According to recent statistics the construction industry is responsible for the largest waste discharges of both dangerous and non-dangerous waste, when disregarding the "non-dangerous" amount of granite waste produced by the mining industry and the waste produced by the pulp and paper industry. Preventive work within waste management is an ongoing practice so to be able to reduce negative environmental effects. One of the most common actions for the companies to take is to separate the different kinds of waste from one another at the construction site. Although by working with the problem in earlier stages of the process a large amount of the waste could already have been reduced. Companies in the construction business that are actively working to decrease environmental impact in their operations often use an EMS (Environmental Management System). By using environmental management as method the company can manage their environmental work so that actions can be taken where they are needed the most. It may though be difficult to adapt the tool for a project-oriented organization such as a construction project. Which effect the environmental work will have does not depend on the fact that the company uses EMS, it depends on how they use it. ICA Real-estate Sweden AB is about to have a new "ICA Kvantum" store built in Avesta, the company has chosen to use an EMS in their environmental work in order to reduce their environmental impact. ICA Real-estate’s environmental review showed that a considerable environmental aspect was waste management in new constructions and rebuilding’s and as a result they have a new environmental goal for the year 2010. The goal was that they would conduct a pilot project within waste management which is currently realized through the construction of the ICA Kvantum store in Avesta. In order to specify how the environmental work should be done in the project and which environmental demands that have been demanded ICA Real-estates has established an environmental program that the entrepreneurs have received and will abide by. Based on the notion from ICA Real-estate concerning the fact that the contractor’s should have high-quality environmental work the company ByggPartner i Dalarna AB was granted the entire contract for the new ICA Kvantum store. ByggPartner also have their own agenda and goals for waste management in the project and are working towards fulfilling them through coordination and planning. The results presented from the investigation that have been done in this report shows that both companies has got many good factors in their environmental work but compared to contemporary research in the area there are still things that could be improved so that the environmental work will be even more successful. / Enligt statistik bidrar byggsektorn med mest farligt och icke-farligt avfall i Sverige, bortsett från ”ofarligt” gråberg från gruvindustrin och avfall från massa- och pappersindustrin. Det arbetas förebyggande med avfallshantering inom sektorn för att minska den negativa miljöpåverkan avfall utgör. Den vanligaste åtgärden företag utför är att källsortera på byggarbetsplatsen men en stor mängd av avfallet kan reduceras genom att arbeta med problemet i byggprocessens tidigare skeden. Majoriteten av företag inom byggbranschen som arbetar med att minska miljöbelastningen använder ett miljöledningssystem. Miljöledning är en metod där företagets miljöarbete styrs så åtgärder utförs där de är mest behövliga. En svårighet som finns inom branschen är att anpassa verktyget till projektorienterade organisationer som ett byggprojekt. Vilket resultat miljöarbetet får beror på hur företaget använder miljöledningssystemet inte att de använder verktyget. ICA Fastigheter Sverige AB skall låta uppföra en ICA Kvantumbutik i Avesta. Företaget använder ett miljöledningssystem i arbetet med minskning av verksamhetens miljöbelastning. ICA Fastigheters miljöutredning visade att en betydande miljöaspekt är avfallshantering vid nyproduktion och ombyggnader, därför sattes ett miljömål upp för 2010. Målet är att bedriva ett pilotprojekt inom avfallshantering vilket nu realiseras genom uppförandet av en ICA Kvantumbutik i Avesta. För att specificera hur miljöarbetet skall gå till i projektet och vilka miljökrav som ställs har ICA Fastigheter upprättat ett miljöprogram som entreprenören skall följa. Baserat på att entreprenören skall ha ett bra miljöarbete inom företaget erhöll ByggPartner i Dalarna AB totalentreprenaden för ICA Kvantumbutiken. ByggPartner har satt upp egna mål angående avfallshanteringen i projektet. Genom samordning och planering arbetar företaget för att uppnå dessa mål samt ICA Fastigheters krav. Resultatet av företagens miljöarbete som beskrivs i rapporten visar att båda företagen har flera bra faktorer i sitt miljöarbete. Jämfört mot forskning inom området finns det delar inom miljöarbetet hos ICA Fastigheter och ByggPartner som har förbättringspotential.

Cerrillos is an Early to Middle Paracas civic-ceremonial site located in the upper Ica Valley of Perú. The site is known for its finely plastered adobe architecture, beautifully decorated ceramics, and complex textiles, many of which are decorated with camelid hair. Cerrillos was located in a strategically important place where the mountains meet the coastal desert and the Ica River bends south, a likely intersection in a road system that connected Cerrillos to contemporary sites in the Paracas region and beyond. This paper focuses on several early textiles, ceramics, and other artifacts, including ceramic palettes used for gold working and wooden earspools, that suggest that Cerrillos was involved in a cultural phenomenon or interaction sphere that linked sites as far away was Chavín de Huántar through the interchange of goods, beliefs, and practices. The paper presents a complete description of the textiles excavated at Cerrillos between 1999 and 2002, focusing on two fabric fragments with images of the Staff Deity and one with an abstract Chavín-like design. The ceramics discussed in the text demonstrate the wide variety of styles found at Cerrillos, including some that resemble the Janabarriu of Chavín de Huántar and several others that are either not Paracas or an Early Paracas style that has never been previously described. / Cerrillos es un sitio cívico-ceremonial con ocupación entre las épocas Paracas Temprano y Medio, localizado en el valle alto de Ica, Perú. Es conocido por su arquitectura de adobe enlucida de manera fina, cerámica bellamente decorada y textiles complejos, muchos de ellos decorados con fibra de camélido. Estuvo localizado en un lugar de importancia estratégica, donde las montañas se encuentran con el desierto costero y el río Ica gira hacia el sur, una probable intersección en un sistema de caminos que lo conectaba con sitios contemporáneos en la región de Paracas y más allá. Este artículo se enfoca en diversos textiles, cerámica y otros artefactos tempranos, entre ellos paletas de cerámica usadas para trabajar el oro y aretes en forma de argollas de madera, lo que sugiere que este complejo estaba involucrado en un fenómeno cultural o esfera de interacción que vinculaba sitios tan lejanos como Chavín de Huántar mediante el intercambio de bienes, creencias y prácticas. Este artículo presenta una completa descripción de los textiles excavados en Cerrillos entre 1999 y 2002, y se enfoca en dos fragmentos textiles, uno con imágenes del Dios de las Varas y el otro con un diseño abstracto parecido al chavín. La cerámica tratada en el texto demuestra la amplia variedad de estilos encontrados, entre ellos algunos que se parecen al Janabarriu de Chavín de Huántar y varios otros que no corresponden al estilo Paracas o que semejan un estilo Paracas Temprano que nunca antes ha sido descrito.

Mnoho rozdílných strategií fúze bylo vyvinuto během posledních 15 let výzkumu simultánního EEG-fMRI. Aktuální dizertační práce shrnuje aktuální současný stav v oblasti výzkumu fúze simultánních EEG-fMRI dat a pokládá si za cíl vylepšit vizualizaci úkolem evokovaných mozkových sítí slepou analýzou přímo z nasnímaných dat. Dva rozdílné modely, které by to měly vylepšit, byly navrhnuty v předložené práci (tj. zobecněný spektrální heuristický model a zobecněný prostorovo-frekvenční heuristický model). Zobecněný frekvenční heuristický model využívá fluktuace relativního EEG výkonu v určitých frekvenčních pásmech zprůměrovaných přes elektrody zájmu a srovnává je se zpožděnými fluktuacemi BOLD signálů pomocí obecného lineárního modelu. Získané výsledky ukazují, že model zobrazuje několik na frekvenci závislých rozdílných úkolem evokovaných EEG-fMRI sítí. Model překonává přístup fluktuací absolutního EEG výkonu i klasický (povodní) heuristický přístup. Absolutní výkon vizualizoval s úkolem nesouvisející širokospektrální EEG-fMRI komponentu a klasický heuristický přístup nebyl senzitivní k vizualizaci s úkolem spřažené vizuální sítě, která byla pozorována pro relativní pásmo pro data vizuálního oddball experimentu. Pro EEG-fMRI data s úkolem sémantického rozhodování, frekvenční závislost nebyla ve finálních výsledcích tak evidentní, neboť všechna pásma zobrazily vizuální síť a nezobrazily aktivace v řečových centrech. Tyto výsledky byly pravděpodobně poškozeny artefaktem mrkání v EEG datech. Koeficienty vzájemné informace mezi rozdílnými EEG-fMRI statistickými parametrickými mapami ukázaly, že podobnosti napříč různými frekvenčními pásmy jsou obdobné napříč různými úkoly (tj. vizuální oddball a sémantické rozhodování). Navíc, koeficienty prokázaly, že průměrování napříč různými elektrodami zájmu nepřináší žádnou novou informaci do společné analýzy, tj. signál na jednom svodu je velmi rozmazaný signál z celého skalpu. Z těchto důvodů začalo být třeba lépe zakomponovat informace ze svodů do EEG-fMRI analýzy, a proto jsme navrhli více obecný prostorovo-frekvenční heuristický model a také jak ho odhadnout za pomoci prostorovo-frekvenční skupinové analýzy nezávislých komponent relativního výkonu EEG spektra. Získané výsledky ukazují, že prostorovo-frekvenční heuristický model vizualizuje statisticky nejvíce signifikantní s úkolem spřažené mozkové sítě (srovnáno s výsledky prostorovo-frekvenčních vzorů absolutního výkonu a s výsledky zobecněného frekvenčního heuristického modelu). Prostorovo-frekvenční heuristický model byl jediný, který zaznamenal s úkolem spřažené aktivace v řečových centrech na datech sémantického rozhodování. Mimo fúzi prostorovo-frekvenčních vzorů s fMRI daty, jsme testovali stabilitu odhadů prostorovo-frekvenčních vzorů napříč různými paradigmaty (tj. vizuální oddball, semantické rozhodování a resting-state) za pomoci k-means shlukovacího algoritmu. Dostali jsme 14 stabilních vzorů pro absolutní EEG výkon a 12 stabilních vzorů pro relativní EEG výkon. Ačkoliv 10 z těchto vzorů vypadají podobně napříč výkonovými typy, prostorovo-frekvenční vzory relativního výkonu (tj. vzory prostorovo-frekvenčního heuristického modelu) mají vyšší evidenci k úkolům.

El presente trabajo busca analizar cuáles son los determinantes cualitativos y cuantitativos del acceso al servicio de gas natural para las familias en las regiones de Lima, Callao e Ica para luego identificar cuáles son los factores que inciden en la demanda de este servicio. Este trabajo es relevante para el contexto peruano en el que se evidencia el poco uso de energía más económica y menos contaminante a pesar de contar con programas que promueven su uso como es el caso de Bono Gas, lo cual no se ve en otros países de Latinoamérica como es el caso de Colombia. El método a utilizar para verificar el análisis es el modelo discreto continuo de Heckman que consta de dos etapas: un modelo Logit y una regresión MCO. Se espera que algunas de las variables cualitativas estén relacionadas a las características del hogar que se justifican con la literatura sobre acceso a los servicios de energías en las familias; y, por otro lado, las variables cuantitativas estarán relacionadas con el ingreso del hogar y el precio del gas natural. En base a los resultados, brindaremos algunas recomendaciones de política con el objetivo de promover el acceso al gas natural domiciliario. / The present work seeks to analyze the qualitative and quantitative determinants of home access to the natural gas service for families in the regions of Lima, Callao and Ica, and once the choice has been made, identify the factors that affect the demand for this service. This work is relevant to the peruvian context in which the little use of cheaper and less polluting energy is evident, despite having programs that promote its use, such as Bono Gas. This fact, however, is not seen in other Latin American countries such as the case of Colombia. The method to use to verify the analysis is the Heckman continuous discrete model consisting of two stages: a logit model and an OLS regression. It is expected that some of the qualitative variables are related to the characteristics of the home that are justified by the literature on access to energy services in families; and, on the other hand, the quantitative variables will be related to the household income and the price of natural gas. Based on the results of the research, we will provide some policy recommendations with the aim of promoting access to household natural gas.

<p>This thesis presents methods for air sampling and determination of isocyanates, amines, aminoisocyanates and anhydrides. These organic compounds are generated during thermal degradation of polymers such as polyurethane (PUR) or epoxy.</p><p>Isocyanates, amines and anhydrides are airway irritants known to cause occupational asthma. Some of the compounds are listed as human carcinogens. Many workers are exposed.</p><p>Isocyanates and anhydrides are reactive and needs to be immediately derivatized during sampling. Methods have been developed for determination of airborne isocyanates, aminoisocyanates and anhydrides using di-n-butylamine (DBA) as reagent to form stabile urea derivatives or amide derivatives. Liquid chromatography-tandem mass spectrometry (LC-MS/MS) enabled detection limits as low as 10 attomoles. A nitrogen-selective LC-detector enabled quantification of DBA-derivatives in reference solutions. </p><p>A novel sampler is presented. The sampler consists of a denuder in series with a three-stage cascade impactor and an end filter. The sampler made it possible to reveal the distribution of isocyanates between gas and different particle size fractions. During thermal degradation of PUR, isocyanates were associated to particle size fractions (<1 µm) that may penetrate to the lower airways. The distribution during 8 minutes changes noticeably. Aromatic isocyanates become associated to small particles (<1 µm). As a reference method, air-sampling was performed using an impinger filled with di-n-butylamine (DBA) in toluene, connected in series with a glass fiber filter. There was a good agreement between the denuder-impactor sampler and the reference method.</p>

This thesis presents methods for air sampling and determination of isocyanates, amines, aminoisocyanates and anhydrides. These organic compounds are generated during thermal degradation of polymers such as polyurethane (PUR) or epoxy. Isocyanates, amines and anhydrides are airway irritants known to cause occupational asthma. Some of the compounds are listed as human carcinogens. Many workers are exposed. Isocyanates and anhydrides are reactive and needs to be immediately derivatized during sampling. Methods have been developed for determination of airborne isocyanates, aminoisocyanates and anhydrides using di-n-butylamine (DBA) as reagent to form stabile urea derivatives or amide derivatives. Liquid chromatography-tandem mass spectrometry (LC-MS/MS) enabled detection limits as low as 10 attomoles. A nitrogen-selective LC-detector enabled quantification of DBA-derivatives in reference solutions. A novel sampler is presented. The sampler consists of a denuder in series with a three-stage cascade impactor and an end filter. The sampler made it possible to reveal the distribution of isocyanates between gas and different particle size fractions. During thermal degradation of PUR, isocyanates were associated to particle size fractions (&lt;1 µm) that may penetrate to the lower airways. The distribution during 8 minutes changes noticeably. Aromatic isocyanates become associated to small particles (&lt;1 µm). As a reference method, air-sampling was performed using an impinger filled with di-n-butylamine (DBA) in toluene, connected in series with a glass fiber filter. There was a good agreement between the denuder-impactor sampler and the reference method.

In this thesis, improving the performance of the automatic recognition of the Doppler radar targets is studied. The radar used in this study is a ground-surveillance doppler radar. Target types are car, truck, bus, tank, helicopter, moving man and running man. The input of this thesis is the output of the real doppler radar signals which are normalized and preprocessed (TRP vectors: Target Recognition Pattern vectors) in the doctorate thesis by Erdogan (2002). TRP vectors are normalized and homogenized doppler radar target signals with respect to target speed, target aspect angle and target range. Some target classes have repetitions in time in their TRPs. By the use of these repetitions, improvement of the target type classification performance is studied. K-Nearest Neighbor (KNN) and Support Vector Machine (SVM) algorithms are used for doppler radar target classification and the results are evaluated. Before classification PCA (Principal Component Analysis), LDA (Linear Discriminant Analysis), NMF (Nonnegative Matrix Factorization) and ICA (Independent Component Analysis) are implemented and applied to normalized doppler radar signals for feature extraction and dimension reduction in an efficient way. These techniques transform the input vectors, which are the normalized doppler radar signals, to another space. The effects of the implementation of these feature extraction algoritms and the use of the repetitions in doppler radar target signals on the doppler radar target classification performance are studied.

<p>This thesis is concerned with the solution of the blind source separation problem (BSS). The BSS problem occurs frequently in various scientific and technical applications. In essence, it consists in separating meaningful underlying components out of a mixture of a multitude of superimposed signals.</p> <P> In the recent research literature there are two related approaches to the BSS problem: The first is known as Independent Component Analysis (ICA), where the goal is to transform the data such that the components become as independent as possible. The second is based on the notion of diagonality of certain characteristic matrices derived from the data. Here the goal is to transform the matrices such that they become as diagonal as possible. In this thesis we study the latter method of approximate joint diagonalization (AJD) to achieve a solution of the BSS problem. After an introduction to the general setting, the thesis provides an overview on particular choices for the set of target matrices that can be used for BSS by joint diagonalization.</p> <P> As the main contribution of the thesis, new algorithms for approximate joint diagonalization of several matrices with non-orthogonal transformations are developed.</p> <P> These newly developed algorithms will be tested on synthetic benchmark datasets and compared to other previous diagonalization algorithms.</p> <P> Applications of the BSS methods to biomedical signal processing are discussed and exemplified with real-life data sets of multi-channel biomagnetic recordings.</p> / <p>Diese Arbeit befasst sich mit der Lösung des Problems der blinden Signalquellentrennung (BSS). Das BSS Problem tritt häufig in vielen wissenschaftlichen und technischen Anwendungen auf. Im Kern besteht das Problem darin, aus einem Gemisch von überlagerten Signalen die zugrundeliegenden Quellsignale zu extrahieren.</p> <P> In wissenschaftlichen Publikationen zu diesem Thema werden hauptsächlich zwei Lösungsansätze verfolgt:</p> <P> Ein Ansatz ist die sogenannte "Analyse der unabhängigen Komponenten", die zum Ziel hat, eine lineare Transformation <B>V</B> der Daten <B>X</B> zu finden, sodass die Komponenten U_n der transformierten Daten <B>U</B> = <B> V X</B> (die sogenannten "independent components") so unabhängig wie möglich sind. Ein anderer Ansatz beruht auf einer simultanen Diagonalisierung mehrerer spezieller Matrizen, die aus den Daten gebildet werden. Diese Möglichkeit der Lösung des Problems der blinden Signalquellentrennung bildet den Schwerpunkt dieser Arbeit.</p> <P> Als Hauptbeitrag der vorliegenden Arbeit präsentieren wir neue Algorithmen zur simultanen Diagonalisierung mehrerer Matrizen mit Hilfe einer nicht-orthogonalen Transformation.</p> <P> Die neu entwickelten Algorithmen werden anhand von numerischen Simulationen getestet und mit bereits bestehenden Diagonalisierungsalgorithmen verglichen. Es zeigt sich, dass unser neues Verfahren sehr effizient und leistungsfähig ist. Schließlich werden Anwendungen der BSS Methoden auf Probleme der biomedizinischen Signalverarbeitung erläutert und anhand von realistischen biomagnetischen Messdaten wird die Nützlichkeit in der explorativen Datenanalyse unter Beweis gestellt.</p>

Resting state functional magnetic resonance imaging (fMRI) is currently at the forefront of research on cognition and the brain’s large-scale organization. Patterns of hemodynamic activity that it records have been strongly linked to certain behaviors and cognitive pathologies. These signals are widely assumed to reflect local neuronal activity but our understanding of the exact relationship between them remains incomplete. Researchers often address this using multimodal approaches, pairing fMRI signals with known measures of neuronal activity such as electroencephalography (EEG). It has long been thought that infraslow (< 0.1 Hz) fMRI signals, which have become so important to the study of brain function, might have a direct electrophysiological counterpart. If true, EEG could be positioned as a low-cost alternative to fMRI when fMRI is impractical and therefore could also become much more influential in the study of functional brain networks. Previous works have produced indirect support for the fMRI-EEG relationship, but until recently the hypothesized link between them had not been tested in resting humans. The objective of this study was to investigate and characterize their relationship by simultaneously recording infraslow fMRI and EEG signals in resting human adults. We present evidence strongly supporting their link by demonstrating significant stationary and dynamic correlations between the two signal types. Moreover, functional brain networks appear to be a fundamental unit of this coupling. We conclude that infraslow electrophysiology is likely playing an important role in the dynamic configuration of the resting state brain networks that are well-known to fMRI research. Our results provide new insights into the neuronal underpinnings of hemodynamic activity and a foundational point on which the use of infraslow EEG in functional connectivity studies can be based.

The last twenty years presented increased interest for the study of cerebral processes caused by external events (stimuli). One of the most significant endogenous components of Evoked Potentials is the P600 component. The P600 component may be defined as the most positive peak in the time window between 500 and 800 msec after an eliciting stimulus. This component is thought to reflect the response selection stage of information processing. P600 component is usually less pronounced compared to other components, such as the N100 or the P300. Frequently the P600 component appears as a not-easily discernible secondary peak overlying the ascending negative-going slope of the P300 waveform. In our study we used ERP data from various groups of patients and healthy controls. Patients were recruited from the outpatient university clinic of Eginition Hospital of the University of Athens. The controls were recruited from hospital staff and local volunteer groups. The aim of the study is the implementation of classification systems for these groups, using P600 features. This is usually not achieved well using as features the ERPs amplitude and latency. So for that reason, in our study, we want to extract new features using advanced techniques for processing the original ERPs, such as the Independent Component Analysis (ICA) method. However as a precursor of ICA, is considered the Principal Component Analysis (PCA) method, which we used for comparison reasons to ICA. In the application of ICA we achieve the decomposition of the recorded signals in ICs, supposing temporally independent components and propose ICs selection techniques in order to recompose the P600 component. The next stage was the use of a classification method based on the features extracted using the original data, data extracted through PCA processing and ICA-processed data. First we applied Kolmogorov-Smirnov test to check the normality of the distribution of the features, then we used the Logistic Regression method for classification and finally we have done two implementations of classification using Probabilistic Neural Networks. The first implementation was done with the creation of 15 features from the P600 peak amplitudes from the subjects’ data and the second implementation was done with the creation of four meta-features from the subjects’ P600 amplitude data. The results show that the application of ICA, combined with the logistic regression classification technique, provides notable improvement, compared to the classification performance based on the original ERPs. The main merit of the application is that classification is based on single parameters, i.e. amplitude of the P600 component, or its latency or its termination latency, which are directly related to the brain mechanisms related to ERP generation and pathological processes. / Τα τελευταία 20 χρόνια παρουσιάζεται αυξημένο ενδιαφέρον για την μελέτη εγκεφαλικών επεξεργασιών που προκλήθηκαν από εξωτερικά γεγονότα (ερέθισμα). Ένα από τα πιο σημαντικά ενδογενή συστατικά των Προκλητών Δυναμικών είναι το συστατικό P600. Το συστατικό P600 μπορεί να οριστεί σαν η πιο θετική αιχμή στο χρονικό διάστημα μεταξύ 500 και 800 msec μετά από ένα εκλυτικό ερέθισμα. Το συστατικό αυτό θεωρείται ότι απεικονίζει το στάδιο επιλογής απόκρισης της επεξεργασίας πληροφορίας. Το συστατικό P600 είναι συνήθως λιγότερο έντονο συγκρίνοντας το με άλλα συστατικά, όπως το N100 ή το P300. Συχνά το συστατικό P600 εμφανίζεται ως μια δυσδιάκριτη δεύτερη αιχμή, επικαλύπτοντας την ανοδική αρνητική κλίση της κυματομορφής του P300. Στη μελέτη μας χρησιμοποιήσαμε δεδομένα ΠΔ από ποικίλες ομάδες ασθενών και υγιών μαρτύρων. Οι ασθενείς συλλέχθησαν από τη πανεπιστημιακή κλινική του Αιγηνήτειου Νοσοκομείου του Πανεπιστημίου Αθηνών. Οι υγιείς συλλέχθησαν από το προσωπικό του νοσοκομείου και ομάδες εθελοντών. Ο σκοπός της μελέτης είναι η εφαρμογή συστημάτων ταξινόμησης για αυτές τις ομάδες, χρησιμοποιώντας χαρακτηριστικά του P600. Αυτό συνήθως δεν επιτυγχάνεται καλά χρησιμοποιώντας σαν χαρακτηριστικά το πλάτος και τον λανθάνοντα χρόνο των ΠΔ. Για αυτό το λόγο, στην μελέτη μας, θέλουμε να εξάγουμε νέα χαρακτηριστικά χρησιμοποιώντας προηγμένες τεχνικές για επεξεργασία των αρχικών ΠΔ, όπως τη μέθοδο Ανάλυσης Ανεξαρτήτων Συνιστωσών (ICA). Εντούτοις ως πρόδρομο της ICA, θεωρείται η μέθοδος Ανάλυσης Κύριων Συνιστωσών (PCA), την οποία χρησιμοποιήσαμε για συγκριτικούς λόγους με την ICA. Στην εφαρμογή της ICA προχωρήσαμε στην αποσύνθεση των καταγραφόμενων σημάτων σε Ανεξάρτητες Συνιστώσες και διερευνήσαμε τρεις τεχνικές επιλογής ανεξαρτήτων συνιστωσών μέσω των οποίων επανασυνθέσαμε το συστατικό P600. Το επόμενο βήμα ήταν η χρήση μεθόδου ταξινόμησης βασισμένης στα χαρακτηριστικά που εξάχθηκαν χρησιμοποιώντας τα αρχικά δεδομένα, τα δεδομένα με επεξεργασία PCA και τα δεδομένα με επεξεργασία ICA. Πρώτα εφαρμόσαμε το τεστ Kolmogorov-Smirnov για τον έλεγχο της κανονικότητας της κατανομής των χαρακτηριστικών, μετά χρησιμοποιήσαμε τη μέθοδο Λογαριθμικής Παλινδρόμησης (Logistic Regression) για ταξινόμηση και τελικά πραγματοποιήσαμε δύο εφαρμογές ταξινόμησης χρησιμοποιώντας Πιθανοκρατικά Νευρωνικά Δίκτυα (Probabilistic Neural Networks). Η πρώτη εφαρμογή έγινε με την δημιουργία 15 χαρακτηριστικών από τα πλάτη των αιχμών του P600 από τα δεδομένα των ομάδων και η δεύτερη εφαρμογή έγινε με την δημιουργία τεσσάρων μετά-χαρακτηριστικών από τα δεδομένα των πλατών των ομάδων. Τα αποτελέσματα δείχνουν ότι η εφαρμογή της ICA, συνδυασμένη με την τεχνική ταξινόμησης λογαριθμικής παλινδρόμησης, παρέχει αξιοσημείωτη βελτίωση, συγκριτικά με την απόδοση ταξινόμησης βάση των αρχικών ΠΔ. Η κύρια αξία της εφαρμογής είναι ότι η ταξινόμηση πετυχαίνει ποσοστά μεγαλύτερα του 80% βασιζόμενη σε μία μόνο κάθε φορά παράμετρο, π.χ. το πλάτος του συστατικού P600, ή τον λανθάνοντα χρόνο του ή τον λανθάνοντα χρόνο τερματισμού του, οι οποίες σχετίζονται άμεσα με τους μηχανισμούς του εγκεφάλου σχετικούς με την παραγωγή ΠΔ και τις παθολογικές διαδικασίες.