Classification of Parkinson’s Disease using MultiPass Lvq,Logistic Model Tree,K-Star for Audio Data set : Classification of Parkinson Disease using Audio Dataset

Parkinson's disease (PD) is a degenerative illness whose cardinal symptoms include rigidity, tremor, and slowness of movement. In addition to its widely recognized effects PD can have a profound effect on speech and voice.The speech symptoms most commonly demonstrated by patients with PD are reduced vocal loudness, monopitch, disruptions of voice quality, and abnormally fast rate of speech. This cluster of speech symptoms is often termed Hypokinetic Dysarthria.The disease can be difficult to diagnose accurately, especially in its early stages, due to this reason, automatic techniques based on Artificial Intelligence should increase the diagnosing accuracy and to help the doctors make better decisions. The aim of the thesis work is to predict the PD based on the audio files collected from various patients.Audio files are preprocessed in order to attain the features.The preprocessed data contains 23 attributes and 195 instances. On an average there are six voice recordings per person, By using data compression technique such as Discrete Cosine Transform (DCT) number of instances can be minimized, after data compression, attribute selection is done using several WEKA build in methods such as ChiSquared, GainRatio, Infogain after identifying the important attributes, we evaluate attributes one by one by using stepwise regression.Based on the selected attributes we process in WEKA by using cost sensitive classifier with various algorithms like MultiPass LVQ, Logistic Model Tree(LMT), K-Star.The classified results shows on an average 80%.By using this features 95% approximate classification of PD is acheived.This shows that using the audio dataset, PD could be predicted with a higher level of accuracy.

Color Segmentation using LVQ-Learning Vector Quantization

This thesis aims to present a color segmentation approach for traffic sign recognition based on LVQ neural networks. The RGB images were converted into HSV color space, and segmented using LVQ depending on the hue and saturation values of each pixel in the HSV color space. LVQ neural network was used to segment red, blue and yellow colors on the road and traffic signs to detect and recognize them. LVQ was effectively applied to 536 sampled images taken from different countries in different conditions with 89% accuracy and the execution time of each image among 31 images was calculated in between 0.726sec to 0.844sec. The method was tested in different environmental conditions and LVQ showed its capacity to reasonably segment color despite remarkable illumination differences. The results showed high robustness.

Search for the Standard Model Higgs Boson in the H -> WW -> lvq '(q)over-bar Decay Channel

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Thermal performance of multipass parallel and counter-cross-flow heat exchangers

A thorough study of the thermal performance of multipass parallel cross-flow and counter-cross-flow heat exchangers has been carried out by applying a new numerical procedure. According to this procedure, the heat exchanger is discretized into small elements following the tube-side fluid circuits. Each element is itself a one-pass mixed-unmixed cross-flow heat exchanger. Simulated results have been validated through comparisons to results from analytical solutions for one- to four-pass, parallel cross-flow and counter-cross-flow arrangements. Very accurate results have been obtained over wide ranges of NTU (number of transfer units) and C* (heat capacity rate ratio) values. New effectiveness data for the aforementioned configurations and a higher number of tube passes is presented along with data for a complex flow configuration proposed elsewhere. The proposed procedure constitutes a useful research tool both for theoretical and experimental studies of cross-flow heat exchangers thermal performance.

Mult-class differentiation of cannabis seedlings in a forensic context

This article presents an experimental study about the classification ability of several classifiers for multi-classclassification of cannabis seedlings. As the cultivation of drug type cannabis is forbidden in Switzerland lawenforcement authorities regularly ask forensic laboratories to determinate the chemotype of a seized cannabisplant and then to conclude if the plantation is legal or not. This classification is mainly performed when theplant is mature as required by the EU official protocol and then the classification of cannabis seedlings is a timeconsuming and costly procedure. A previous study made by the authors has investigated this problematic [1]and showed that it is possible to differentiate between drug type (illegal) and fibre type (legal) cannabis at anearly stage of growth using gas chromatography interfaced with mass spectrometry (GC-MS) based on therelative proportions of eight major leaf compounds. The aims of the present work are on one hand to continueformer work and to optimize the methodology for the discrimination of drug- and fibre type cannabisdeveloped in the previous study and on the other hand to investigate the possibility to predict illegal cannabisvarieties. Seven classifiers for differentiating between cannabis seedlings are evaluated in this paper, namelyLinear Discriminant Analysis (LDA), Partial Least Squares Discriminant Analysis (PLS-DA), Nearest NeighbourClassification (NNC), Learning Vector Quantization (LVQ), Radial Basis Function Support Vector Machines(RBF SVMs), Random Forest (RF) and Artificial Neural Networks (ANN). The performance of each method wasassessed using the same analytical dataset that consists of 861 samples split into drug- and fibre type cannabiswith drug type cannabis being made up of 12 varieties (i.e. 12 classes). The results show that linear classifiersare not able to manage the distribution of classes in which some overlap areas exist for both classificationproblems. Unlike linear classifiers, NNC and RBF SVMs best differentiate cannabis samples both for 2-class and12-class classifications with average classification results up to 99% and 98%, respectively. Furthermore, RBFSVMs correctly classified into drug type cannabis the independent validation set, which consists of cannabisplants coming from police seizures. In forensic case work this study shows that the discrimination betweencannabis samples at an early stage of growth is possible with fairly high classification performance fordiscriminating between cannabis chemotypes or between drug type cannabis varieties.

Selecting Wavelet Filter for Compression of Spectra from Multispectral Images

The problem of selecting anappropriate wavelet filter is always present in signal compression based on thewavelet transform. In this report, we propose a method to select a wavelet filter from a predefined set of filters for the compression of spectra from a multispectral image. The wavelet filter selection is based on the Learning Vector Quantization (LVQ). In the training phase for the test images, the best wavelet filter for each spectrum has been found by a careful compression-decompression evaluation. Certain spectral features are used in characterizing the pixel spectra. The LVQ is used to form the best wavelet filter class for different types of spectra from multispectral images. When a new image is to be compressed, a set of spectra from that image is selected, the spectra are classified by the trained LVQand the filter associated to the largest class is selected for the compression of every spectrum from the multispectral image. The results show, that almost inevery case our method finds the most suitable wavelet filter from the pre-defined set for the compression.

KOIVUVIILUN LAATULAJITTELUN KEHITTÄMINEN

Työssä on tutkittu Koskisen Oy:n vaneritehtaan 2. kuivauslinjalla toimivaa viilun laatulajittelujärjestelmää, jonka toiminnan tehostamiseksi haettiin uusia, vaihtoehtoisia ratkaisuja. Lajittelujärjestelmän toiminnan nopeuttamiseen ja toimivuuden kehittämiseksi haettiin ratkaisuja dimensio-, reuna- ja sisävikojen käsittelyyn. Linjan käyttöasteen kasvattamiseksi sen vikadiagnostiikkaan ja toi¬min¬nan seurantaan haettiin myös uusia menetelmiä. Kuvatun arkin reunatietojen avulla pystytään ottamaan huomioon käytönaikaisten asemointivirheiden aiheuttamat mittavirheet. Vika-alueiden harmaatasoarvoista kerättyä tietoa käytetään histogrammipiirteiden irrotuksessa oksien luokittelua parantamiseksi. Neuroluokittelijoiden käyttöönottoa luokittelijoina puoltavat niiden luokittelunopeus itse luokittelussa ja lähes k-NN-luokittimen tasoon yltävä luokittelutarkkuus. Neuroluokittelijoista tutkittiin monikerros-Perceptron- (MLP) ja oppiva vektorikvantisaatio- (LVQ) luokittelijat. Edellä mainittujen muutosten käyttöönoton avulla parantuneen viiluarkin onnistunut laadutus tuo kustannussäästöjä yritykselle sekä viiluarkkien paremman hyväksikäytön että viilun jatkokäsittelyssä säästyvän työmäärän avulla.

Adsorção do corante Reativo Azul 19 em solução aquosa por lama vermelha tratada quimicamente com peróxido de hidrogênio

Adsorption of Reactive Blue 19 dye onto activated red mud was investigated. Red mud was treated with hydrogen peroxide (LVQ) and heated at both 400 ºC (LVQ400) and 500 ºC (LVQ500). These samples were characterized by pH, specific surface area, point of zero charge and mineralogical composition. Adsorption was found to be significantly dependent on solution pH, with acidic conditions proving to be the most favorable. The adsorption followed pseudo-second-order kinetics. The Langmuir isotherm was the most appropriate to describe the phenomenon of dye removal using LVQ, LVQ400 and LVQ500, with maximum adsorption capacity of 384.62, 357.14 and 454.54 mg g-1, respectively.

Lujien painelaiteterästen hitsaus

Työn tavoitteena oli tutkia lujan nuorrutetun painelaiteteräksen P500QL2 hitsattavuutta ja koehitsausten avulla löytää optimaaliset hitsausparametrit ja lämmöntuonti teräksen hitsaukseen. Työn tavoitteena oli myös selvittää ja käsitellä kaikkien painelaiteterässtandardissa esitettyjen lujien painelaiteterästen hitsauksessa huomioon otettavia asioita. Työn teoriaosuudessa käsitellään lujien painelaiteterästen hitsauksessa huomioitavia erityispiirteitä, kuten lämmöntuontia, jäähtymisaikaa, esilämmitystä sekä hitsausaineiden valintaa. Lisäksi teoriaosuudessa käsitellään painelaitteiden valmistusta, painelaiteterässtandardiin kuuluvia lujia painelaiteteräksiä sekä keinoja lujien terästen hitsattavuuden arviointiin. Työn kokeellisessa osassa tutkittiin aineenvahvuudeltaan 50 mm paksun P500QL2-teräksen päittäisliitoksen mekaanisia ominaisuuksia eri lämmöntuonneilla hitsattuna. Kokeellisessa osassa tutkittiin myös myöstön poisjättämisen vaikutuksia liitoksen mekaanisiin ominaisuuksiin. Mekaanisia ominaisuuksia tutkittiin toteuttamalla koekappaleiden aineenkoetus menetelmäkoestandardin vaatimuksia soveltaen. Tutkimuksessa käytettyjä testausmenetelmiä olivat silmämääräinen tarkastus, magneettijauhetarkastus, ultraäänitarkastus, mikro- ja makrorakennetarkastelu, kovuuskokeet, vetokokeeet ja iskukokeet. Testauksessa saatujen tulosten avulla lujan painelaiteteräksen P500QL2 hitsaukseen laadittiin alustava hitsausohje. Hitsausliitosten testauksessa saatujen tulosten perusteella havaittiin hitsien lujuuden ja kovuuden laskevan lämmöntuonnin kasvaessa. Hitsausliitosten iskusitkeysominaisuudet olivat erinomaiset vielä suurellakin lämmöntuonnilla, mutta liitosten murtovenymäarvot laskivat lämmöntuonnin kasvaessa. Myöstön havaittiin parantavan hitsin mekaanisia ominaisuuksia huomattavasti. Tutkimuksen tulosten perusteella painelaiteteräs P500QL2 on hitsattavissa suurella lämmöntuonnilla ja suurella tuottavuudella liitoksen täyttäessä painelaitevalmistuksen edellyttämät vaatimukset.

Tandem-MAG-welding of high strength steels for shipbuilding applications

Tämän työn tavoitteena oli hitsata tandem MAG –laitteistolla 25 mm paksua Ruukin E500 TMCP terästä. Työssä oli tarkoituksena vähentää railotilavuutta mahdollisimman paljon sekä suorittaa testihitsaukset 0.8 kJ/mm sekä 2.5 kJ/mm lämmöntuonneilla. Teoriaosuudessa käsiteltiin Tandem MAG-hitsaukseen, sen tuottavuuteen ja laatukysymyksiin liittyviä asioita sekä siinä perehdyttiin suurlujuusteräksien käyttöön hitsauksessa sekä laivanrakennuksessa. Kokeellisessa osuudessa perehdyttiin hitsauksessa huomattuihin etuihin, ongelmiin sekä ongelmien ratkaisumahdollisuuksiin. Hitsausliitoksen mekaaniset ominaisuudet tutkittiin rikkomattomin sekä rikkovin menetelmin. Alustavat hitsausohjeet luotiin kummallekin lämmöntuonnille. Testaukset aloitettiin 30 º railokulmalla pienentäen kulmaa mahdollisuuksien mukaan. Testauksissa ei saatu hitsattua onnistuneesti alle 30 º railokulmalla. Hitsaustestien aikana huomattiin magneettisen puhalluksen vaikutus hitsaustapahtumaan. Kaasunvirtausnopeuden tuli olla tietyn suuruinen jotta palkokerrokset onnistuivat ilman huokoisuusongelmaa. Pienemmällä lämmöntuonnilla hitsattaessa kaasunvirtausnopeudet olivat tärkeämpiä hitsatessa ylempiä palkokerroksia. Kääntämällä hitsauspoltinta sivuttaissuunnassa 7-10 astetta auttoi ehkäisemään reunahaavan syntymistä. Rikkovista menetelmistä testitulokset olivat hyväksyttyjä kaikkien muiden paitsi päittäishitsin sivutaivutuskokeen osalta.

SAXS observation of RCM1 under cyclical shear

A cylinder forming poly(styrene-b-butadiene-b-styrene) triblock copolymer melt is cyclically processed through a capillary at a high shear rate in the Cambridge Multipass Rheometer (MPR). In situ X-ray diffraction experiments enable observation of the effect of the shear on the block copolymer (BCP) nanophase orientation, both during and after processing. Temporal resolution of the X-ray exposures is increased, whilst retaining intensity, by exploiting the cyclical nature of the shear and the material's response to it; short exposures from many cycles, individually having few counts, are added together to produce well resolved X-ray patterns. Orientation of the cylinders reduces during processing, then increases during pauses between processing. The loss of orientation is attributed to the high shear rate deforming the melt faster than the structure can respond, whilst it is believed that melt relaxation, linked to the compressibility of the material, produces much lower shear rates after mechanical processing has ceased, which induces strong orientation of the nanostructure.

Near-infrared water vapour self-continuum at close to room temperature

The gaseous absorption of solar radiation within near-infrared atmospheric windows in the Earth's atmosphere is dominated by the water vapour continuum. Recent measurements by Baranov et al. (2011) [17] in 2500 cm−1 (4 μm) window and by Ptashnik et al. (2011) [18] in a few near-infrared windows revealed that the self-continuum absorption is typically an order of magnitude stronger than given by the MT_CKD continuum model prior to version 2.5. Most of these measurements, however, were made at elevated temperatures, which makes their application to atmospheric conditions difficult. Here we report new laboratory measurements of the self-continuum absorption at 289 and 318 K in the near-infrared spectral region 1300–8000 cm−1, using a multipass 30 m base cell with total optical path 612 m. Our results confirm the main conclusions of the previous measurements both within bands and in windows. Of particular note is that we present what we believe to be the first near-room temperature measurement using Fourier Transform Spectrometry of the self-continuum in the 6200 cm−1 (1.6 μm) window, which provides tentative evidence that, at such temperatures, the water vapour continuum absorption may be as strong as it is in 2.1 μm and 4 μm windows and up to 2 orders of magnitude stronger than the MT_CKD-2.5 continuum. We note that alternative methods of measuring the continuum in this window have yielded widely differing assessment of its strength, which emphasises the need for further measurements.

Mechanical and tribological properties of PVD-coated cemented carbide as evaluated by a new multi-pass scratch testing method

A new test method based on multipass scratch testing has been developed for evaluating the mechanical and tribological properties of thin, hard coatings. The proposed test method uses a pin-on-disc tribometer and during testing a Rockwell C diamond stylus is used as the “pin” and loaded against the rotating coated sample. The influence of normal load on the number of cycles to coating damage is investigated and the resulting coating damage mechanisms are evaluated by posttest scanning electron microscopy. The present study presents the test method by evaluating the performance of Ti0.86Si0.14N, Ti0.34Al0.66N, and (Al0.7Cr0.3)2O3 coatings deposited by cathodic arc evaporation on cemented carbide inserts. The results show that the test method is quick, simple, and reproducible and can preferably be used to obtain relevant data concerning the fatigue, wear, chipping, and spalling characteristics of different coating-substrate composites. The test method can be used as a virtually nondestructive test and, for example, be used to evaluate the fatigue and wear resistance as well as the cohesive and adhesive interfacial strength of coated cemented carbide inserts prior to cutting tests.

Adsorção do corante reativo azul 19 em solução aquosa por lama vermelha tratada quimicamente com peró:xido de hidrogênio

Adsorption of Reactive Blue 19 dye onto activated red mud was investigated. Red mud was treated with hydrogen peroxide (LVQ) and heated at both 400 °C (LVQ400) and 500 °C (LVQ500). These samples were characterized by pH, specific surface area, point of zero charge and mineralogical composition. Adsorption was found to be significantly dependent on solution pH, with acidic conditions proving to be the most favorable. The adsorption followed pseudo-second-order kinetics. The Langmuir isotherm was the most appropriate to describe the phenomenon of dye removal using LVQ, LVQ400 and LVQ500, with maximum adsorption capacity of 384.62, 357.14 and 454.54 mg g-1, respectively.

Rigor mortis at the myocardium investigated by post-mortem magnetic resonance imaging

INTRODUCTION Post-mortem cardiac MR exams present with different contraction appearances of the left ventricle in cardiac short axis images. It was hypothesized that the grade of post-mortem contraction may be related to the post-mortem interval (PMI) or cause of death and a phenomenon caused by internal rigor mortis that may give further insights in the circumstances of death. METHOD AND MATERIALS The cardiac contraction grade was investigated in 71 post-mortem cardiac MR exams (mean age at death 52y, range 12-89y; 48 males, 23 females). In cardiac short axis images the left ventricular lumen volume as well as the left ventricular myocardial volume were assessed by manual segmentation. The quotient of both (LVQ) represents the grade of myocardial contraction. LVQ was correlated to the PMI, sex, age, cardiac weight, body mass and height, cause of death and pericardial tamponade when present. In cardiac causes of death a separate correlation was investigated for acute myocardial infarction cases and arrhythmic deaths. RESULTS LVQ values ranged from 1.99 (maximum dilatation) to 42.91 (maximum contraction) with a mean of 15.13. LVQ decreased slightly with increasing PMI, however without significant correlation. Pericardial tamponade positively correlated with higher LVQ values. Variables such as sex, age, body mass and height, cardiac weight and cause of death did not correlate with LVQ values. There was no difference in LVQ values for myocardial infarction without tamponade and arrhythmic deaths. CONCLUSION Based on the observation in our investigated cases, the phenomenon of post-mortem myocardial contraction cannot be explained by the influence of the investigated variables, except for pericardial tamponade cases. Further research addressing post-mortem myocardial contraction has to focus on other, less obvious factors, which may influence the early post-mortem phase too.