Multidimensional Classification Method Research Articles

Multi-dimensional classification via class space fusion and comprehensive label correlations

Multi-dimensional Classification (MDC) is a new multi-output learning paradigm, where each instance in this framework is annotated with labels from multiple semantic class spaces. The vital challenge in MDC problem is how to address the heterogeneity of output space. Existing methods typically focus on the decomposition of output space, rarely consider the comprehensive fine-grained label correlations and the exploration of the intrinsic structure of the output space. And the local label correlations, which only exist within specific groups of instances, remain largely untapped in existing MDC methods. Therefore, we focus on tackling these above problems in this paper by simultaneously conducting label space fusion and considering the comprehensive label correlations to fully exploit the latent discriminative information hidden in the output space. Heuristically, we utilize low-rank representation method to achieve label space fusion to capture the intrinsic structure and implicit global correlation of label space. Then the predictive MDC model is extrapolated from the reconstructed instances equipped with the fused label space. Moreover, the topological structure information of samples is fully taken advantage of for MDC model establishment. Benefiting from these strategies, the heterogeneous label space can be fully excavated to boost the performance of MDC. Empirically, comparative experiments are conducted over several multi-dimensional benchmark data sets, and corresponding experimental results firmly illustrate that the proposed algorithm can effectively solve the MDC problem and outperform state-of-the-art methods.

Analytical Capabilities of Statistical Methodology for Assessing Threats to Economic Security

Subject. Reduction of threats to economic security based on the construction of multifactorial statistical models that quantify the impact of factors on the level of economic crime, in particular, on the scale of material damage from economic crime. Purposes. Adaptation and application of statistical methodology for complex quantitative assessment of threats to economic security, multifactor modeling of patterns and trends of economic crime. Methods. Applied methods of multidimensional classification - cluster analysis, correlation and regression, trend models and forecasting. Results. Statistical modeling was carried out in the context of clusters formed during the study, reflecting the specification of their regions based on the application of statistical methodology for the typologization of the regions of the Russian Federation and the construction of multifactorial statistical models that quantitatively describe the impact of factors on the level of economic crime (the scale of material damage from economic crime). Conclusions. The results of the conducted research can be used in information and analytical work and activities of departments of internal affairs bodies, public administration bodies to develop directions for reducing economic security risks from criminalization factors. The obtained substantiation of the significance of the factors provides the basis for their inclusion in the dynamic regression model, according to which it is advisable to create short-term forecasts of the crime level of an economic orientation.

Statistical analysis of the differentiation of regions of the Russian Federation by tax revenues of consolidated budgets using the R language

The subject area of this article is the application of descriptive statistics and multidimensional classification methods to describe the regional features of the formation of tax components of revenues of consolidated budgets of the Russian Federation. The aim of the work is to demonstrate the simplicity and effectiveness of using mathematical and statistical methods and the functionality of the open source language R to solve problems of structural analysis of tax revenues, identify regional specifics, and comparative analysis of regions from the point of view of tax revenues. The apparatus of mathematical statistics implemented in the R language, in particular, opens up wide opportunities for classifying tax subjects, including multidimensional ones, significantly facilitating the procedures of analysis, ranking and planning. The functionality described in the article can be used in the process of forming and adjusting tax policy at different levels. The possibilities of the mathematical statistics apparatus in combination with the instrumental methods of the R language are revealed by the example of the classification analysis of the regions of the Russian Federation. At the same time, the absolute and relative values of tax revenues in the revenues of regional budgets are selected as classification features. The classification by belonging to the federal district and the study of the "natural" stratification by the method of cluster analysis are considered. The apparatus of mathematical statistics and, especially, the tools of the R language are used unreasonably rarely in research of this kind, despite the ease of use and the absence of the need for special training, these circumstances determine the relevance of this article. Aggregation by federal districts made it possible to identify: the Ural Federal District as the leader in terms of the average regional share of tax revenues in the revenue part of the budget and the North Caucasus Federal District, characterized by the lowest average regional contributions of tax payments to regional budgets. The analysis of the natural stratification of the regions of the Russian Federation by their relative tax contributions to consolidated budgets made it possible to identify groups: the most typical regions, subsidized regions, donor regions and regions in which the most expensive assets of enterprises of the Russian Federation are concentrated

The Capacity to Forecast Enterprise Insolvency on the Polish Market Using the Precursory Altman Z-Score Model (1968)

Theoretical background: Many years have passed since the publication of the first multidimensional model (Z-score) of early bankruptcy warning by E.I. Altman in 1968. New models have since emerged in different countries. In this research stream, the share of econometric modelling based on the assumptions of discriminant analysis, i.e. MDA – Multiple Discriminant Analysis – one of the multidimensional classification methods categorised as empirical-induction methods, plays a particularly important role. Purpose of the article: The article assesses the capacity of the Altman Z-Score to forecast (1 year ahead) insolvency of enterprises on the Polish market. Research methods: Due to the sample size (i.e. over 2,700 bankrupt entities in Poland), the study constitutes one of the broadest studies carried out so far on the assessment of the predictive capacity of early warning models in Polish economy. Main findings: The authors, conducting research in this area, put forward a hypothesis that the variables that were well identified and introduced to discriminatory models in one economy work equally well in other countries. Despite the economic differences in these countries and the phases of the business cycle, the financial-analysis indicators that allow effective forecasting of enterprise bankruptcy are valid for different economies. The discriminant-function variability ranges that are characteristic of failing and healthy economic entities change but the variables themselves are good predictors.

An Ordinal Multi-Dimensional Classification (OMDC) for Predictive Maintenance

Predictive Maintenance is a type of condition-based maintenance that assesses the equipment's states and estimates its failure probability and when maintenance should be performed. Although machine learning techniques have been frequently implemented in this area, the existing studies disregard to the natural order between the target attribute values of the historical sensor data. Thus, these methods cause losing the inherent order of the data that positively affects the prediction performances. To deal with this problem, a novel approach, named Ordinal Multi-dimensional Classification (OMDC), is proposed for estimating the conditions of a hydraulic system's four components by taking into the natural order of class values. To demonstrate the prediction ability of the proposed approach, eleven different multi-dimensional classification algorithms (traditional Binary Relevance (BR), Classifier Chain (CC), Bayesian Classifier Chain (BCC), Monte Carlo Classifier Chain (MCC), Probabilistic Classifier Chain (PCC), Classifier Dependency Network (CDN), Classifier Trellis (CT), Classifier Dependency Trellis (CDT), Label Powerset (LP), Pruned Sets (PS), and Random k-Labelsets (RAKEL)) were implemented using the Ordinal Class Classifier (OCC) algorithm. Besides, seven different classification algorithms (Multilayer Perceptron (MLP), Support Vector Machine (SVM), k-Nearest Neighbour (kNN), Decision Tree (C4.5), Bagging, Random Forest (RF), and Adaptive Boosting (AdaBoost)) were chosen as base learners for the OCC algorithm. The experimental results present that the proposed OMDC approach using binary relevance multi-dimensional classification methods predicts the conditions of a hydraulic system's multiple components with high accuracy. Also, it is clearly seen from the results that the OMDC models that utilize ensemble-based classification algorithms give more reliable prediction performances with an average Hamming score of 0.853 than the others that use traditional algorithms as base learners.

A Fused Multidimensional EEG Classification Method Based on an Extreme Tree Feature Selection.

When a brain-computer interface (BCI) is designed, high classification accuracy is difficult to obtain for motor imagery (MI) electroencephalogram (EEG) signals in view of their relatively low signal-to-noise ratio. In this paper, a fused multidimensional classification method based on extreme tree feature selection (FMCM-ETFS) is proposed for discerning motor imagery EEG tasks. First, the EEG signal was filtered by a Butterworth filter for preprocessing. Second, C3, C4, and CZ channels were selected to extract time-frequency domain and spatial domain features using autoregressive (AR), common spatial pattern (CSP), and discrete wavelet transform (DWT). The extracted features were fused for a further feature elimination. Then, the features were selected using three feature selection methods: recursive feature elimination (RFE), principal component analysis method (PCA), and extreme trees (ET). The selected feature vectors were classified using support vector machines (SVM). Finally, a total of twelve subjects' EEG data from Inner Mongolia University of Technology (IMUT data), the 2nd BCI competition in 2003, and the 4th BCI competition in 2008 were employed to show the effectiveness of this proposed FMCM-ETFS method. The results show that the classification accuracy using the multidimensional fused feature extraction (AR + CSP + DWT) is 3%–20% higher than those using the aforementioned three single feature extractions (AR, CSP, and DWT). Extreme trees (ET), which is a sort of tree-based model method, outperforms RFE and PCA by 1%–9% in term of classification accuracies, when these three methods were applied to the procedure of feature extraction, respectively.

Моделирование динамики финансового и потребительского поведения россиян

The issue of studying the socio-economic inequality of the population in the regional context is a broad field for research. Of interest are studies based on the analysis of the relationships between the population’s income, debt load or the propensity to accumulation of money, as well as the population’s ability to spend leisure time in restaurants and other similar establishments. The purpose of the article is to identify the features and analyze the dynamics of financial and consumer behavior of the population of the Russian Federation in the regional context. The article studies the financial and consumer behavior of the population of Russian regions, both in time and spatial terms, based on open data from SBER. The spatial regression heterogeneity of data is proved by using the multidimensional classification methods and the time heterogeneity of data is proved by using special statistical criteria used in time series analysis. The revealed differentiation of the regions of the Russian Federation in terms of financial and consumer behavior shows the stability of the class with the highest incomes and consumer expenditures. This class includes the capital regions and the Northern regions where mining operations as economic activity is developed. Meanwhile, almost all of Central Russia belongs to regions with very low incomes, which means that the population of these regions does not have the opportunity to saving up. The population of these regions is characterized by the lowest spending not only in restaurants, but also in fast food cafes. The developed system of equations model based on panel data has a scientific novelty, which allows displaying structural relationships between the population’s income, financial and consumer behavior. In future research, when information for 2020 becomes publicly available, the model parameters should be re-evaluated, and to account for the impact of quarantine measures, appropriate variables (dummies, perhaps) may be introduced into the model. The obtained results and conclusions can be used in the development and evaluation of the effectiveness of projects aimed at demographic development or any socio-economic programs.

МОДЕЛИРОВАНИЕ ЭФФЕКТИВНОСТИ РАБОТЫ СИСТЕМЫ ВЫСШЕГО ОБРАЗОВАНИЯ (ВУЗОВ) ПРИВОЛЖСКОГО ФЕДЕРАЛЬНОГО ОКРУГА

The article is devoted to the multidimensional classification method application - a generalized discriminant analysis for the classification of universities in the Volga Federal District by the level of efficiency. The subject of the research is the possibility of classifying universities according to the effectiveness and results of their activities. The purpose of the work is to determine the real situation and positions of 90 universities in the Volga Federal District according to three levels of efficiency: high，medium，low. Discriminant analysis was used as a research method. With the help of discriminant analysis，a predictive model is created (the formation of classification functions)，which makes it possible to classify other universities according to the selected system of indicators to check the possible assignment of them to one of the groups according to the level of their effectiveness. To carry out the classification，the variable “Expert assessment”，categorical predictors have been determined as a dependent variable: “Type of university”，“Accreditation”，“Dormitory”，continuous predictors (these are the numerical variables “Number of students”，“Average score of the Exam”，“Number of training areas” and “Number of publications of the RSCI”). Thus, according to the results of the analysis, an automatic classification has been created, which allows it to be used in the future to more accurately determining of a particular university class without contacting with experts. To improve the accuracy of the classification, it has been determined which of the observations are classified incorrectly and the relevant expert assessments have been corrected. To do this, the values of the squares of mahalanobis distances and a posteriori probabilities have been analyzed. Thus, using classification methods with training, it is possible to build models that can be used for the purposes of preliminary analysis and forecasting of the activities of both higher education institutions based on the results of their activities, and other enterprises and firms

METHODICAL APPROACH TO ENSURING CLUSTER AND LOGISTICS DEVELOPMENT OF THE MARKET OF TRANSPORT SYSTEMS OF UKRAINE

Topicality. In solving socio-economic problems in recent years, increasing contradictions between market participants at all levels of the national economy; This is especially true when it comes to the justification and practical implementation of possible options based on the analysis and further interpretation of empirical data relating to certain areas of development of territorial production systems or locally established industry markets, including transport services markets (RTP). within certain regions of the country. In this regard, there is a need to form a methodological framework for the possibility of implementing a cluster-logistics approach to the development of RTP.
 Aim and tasks. The purpose of writing this work is to develop a methodological support for cluster-logistics approach to the development of RTP with the definition of organizational forms of interaction of regional markets in the form of transport and logistics clusters (TLC).
 Research results. When analyzing and forecasting socio-economic phenomena, the researcher often encounters the multidimensionality of their description. Methods of multidimensional analysis are the most effective quantitative tool for the study of socio-economic processes, described by a large number of characteristics. These include cluster analysis, taxonomy, pattern recognition, factor analysis, and more. Cluster analysis most clearly reflects the features of multidimensional analysis in the classification, and factor analysis in the study of communication. The main purpose of cluster analysis is the breakdown of the set of studied objects and features into homogeneous groups in the appropriate sense of clusters. In cluster analysis, the concept of metrics is introduced to quantify similarity, and the similarity or difference between classified objects is set depending on the metric distance between them.In this paper, a single connection within a group of algorithms using a quadratic Euclidean distance is used. Cluster analysis most clearly reflects the features of multidimensional analysis in the classification. That is why a dimensionless model based on the use of relative coefficients of hierarchical agglomerative type is proposed to analyze the development of RTP and its transport infrastructure. The use of multidimensional classification methods allowed to group districts, in contrast to the traditional geographical or administrative division, by level of socio-economic development, which determines the needs of districts in transport infrastructure and cooperation, which, in particular through TLC, will ensure maximum use of existing economic potential. economy and equalization of living conditions of the population in different territories.Conclusion. Thus, the transport and socio-economic potential of the regions was analyzed, as a result of which two formed TLCs and five nuclei were identified, on the basis of which it is proposed to develop TLCs of appropriate types by joining regions with medium and low transport potential.

Information and communication technologies as a basis for the development of the information society: Russia in the system of international statistical indicators

The purpose of the study.The first goal of the study is a comparative analysis of general indicators of information and communication technologies (ICT) development and the principles of their construction, identifying the possibilities of their use for cross-country comparisons. The second goal is cross-country comparisons based on selected indicators and an assessment of the place and prospects of Russia in the context of ICT development. The objectives of the study are due to the growing worldwide interest of the international scientific community, business and government structures to the development of information and communication technologies and the formation of the information society. The Okinawa Charter on the Global Information Society, adopted in 2000, states that information and communication technologies in the 21st century will be one of the most powerful forces and their impact will change people’s lifestyles, ways of learning and working, as well as ways and possibilities for governments to interact with citizens. In this regard, the actual issue is the formation of an adequate information base for studying information and communication technologies not only as an independent object, but also as the most important factor in the formation of the functioning of the digital economy and the formation of the information society.Materials and methods.For the study, the methods of multidimensional classification, analysis of variation, as well as a tabular method of visual presentation of the research results were used as statistical tools. For the processing of primary information, application packages of statistical analysis were used: Microsoft Excel and STATISTICA 10.0.Results.Comparison of the indicators revealed the need for their further structuring in order to ensure the comparability of statistical analysis for the largest possible set of countries. Comparison of countries and assessment of the place of Russia was carried out on the basis of the proposed system of indicators using the methods of multidimensional classification, analysis of distributions and studying the dynamics of the indicators. The variety of tasks solved in the study of information and communication technologies and their components predetermined the presence of a large number of generalizing indicators used in cross-country comparisons, as well as a variety of approaches, both to building indicators themselves, and to forming data collection systems that ensure their calculation and comparisons. Considerable scientific and practical interest is the formation of a system of statistical indicators of ICT development, providing multi-level comparability at both country and national levels.Conclusion. According to the results of a statistical research, Russia’s positions on the accessibility infrastructure characteristics and the use of information and communication technologies are revealed. The country’s lagging behind in terms of the development of both physical and information infrastructure not only from economically developed countries, but also from some BRICS and CIS countries, overcoming of which will make it possible to solve the tasks defined by the Information Society Development Strategy of the country.

A Multidimensional Classification for the Information Technology Market

This paper expands the existing informational and analytical opportunities of application of the results of business tendency surveys which solve the problem of the loss of valuable statistical information in its traditional aggregation into simple and composite indicators. Based on methods of multidimensional classification, an algorithm of statistical analysis significantly raises the analytical opportunities for the more wide measurement of trajectories of development and short-term fluctuations of branch of the information technology (IT) is developed and discussed. This allows the construction of behavioral models of business tendency data which improve the understanding of the business cycle in more detail. Furthermore the empirical results confirm the possibility of receiving various information which increases the analytical potential of business tendency surveys.

Multidimensional Classification Method in the Study of Natural and Anthropogenic Systems

In this article the problem of build and use classification of multivariate observations; this issue has played a leading role in the knowledge of the world around us. When studying natural- anthropogenic systems have the greatest value probably-statistical simulation methods of objects, phenomena and processes. Among classification technologies to focus on situations of constructing classifications if there is no a priori information about the taxonomic structure of the observations. In the work described the rationale for the original statistical criterion Z2 and G-classification methods of multivariate observations. This used quantity conversion method dependent traits in an equivalent number of independent. G-method lets you select homogeneous classes and sub-classes of observations, evaluate differences between taxons, determine the informative signs and much more. The application of the classification shown in the case study method regularities of formation of chemical composition of mine waters in the Eastern Donbass. It is four main types of changes in the composition of mine waters: the first type has the most significant impact on environmental degradation in the region; the second and third types reflects the influence composition of groundwater chloride in the composition of mine water; the fourth type is the soda water, which may indicate the presence of the region's oil and gas fields.

Cluster Analysis as an Analytical Tool of Population Policy

The predicted negative trends in Russian demography (falling birth rates, population decline) actualize the need to strengthen measures of family and population policy. Our research purpose is to identify groups of Russian regions with similar characteristics in the family sphere using cluster analysis. The findings should make an important contribution to the field of family policy. We used hierarchical cluster analysis based on the Ward method and the Euclidean distance for segmentation of Russian regions. Clustering is based on four variables, which allowed assessing the family institution in the region. The authors used the data of Federal State Statistics Service from 2010 to 2015. Clustering and profiling of each segment has allowed forming a model of Russian regions depending on the features of the family institution in these regions. The authors revealed four clusters grouping regions with similar problems in the family sphere. This segmentation makes it possible to develop the most relevant family policy measures in each group of regions. Thus, the analysis has shown a high degree of differentiation of the family institution in the regions. This suggests that a unified approach to population problems’ solving is far from being effective. To achieve greater results in the implementation of family policy, a differentiated approach is needed. Methods of multidimensional data classification can be successfully applied as a relevant analytical toolkit. Further research could develop the adaptation of multidimensional classification methods to the analysis of the population problems in Russian regions. In particular, the algorithms of nonparametric cluster analysis may be of relevance in future studies.

Conditional abnormality detection based on AMI data mining

As advanced metering infrastructure (AMI) is deployed, the AMI data is used to detect an energy fraud. Along with context analysis of AMI data such as detection of an unreasonably low consumption AMI data mining is a primary solution for detecting abnormalities that cannot be detected using simple context analysis. Traditionally, abnormality detection based on AMI data mining compares a load profile with predefined normal prototypes. However, since a load profile can be normal in one condition and abnormal in another, the condition associated with the load profile should be considered as determining the normality. However, existing methods do not connect the normality of a prototype and a specific condition. In this study, the authors propose a mechanism that incorporates the conditional probability into determination of the normality of the prototype for comparison. The novelty of their study is its generating a two-dimensional space using similarity and conditional probability, so that several multi-dimensional classification methods can be applied. They compare the proposed mechanism with best-fit and average prototype-based abnormality detection methods. In conclusion, the proposed mechanism can distinguish fraud data with a higher precision than the traditional methods. They also explore the accuracy of the mechanism with various parameters.

Theoretical basis of decision-making model formalizing in frame of professional activity’s estimation algorithm with help of information technology

Actual question of decision-making model formalizing with aim of future using them duringdeveloping intellectual information technology for professional activity’s estimation and analysis, using multidimensional classification methods of statistics analysis

The Conceptual Approaches to the Analysis of the Labour Market and Employment

Economic reforms in the Russian Federation are closely connected with the problems of formation and development of the labour market. Among the new socio-economic realities, determined by the reformation processes, it is the labour market that combines the most urgent and sensitive social problems. The labour market is an essential system-forming factor of the territorial socio-economic system. Both directions and rates of macroeconomic development of a region and standard and quality of living depend on the effectiveness of the labour market. Situation at this market is the key parameter, and most indicators of socio-economic development are derived. The present article is dedicated to the development of conceptual approaches to statistical analysis of the labour market and employment at the regional level. The object of study is represented by the Volga Federal District. The subject is qualitative and quantitative laws arising in the process of the development of the labour market and the sphere of employment of the region. Information base of the study is the data presented in official collections of the Federal State Statistics Service of the Russian Federation. Within this study methodological approaches to statistical evaluation of the regions of the VFD are suggested at different levels of integration of institutional mechanism of employment system management and factors are defined, which determine the effectiveness of economic policy. These approaches are based on methods of multidimensional classification, which allowed to define territorial disproportions and to identify the groups of regions with different levels of integration activity. The main provisions, conclusions and recommendations are aimed at the improvement of the quality of statistical information on the trends in the sphere of regional employment in order to provide up-to-date effective management decisions.

On feature extraction and classification in prostate cancer radiotherapy using tensor decompositions

External beam radiotherapy is commonly prescribed for prostate cancer. Although new radiation techniques allow high doses to be delivered to the target, the surrounding healthy organs (rectum and bladder) may suffer from irradiation, which might produce undesirable side-effects. Hence, the understanding of the complex toxicity dose–volume effect relationships is crucial to adapt the treatment, thereby decreasing the risk of toxicity. In this paper, we introduce a novel method to classify patients at risk of presenting rectal bleeding based on a Deterministic Multi-way Analysis (DMA) of three-dimensional planned dose distributions across a population. After a non-rigid spatial alignment of the anatomies applied to the dose distributions, the proposed method seeks for two bases of vectors representing bleeding and non bleeding patients by using the Canonical Polyadic (CP) decomposition of two fourth order arrays of the planned doses. A patient is then classified according to its distance to the subspaces spanned by both bases. A total of 99 patients treated for prostate cancer were used to analyze and test the performance of the proposed approach, named CP-DMA, in a leave-one-out cross validation scheme. Results were compared with supervised (linear discriminant analysis, support vector machine, K-means, K-nearest neighbor) and unsupervised (recent principal component analysis-based algorithm, and multidimensional classification method) approaches based on the registered dose distribution. Moreover, CP-DMA was also compared with the Normal Tissue Complication Probability (NTCP) model. The CP-DMA method allowed rectal bleeding patients to be classified with good specificity and sensitivity values, outperforming the classical approaches.

The Methodological Aspect of Development and Application Multivariate Classification G-Mode for Analyses Geochemical Trend

This article is unique G-mode of multidimensional classification method and its application in the analysis of hydrogeochemistry Donetsk basin. He has the following main advantages over other methods of classification: does not require a priori information for classification of observations; earmarks homogeneous observing classes and subclasses; evaluates information weight of each indicator, determines the distance between the homogeneous taxon's; assessment of the descriptiveness of the sign of the classification and others. G-method is widely used to analyze geochemical, environmental, kosmochemical, distance and other types of information. The method successfully used in examining objects, phenomena and processes on Earth, Moon, Mars, Saturn, comets, asteroids and deep space. The results of the use of G-method in analysis of hydrogeological data for the Donetsk basin identified direct and inverse geochemical zonality. This shows that in the region can be discovered oil and gas accumulations.

Efficient monte carlo methods for multi-dimensional learning with classifier chains

Multi-dimensional classification (MDC) is the supervised learning problem where an instance is associated with multiple classes, rather than with a single class, as in traditional classification problems. Since these classes are often strongly correlated, modeling the dependencies between them allows MDC methods to improve their performance – at the expense of an increased computational cost. In this paper we focus on the classifier chains (CC) approach for modeling dependencies, one of the most popular and highest-performing methods for multi-label classification (MLC), a particular case of MDC which involves only binary classes (i.e., labels). The original CC algorithm makes a greedy approximation, and is fast but tends to propagate errors along the chain. Here we present novel Monte Carlo schemes, both for finding a good chain sequence and performing efficient inference. Our algorithms remain tractable for high-dimensional data sets and obtain the best predictive performance across several real data sets.

Reducing Payload Inspection Cost Using Rule Classification for Fast Attack Signature Matching

Network intrusion detection systems rely on a signature-based detection engine. When under attack or during heavy traffic, the detection engines need to make a fast decision whether a packet or a sequence of packets is normal or malicious. However, if packets have a heavy payload or the system has a great deal of attack patterns, the high cost of payload inspection severely diminishes detection performance. Therefore, it would be better to avoid unnecessary payload scans by checking the protocol fields in the packet header, before executing their heavy operations of payload inspection. When payload inspection is necessary, it is better to compare a minimum number of attack patterns. In this paper, we propose new methods to classify attack signatures and make pre-computed multi-pattern groups. Based on IDS rule analysis, we grouped the signatures of attack rules by a multi-dimensional classification method adapted to a simplified address flow. The proposed methods reduce unnecessary payload scans and make light pattern groups to be checked. While performance improvements are dependent on a given networking environment, the experimental results with the DARPA data set and university traffic show that the proposed methods outperform the most recent Snort by up to 33%.