Feature selection by multi-objective optimisation: Application to network anomaly detection by hierarchical self-organising maps

Feature selection is an important and active issue in clustering and classification problems. By choosing an adequate feature subset, a dataset dimensionality reduction is allowed, thus contributing to decreasing the classification computational complexity, and to improving the classifier performance by avoiding redundant or irrelevant features. Although feature selection can be formally defined as an optimisation problem with only one objective, that is, the classification accuracy obtained by using the selected feature subset, in recent years, some multi-objective approaches to this problem have been proposed. These either select features that not only improve the classification accuracy, but also the generalisation capability in case of supervised classifiers, or counterbalance the bias toward lower or higher numbers of features that present some methods used to validate the clustering/classification in case of unsupervised classifiers. The main contribution of this paper is a multi-objective approach for feature selection and its application to an unsupervised clustering procedure based on Growing Hierarchical Self-Organising Maps (GHSOMs) that includes a new method for unit labelling and efficient determination of the winning unit. In the network anomaly detection problem here considered, this multi-objective approach makes it possible not only to differentiate between normal and anomalous traffic but also among different anomalies. The efficiency of our proposals has been evaluated by using the well-known DARPA/NSL-KDD datasets that contain extracted features and labelled attacks from around 2 million connections. The selected feature sets computed in our experiments provide detection rates up to 99.8% with normal traffic and up to 99.6% with anomalous traffic, as well as accuracy values up to 99.12%.

Model Probability in Self-organising Maps

Growing models have been widely used for clustering or topology learning. Traditionally these models work on stationary environments, grow incrementally and adapt their nodes to a given distribution based on global parameters. In this paper, we present an enhanced unsupervised self-organising network for the modelling of visual objects. We first develop a framework for building non-rigid shapes using the growth mechanism of the self-organising maps, and then we define an optimal number of nodes without overfitting or underfitting the network based on the knowledge obtained from information-theoretic considerations. We present experimental results for hands and we quantitatively evaluate the matching capabilities of the proposed method with the topographic product.

Understanding the socio-economic distribution of multiple deprivation: An application of self-organising maps

In this paper we seek to contribute to recent efforts to develop and implement multi-dimensional approaches to social exclusion by applying self-organising maps (SOMs) to a set of material deprivation indicators from the Irish component of EU-SILC. The first stage of our analysis involves the identification of sixteen clusters that confirm the multi-dimensional nature of deprivation in contemporary Ireland and the limitations of focusing solely on income. In going beyond this mapping stage, we consider both patterns of socio-economic differentiation in relation to cluster membership and the extent to which such membership contributes to our understanding of economic stress. Our analysis makes clear the continuing importance of traditional forms of stratification relating to factors such as income, social class and housing tenure in accounting for patterns of multiple deprivation. However, it also confirms the role of acute life events and life cycle and location influences. Most importantly, it demonstrates that conclusions relating to the relative impact of different kinds of socio-economic influences are highly dependent on the form of deprivation being considered. Our analysis suggests that debates relating to the extent to which poverty and social exclusion have become individualized should take particular care to distinguish between different kinds of outcomes. Further analysis demonstrates that the SOM approach is considerably more successful than a comparable latent class analysis in identifying those exposed to subjective economic stress. (C) 2010 International Sociological Association Research Committee 28 on Social Stratification and Mobility. Published by Elsevier Ltd. All rights reserved.

Mapping patterns of multiple deprivation using self-organising maps: An application to EU-SILC data for Ireland

The development of conceptual frameworks for the analysis of social exclusion has somewhat out-stripped related methodological developments. This paper seeks to contribute to filling this gap through the application of self-organising maps (SOMs) to the analysis of a detailed set of material deprivation indicators relating to the Irish case. The SOM approach allows us to offer a differentiated and interpretable picture of the structure of multiple deprivation in contemporary Ireland. Employing this approach, we identify 16 clusters characterised by distinct profiles across 42 deprivation indicators. Exploratory analyses demonstrate that, controlling for equivalised household income, SOM cluster membership adds substantially to our ability to predict subjective economic stress. Moreover, in comparison with an analogous latent class approach, the SOM analysis offers considerable additional discriminatory power in relation to individuals' experience of their economic circumstances. The results suggest that the SOM approach could prove a valuable addition to a 'methodological platform' for analysing the shape and form of social exclusion. (c) 2009 Elsevier Inc. All rights reserved.

Triggering Solar-Powered Vehicle Activated Signs using Self Organising Maps with K-means

Solar-powered vehicle activated signs (VAS) are speed warning signs powered by batteries that are recharged by solar panels. These signs are more desirable than other active warning signs due to the low cost of installation and the minimal maintenance requirements. However, one problem that can affect a solar-powered VAS is the limited power capacity available to keep the sign operational. In order to be able to operate the sign more efficiently, it is proposed that the sign be appropriately triggered by taking into account the prevalent conditions. Triggering the sign depends on many factors such as the prevailing speed limit, road geometry, traffic behaviour, the weather and the number of hours of daylight. The main goal of this paper is therefore to develop an intelligent algorithm that would help optimize the trigger point to achieve the best compromise between speed reduction and power consumption. Data have been systematically collected whereby vehicle speed data were gathered whilst varying the value of the trigger speed threshold. A two stage algorithm is then utilized to extract the trigger speed value. Initially the algorithm employs a Self-Organising Map (SOM), to effectively visualize and explore the properties of the data that is then clustered in the second stage using K-means clustering method. Preliminary results achieved in the study indicate that using a SOM in conjunction with K-means method is found to perform well as opposed to direct clustering of the data by K-means alone. Using a SOM in the current case helped the algorithm determine the number of clusters in the data set, which is a frequent problem in data clustering.

A combined measure for quantifying and qualifying the topology preservation of growing self-organizing maps

The Self-OrganizingMap (SOM) is a neural network model that performs an ordered projection of a high dimensional input space in a low-dimensional topological structure. The process in which such mapping is formed is defined by the SOM algorithm, which is a competitive, unsupervised and nonparametric method, since it does not make any assumption about the input data distribution. The feature maps provided by this algorithm have been successfully applied for vector quantization, clustering and high dimensional data visualization processes. However, the initialization of the network topology and the selection of the SOM training parameters are two difficult tasks caused by the unknown distribution of the input signals. A misconfiguration of these parameters can generate a feature map of low-quality, so it is necessary to have some measure of the degree of adaptation of the SOM network to the input data model. The topologypreservation is the most common concept used to implement this measure. Several qualitative and quantitative methods have been proposed for measuring the degree of SOM topologypreservation, particularly using Kohonen's model. In this work, two methods for measuring the topologypreservation of the Growing Cell Structures (GCSs) model are proposed: the topographic function and the topology preserving map

A three-dimensional representation method for noisy point clouds based on growing self-organizing maps accelerated on GPUs

The research described in this thesis was motivated by the need of a robust model capable of representing 3D data obtained with 3D sensors, which are inherently noisy. In addition, time constraints have to be considered as these sensors are capable of providing a 3D data stream in real time. This thesis proposed the use of Self-Organizing Maps (SOMs) as a 3D representation model. In particular, we proposed the use of the Growing Neural Gas (GNG) network, which has been successfully used for clustering, pattern recognition and topology representation of multi-dimensional data. Until now, Self-Organizing Maps have been primarily computed offline and their application in 3D data has mainly focused on free noise models, without considering time constraints. It is proposed a hardware implementation leveraging the computing power of modern GPUs, which takes advantage of a new paradigm coined as General-Purpose Computing on Graphics Processing Units (GPGPU). The proposed methods were applied to different problem and applications in the area of computer vision such as the recognition and localization of objects, visual surveillance or 3D reconstruction.

Self-Organizing Maps of Molecular Descriptors for Sesquiterpene Lactones and Their Application to the Chemotaxonomy of the Asteraceae Family

The Asteraceae, one of the largest families among angiosperms, is chemically characterised by the production of sesquiterpene lactones (SLs). A total of 1,111 SLs, which were extracted from 658 species, 161 genera, 63 subtribes and 15 tribes of Asteraceae, were represented and registered in two dimensions in the SISTEMATX, an in-house software system, and were associated with their botanical sources. The respective 11 block of descriptors: Constitutional, Functional groups, BCUT, Atom-centred, 2D autocorrelations, Topological, Geometrical, RDF, 3D-MoRSE, GETAWAY and WHIM were used as input data to separate the botanical occurrences through self-organising maps. Maps that were generated with each descriptor divided the Asteraceae tribes, with total index values between 66.7% and 83.6%. The analysis of the results shows evident similarities among the Heliantheae, Helenieae and Eupatorieae tribes as well as between the Anthemideae and Inuleae tribes. Those observations are in agreement with systematic classifications that were proposed by Bremer, which use mainly morphological and molecular data, therefore chemical markers partially corroborate with these classifications. The results demonstrate that the atom-centred and RDF descriptors can be used as a tool for taxonomic classification in low hierarchical levels, such as tribes. Descriptors obtained through fragments or by the two-dimensional representation of the SL structures were sufficient to obtain significant results, and better results were not achieved by using descriptors derived from three-dimensional representations of SLs. Such models based on physico-chemical properties can project new design SLs, similar structures from literature or even unreported structures in two-dimensional chemical space. Therefore, the generated SOMs can predict the most probable tribe where a biologically active molecule can be found according Bremer classification.

Using self-organising feature maps for the control of artificial organisms

Variations on the standard Kohonen feature map can enable an ordering of the map state space by using only a limited subset of the complete input vector. Also it is possible to employ merely a local adaptation procedure to order the map, rather than having to rely on global variables and objectives. Such variations have been included as part of a hybrid learning system (HLS) which has arisen out of a genetic-based classifier system. In the paper a description of the modified feature map is given, which constitutes the HLSs long term memory, and results in the control of a simple maze running task are presented, thereby demonstrating the value of goal related feedback within the overall network.

Fast training of self organizing maps for the visual exploration of molecular compounds

Visual exploration of scientific data in life science area is a growing research field due to the large amount of available data. The Kohonen’s Self Organizing Map (SOM) is a widely used tool for visualization of multidimensional data. In this paper we present a fast learning algorithm for SOMs that uses a simulated annealing method to adapt the learning parameters. The algorithm has been adopted in a data analysis framework for the generation of similarity maps. Such maps provide an effective tool for the visual exploration of large and multi-dimensional input spaces. The approach has been applied to data generated during the High Throughput Screening of molecular compounds; the generated maps allow a visual exploration of molecules with similar topological properties. The experimental analysis on real world data from the National Cancer Institute shows the speed up of the proposed SOM training process in comparison to a traditional approach. The resulting visual landscape groups molecules with similar chemical properties in densely connected regions.

Self-organising neural networks for adaptive control

Self-organizing neural networks have been implemented in a wide range of application areas such as speech processing, image processing, optimization and robotics. Recent variations to the basic model proposed by the authors enable it to order state space using a subset of the input vector and to apply a local adaptation procedure that does not rely on a predefined test duration limit. Both these variations have been incorporated into a new feature map architecture that forms an integral part of an Hybrid Learning System (HLS) based on a genetic-based classifier system. Problems are represented within HLS as objects characterized by environmental features. Objects controlled by the system have preset targets set against a subset of their features. The system's objective is to achieve these targets by evolving a behavioural repertoire that efficiently explores and exploits the problem environment. Feature maps encode two types of knowledge within HLS — long-term memory traces of useful regularities within the environment and the classifier performance data calibrated against an object's feature states and targets. Self-organization of these networks constitutes non-genetic-based (experience-driven) learning within HLS. This paper presents a description of the HLS architecture and an analysis of the modified feature map implementing associative memory. Initial results are presented that demonstrate the behaviour of the system on a simple control task.