Simultaneous feature selection and feature weighting using Hybrid Tabu Search/K-nearest neighbor classifier

Feature selection and feature weighting are useful techniques for improving the classification accuracy of K-nearest-neighbor (K-NN) rule. The term feature selection refers to algorithms that select the best subset of the input feature set. In feature weighting, each feature is multiplied by a weight value proportional to the ability of the feature to distinguish pattern classes. In this paper, a novel hybrid approach is proposed for simultaneous feature selection and feature weighting of K-NN rule based on Tabu Search (TS) heuristic. The proposed TS heuristic in combination with K-NN classifier is compared with several classifiers on various available data sets. The results have indicated a significant improvement in the performance in classification accuracy. The proposed TS heuristic is also compared with various feature selection algorithms. Experiments performed revealed that the proposed hybrid TS heuristic is superior to both simple TS and sequential search algorithms. We also present results for the classification of prostate cancer using multispectral images, an important problem in biomedicine.

Characterization and Modeling of the Indoor Radio Channel at 868 MHz for a Mobile Bodyworn Wireless Personal Area Network

This letter reports the statistical characterization and modeling of the indoor radio channel for a mobile wireless personal area network operating at 868 MHz. Line of sight (LOS) and non-LOS conditions were considered for three environments: anechoic chamber, open office area and hallway. Overall, the Nakagami-m cdf best described fading for bodyworn operation in 60% of all measured channels in anechoic chamber and open office area environments. The Nakagami distribution was also found to provide a good description of Rician distributed channels which predominated in the hallway. Multipath played an important role in channel statistics with the mean recorded m value being reduced from 7.8 in the anechoic chamber to 1.3 in both the open office area and hallway.

Structural and chemical embrittlement of grain boundaries by impurities: A general theory and first-principles calculations for copper

First-principles calculations of the Sigma 5(310)[001] symmetric tilt grain boundary in Cu with Bi, Na, and Ag substitutional impurities provide evidence that in the phenomenon of Bi embrittlement of Cu grain boundaries electronic effects do not play a major role; on the contrary, the embrittlement is mostly a structural or "size" effect. Na is predicted to be nearly as good an embrittler as Bi, whereas Ag does not embrittle the boundary in agreement with experiment. While we reject the prevailing view that "electronic" effects (i.e., charge transfer) are responsible for embrittlement, we do not exclude the role of chemistry. However, numerical results show a striking equivalence between the alkali metal Na and the semimetal Bi, small differences being accounted for by their contrasting "size" and "softness" (defined here). In order to separate structural and chemical effects unambiguously if not uniquely, we model the embrittlement process by taking the system of grain boundary and free surfaces through a sequence of precisely defined gedanken processes; each of these representing a putative mechanism. We thereby identify three mechanisms of embrittlement by substitutional impurities, two of which survive in the case of embrittlement or cohesion enhancement by interstitials. Two of the three are purely structural and the third contains both structural and chemical elements that by their very nature cannot be further unraveled. We are able to take the systems we study through each of these stages by explicit computer simulations and assess the contribution of each to the net reduction in intergranular cohesion. The conclusion we reach is that embrittlement by both Bi and Na is almost exclusively structural in origin; that is, the embrittlement is a size effect.

System oriented neural networks - Problem formulation, methodology and application

A novel methodology is proposed for the development of neural network models for complex engineering systems exhibiting nonlinearity. This method performs neural network modeling by first establishing some fundamental nonlinear functions from a priori engineering knowledge, which are then constructed and coded into appropriate chromosome representations. Given a suitable fitness function, using evolutionary approaches such as genetic algorithms, a population of chromosomes evolves for a certain number of generations to finally produce a neural network model best fitting the system data. The objective is to improve the transparency of the neural networks, i.e. to produce physically meaningful

Host-based P2P flow identification and use in real-time

Data identification is a key task for any Internet Service Provider (ISP) or network administrator. As port fluctuation and encryption become more common in P2P traffic wishing to avoid identification, new strategies must be developed to detect and classify such flows. This paper introduces a new method of separating P2P and standard web traffic that can be applied as part of a data mining process, based on the activity of the hosts on the network. Unlike other research, our method is aimed at classifying individual flows rather than just identifying P2P hosts or ports. Heuristics are analysed and a classification system proposed. The accuracy of the system is then tested using real network traffic from a core internet router showing over 99% accuracy in some cases. We expand on this proposed strategy to investigate its application to real-time, early classification problems. New proposals are made and the results of real-time experiments compared to those obtained in the data mining research. To the best of our knowledge this is the first research to use host based flow identification to determine a flows application within the early stages of the connection.

Software project initiation and planning – an empirical study

This study describes a study of 14 software companies, on how they initiate and pre-plan software projects. The aim was to obtain an indication of the range of planning activities carried out. The study, using a convenience sample, was carried out using structured interviews, with questions about early software project planning activities. The study offers evidence that an iterative and incremental development process presents extra difficulties in the case of fixed-contract projects. The authors also found evidence that feasibility studies were common, but generally informal in nature. Documentation of the planning process, especially for project scoping, was variable. For incremental and iterative development projects, an upfront decision on software architecture was shown to be preferred over allowing the architecture to just ‘emerge’. There is also evidence that risk management is recognised but often performed incompletely. Finally appropriate future research arising from the study is described.

Simple and accurate analytical model of planar grids and high-impedance surfaces, comprising metal strips or patches

Simple analytical formulas are introduced for the grid impedance of electrically dense arrays of square patches and for the surface impedance of high-impedance surfaces based on the dense arrays of metal strips or square patches over ground planes. Emphasis is on the oblique-incidence excitation. The approach is based on the known analytical models for strip grids combined with the approximate Babinet principle for planar grids located at a dielectric interface. Analytical expressions for the surface impedance and reflection coefficient resulting from our analysis are thoroughly verified by full-wave simulations and compared with available data in open literature for particular cases. The results can be used in the design of various antennas and microwave or millimeter wave devices which use artificial impedance surfaces and artificial magnetic conductors (reflect-array antennas, tunable phase shifters, etc.), as well as for the derivation of accurate higher-order impedance boundary conditions for artificial (high-) impedance surfaces. As an example, the propagation properties of surface waves along the high-impedance surfaces are studied.