An automatic diabetes diagnosis system based on LDA-Wavelet Support Vector Machine Classifier

In this paper, an automatic diagnosis system for diabetes on Linear Discriminant Analysis (LDA) and Morlet Wavelet Support Vector Machine Classifier: LDA–MWSVM is introduced. The structure of this automatic system based on LDA-MWSVM for the diagnosis of diabetes is composed of three stages: The feature extraction and feature reduction stage by using the Linear Discriminant Analysis (LDA) method and the classification stage by using Morlet Wavelet Support Vector Machine (MWSVM) classifier stage. The Linear Discriminant Analysis (LDA) is used to separate features variables between healthy and patient (diabetes) data in the first stage. The healthy and patient (diabetes) features obtained in the first stage are given to inputs of the MWSVM classifier in the second stage. Finally, in the third stage, the correct diagnosis performance of this automatic system based on LDA–MWSVM for the diagnosis of diabetes is calculated by using sensitivity and specificity analysis, classification accuracy, and confusion matrix, respectively. The classification accuracy of this system was obtained at about 89.74%.     

Filling of very deep, wide trenches by BenzoCycloButene polymer

A process for deep trench filling by BenzoCycloButene (BCB) polymer is explored. Deep trenches with 100-μm depth and different aspect ratios from 1.4 to 20 have been successfully filled by BCB. Besides, chemical mechanical polishing (CMP) of BCB is studied with the main goals of smoothing surface topography of substrate after BCB filling and removing excess BCB coating which may be necessary in some applications. Removal rate for BCB, V _RR, of about 0.24 μm/min has been achieved for hard cured BCB films using acid slurry. After CMP, the BCB layer showed a roughness of about 1.36 nm (Rq, measured by atomic force microscopy, AFM).     

Supporting the consumption and co-authoring of locative media experiences for a rural village community: design and field trial evaluation of the SHARC2.0 framework

Locative Media Experiences (LMEs) have significant potential in enabling visitors to engage with the places that they visit through an appreciation of local history. For example, a visitor to Berlin that is exploring remnants of the Berlin Wall may be encouraged to appreciate (or in part experience) the falling of the Berlin wall by consuming multimedia directly related to her current location such as listening to audio recordings of the assembled crowds on 10th November 1989. However, despite the growing popularity of enabling technologies (such as GPS-equipped smart phones and tablets), the availability of tools that support the authoring of LMEs is limited. In addition, mobile apps that support the consumption of LMEs typically adopt an approach that precludes users from being able to respond with their own multimedia contributions. In this article we describe the design and evaluation of the SHARC2.0 framework that has been developed as part of our long-term and participatory engagement with the rural village of Wray in the north of England. Wray has very limited cellular data coverage which has placed a requirement on the framework and associated tools to operate without reliance on network connectivity. A field study is presented which featured a LME relating to Wray’s local history and which contained multimedia content contributed by members of the community including historic photos (taken from an existing ‘Digital Noticeboard’ system), audio-clips (from a local historian and village residents) and video (contributed during a design workshop). The novelty of our approach relates to the ability of multiple authors to contribute to a LME in-situ, and the utilisation of personal cloud storage for storing the contents associated with a multi-authored LME.

     

Discrimination of quarry blasts and earthquakes in the vicinity of Istanbul using soft computing techniques

The purpose of this article is to demonstrate the use of feedforward neural networks (FFNNs), adaptive neural fuzzy inference systems (ANFIS), and probabilistic neural networks (PNNs) to discriminate between earthquakes and quarry blasts in Istanbul and vicinity (the Marmara region). The tectonically active Marmara region is affected by the Thrace-Eski?ehir fault zone and especially the North Anatolian fault zone (NAFZ). Local MARNET stations, which were established in 1976 and are operated by the Kandilli Observatory and Earthquake Research Institute (KOERI), record not only earthquakes that occur in the region, but also quarry blasts. There are a few quarry-blasting areas in the Gaziosmanpa?a, Çatalca, Ömerli, and Hereke regions. Analytical methods were applied to a set of 175 seismic events (2001-2004) recorded by the stations of the local seismic network (ISK, HRT, and CTT stations) operated by the KOERI National Earthquake Monitoring Center (NEMC). Out of a total of 175 records, 148 are related to quarry blasts and 27 to earthquakes. The data sets were divided into training and testing sets for each region. In all the models developed, the input vectors consist of the peak amplitude ratio (S/P ratio) and the complexity value, and the output is a determination of either earthquake or quarry blast. The success of the developed models on regional test data varies between 97.67% and 100%.     

Stability radius of implicit dynamic equations with constant coefficients on time scales

This paper deals with the stability radii of implicit dynamic equations on time scales when the structured perturbations act on both the coefficient of derivative and the right-hand side. Formulas of the stability radii are derived as a unification and generalization of some previous results. A special case where the real stability radius and the complex stability radius are equal is studied. Examples are derived to illustrate results.     

Numerical analysis of coronary artery bypass grafts: An over view

Arterial bypass grafts tend to fail after some years due to the development of intimal thickening (restenosis). Non-uniform hemodynamics following a bypass operation contributes to restenosis and bypass failure can occur due to the focal development of anastomotic intimal hyperplasia. Additionally, surgical injury aggravated by compliance mismatch between the graft and artery has been suggested as an initiating factor for progress of wall thickening along the suture line Vascular grafts that are small in diameter tend to occlude rapidly. Computational fluid dynamics (CFD) methods have been effectively used to simulate the physical and geometrical parameters characterizing the hemodynamics of various arteries and bypass configurations. The effects of such changes on the pressure and flow characteristics as well as the wall shear stress during a cardiac cycle can be simulated. Recently, utilization of fluid and structure interactions have been used to determine fluid flow parameters and structure forces including stress and strains relationships under steady and transient conditions. In parallel to this, experimental diagnostics techniques such as Laser Doppler Anemometry, Particle Image Velocimetry, Doppler Guide wire and Magnetic Resonance Imaging have been used to provide essential information and to validate the numerical results. Moreover, clinical imaging techniques such as magnetic resonance or computed tomography have assisted considerably in gaining a detailed patient-specific picture of the blood flow and structure dynamics. This paper gives a review of recent numerical investigations of various configurations of coronary artery bypass grafts (CABG). In addition, the paper ends with a summary of the findings and the future directions.     

Modeling and experimental investigation for electrolytic corrosion prevention in high frequency micro EDM using deionized water

The characteristics of the prevention of electrolytic corrosion during micro electrical discharge machining (EDM) using deionized water and high frequency bipolar pulse were investigated. Electrolytic corrosion during micro EDM using deionized water was analyzed using an equivalent electrical circuit based on the electrical double layer theory. Based on the analysis and experimental verification, a narrow positive pulse duration should be provided to the workpiece to prevent corrosion. A negative voltage with zero average applied voltage (V_{avg, app}) is also essential for this purpose. If V_{avg, app} is positive or negative, electrolytic corrosion occurs on the workpiece or tool, respectively. Micro holes and 3D structures without corrosion were successfully fabricated using a high frequency bipolar pulse with a pulse duration of 0.2?μs and a period of 1?μs, as well as V_{avg, app}?=?0?V.     

Fractal analysis of pressure fluctuations in a three phase bubble column reactor operating at low pressure

Pressure fluctuations in a three phase bubble column reactor operating at relatively low pressure (92 KPa) have been analyzed by adopting the spectral and fractal analyses to get the engineering informations for the on-line control and fault diagnosis of the reactors. The mean value, standard deviation, skewness and kurtosis of the pressure fluctuations have been obtained. The local fractal dimension has been determined from the Pox diagram obtained by means of the rescaled range analysis of the pressure fluctuations based on the fractional Brownian motion. The local fractal dimension of pressure fluctuations has increased and thus the pressure fluctuation signals have become less persistent and irregular, with increases in the gas flow rate reaction temperature, particle size and solid content in the slurry phase. The local fractal dimension has been well correlated in terms of the operating variables.