-tracing, and then wavelet transform and singular value decomposition are used for getting the character of location from the time series and build the character-location...
Considering the current forecasting model had limited understanding of watershed hydro meteorological and a single model could hardly reflect the objective laws, by theoretical studying and practicing of combined forecasting method, the hydrological time series forecasting method based on multi-model combination was proposed. This method makes up for the lack of a single model, and makes full use...
The paper suggests a new metric space index data structure b-tree, which constructs the index structure on the basis of bottom-up hierarchical clusters, when most of the traditional metric space index data structures are constructed top-down. Comparing to the traditional construction method, b-tree can contain more objects with shorter indexing radius, which is more favorable for the query's selection.
Since EEG signal has the time-variant nature, time-frequency techniques can provide desired analysis. In this paper, sorts of time-frequency methods were applied to provide time-frequency distributions in a time series, and the results of these analyses were compared, presenting their strengths and weakness, especially finding the advantages of S-transform analyzing the signal with multiple frequencies...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.