Analysis of Satellite Data for Forest Segmentation

In this work we study the classification of forest types using mathematics based image analysis on satellite data. We are interested in improving classification of forest segments when a combination of information from two or more different satellites is used. The experimental part is based on real satellite data originating from Canada. This thesis gives summary of the mathematics basics of the image analysis and supervised learning , methods that are used in the classification algorithm. Three data sets and four feature sets were investigated in this thesis. The considered feature sets were 1) histograms (quantiles) 2) variance 3) skewness and 4) kurtosis. Good overall performances were achieved when a combination of ASTERBAND and RADARSAT2 data sets was used.

Segmentation of Industrial Customers – Case: Finnish Mechanical Engineering Companies

Segmentointi on perinteisesti ollut erityisesti kuluttajamarkkinoinnin työkalu, mutta siirtymä tuotteista palveluihin on lisännyt segmentointitarvetta myös teollisilla markkinoilla. Tämän tutkimuksen tavoite on löytää selkeästi toisistaan erottuvia asiakasryhmiä suomalaisen liikkeenjohdon konsultointiyritys Synocus Groupin tarjoaman case-materiaalin pohjalta. K-means-klusteroinnin avulla löydetään kolme potentiaalista markkinasegmenttiä perustuen siihen, mitkä tarjoamaelementit 105 valikoitua suomalaisen kone- ja metallituoteteollisuuden asiakasta ovat maininneet tärkeimmiksi. Ensimmäinen klusteri on hintatietoiset asiakkaat, jotka laskevat yksikkökohtaisia hintoja. Toinen klusteri koostuu huolto-orientoituneista asiakkaista, jotka laskevat tuntikustannuksia ja maksimoivat konekannan käyttötunteja. Tälle kohderyhmälle kannattaisi ehkä markkinoida teknisiä palveluja ja huoltosopimuksia. Kolmas klusteri on tuottavuussuuntautuneet asiakkaat, jotka ovat kiinnostuneita suorituskyvyn kehittämisestä ja laskevat tonnikohtaisia kustannuksia. He tavoittelevat alempia kokonaiskustannuksia lisääntyneen suorituskyvyn, pidemmän käyttöiän ja alempien huoltokustannusten kautta.

Dental Health in Primary Teeth after Prevention of Mother-Child Transmission of Mutans Streptococci. A Historical Cohort Study on Restorative Visits and Maternal Prevention Costs

Mutansstreptokokkitartunnan ehkäisemisen pitkäaikaisvaikutukset maitohampaiden terveyteen. Kohorttitutkimus korjaavan hoidon määrästä ja kariesehkäisyn kustannuksista. Tutkimuksen tarkoituksena oli selvittää varhaisen mutansstreptokokki (MS)-kolonisaation ehkäisyn pitkäaikaisvaikutuksia korkean kariesriskin omaavien lasten maitohampaistossa sekä tarkastella MS-tartunnan estämisen kustannuksia. Tiedot lasten hampaiden terveydestä ja hammashoitotoimenpiteistä syntymästä 10-vuotiaaksi sekä äiteihin kohdistuneen kariesehkäisyn kustannuksista kerättiin Ylivieskan terveyskeskuksen asiakirjoista. Tutkimuksessa oli mukana yhteensä 507 lasta, heistä 148 oli osallistunut aikaisempaan Ylivieskan äiti-lapsitutkimukseen, jossa verrattiin äitien käyttämän ksylitolipurukumin ja äidille tehtyjen fluori- tai klooriheksidiinilakkausten vaikutusta pikkulasten hampaiden terveyteen. Maitohammaskariesta esiintyi 10-vuotiaaksi asti merkitsevästi vähemmän lapsilla, jotka eivät olleet saaneet MS-tartuntaa alle 2-vuotiaana, heidän maitohampaansa säilyivät 3,4 vuotta kauemmin täysin ehjinä (p<0.001) ja he tarvitsivat vähemmän maitohampaiden korjaavaa hoitoa (p=0.005) kuin lapset, joiden hampaisto oli kolonisoitunut MS-bakteerilla jo 2-vuotiaana. Koska ksylitoliryhmän lasten MS-kolonisaatio oli vähäisintä, heidän maitohampaissaan oli vähemmän kariesta ja korjaavan hoidon tarvetta kuin kahden muun korkeariskisen ryhmän lapsilla. Äitien käyttämän ksylitolipurukumin kustannukset olivat yhteensä 116 euroa ja lapsen maitohampaiden säilyminen täysin ehjinä vuoden pidempään maksoi 37 euroa. Kun MS-tartunta oli saatu estettyä, korkean kariesriskin omaavien lasten hampaiden terveys oli samalla tasolla kuin keskimäärin koko ikäkohortilla. Lapsen maitohampaat säilyvät terveinä pidempään ja korjaavan hoidon tarve vähenee, kun MS-kolonisaatio alle 2-vuotiaana saadaan estettyä. Lapsen MS-kolonisaatio vähenee merkitsevästi, kun äiti käyttää ksylitolipurukumia lapsen ollessa 0-2 vuoden ikäinen, siten pikkulapsen äidin säännöllinen ksylitolipurukumin käyttö saattaa olla julkisen tereydenhuollon kannalta tarkoituksenmukainenterveyttä edistävä menetelmä.

Speaker diarization: Segmentation and clustering of speeches

Speaker diarization is the process of sorting speeches according to the speaker. Diarization helps to search and retrieve what a certain speaker uttered in a meeting. Applications of diarization systemsextend to other domains than meetings, for example, lectures, telephone, television, and radio. Besides, diarization enhances the performance of several speech technologies such as speaker recognition, automatic transcription, and speaker tracking. Methodologies previously used in developing diarization systems are discussed. Prior results and techniques are studied and compared. Methods such as Hidden Markov Models and Gaussian Mixture Models that are used in speaker recognition and other speech technologies are also used in speaker diarization. The objective of this thesis is to develop a speaker diarization system in meeting domain. Experimental part of this work indicates that zero-crossing rate can be used effectively in breaking down the audio stream into segments, and adaptive Gaussian Models fit adequately short audio segments. Results show that 35 Gaussian Models and one second as average length of each segment are optimum values to build a diarization system for the tested data. Uniting the segments which are uttered by same speaker is done in a bottom-up clustering by a newapproach of categorizing the mixture weights.

Histopathological and histomicrobiological study of root canal therapy medication, comparison of calcium hydroxide versus gutta-percha with zinc oxide/eugenol in the teeth of dogs

The presence of microorganisms in dental structures with experimentally induced necrosis was evaluated. The materials were tested to evaluate their antimicrobial activity and tissue repair efficacy. Four dogs were used in this experiment, with a total of 64 roots of premolar teeth, divided into three groups. The root canals of Group I were filled with gutta-percha and zinc oxide/eugenol cement; Group II were filled with calcium hydroxide, and Group III were not filled. All animals were clinically and radiographically examined 15 days after surgery andthen again every subsequent 15 days until 120 days, when the teeth were extracted en bloc.Histopathological analysis showed inflammatory infiltration, cement and bone resorption andnecrotic tissue in the apical delta in different proportions. Histomicrobiological analysis showedthe presence of microorganisms inside the teeth structures, with different concentrationsaccording to the treatment used. There was statistical significance between the groups(p>0.05). Gutta-percha with zinc oxide/eugenol demonstrated good antimicrobial activity;calcium hydroxide was not efficient. The conclusion of this study is that gutta-percha withzinc oxide/eugenol is the better protocol for filling root canals in dogs.

The effect of timing temporary cements to treat induced pulp necrosis in the teeth of dogs

During endodontic therapy (pulpectomy, root canal debridement and root canal filling) microbiological management is a major concern. Bacteria present in dentine tubules, apical foramina and apical delta are causally related to failure of the procedure. Studies have shown that during single session endodontic treatment bacteria remain within dental structures. The aim of the present study was to evaluate endodontic treatment performed as two sessions, using temporary endodontic dressing materials for different periods in four groups of experimental dogs. A total of 80 roots of second and third upper premolar teeth and second, third and fourth lower premolar teeth were divided into four groups. The pulp chamber was opened with burrs and the pulp exposed for 60 days to induce pulpal inflammation and necrosis. Groups II, III and IV were treated with calcium hydroxide plus camphorated paramono-chlorophenol (PMCC) for 7, 15 and 30 days, respectively. In all groups, the root canals were filled with zinc oxide-eugenol and gutta-percha cones. Clinical and radiographical measurements were performed every 2 weeks. After 60 days a small block section containing the teeth, surrounding periapical tissues and the periodontium was removed for histological and microbiological study. Histological analysis revealed intense inflammatory response in all groups. Microbiological analysis showed microbial reduction inversely proportional to the period of time that the intracanal temporary medicament was left in place.

Macroscopic description of teeth of Azara's agouti (Dasyprocta azarae)

The teeth of Azara's agouti (Dasyprocta azarae) were described macroscopically in order to provide biological data on one of the largest wild rodents of the Americas. Radiography was taken on six heads and the teeth were described. Enamel surrounds the coronal dentin, projects to the roots and is present as parallel inner laminae in buccolingual direction. The dentin is located among the enamel laminae and surrounds the pulp horns. The cementum is located internally to the enamel laminae. On the lingual surface, the cementum and dentin are the outer elements.

Customer Segmentation in Industrial Markets - CASE: Labelstock Company

The aim of this thesis is to study segmentation in industrial markets and develop a segmenting method proposal and criteria case study for a labelstock manufacturing company. An industrial company is facing many different customers with varying needs. Market segmentation is a process for dividing a market into smaller groups in which customers have the same or similar needs. Segmentation gives tools to the marketer to better match the product or service more closely to the needs of the target market. In this thesis a segmentation tool proposal and segmenting criteria is case studied for labelstock company’s Europe, Middle East and Africa business area customers and market. In the developed matrix tool different customers are planned to be evaluated based on customer characteristic variables. The criteria for the evaluating matrix are based on the customer’s buying organizations characteristics and buying behaviour. There are altogether 13 variables in the evaluating matrix. As an example of variables there are loyalty, size of the customer, estimated growth of the customer purchases and customer’s decision-making and buying behaviour. These characteristic variables will help to identify market segments to target and the customers belonging to those segments.

Anatomical and histological characteristics of teeth in agouti (Dasyprocta prymnolopha Wagler, 1831)

The agouti species Dasyprocta prymnolopha (D. prymnolopha) is a medium-sized rodent, diurnal, and characteristic of northeastern Brazil, south of the Amazon. Several studies have been made on these rodents. However, there is a lack of analysis of masticatory system, in particular morphology of the teeth. Thus, this research seeks to describe anatomical and histological aspects of the agouti teeth. For this purpose, we used adult agouti, in which measurements and descriptions of teeth and dental tissues were made. It was observed that the dental arch of D. prymnolopha comprises of twenty teeth, evenly distributed in the upper and lower arch, being inferior teeth larger than their corresponding higher. The incisors are larger, and between the posterior premolars and molars, there is a gradual increase in length in the anterior-posterior arch. In microscopic examination, a prismatic appearance was observed consisting of enamel prisms arranged in different directions, behind the enamel and dentin with standard tubular dentinal tubules with variable diameter and far between, also showing a sinuous path from the inner portion to the junction with more superficial enamel. Morphological analysis of dental tissues showed that an enamel with structural organization adapted to the act of chewing and high impact dentin compatible with standard tubular function resilience and mechanical damping of masticatory forces, as found in larger animals, confirming the understanding of eating habits that define much of its ecological functions within the ecosystem they inhabit.

Visual customer segmentation and behavior analysis : a SOM-based approach

Ett ämne som väckt intresse både inom industrin och forskningen är hantering av kundförhållanden (CRM, eng. Customer Relationship Management), dvs. en kundorienterad affärsstrategi där företagen från att ha varit produktorienterade väljer att bli mera kundcentrerade. Numera kan kundernas beteende och aktiviteter lätt registreras och sparas med hjälp av integrerade affärssystem (ERP, eng. Enterprise Resource Planning) och datalager (DW, eng. Data Warehousing). Kunder med olika preferenser och köpbeteende skapar sin egen ”signatur” i synnerhet via användningen av kundkort, vilket möjliggör mångsidig modellering av kundernas köpbeteende. För att få en översikt av kundernas köpbeteende och deras lönsamhet, används ofta kundsegmentering som en metod för att indela kunderna i grupper utgående från deras likheter. De mest använda metoderna för kundsegmentering är analytiska modeller konstruerade för en viss tidsperiod. Dessa modeller beaktar inte att kundernas beteende kan förändras med tiden. I föreliggande avhandling skapas en holistisk översikt av kundernas karaktär och köpbeteende som utöver de konventionella segmenteringsmodellerna även beaktar dynamiken i köpbeteendet. Dynamiken i en kundsegmenteringsmodell innefattar förändringar i segmentens struktur och innehåll, samt förändringen av individuella kunders tillhörighet i ett segment (s.k migrationsanalyser). Vardera förändringen modelleras, analyseras och exemplifieras med visuella datautvinningstekniker, främst med självorganiserande kartor (SOM, eng. Self-Organizing Maps) och självorganiserande tidskartor (SOTM), en vidareutveckling av SOM. Visualiseringen anteciperas underlätta tolkningen av identifierade mönster och göra processen med kunskapsöverföring mellan den som gör analysen och beslutsfattaren smidigare. Asiakkuudenhallinta (CRM) eli organisaation muuttaminen tuotepainotteisesta asiakaskeskeiseksi on herättänyt mielenkiintoa niin yliopisto- kuin yritysmaailmassakin. Asiakkaiden käyttäytymistä ja toimintaa pystytään nykyään helposti tallentamaan ja varastoimaan toiminnanohjausjärjestelmien ja tietovarastojen avulla; asiakkaat jättävät jatkuvasti piirteistään ja ostokäyttäytymisestään kertovia tietojälkiä, joita voidaan analysoida. On tavallista, että asiakkaat poikkeavat toisistaan eri tavoin, ja heidän mieltymyksensä kuten myös ostokäyttäytymisensä saattavat olla hyvinkin erilaisia. Asiakaskäyttäytymisen monimuotoisuuteen ja tuottavuuteen paneuduttaessa käytetäänkin laajalti asiakassegmentointia eli asiakkaiden jakamista ryhmiin samankaltaisuuden perusteella. Perinteiset asiakassegmentoinnin ratkaisut ovat usein yksittäisiä analyyttisia malleja, jotka on tehty tietyn aikajakson perusteella. Tämän vuoksi ne monesti jättävät huomioimatta sen, että asiakkaiden käyttäytyminen saattaa ajan kuluessa muuttua. Tässä väitöskirjassa pyritäänkin tarjoamaan holistinen kuva asiakkaiden ominaisuuksista ja ostokäyttäytymisestä tarkastelemalla kahta muutosvoimaa tiettyyn aikarajaukseen perustuvien perinteisten segmentointimallien lisäksi. Nämä kaksi asiakassegmentointimallin dynamiikkaa ovat muutokset segmenttien rakenteessa ja muutokset yksittäisten asiakkaiden kuulumisessa ryhmään. Ensimmäistä dynamiikkaa lähestytään ajallisen asiakassegmentoinnin avulla, jossa visualisoidaan ajan kuluessa tapahtuvat muutokset segmenttien rakenteissa ja profiileissa. Toista dynamiikkaa taas lähestytään käyttäen nk. segmenttisiirtymien analyysia, jossa visuaalisin keinoin tunnistetaan samantyyppisesti segmentistä toiseen vaihtavat asiakkaat. Visualisoinnin tehtävänä on tukea havaittujen kaavojen tulkitsemista sekä helpottaa tiedonsiirtoa analysoijan ja päättäjien välillä. Visuaalisia tiedonlouhintamenetelmiä, kuten itseorganisoivia karttoja ja niiden laajennuksia, käytetään osoittamaan näiden menetelmien hyödyllisyys sekä asiakkuudenhallinnassa yleisesti että erityisesti asiakassegmentoinnissa.

Supplier Segmentation for Nordic Petrochemical Industry

Objective of this thesis was to map possibilities for systematic supplier management in field of chemical process industry. Through this study it was aimed to develop a tool for supplier management that could be integrated with operations in business unit. With developed tool suppliers should be able to be segmented based on their willingness and capability, and segmentation could be applied in purchasing decisions. In this thesis there was made a survey of methods that are recognized in literature to manage and allocate suppliers. This thesis recognizes segmentation as a method to group and select suppliers in procurement. Based on literature, a proposal for segmentation framework and evaluation criteria factors will be constituted. Based on theoretical proposal, in an expertise workshop a final segmentation framework was constituted, which covers segments with descriptions and evaluation part. Evaluation part includes an evaluation framework which helps to score suppliers with selected factors and leads to total grades in willingness and capability. These total grades will be the coordinates and they determine the segment where the supplier under evaluation belongs. In this thesis segments definitions, objectives, and road maps will be described.

Segmentation of overlapping convex objects

This thesis presents a framework for segmentation of clustered overlapping convex objects. The proposed approach is based on a three-step framework in which the tasks of seed point extraction, contour evidence extraction, and contour estimation are addressed. The state-of-art techniques for each step were studied and evaluated using synthetic and real microscopic image data. According to obtained evaluation results, a method combining the best performers in each step was presented. In the proposed method, Fast Radial Symmetry transform, edge-to-marker association algorithm and ellipse fitting are employed for seed point extraction, contour evidence extraction and contour estimation respectively. Using synthetic and real image data, the proposed method was evaluated and compared with two competing methods and the results showed a promising improvement over the competing methods, with high segmentation and size distribution estimation accuracy.

Supplier segmentation and development in project business

The purpose of this study was to expand the applicability of supplier segmentation and development approaches to the project-driven construction industry. These practices are less exploited and not well documented in this operational environment compared to the process-centric manufacturing industry. At first, portfolio models to supply base segmentation and various supplier development efforts were investigated in literature review. A step-wise framework was structured for the empirical research. The empirical study employed multiple research methods in three case studies in a large Finnish construction company. The first study categorized the construction item classes into the purchasing portfolio and positioned suppliers to the power matrix by investigating buyer-supplier relations. Using statistical tests, the study also identified factors that affect suppliers’ performance. The final case study identified improvement areas of the interface between a main contractor and one if its largest suppliers. The final results indicate that only by assessing the supply base in a holistic manner and the power circumstances in it, buyers comprehend how to best establish appropriate supplier development strategies in the project environment.

Statistical segmentation methods and color variance analysis of retinal images

In this research, the effectiveness of Naive Bayes and Gaussian Mixture Models classifiers on segmenting exudates in retinal images is studied and the results are evaluated with metrics commonly used in medical imaging. Also, a color variation analysis of retinal images is carried out to find how effectively can retinal images be segmented using only the color information of the pixels.