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%.

Subsidence activity maps derived from DInSAR data: Orihuela case study

A new methodology is proposed to produce subsidence activity maps based on the geostatistical analysis of persistent scatterer interferometry (PSI) data. PSI displacement measurements are interpolated based on conditional Sequential Gaussian Simulation (SGS) to calculate multiple equiprobable realizations of subsidence. The result from this process is a series of interpolated subsidence values, with an estimation of the spatial variability and a confidence level on the interpolation. These maps complement the PSI displacement map, improving the identification of wide subsiding areas at a regional scale. At a local scale, they can be used to identify buildings susceptible to suffer subsidence related damages. In order to do so, it is necessary to calculate the maximum differential settlement and the maximum angular distortion for each building of the study area. Based on PSI-derived parameters those buildings in which the serviceability limit state has been exceeded, and where in situ forensic analysis should be made, can be automatically identified. This methodology has been tested in the city of Orihuela (SE Spain) for the study of historical buildings damaged during the last two decades by subsidence due to aquifer overexploitation. The qualitative evaluation of the results from the methodology carried out in buildings where damages have been reported shows a success rate of 100%.

Orbscan Topography in Primary Open-Angle Glaucoma

Purpose: To compare anterior and posterior corneal curvatures between eyes with primary open-angle glaucoma (POAG) and healthy eyes. Methods: This is a prospective, cross-sectional, observer-masked study. A total of 138 white subjects (one eye per patient) were consecutively recruited; 69 eyes had POAG (study group), and the other 69 comprised a group of healthy control eyes matched for age and central corneal pachymetry with the study ones. Exclusion criteria included any corneal or ocular inflammatory disease, previous ocular surgery, or treatment with carbonic anhydrase inhibitors. The same masked observer performed Goldmann applanation tonometry, ultrasound pachymetry, and Orbscan II topography in all cases. Central corneal thickness, intraocular pressure, and anterior and posterior topographic elevation maps were analyzed and compared between both groups. Results: Patients with POAG had greater forward shifting of the posterior corneal surface than that in healthy control eyes (p < 0.01). Significant differences in anterior corneal elevation between controls and POAG eyes were also found (p < 0.01). Conclusions: Primary open-angle glaucoma eyes have a higher elevation of the posterior corneal surface than that in central corneal thickness–matched nonglaucomatous eyes.

Using causal maps to support ex-post assessment of social impacts of dams

This paper presents the results of an ex-post assessment of two important dams in Brazil. The study follows the principles of Social Impact Management, which offer a suitable framework for analyzing the complex social transformations triggered by hydroelectric dams. In the implementation of this approach, participative causal maps were used to identify the ex-post social impacts of the Porto Primavera and Rosana dams on the community of Porto Rico, located along the High Paraná River. We found that in the operation of dams there are intermediate causes of a political nature, stemming from decisions based on values and interests not determined by neutral, exclusively technical reasons; and this insight opens up an area of action for managing the negative impacts of dams.

Causal Maps and Indirect Influences Analysis in the Diagnosis of Second-Home Tourism Impacts

This paper proposes a method for diagnosing the impacts of second-home tourism and illustrates it for a Mediterranean Spanish destination. This method proposes the application of network analysis software to the analysis of causal maps in order to create a causal network model based on stakeholder-identified impacts. The main innovation is the analysis of indirect relations in causal maps for the identification of the most influential nodes in the model. The results show that the most influential nodes are of a political nature, which contradicts previous diagnoses identifying technical planning as the ultimate cause of problems.

Clinical utility of ocular residual astigmatism and topographic disparity vector indexes in subclinical and clinical keratoconus

Purpose. We aimed to characterize the distribution of the vector parameters ocular residual astigmatism (ORA) and topography disparity (TD) in a sample of clinical and subclinical keratoconus eyes, and to evaluate their diagnostic value to discriminate between these conditions and healthy corneas. Methods. This study comprised a total of 43 keratoconic eyes (27 patients, 17–73 years) (keratoconus group), 11 subclinical keratoconus eyes (eight patients, 11–54 years) (subclinical keratoconus group) and 101 healthy eyes (101 patients, 15–64 years) (control group). In all cases, a complete corneal analysis was performed using a Scheimpflug photography-based topography system. Anterior corneal topographic data was imported from it to the iASSORT software (ASSORT Pty. Ltd), which allowed the calculation of ORA and TD. Results. Mean magnitude of the ORA was 3.23 ± 2.38, 1.16 ± 0.50 and 0.79 ± 0.43 D in the keratoconus, subclinical keratoconus and control groups, respectively (p < 0.001). Mean magnitude of the TD was 9.04 ± 8.08, 2.69 ± 2.42 and 0.89 ± 0.50 D in the keratoconus, subclinical keratoconus and control groups, respectively (p < 0.001). Good diagnostic performance of ORA (cutoff point: 1.21 D, sensitivity 83.7 %, specificity 87.1 %) and TD (cutoff point: 1.64 D, sensitivity 93.3 %, specificity 92.1 %) was found for the detection of keratoconus. The diagnostic ability of these parameters for the detection of subclinical keratoconus was more limited (ORA: cutoff 1.17 D, sensitivity 60.0 %, specificity 84.2 %; TD: cutoff 1.29 D, sensitivity 80.0 %, specificity 80.2 %). Conclusion. The vector parameters ORA and TD are able to discriminate with good levels of precision between keratoconus and healthy corneas. For the detection of subclinical keratoconus, only TD seems to be valid.

Accounts related to maps and pamphlets, 1809-1823

This folder contains eight handwritten account statements and notes primarily related to the collection of subscriptions for Croswell's maps and pamphlets, as well as the disbursement and storage of his printed maps and pamphlets.

Providence, Rhode Island, -- Sewers, 1884 (Raster Image)

This layer is a georeferenced raster image of the historic paper map entitled: Topographical map of the city of Providence showing proposed sewerage system together with sewers already constructed, compiled in the City Engineers Office. It was published Oct. 24, 1884 by the City Engineers Office, Sewer Dept. Scale [ca. 1:20,000]. Covers the city of Providence, Rhode Island and portions of the surrounding towns/cities. The image inside the map neatline is georeferenced to the surface of the earth and fit to the Rhode Island State Plane Coordinate System (Feet) (FIPS 3800). All map collar and inset information is also available as part of the raster image, including any inset maps, profiles, statistical tables, directories, text, illustrations, or other information associated with the principal map. This map shows features such as roads, railroads, topography, drainage, selected buildings, constructed and proposed sewer lines, town boundaries, city districts, and more. Relief shown by contours. This layer is part of a selection of digitally scanned and georeferenced historic maps of New England from the Harvard Map Collection. These maps typically portray both natural and manmade features. The selection represents a range of regions, originators, ground condition dates, scales, and map purposes.

Lower Manhattan, New York, N.Y. 1767 (Raster Image)

This layer is a georeferenced raster image of the historic paper map entitled: To His Excellency Sr. Henry Moore, Bart., captain general and governour in chief in & over the province of New York & the territories depending thereon in America, chancellor & vice admiral of the same, this plan of the city of New York is most humbly inscribed, by His Excellency's most obedient servant, Bern'd Ratzen [sic], lieut't in the 60th Reg't ; T. Kitchin, sculp't. It was published ca. 1769. Scale [ca. 1:4,800]. Covers Manhattan below 14th St. and a portion of Brooklyn. "Survey'd in 1767." The image inside the map neatline is georeferenced to the surface of the earth and fit to the Universal Transverse Mercator (UTM) Zone 18N NAD83 projection. All map collar and inset information is also available as part of the raster image, including any inset maps, profiles, statistical tables, directories, text, illustrations, index maps, legends, or other information associated with the principal map. This map shows features such as roads, drainage, ground cover, city wards, selected public buildings and names of property owners, city wards, and more. Relief is shown by hachures and shading. Includes index of "References" and coat-of-arms. This layer is part of a selection of digitally scanned and georeferenced historic maps from The Harvard Map Collection as part of the Imaging the Urban Environment project. Maps selected for this project represent major urban areas and cities of the world, at various time periods. These maps typically portray both natural and manmade features at a large scale. The selection represents a range of regions, originators, ground condition dates, scales, and purposes.

Pittsburgh, Pennsylvania, 1904 (Raster Image)

This layer is a georeferenced raster image of the historic, topographic paper map entitled: Pennsylvania, Pittsburgh quadrangle, Department of the Interior; U.S. Geological Survey; State of Pennsylvania represented by the Department of Internal Affairs Topographic and Geological Survey; H. W. Wilson geographer; Frank Sutton and Robt. D. Commin, in charge of section; topography by E.B. Clark, J.H. Wheat, A.C. Roberts and E.G. Hamilton; assistants J.S.B. Daingerfield and B.B. Alexander; and various town, city, and park surveys; control by D.H. Baldwin, W.R. Harper and R.W. Berry; river shoreline by U.S. Army Engineers. It was published by the U.S. Geoloogical Survey. Ed. of 1907, reprinted in 1928. Surveyed in 1903-1904. Scale 1:62,500. The image inside the map neatline is georeferenced to the surface of the earth and fit to the Pennsylvania South State Plane NAD 1927 coordinate projection (in Feet) (Fipszone 3702). All map collar and inset information is also available as part of the raster image, including any inset maps, profiles, statistical tables, directories, text, illustrations, index maps, legends, or other information associated with the principal map. This is a typical topographic map portraying both natural and manmade features. It shows and names works of nature, such as mountains, valleys, lakes, rivers, vegetation, etc. It also identify the principal works of humans, such as roads, railroads, boundaries, transmission lines, major buildings, etc. Relief is shown by spot heighs and with standard contour intervals of 20 feet. This layer is part of a selection of digitally scanned and georeferenced historic maps from The Harvard Map Collection as part of the Imaging the Urban Environment project. Maps selected for this project represent major urban areas and cities of the world, at various time periods. These maps typically portray both natural and manmade features at a large scale. The selection represents a range of regions, originators, ground condition dates, scales, and purposes.

Pittsburgh and Vicinity, Pennsylvania, 1962 (Raster Image)

This layer is a georeferenced raster image of the historic, topographic paper map entitled: Pittsburgh and vicinity, Pennsylvania, mapped, edited, and published by the Geological Survey. It was published by The Survey in 1962. Scale 1:24,000. Compiled from 1:24,000-scale maps of New Kensington West, Glenshaw, Emsworth, Ambridge, Oakdale, Pittsburgh West, Pittsburgh East, Braddock McKeesport, Glassport, Bridgeville, and Canonsburg 1960 7.5 minute quadrangles. The image inside the map neatline is georeferenced to the surface of the earth and fit to the Pennsylvania South State Plane NAD 1927 coordinate projection (in Feet) (Fipszone 3702). All map collar and inset information is also available as part of the raster image, including any inset maps, profiles, statistical tables, directories, text, illustrations, index maps, legends, or other information associated with the principal map. This is a typical topographic map portraying both natural and manmade features. It shows and names works of nature, such as mountains, valleys, lakes, rivers, vegetation, etc. It also identify the principal works of humans, such as roads, railroads, boundaries, transmission lines, major buildings, etc. Relief is shown with spot heights and standard contour intervals of 20 feet. This layer is part of a selection of digitally scanned and georeferenced historic maps from The Harvard Map Collection as part of the Imaging the Urban Environment project. Maps selected for this project represent major urban areas and cities of the world, at various time periods. These maps typically portray both natural and manmade features at a large scale. The selection represents a range of regions, originators, ground condition dates, scales, and purposes.

Washington, D.C., 1855 (Raster Image)

This layer is a georeferenced raster image of the historic paper map entitled: Colton's Georgetown and the city of Washington : the capital of the United States of America. It was published by J.H. Colton in 1855. Scale [ca. 1:25,750]. The image inside the map neatline is georeferenced to the surface of the earth and fit to the Maryland State Plane Coordinate System Meters NAD83 (Fipszone 1900). All map collar and inset information is also available as part of the raster image, including any inset maps, profiles, statistical tables, directories, text, illustrations, index maps, legends, or other information associated with the principal map. This map shows features such as roads, drainage, block numbers, city wards, built-up areas, selected government buildings, parks, and more. Includes views: Smithsonian Institution -- The Capitol -- Washington Monument. This layer is part of a selection of digitally scanned and georeferenced historic maps from The Harvard Map Collection as part of the Imaging the Urban Environment project. Maps selected for this project represent major urban areas and cities of the world, at various time periods. These maps typically portray both natural and manmade features at a large scale. The selection represents a range of regions, originators, ground condition dates, scales, and purposes.

Washington, D.C., 1884 (Raster Image)

This layer is a georeferenced raster image of the historic paper map entitled: Topographical map of the District of Columbia and a portion of Virginia, compiled under the direction of Major G.J. Lydecker, Corps of Engineers, Engineer Commissioner D.C., by Captain F.V. Greene, Corps of Engineers ; drawn by W.T.O. Bruff. It was published in 1884. Scale [1:15,840]. The image inside the map neatline is georeferenced to the surface of the earth and fit to the Maryland State Plane Coordinate System Meters NAD83 (Fipszone 1900). All map collar and inset information is also available as part of the raster image, including any inset maps, profiles, statistical tables, directories, text, illustrations, index maps, legends, or other information associated with the principal map. This map shows features such as roads, railroads, drainage, selected public buildings, selected private residences and names of landowners, built-up areas, parks, and more. Relief shown by contours. Depths shown by soundings. Includes source materials note. This layer is part of a selection of digitally scanned and georeferenced historic maps from The Harvard Map Collection as part of the Imaging the Urban Environment project. Maps selected for this project represent major urban areas and cities of the world, at various time periods. These maps typically portray both natural and manmade features at a large scale. The selection represents a range of regions, originators, ground condition dates, scales, and purposes.