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.
Multivariate time series (MTS) exist in many applications. Due to all kinds of interference factors, missing data in MTS is inevitable. Aiming at this problem, a filling method based on least squares support vector machine (LSSVM) is proposed. Firstly, for the series containing missing data, similar series are searched, and its results are viewed as the training set. Secondly, to make use of the correlation...
Time series classification is an important task in data mining that has been traditionally addressed with the use of similarity-based classifiers. The 1-NN DTW is typically considered the most accurate model for temporal data. Nevertheless, some authors have recently proposed ingenious alternatives to the 1-NN DTW by using diversity of time series representation or by using DTW for feature extraction...
Multiple time series clinical data are very sensitive to analysis and predict the disease. In multiple time series clinical data contains multiple measurement data are collected from different time interval and different dataset are merged using merging algorithm and statistical measurement are used to determine the distribution of data then those data are given to classifier to predict Hepatocellular...
The paper presents a new approach for processing of rhinomanometric signals based on F-transform approximation of phase diagrams. Methods of nonlinear dynamics for processing of time series allow us to obtain a significant features of rhinomanometric signals. Research indicated that the results of classification with F-transform approximation is more accurate than results of classification with FFT...
Data-Driven Software Reliability Modeling (DDSRM) is an approach in software reliability prediction problem which only relies on software failure data. There are two kinds of model architecture in this modeling, which are Single-Input Single-Output (SISO) and Multiple-Delayed-Input Single-Output (MDISO). In MDISO architecture, the prediction process involves having multiple inputs from the failure...
Data presented in form of time series as its analysis and applications recently have become increasingly important in different areas and domains. In this paper brief overview of some recently important standard problems, activities and models necessary for time series analysis and applications are presented. Paper also discusses some specific practical applications.
Classifying sequential data is an important problem in machine learning with applications in time series, sensor streams, and image analysis. The ordered structure of sequential data presents a difficulty for the standard classification models, which has motivated the task of generating features for vector-based discriminative models. Shapelet methods, which have been extensively studied in this topic,...
Large amount of hydrological data set is a kind of big data, which has much hidden and potentially useful knowledge. Hydrological prediction is important for the state flood control and drought relief. How to forecast accurately and timely with hydrological big data becomes a big challenge. There are some forecasting techniques used widely. However, they are limited by their adaptability, the data...
Churn prediction is a customer relationship process that predicts for customers who are at the brink of transferring all the business to competitor. It is predicted by modeling customer behaviors in order to extract patterns. An acquaintance of a customer is more costly than retainment of an existing customer. Churn predictions shed light on members about to leave the service and support promotion...
This paper focuses on estimated Gaussian Graphical Models (GGM) from sets of experimental data. Some extension of known Bayesian methods are proposed, allowing to introduce score functions to measure the relevance of the obtained GGM structure to describe the data. These score functions form the basic measurement to derive a new dissimilarity matrix based on the GGM structure. This latter is then...
The success of opinion mining for automatically processing vast amounts of opinionated content available on the Internet has been demonstrated as a less expensive and lower latency solution for gathering public opinion. In this paper, we investigate whether it is possible to predict variations in vote intention based on sentiment time series extracted from news comments, using three Brazilian elections...
Forecasting is a tool to predict the future event with the uncertainty and depending on the historical data. It is important for an upcoming planning event because the forecasting result will deliver the initial view for the future. This paper reviews the Least Square Support Vector Machine (LSSVM) and Group Method of Data Handling (GMDH) used in different application of forecasting. Besides, this...
In this paper briefly introduces the basic theory of Support Vector Regress(SVR), and applies v-SVR combined with neural network(v-SVRNN) to create a model, which also can be used for forecasting the financial time series. Different input variables, multi-step prediction and one-step prediction are studied in this paper. The results of simulation show that the new model is the least in the mean squared...
The characteristics of financial time series: (1)the selection process is random, complex; (2)contain most of the noise; (3)between the data with strong non-linear. The traditional prediction technologies cannot disclose the inherent rule of stock market. In this paper briefly introduces the basic theory of Support Vector Regress (SVR), and applies SVR combined with neural network (BP-SVR) to create...
Based on the dynamic association rules, this paper puts forward the formal definition of meta-rules which makes use of the support vector and confidence vector as evaluation of rules, and introduces the usual mining process of the Meta-association Rules for dynamic association rule by the model of AR-Markov, the examples show that this method is effective in the analysing and predicting the change...
Wind speed forecasting is very important to the utilization of wind energy in wind farm. In order to improve the forecast precision, a forecasting method based on empirical mode decomposition (EMD) and wavelet decomposition combine with least square support vector machine (LSSVM) is proposed in this paper. The wind speed time series was decomposed into several intrinsic mode functions (IMF) and the...
Imbalanced data sets present a particular challenge to the data mining community. Often, it is the rare event that is of interest and the cost of misclassifying the rare event is higher than misclassifying the usual event. When the data is highly skewed toward the usual, it can be very difficult for a learning system to accurately detect the rare event. There have been many approaches in recent years...
The increased availability of time series datasets prompts the development of new tools and methods that allow machine learning classifiers to better cope with time series data. Time series data are usually characterized by a high space dimensionality and a very strong correlation among features. This special nature makes the development of effective time series classifiers a challenging task. This...
Distributed denial-of-service (DDoS) attacks present serious threats to servers in the Internet. We argue that the difference of the goals, manners and results of the interaction behaviors of normal flows and attack flows, which show different characteristics on IP addresses and ports. IAI (IP Address Interaction Feature) algorithm is proposed based on the addresses interaction, abrupt traffic change,...
It is significant that to get accurate prediction of dynamic traffic flow for intelligent traffic system management and control. A traffic flow prediction model of spatial-temporal 2D (2-dimension) data fusing based on SVM (Support Vector Machines) is put forward in this paper. The section flow results predicted by temporal SVM, spatial SVM and spatial-temporal 2D data fusing are all satisfied the...
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.