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%.

Numerical and experimental investigation of structural stiffness influence on ratcheting convection cell in granular soils under cyclic loading

Lateral cyclic loaded structures in granular soils can lead to an accumulation of irreversible strains by changing their mechanical response (densification) and forming a closed convective cell in the upper layer of the bedding. In the present thesis the convective cell dimension, formation and grain migration inside this closed volume have been studied and presented in relation to structural stiffness and different loads. This relation was experimentally investigated by applying a cyclic lateral force to a scaled flexible vertical element embedded in dry granular soil. The model was monitored with a camera in order to derive the displacement field by means of the PIV technique. Modelling large soil deformation turns out to be difficult, using mesh-based methods. Consequently, a mesh-free approach (DEM) was chosen in order to investigate the granular flow with the aim of extracting interesting micromechanical information. In both the numerical and experimental analyses the effect of different loading magnitudes and different dimensions of the vertical element were considered. The main results regarded the different development, shape and dimensions of the convection cell and the surface settlements. Moreover, the Discrete Element Method has proven to give satisfactory results in the modelling of large deformation phenomena such as the ratcheting convective cell.

Indications for treatment in adults with tricuspid valve dysfunction due to a congential cardiac anomaly

The tricuspid valve is frequently affected in adults with congenital heart disease (CHD). Disease of this valve can occur primarily or develop secondary to changes in the right ventricle caused by other defects. Quantitative echocardiographic assessment of tricuspid regurgitation is essential to assess its cause and prognosis. Treatment options vary depending on the underlying defect and right ventricular function. Surgical management of tricuspid valve disease is complex and evolving.

Composition of basalts from the north part of the Bougault anomaly, Mid-Atlantic Ridge 15°N

A quantitative model of development of magmatic and ore-magmatic systems under crests of mid-ocean ridges is constructed. Correct physical models of melting zone formation in approximation to active spreading, non-stationary dynamics of magma intrusion from a center of generation, filling of magma chambers of various shapes, feeding of fissure-type volcanoes, and retrograde boiling of melts during solidification of intrusive bodies beneath axial zones of spreading in crests of ridges are proposed. Physicochemical and mathematical theories of disintegration of multi-component solutions, growth of liquational drops of ore melts, and sublimation of components from magmatic gases are elaborated. Methods for constructing physically correct models of heat and mass transfer in heterophase media are devised. Modeling of development of magmatic and ore-magmatic systems on the basis of the Usov-Kuznetsov facies method and the Pospelov system approach are advanced. For quantitative models numerical circuits are developed and numerical experiments are carried out.

(Table T2) Remanent anomaly and Koenigsberger ratio of ODP holes

Magnetic field strength and magnetic susceptibility were logged with the geological high-resolution magnetic tool (GHMT) at three of the holes drilled during Ocean Drilling Program Leg 178 to the west of the Antarctic Peninsula. Polarity stratigraphies derived from the GHMT logs bear close resemblance to the polarities determined from core paleomagnetism at two of the holes and were used for magnetostratigraphic dating, especially in intervals where no core was recovered. Polarity is determined in the following way. First, the susceptibility log is used to determine the induced magnetization of the sediment. Then the background field, the field of the metal drill pipe, and the field anomaly of the sediment's induced magnetization are removed from the measured total field to leave the downhole anomaly of the sediment's remanent magnetization. The sign (positive or negative) of this anomaly gave a good polarity stratigraphy for Holes 1095B and 1096C, which are located in sediment drifts. A further step, correlation analysis, is based on the fact that in an interval of normal polarity sediment the remanent anomaly will correlate with the induced anomaly, whereas in reversed polarity sediment they will anticorrelate. The magnetite-rich, fine-grained sediments found in the two holes drilled into the sediment drift have a ratio of remanent to induced magnetization (the Koenigsberger ratio) of ~1. In contrast, the coarser-grained diamict sediments on the shelf have a Koenigsberger ratio of ~0.2, and extracting the remanent part of the downhole anomaly is much more difficult. By the comparison of core and log results, we can assess the viability of the GHMT polarities in detail, what proportion of the overprint in the cores is imparted by the coring process, and whether any paleointensity information is extractable from the GHMT logs.

Results of calculated surface air temperature anomaly of COSMOS Pliocene experiment 2 in NetCDF format

In this manuscript we describe the experimental procedure employed at the Alfred Wegener Institute in Germany in the preparation of the simulations for the Pliocene Model Intercomparison Project (PlioMIP). We present a description of the utilized Community Earth System Models (COSMOS, version: COSMOS-landveg r2413, 2009) and document the procedures that we applied to transfer the Pliocene Research, Interpretation and Synoptic Mapping (PRISM) Project mid-Pliocene reconstruction into model forcing fields. The model setup and spin-up procedure are described for both the paleo- and preindustrial (PI) time slices of PlioMIP experiments 1 and 2, and general results that depict the performance of our model setup for mid-Pliocene conditions are presented. The mid-Pliocene, as simulated with our COSMOS setup and PRISM boundary conditions, is both warmer and wetter in the global mean than the PI. The globally averaged annual mean surface air temperature in the mid-Pliocene standalone atmosphere (fully coupled atmosphere-ocean) simulation is 17.35 °C (17.82 °C), which implies a warming of 2.23 °C (3.40 °C) relative to the respective PI control simulation.

Turbulent forced convection heat transfer in circular tubes containing sodium hydroxide.

"ORNL-1370."

Variational and Lagrangian thermodynamics of thermal convection-- fundamental shortcomings of the heat-transfer coefficient.

Mode of access: Internet.

Experimental results of forced convection boiling potassium heat transfer and pressure drop tests /

"Contract AT(30-1)-2789."

Forced convection boiling potassium experiments /

Work performed at CANEL.

Model laws for the transition from nucleate to film boiling with forced convection /

"Report title: Theoretical investigations of the transition from bubble boiling to film boiling at forced convection"--p. v.

Recent developments connected with the hypersonic facility of the Polytechnic Institute of Brooklyn. Pt. I: Tests of the compression heater. Pt. II: Aspects of the design, construction and installation of a multiple-outlet collector for the convection heater.

Mode of access: Internet.

Free thermal convection near the linear source of heat,

Photocopy. Washington? Clearinghouse for Federal Scientific and Technical Information of the U. S. Dept. of Commerce, 1965.