Differential evolution based classification with pool of distances and aggregation operators

The objective of this thesis is to develop and generalize further the differential evolution based data classification method. For many years, evolutionary algorithms have been successfully applied to many classification tasks. Evolution algorithms are population based, stochastic search algorithms that mimic natural selection and genetics. Differential evolution is an evolutionary algorithm that has gained popularity because of its simplicity and good observed performance. In this thesis a differential evolution classifier with pool of distances is proposed, demonstrated and initially evaluated. The differential evolution classifier is a nearest prototype vector based classifier that applies a global optimization algorithm, differential evolution, to determine the optimal values for all free parameters of the classifier model during the training phase of the classifier. The differential evolution classifier applies the individually optimized distance measure for each new data set to be classified is generalized to cover a pool of distances. Instead of optimizing a single distance measure for the given data set, the selection of the optimal distance measure from a predefined pool of alternative measures is attempted systematically and automatically. Furthermore, instead of only selecting the optimal distance measure from a set of alternatives, an attempt is made to optimize the values of the possible control parameters related with the selected distance measure. Specifically, a pool of alternative distance measures is first created and then the differential evolution algorithm is applied to select the optimal distance measure that yields the highest classification accuracy with the current data. After determining the optimal distance measures for the given data set together with their optimal parameters, all determined distance measures are aggregated to form a single total distance measure. The total distance measure is applied to the final classification decisions. The actual classification process is still based on the nearest prototype vector principle; a sample belongs to the class represented by the nearest prototype vector when measured with the optimized total distance measure. During the training process the differential evolution algorithm determines the optimal class vectors, selects optimal distance metrics, and determines the optimal values for the free parameters of each selected distance measure. The results obtained with the above method confirm that the choice of distance measure is one of the most crucial factors for obtaining higher classification accuracy. The results also demonstrate that it is possible to build a classifier that is able to select the optimal distance measure for the given data set automatically and systematically. After finding optimal distance measures together with optimal parameters from the particular distance measure results are then aggregated to form a total distance, which will be used to form the deviation between the class vectors and samples and thus classify the samples. This thesis also discusses two types of aggregation operators, namely, ordered weighted averaging (OWA) based multi-distances and generalized ordered weighted averaging (GOWA). These aggregation operators were applied in this work to the aggregation of the normalized distance values. The results demonstrate that a proper combination of aggregation operator and weight generation scheme play an important role in obtaining good classification accuracy. The main outcomes of the work are the six new generalized versions of previous method called differential evolution classifier. All these DE classifier demonstrated good results in the classification tasks.

On the Condition Monitoring of Induction machines

The research of condition monitoring of electric motors has been wide for several decades. The research and development at universities and in industry has provided means for the predictive condition monitoring. Many different devices and systems are developed and are widely used in industry, transportation and in civil engineering. In addition, many methods are developed and reported in scientific arenas in order to improve existing methods for the automatic analysis of faults. The methods, however, are not widely used as a part of condition monitoring systems. The main reasons are, firstly, that many methods are presented in scientific papers but their performance in different conditions is not evaluated, secondly, the methods include parameters that are so case specific that the implementation of a systemusing such methods would be far from straightforward. In this thesis, some of these methods are evaluated theoretically and tested with simulations and with a drive in a laboratory. A new automatic analysis method for the bearing fault detection is introduced. In the first part of this work the generation of the bearing fault originating signal is explained and its influence into the stator current is concerned with qualitative and quantitative estimation. The verification of the feasibility of the stator current measurement as a bearing fault indicatoris experimentally tested with the running 15 kW induction motor. The second part of this work concentrates on the bearing fault analysis using the vibration measurement signal. The performance of the micromachined silicon accelerometer chip in conjunction with the envelope spectrum analysis of the cyclic bearing faultis experimentally tested. Furthermore, different methods for the creation of feature extractors for the bearing fault classification are researched and an automatic fault classifier using multivariate statistical discrimination and fuzzy logic is introduced. It is often important that the on-line condition monitoring system is integrated with the industrial communications infrastructure. Two types of a sensor solutions are tested in the thesis: the first one is a sensor withcalculation capacity for example for the production of the envelope spectra; the other one can collect the measurement data in memory and another device can read the data via field bus. The data communications requirements highly depend onthe type of the sensor solution selected. If the data is already analysed in the sensor the data communications are needed only for the results but in the other case, all measurement data need to be transferred. The complexity of the classification method can be great if the data is analysed at the management level computer, but if the analysis is made in sensor itself, the analyses must be simple due to the restricted calculation and memory capacity.

Laatupoikkeamienkäsittelyn tehostaminen Olkiluoto 3 -projektissa

Diplomityössä tutustaan Olkiluoto 3-laitoksen suunnittelu- ja rakennusvaiheen aikaisiin laatupoikkeamiin ja niiden käsittelyyn. Työn tavoitteena on paikantaa poikkeamakäsittelyn pahimmat ongelmakohdat, ja kehittää menetelmiä ongelmien ratkaisemiseksi. Diplomityön tutkimusmenetelmänä käytettiin toimintatutkimusta. Tutkimus toteutettiin kevään 2007 aikana havainnoimalla Olkiluoto 3-projektin laadunhallinnan toimintaa ja analysoimalla projektissa syntyneitä poikkeamia. Työn toteuttamisessa tutustuttiin kansallisin ja kansainvälisiin laadunhallinnan standardeihin sekä erityisesti ydinvoima-alaa koskeviin laadunhallinnan ohjeistuksiin. Diplomityön tuloksena kehitettiin menetelmä OL 3-projektin toiminnallisten poikkeamien luokittelemiseksi. Jatkossa luokittelumenetelmää voidaan hyödyntää aiempaa tarkemman poikkeamatiedon analysoinnissa, sisäisessä päätöksenteossa sekä OL 3-projektin tiedotuksessa.

Inhimillisten virheiden tarkastelu ydinvoimalaitosten käyttökokemusten hyödyntämisessä

Tässä työssä on kuvattu ydinvoimalaitosten käyttökokemusten tutkimusta keskittyen erityisesti inhimillisten toimintojen tarkasteluun. Työssä on kerrottu kansainvälisistä vaatimuksista ja järjestöistä sekä yleisesti käyttökokemusten tutkimuksessa käytössä olevista menetelmistä keskittyen perussyyanalyysimenetelmiin. Suomen osalta työssä on käsitelty lainsäädännön asettamia velvoitteita ja muita vaatimuksia, jotka ydinvoima-alalla koostuvat lähinnä Säteilyturvakeskuksen YVL-ohjeista. Viranomaisena toimivan Säteilyturvakeskuksen, alan tutkimusta suorittavan Valtion teknillisen tutkimuskeskuksen ja Teollisuuden Voima Oy:n käyttökokemusten tutkimiseen liittyvät organisaatiot ja menettelytavat on esitelty. Fortum Power and Heat Oy:n omistaman ja käyttämän Loviisan ydinvoimalaitoksen käyttökokemusten hyödyntäminen on käsitelty tarkemmin. Loviisan voimalaitoksen organisaatio ja käyttökokemusten sekä inhimillisten virheiden käsittelymenetelmiä on esitelty ja analysoitu. Työn alkuvaiheessa Loviisan voimalaitoksella inhimillisistä virheistä kerätystä tiedosta koottu tietokanta järjesteltiin kuntoon. Järjestelyn jälkeen tietoa analysoitiin ja analysoinnin tulokset on esitetty tässä työssä. Sekä järjestelyn että analysoinnin aikana havaitut kehityskohteet kirjattiin muistiin. Pienet toimenpiteet suoritettiin heti ja suuremmat kirjattiin tämän työn toimenpide-ehdotuksiin. Kehittämiskeinoja on ehdotettu virheiden luokittelumenetelmään ja käyttökokemusten käsittelymenetelmiin.

Rakennukset ja rakentajat Raision Ihalassa rautakauden lopulla ja varhaisella keskiajalla

Turun yliopiston arkeologian oppiaine tutki Raision Ihalan historiallisella kylätontilla, ns. Mullin eduspellolla, asuinpaikan, josta löydettiin maamme oloissa harvinaisen hyvin säilyneitä rakennusten puuosien jäännöksiä. Löytö on ainutlaatuinen Suomen oloissa ja sillä on kansainvälistäkin merkitystä, koska hyvin säilyneet myöhemmän rautakauden ja varhaisen keskiajan maaseutuasuinpaikat, joista tavataan puujäännöksiä, ovat harvinaisia erityisesti itäisen Itämeren piirissä. Rakennukset on ennallistettu käyttäen tiukkaa paikallisen analogian (’Tight Local Analogy’) metodia, erityisesti suoraa historiallista analogista lähestymistapaa. Tätä tarkoitusta varten muodostettiin aluksi arkeologinen, historiallinen ja etnografinen lähdemalli. Tämä valittiin maantieteellisesti ja ajallisesti relevantista tutkimusaineistosta pohjoisen Itämeren piiristä. Tiedot lounaisen Suomen rakennuksista ja rakennusteknologiasta katsottiin olevan tärkein osa mallia johtuen historiallisesta ja spatiaalisesta jatkuvuudesta. Lähdemalli yhdistettiin sitten Mullin arkeologiseen aineistoon ja analyysin tuloksena saatiin rakennusten ennallistukset. Mullista on voitu ennallistaa ainakin kuusi eri rakennusta neljässä eri rakennuspaikassa. Rakennusteknologia perustui kattoa kannattaviin horisontaalisiin pitkiin seinähirsiin, jotka oli nurkissa yhdistetty joko salvoksella tai varhopatsaalla. Kaikissa rakennuksissa ulkoseinän pituus oli 5 – 7 metriä. Löydettiin lisäksi savi- ja puulattioita sekä kaksi tulisijaa, savikupoliuuni ja avoin liesi. Runsaan palaneen saven perusteella on mahdollista päätellä, että katto oli mitä todennäköisimmin kaksilappeinen vuoliaiskatto, joka oli katettu puulla ja/tai turpeella. Kaikki rakennukset olivat samaa tyyppiä ja ne käsittivät isomman huoneen ja kapean eteisen. Kaikki analysoitu puu oli mäntyä. Ulkoalueelta tavattiin lisäksi tunkioita, ojia, aitoja ja erilaisia varastokuoppia. Rakennukset on ajoitettu 900-luvun lopulta 1200-luvun lopulle (cal AD). Lopuksi tutkittiin rakennuksia yhteisöllisessä ympäristössään, niiden ajallista asemaa sekä asukkaiden erilaisia spatiaalisia kokemuksia ja yhteyksiä. Raision Ihalaa analysoidaan sosiaalisen identiteetin ja sen materiaalisten ilmenemismuotojen kautta. Nämä sosiaaliset identiteetit muodostuvat kommunikaatioverkostoista eri spatiaalisilla ja yhteisöllisillä ta¬soilla. Näitä eri tasoja ovat: 1) kotitalous arjen toimintoineen, perhe ja sukulaisuussuhteet traditioineen; 2) paikallinen identiteetti, rakennus, rakennuspaikka, asuinpaikan ympäristö ja sen käyttö, (maa)talo ja kylä; 3) Raision Ihalan kylä laajemmassa alueellisessa kontekstissaan pohjoisen Itämeren piirissä: kauppiaiden ja käsityöläisten kontaktiverkostot, uskonnollinen identiteetti ja sen muutokset.

ContinuousMultimodal Global Optimization with Differential Evolution-Based Methods

Metaheuristic methods have become increasingly popular approaches in solving global optimization problems. From a practical viewpoint, it is often desirable to perform multimodal optimization which, enables the search of more than one optimal solution to the task at hand. Population-based metaheuristic methods offer a natural basis for multimodal optimization. The topic has received increasing interest especially in the evolutionary computation community. Several niching approaches have been suggested to allow multimodal optimization using evolutionary algorithms. Most global optimization approaches, including metaheuristics, contain global and local search phases. The requirement to locate several optima sets additional requirements for the design of algorithms to be effective in both respects in the context of multimodal optimization. In this thesis, several different multimodal optimization algorithms are studied in regard to how their implementation in the global and local search phases affect their performance in different problems. The study concentrates especially on variations of the Differential Evolution algorithm and their capabilities in multimodal optimization. To separate the global and local search search phases, three multimodal optimization algorithms are proposed, two of which hybridize the Differential Evolution with a local search method. As the theoretical background behind the operation of metaheuristics is not generally thoroughly understood, the research relies heavily on experimental studies in finding out the properties of different approaches. To achieve reliable experimental information, the experimental environment must be carefully chosen to contain appropriate and adequately varying problems. The available selection of multimodal test problems is, however, rather limited, and no general framework exists. As a part of this thesis, such a framework for generating tunable test functions for evaluating different methods of multimodal optimization experimentally is provided and used for testing the algorithms. The results demonstrate that an efficient local phase is essential for creating efficient multimodal optimization algorithms. Adding a suitable global phase has the potential to boost the performance significantly, but the weak local phase may invalidate the advantages gained from the global phase.

Sekajätteen koostumustutkimusten luokitteluohjeen päivittäminen ja testaaminen

Tässä diplomityössä päivitettiin ja testattiin sekajätteen koostumustutkimuksiin tarkoitettua jätejakeiden luokitteluohjetta. Työn tavoitteena oli selvittää, miten luokitteluohje vastaa jätelainsäädännön muutoksiin ja tavoitteisiin, miten ohje toimii käytännössä sekä miten luokitteluohjetta tulee päivittää, jotta se sekä vastaa jätelainsäädännön ja jätealan toimijoiden tietotarpeisiin sekajätteen koostumuksesta että toimii myös käytännössä. Työssä toteutettiin kyselytutkimus ja kaksi sekajätteen koostumustutkimusta. Jätealan toimijoille lähetetyn kyselyn avulla kartoitettiin luokitteluohjeen kehityskohtia. Kyselytutkimuksen vastaajat kokivat, että luokitteluohjeessa on eniten kehitettävää muovien luokittelussa. Muovien luokittelun lisäksi biojätteen sekä kierrätettävien ja vaarallisten jätteiden luokitteluun liittyvät mahdolliset kehityskohdat muodostettiin kyselyn vastausten perusteella. Sekajätteen koostumustutkimusten avulla testattiin luokitteluohjeen toimivuutta. Koostumustutkimukset toteutettiin ohjeen tarkimman tason mukaisesti. Jätteiden lajittelu osoittautui huomattavasti hitaammaksi kuin etukäteen oli arvioitu. Lisäksi monia materiaaleja sisältävien jätteiden lajittelu oli haasteellista molemmissa tutkimuksissa. Luokitteluohjetta päivitettiin kyselytutkimuksen ja koostumustutkimusten perusteella. Jätteet on luokiteltu päivitetyssä ohjeessa alkuperäisen ohjeen tavoin jätemateriaalien perusteella. Luokitteluohjetta päivitettiin jäteluokkien termistön sekä keittiöjätteen ja kierrätettävien jätteiden luokittelun osalta. Päivitetyn ohjeen avulla koostumustutkimuksen toteuttaja saa enemmän tietoa sekajätteestä biojätteen sekä kierrätettävien jätteiden osalta, mikä on tärkeää jätelainsäädännöllisten tavoitteiden kannalta.

Finding Methods for Recognizing and Classifying Spare Part Criticality – Case Full Deposit Stripping Machines

The aim of this Master’s thesis is to find a method for classifying spare part criticality in the case company. Several approaches exist for criticality classification of spare parts. The practical problem in this thesis is the lack of a generic analysis method for classifying spare parts of proprietary equipment of the case company. In order to find a classification method, a literature review of various analysis methods is required. The requirements of the case company also have to be recognized. This is achieved by consulting professionals in the company. The literature review states that the analytic hierarchy process (AHP) combined with decision tree models is a common method for classifying spare parts in academic literature. Most of the literature discusses spare part criticality in stock holding perspective. This is relevant perspective also for a customer orientated original equipment manufacturer (OEM), as the case company. A decision tree model is developed for classifying spare parts. The decision tree classifies spare parts into five criticality classes according to five criteria. The criteria are: safety risk, availability risk, functional criticality, predictability of failure and probability of failure. The criticality classes describe the level of criticality from non-critical to highly critical. The method is verified for classifying spare parts of a full deposit stripping machine. The classification can be utilized as a generic model for recognizing critical spare parts of other similar equipment, according to which spare part recommendations can be created. Purchase price of an item and equipment criticality were found to have no effect on spare part criticality in this context. Decision tree is recognized as the most suitable method for classifying spare part criticality in the company.

Local Binary Patterns in Focal-Plane Processing. Analysis and Applications

Feature extraction is the part of pattern recognition, where the sensor data is transformed into a more suitable form for the machine to interpret. The purpose of this step is also to reduce the amount of information passed to the next stages of the system, and to preserve the essential information in the view of discriminating the data into different classes. For instance, in the case of image analysis the actual image intensities are vulnerable to various environmental effects, such as lighting changes and the feature extraction can be used as means for detecting features, which are invariant to certain types of illumination changes. Finally, classification tries to make decisions based on the previously transformed data. The main focus of this thesis is on developing new methods for the embedded feature extraction based on local non-parametric image descriptors. Also, feature analysis is carried out for the selected image features. Low-level Local Binary Pattern (LBP) based features are in a main role in the analysis. In the embedded domain, the pattern recognition system must usually meet strict performance constraints, such as high speed, compact size and low power consumption. The characteristics of the final system can be seen as a trade-off between these metrics, which is largely affected by the decisions made during the implementation phase. The implementation alternatives of the LBP based feature extraction are explored in the embedded domain in the context of focal-plane vision processors. In particular, the thesis demonstrates the LBP extraction with MIPA4k massively parallel focal-plane processor IC. Also higher level processing is incorporated to this framework, by means of a framework for implementing a single chip face recognition system. Furthermore, a new method for determining optical flow based on LBPs, designed in particular to the embedded domain is presented. Inspired by some of the principles observed through the feature analysis of the Local Binary Patterns, an extension to the well known non-parametric rank transform is proposed, and its performance is evaluated in face recognition experiments with a standard dataset. Finally, an a priori model where the LBPs are seen as combinations of n-tuples is also presented

A modified structural stress method for fatigue assessment of welded structures

Fatigue life assessment of weldedstructures is commonly based on the nominal stress method, but more flexible and accurate methods have been introduced. In general, the assessment accuracy is improved as more localized information about the weld is incorporated. The structural hot spot stress method includes the influence of macro geometric effects and structural discontinuities on the design stress but excludes the local features of the weld. In this thesis, the limitations of the structural hot spot stress method are discussed and a modified structural stress method with improved accuracy is developed and verified for selected welded details. The fatigue life of structures in the as-welded state consists mainly of crack growth from pre-existing cracks or defects. Crack growth rate depends on crack geometry and the stress state on the crack face plane. This means that the stress level and shape of the stress distribution in the assumed crack path governs thetotal fatigue life. In many structural details the stress distribution is similar and adequate fatigue life estimates can be obtained just by adjusting the stress level based on a single stress value, i.e., the structural hot spot stress. There are, however, cases for which the structural stress approach is less appropriate because the stress distribution differs significantly from the more common cases. Plate edge attachments and plates on elastic foundations are some examples of structures with this type of stress distribution. The importance of fillet weld size and weld load variation on the stress distribution is another central topic in this thesis. Structural hot spot stress determination is generally based on a procedure that involves extrapolation of plate surface stresses. Other possibilities for determining the structural hot spot stress is to extrapolate stresses through the thickness at the weld toe or to use Dong's method which includes through-thickness extrapolation at some distance from the weld toe. Both of these latter methods are less sensitive to the FE mesh used. Structural stress based on surface extrapolation is sensitive to the extrapolation points selected and to the FE mesh used near these points. Rules for proper meshing, however, are well defined and not difficult to apply. To improve the accuracy of the traditional structural hot spot stress, a multi-linear stress distribution is introduced. The magnitude of the weld toe stress after linearization is dependent on the weld size, weld load and plate thickness. Simple equations have been derived by comparing assessment results based on the local linear stress distribution and LEFM based calculations. The proposed method is called the modified structural stress method (MSHS) since the structural hot spot stress (SHS) value is corrected using information on weld size andweld load. The correction procedure is verified using fatigue test results found in the literature. Also, a test case was conducted comparing the proposed method with other local fatigue assessment methods.

Classification-Based compression of Multispectral Images

The purpose of this thesis is to present a new approach to the lossy compression of multispectral images. Proposed algorithm is based on combination of quantization and clustering. Clustering was investigated for compression of the spatial dimension and the vector quantization was applied for spectral dimension compression. Presenting algo¬rithms proposes to compress multispectral images in two stages. During the first stage we define the classes' etalons, another words to each uniform areas are located inside the image the number of class is given. And if there are the pixels are not yet assigned to some of the clusters then it doing during the second; pass and assign to the closest eta¬lons. Finally a compressed image is represented with a flat index image pointing to a codebook with etalons. The decompression stage is instant too. The proposed method described in this paper has been tested on different satellite multispectral images from different resources. The numerical results and illustrative examples of the method are represented too.

Classification and inventory management of abnormal demand items

The main objective of the study is to form a framework that provides tools to recognise and classify items whose demand is not smooth but varies highly on size and/or frequency. The framework will then be combined with two other classification methods in order to form a three-dimensional classification model. Forecasting and inventory control of these abnormal demand items is difficult. Therefore another object of this study is to find out which statistical forecasting method is most suitable for forecasting of abnormal demand items. The accuracy of different methods is measured by comparing the forecast to the actual demand. Moreover, the study also aims at finding proper alternatives to the inventory control of abnormal demand items. The study is quantitative and the methodology is a case study. The research methods consist of theory, numerical data, current state analysis and testing of the framework in case company. The results of the study show that the framework makes it possible to recognise and classify the abnormal demand items. It is also noticed that the inventory performance of abnormal demand items differs significantly from the performance of smoothly demanded items. This makes the recognition of abnormal demand items very important.

Determining the location for a mobile device by utilization of local resources of the environment

The subject being analyzed of this Master’s Thesis is a development of a service that is used to define a current location of a mobile device. The service utilized data that is obtained from own GPS receiver in some possible cases and as well data from mobile devices which can be afforded for the current environment for acquisition of more precise position of the device. The computation environment is based on context of a mobile device. The service is implemented as an application for communicator series Nokia N8XX. The Master’s Thesis presents theoretical concept of the method and its practical implementation, architecture of the application, requirements and describes a process of its functionality. Also users’ work with application is presented and recommendations for possible future improvements are made.

Purchasing portfolio analysis and supplier classification

The purpose of the thesis is to classify suppliers and to enhance strategic purchasing in the case company. Supplier classification is conducted to fulfill the requirements of the company quality manual and international quality standards. To gain more benefit, a strategic purchasing tool, Kraljic’s purchasing portfolio and analytical hierarchy process are utilized for the base of supplier classification. Purchasing portfolio is used to give quick and easy visual insight on product group management form the viewpoint of purchasing. From the base on purchasing portfolio alternative purchasing and supplier strategies can be formed that enhance the strategic orientation of purchasing. Thus purchasing portfolio forces the company to orient on proactive and strategic purchasing. As a result a survey method for implementing purchasing portfolio in the company is developed that exploits analytical hierarchy process. Experts from the company appoint the categorization criteria and in addition, participate in the survey to categorize product groups on the portfolio. Alternative purchasing strategies are formed. Suppliers are classified depending on the importance and characteristics of the product groups supplied.