Land use/cover classification in the Brazilian Amazon using satellite images

Land use/cover classification is one of the most important applications in remote sensing. However, mapping accurate land use/cover spatial distribution is a challenge, particularly in moist tropical regions, due to the complex biophysical environment and limitations of remote sensing data per se. This paper reviews experiments related to land use/cover classification in the Brazilian Amazon for a decade. Through comprehensive analysis of the classification results, it is concluded that spatial information inherent in remote sensing data plays an essential role in improving land use/cover classification. Incorporation of suitable textural images into multispectral bands and use of segmentation‑based method are valuable ways to improve land use/cover classification, especially for high spatial resolution images. Data fusion of multi‑resolution images within optical sensor data is vital for visual interpretation, but may not improve classification performance. In contrast, integration of optical and radar data did improve classification performance when the proper data fusion method was used. Among the classification algorithms available, the maximum likelihood classifier is still an important method for providing reasonably good accuracy, but nonparametric algorithms, such as classification tree analysis, have the potential to provide better results. However, they often require more time to achieve parametric optimization. Proper use of hierarchical‑based methods is fundamental for developing accurate land use/cover classification, mainly from historical remotely sensed data.

Classification and fingerprinting of different berries based on biochemical profiling and antioxidant capacity

The objective of this work was to evaluate the biochemical composition of six berry types belonging to Fragaria, Rubus, Vaccinium and Ribes genus. Fruit samples were collected in triplicate (50 fruit each) from 18 different species or cultivars of the mentioned genera, during three years (2008 to 2010). Content of individual sugars, organic acids, flavonols, and phenolic acids were determined by high performance liquid chromatography (HPLC) analysis, while total phenolics (TPC) and total antioxidant capacity (TAC), by using spectrophotometry. Principal component analysis (PCA) and hierarchical cluster analysis (CA) were performed to evaluate the differences in fruit biochemical profile. The highest contents of bioactive components were found in Ribes nigrum and in Fragaria vesca, Rubus plicatus, and Vaccinium myrtillus. PCA and CA were able to partially discriminate between berries on the basis of their biochemical composition. Individual and total sugars, myricetin, ellagic acid, TPC and TAC showed the highest impact on biochemical composition of the berry fruits. CA separated blackberry, raspberry, and blueberry as isolate groups, while classification of strawberry, black and red currant in a specific group has not occurred. There is a large variability both between and within the different types of berries. Metabolite fingerprinting of the evaluated berries showed unique biochemical profiles and specific combination of bioactive compound contents.

Prediction of crude protein and classification of the growth stage of wheat plant samples from NIR spectra

Near-infrared spectroscopy (NIRS) was used to analyse the crude protein content of dried and milled samples of wheat and to discriminate samples according to their stage of growth. A calibration set of 72 samples from three growth stages of wheat (tillering, heading and harvest) and a validation set of 28 samples was collected for this purpose. Principal components analysis (PCA) of the calibration set discriminated groups of samples according to the growth stage of the wheat. Based on these differences, a classification procedure (SIMCA) showed a very accurate classification of the validation set samples : all of them were successfully classified in each group using this procedure when both the residual and the leverage were used in the classification criteria. Looking only at the residuals all the samples were also correctly classified except one of tillering stage that was assigned to both tillering and heading stages. Finally, the determination of the crude protein content of these samples was considered in two ways: building up a global model for all the growth stages, and building up local models for each stage, separately. The best prediction results for crude protein were obtained using a global model for samples in the two first growth stages (tillering and heading), and using a local model for the harvest stage samples.

Quelle perception ont les médecins de famille en Suisse de leur rôle dans la prévention et la promotion de la santé? : comprendre les barrières à l'implémentation

Introduction: The importance of health promotion and prevention and the potential of general practitioners (GPs) to conduct individual prevention procedures have been demonstrated in several studies. Clinical recommendations for screening and prevention activities, an important condition for success, are published regularly, but their implementation into daily practice does not necessarily follow. Information is lacking about the actual conditions of how prevention is carried out on a daily basis by Swiss GPs, about their perceptions and needs, their attitudes and the present barriers they face. Such information is essential for the development of new tools and programs targeting better implementation of clinical recommendations for prevention in primary care in Switzerland. Objectives: The objectives of the study were to analyze how Swiss GPs perceive their role in prevention by obtaining information regarding the following issues: What do disease prevention and health promotion mean to them? What are the current incentives and barriers they face? What are their ideas and suggestions to deal with these barriers? What are their needs and expectations regarding prevention guidelines and tools? Methods: We conducted a qualitative research project using focus groups to examine the questions mentioned above. A total of 13 focus groups took place including GPs from eight cantons: five groups in German- speaking Switzerland and eight in French- speaking Switzerland. Each group was composed of 4-11 GPs, making in total 102 participants, who were paid expenses to cover their participation. The sessions were audio-recorded and transcribed verbatim. Data analysis: Content analysis of the transcriptions began by classifying the data according to a typology, the first level of which was developed in line with the structure of the interview guide. This typology was extended by successively regrouping similar statements. Synopsis and interpretation was then performed on each category thus obtained. This research report is based on the results from the French-speaking cantons. Results: Physicians perceive a change in their role as a consequence of changes in society and the health system. They emphasize the importance of a personalized and long lasting relationship between the family doctor and his/her patient; a privileged position allowing them to perform individualized prevention activities, considered to be more effective, as they are appropriate to the specific situation and needs of the patient. They point out their need for training and for better information concerning prevention and health promotion interventions, and stress difficulties arising from the lack of a clear political signal conferring them with a mandate for prevention. -- INTRODUCTION L'importance de la prévention et de la promotion de la santé et le potentiel des médecins de famillea à mettre en oeuvre des mesures individuelles de prévention, de dépistage et de conseils, a été démontrée dans plusieurs études. Régulièrement durant les dernières années, de nombreuses associations médicales ont publié des recommandations cliniques concernant les activités de dépistage et de prévention qui sont une condition essentielle pour le succès, mais ne sont pas forcément appliquées de manière systématique dans la pratique médicale quotidienne. Des contraintes spécifiques contribuent à l'écart entre le désir des médecins de pratiquer une médecine préventive et la réalité d'un cabinet médical. Nous n'avons que peu de données sur les conditions actuelles dans lesquelles la prévention et la promotion de la santé sont réalisées par les médecins de famille suisses dans leur travail quotidien. Des informations précises et représentatives sur leurs perceptions et leurs besoins, leurs attitudes et les contraintes auxquelles ils sont confrontés manquent. Or ces données sont essentielles dans le développement de nouveaux outils et programmes visant une meilleure implémentation des recommandations cliniques dans le domaine de la prévention et la promotion de la santé dans la médecine de famille en Suisse. OBJECTIFS Le développement de concepts pour une prévention systématique ainsi que d'outils adéquats, tout comme l'amélioration des conditions qui permettent une implémentation à grande échelle, implique, avant tout, l'analyse de la perception que les médecins de famille suisses ont de leur rôle dans la prévention. Par conséquent, cette étude a eu pour objectif d'obtenir des informations concernant les questions suivantes : ? Que signifient la prévention et la promotion de la santé pour les médecins de famille suisses ? ? Quelles sont leurs incitations et les barrières rencontrées ? ? Quelles sont leurs idées et leurs suggestions pour faire face à ces contraintes ? ? Quels sont leurs besoins et leurs attentes concernant les outils pour la prévention ? METHODES Nous avons mené un projet de recherche qualitative en utilisant la technique des focus groups pour examiner les questions mentionnées ci-dessus. Une telle technique de collecte de données est particulièrement adaptée à un domaine où l'on connaît mal les perceptions des parties prenantes. Nous avons mené 13 focus groups au total, comprenant des médecins issus de huit cantons: cinq groupes ont eu lieu en Suisse alémanique et huit groupes en Suisse romande. Chaque groupe était composé de 4 à 11 médecins de famille, avec au total 102 participants qui ont été défrayés pour leur participation. Les séances ont été audio-enregistrées et transcrites. ANALYSE DES DONNEES L'analyse du contenu des transcriptions a commencé par la classification des données selon une typologie dont le premier niveau a été développé à partir de la structure de la grille d'entretiens. Cette typologie a été affinée et élargie en regroupant successivement des propos similaires. Une synthèse a été effectuée pour chaque catégorie. Ce rapport est basé sur les résultats de l'analyse des données des cantons francophones. RESULTATS Les médecins perçoivent un changement de leur rôle dans une société et dans un système de santé qui évoluent. Ils soulignent l'importance de la relation personnalisée et durable du médecin de famille avec son patient, atout précieux, qui leur permet de réaliser des activités de prévention individualisées et adaptées à la situation et aux besoins du patient, considérées plus efficaces. Afin de surmonter leur doutes et découragement par rapport aux interventions de prévention, ils pointent la nécessité d'une formation aux nouvelles connaissances en prévention et promotion de la santé et d'une meilleure information aux médecins quant à leur efficacité et importance. Ils montrent le besoin d'un signal clair des politiques par rapport à l'attribution de ce mandat aux médecins de famille et de leur reconnaissance en tant qu'acteur de prévention dans le système de santé.

Variations of plasmid content in Rickettsia felis.

BACKGROUND: Since its first detection, characterization of R. felis has been a matter of debate, mostly due to the contamination of an initial R. felis culture by R. typhi. However, the first stable culture of R. felis allowed its precise phenotypic and genotypic characterization, and demonstrated that this species belonged to the spotted fever group rickettsiae. Later, its genome sequence revealed the presence of two forms of the same plasmid, physically confirmed by biological data. In a recent article, Gillespie et al. (PLoS One. 2007;2(3):e266.) used a bioinformatic approach to refute the presence of the second plasmid form, and proposed the creation of a specific phylogenetic group for R. felis. METHODOLOGY/PRINCIPAL FINDINGS: In the present report, we, and five independent international laboratories confirmed unambiguously by PCR the presence of two plasmid forms in R. felis strain URRWXCal(2) (T), but observed that the plasmid content of this species, from none to 2 plasmid forms, may depend on the culture passage history of the studied strain. We also demonstrated that R. felis does not cultivate in Vero cells at 37 degrees C but generates plaques at 30 degrees C. Finally, using a phylogenetic study based on 667 concatenated core genes, we demonstrated the position of R. felis within the spotted fever group. SIGNIFICANCE: We demonstrated that R. felis, which unambiguously belongs to the spotted fever group rickettsiae, may contain up to two plasmid forms but this plasmid content is unstable.

Using appearance and context for outdoor scene object classification

We propose a probabilistic object classifier for outdoor scene analysis as a first step in solving the problem of scene context generation. The method begins with a top-down control, which uses the previously learned models (appearance and absolute location) to obtain an initial pixel-level classification. This information provides us the core of objects, which is used to acquire a more accurate object model. Therefore, their growing by specific active regions allows us to obtain an accurate recognition of known regions. Next, a stage of general segmentation provides the segmentation of unknown regions by a bottom-strategy. Finally, the last stage tries to perform a region fusion of known and unknown segmented objects. The result is both a segmentation of the image and a recognition of each segment as a given object class or as an unknown segmented object. Furthermore, experimental results are shown and evaluated to prove the validity of our proposal

Comparison of Local Feature Detectors and Descriptors for Visual Object Categorization

Local features are used in many computer vision tasks including visual object categorization, content-based image retrieval and object recognition to mention a few. Local features are points, blobs or regions in images that are extracted using a local feature detector. To make use of extracted local features the localized interest points are described using a local feature descriptor. A descriptor histogram vector is a compact representation of an image and can be used for searching and matching images in databases. In this thesis the performance of local feature detectors and descriptors is evaluated for object class detection task. Features are extracted from image samples belonging to several object classes. Matching features are then searched using random image pairs of a same class. The goal of this thesis is to find out what are the best detector and descriptor methods for such task in terms of detector repeatability and descriptor matching rate.

Soil penetration resistance in a rhodic eutrudox affected by machinery traffic and soil water content

Soil compaction caused by machinery traffic reduces crop yields. This study aimed to evaluate the effects of intensive traffic, and the soil water content, on the soil penetration resistance (PR) of a Rhodic Eutrudox (Distroferric Red Latosol, Brazilian Classification), managed under no-tillage (NT). The experiment consisted of six treatments: NT with recent chiseling, NT without additional compaction, and NT with additional compaction by 4, 8, 10 and 20 passes of a harvester with a weight of 100 kN (70 kN on the front axle). Undisturbed soil samples were collected at 5.5-10.5 cm and 13.5-18.5 cm depth to quantify the soil bulk density (BD). The PR was assessed in four periods, using an impact penetrometer, inserted in the soil to a depth of 46 cm. The effect of traffic intensities on the PR was small when this variable was assessed with the soil in the plastic consistency. Differences in PR among treatments increased as the soil water content decreased. The increase in the values of PR and BD was higher in the first passes, but the increase in the number of traffics resulted in deeper soil compaction. The machinery traffic effects on PR are better characterized in the friable soil consistency.

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.

Assessment of Young Learners’ English Proficiency in Bilingual Content Instruction CLIL

This applied linguistic study in the field of second language acquisition investigated the assessment practices of class teachers as well as the challenges and visions of language assessment in bilingual content instruction (CLIL) at primary level in Finnish basic education. Furthermore, pupils’ and their parents’ perceptions of language assessment and LangPerform computer simulations as an alternative, modern assessment method in CLIL contexts were examined. The study was conducted for descriptive and developmental purposes in three phases: 1) a CLIL assessment survey; 2) simulation 1; and 3) simulation 2. All phases had a varying number of participants. The population of this mixed methods study were CLIL class teachers, their pupils and the pupils’ parents. The sampling was multi-staged and based on probability and random sampling. The data were triangulated. Altogether 42 CLIL class teachers nationwide, 109 pupils from the 3rd, 4th and 5th grade as well as 99 parents from two research schools in South-Western Finland participated in the CLIL assessment survey followed by an audio-recorded theme interview of volunteers (10 teachers, 20 pupils and 7 parents). The simulation experimentations 1 and 2 produced 146 pupil and 39 parental questionnaires as well as video interviews of volunteered pupils. The data were analysed both quantitatively using percentages and numerical frequencies and qualitatively employing thematic content analysis. Based on the data, language assessment in primary CLIL is not an established practice. It largely appears to be infrequent, incidental, implicit and based on impressions rather than evidence or the curriculum. The most used assessment methods were teacher observation, bilingual tests and dialogic interaction, and the least used were portfolios, simulations and peer assessment. Although language assessment was generally perceived as important by teachers, a fifth of them did not gather assessment information systematically, and 38% scarcely gave linguistic feedback to pupils. Both pupils and parents wished to receive more information on CLIL language issues; 91% of pupils claimed to receive feedback rarely or occasionally, and 63% of them wished to get more information on their linguistic coping in CLIL subjects. Of the parents, 76% wished to receive more information on the English proficiency of their children and their linguistic development. This may be a response to indirect feedback practices identified in this study. There are several challenges related to assessment; the most notable is the lack of a CLIL curriculum, language objectives and common ground principles of assessment. Three diverse approaches to language in CLIL that appear to affect teachers’ views on language assessment were identified: instrumental (language as a tool), dual (language as a tool and object of learning) and eclectic (miscellaneous views, e.g. affective factors prioritised). LangPerform computer simulations seem to be perceived as an appropriate alternative assessment method in CLIL. It is strongly recommended that the fundamentals for assessment (curricula and language objectives) and a mutual assessment scheme should be determined and stakeholders’ knowledge base of CLIL strengthened. The principles of adequate assessment in primary CLIL are identified as well as several appropriate assessment methods suggested.

Invenio customization for CERN Document Server

Presentation at Open Repositories 2014, Helsinki, Finland, June 9-13, 2014

Manual and semi-automatic quantification of in vivo ¹H-MRS data for the classification of human primary brain tumors

In vivo proton magnetic resonance spectroscopy (¹H-MRS) is a technique capable of assessing biochemical content and pathways in normal and pathological tissue. In the brain, ¹H-MRS complements the information given by magnetic resonance images. The main goal of the present study was to assess the accuracy of ¹H-MRS for the classification of brain tumors in a pilot study comparing results obtained by manual and semi-automatic quantification of metabolites. In vivo single-voxel ¹H-MRS was performed in 24 control subjects and 26 patients with brain neoplasms that included meningiomas, high-grade neuroglial tumors and pilocytic astrocytomas. Seven metabolite groups (lactate, lipids, N-acetyl-aspartate, glutamate and glutamine group, total creatine, total choline, myo-inositol) were evaluated in all spectra by two methods: a manual one consisting of integration of manually defined peak areas, and the advanced method for accurate, robust and efficient spectral fitting (AMARES), a semi-automatic quantification method implemented in the jMRUI software. Statistical methods included discriminant analysis and the leave-one-out cross-validation method. Both manual and semi-automatic analyses detected differences in metabolite content between tumor groups and controls (P < 0.005). The classification accuracy obtained with the manual method was 75% for high-grade neuroglial tumors, 55% for meningiomas and 56% for pilocytic astrocytomas, while for the semi-automatic method it was 78, 70, and 98%, respectively. Both methods classified all control subjects correctly. The study demonstrated that ¹H-MRS accurately differentiated normal from tumoral brain tissue and confirmed the superiority of the semi-automatic quantification method.

Evaluation of lignin content of soybean seed coat stored in a controlled environment

Breeding soybean for high seed quality is an important approach for developing cultivars for tropical regions, and the lignin content in the seed coat is one of the screening parameters for this trait. Considering that many breeding lines are evaluated in each growing season using the presently recommended method for lignin determination, a long period is required for the evaluation of the whole breeding program. This time limitation may influence lignin content assessment, if lignin is degraded during storage. This research reported was designed to determine whether lignin was degraded in the seed coat of soybean seed cultivars stored for one year in a controlled environment (10°C temperature and 50% air relative humidity). Seeds of 12 selected soybean cultivars that had a range in seed coat lignin content were evaluated. Seeds were hand harvested just after physiological maturity and evaluated for seed coat lignin content at harvest and after one year of storage in a cold room (10°C and 50% RH). The lignin content in seed coats differed significantly among cultivars in both analyses, but for both results the sequence of cultivar classification and the lignin content values of each cultivar did not change. A regression analysis of lignin content at harvest and after one year of storage indicated a direct relationship between both lignin determinations suggesting no differences between the lignin content of each cultivar due to prolonged storage (r² = 0.98***). This indicates that the lignin determination in the soybean seed coat can be performed over a long time period without any bias due to change in its content.

Wood species identification by visual characterization of fibers

Kandidaatintyö tehtiin osana PulpVision-tutkimusprojektia, jonka tarkoituksena on kehittää kuvapohjaisia laskenta- ja luokittelumetodeja sellun laaduntarkkailuun paperin valmistuksessa. Tämän tutkimusprojektin osana on aiemmin kehitetty metodi, jolla etsittiin kaarevia rakenteita kuvista, ja tätä metodia hyödynnettiin kuitujen etsintään kuvista. Tätä metodia käytettiin lähtökohtana kandidaatintyölle. Työn tarkoituksena oli tutkia, voidaanko erilaisista kuitukuvista laskettujen piirteiden avulla tunnistaa kuvassa olevien kuitujen laji. Näissä kuitukuvissa oli kuituja neljästä eri puulajista ja yhdestä kasvista. Nämä lajit olivat akasia, koivu, mänty, eukalyptus ja vehnä. Jokaisesta lajista valittiin 100 kuitukuvaa ja nämä kuvat jaettiin kahteen ryhmään, joista ensimmäistä käytettiin opetusryhmänä ja toista testausryhmänä. Opetusryhmän avulla jokaiselle kuitulajille laskettiin näitä kuvaavia piirteitä, joiden avulla pyrittiin tunnistamaan testausryhmän kuvissa olevat kuitulajit. Nämä kuvat oli tuottanut CEMIS-Oulu (Center for Measurement and Information Systems), joka on mittaustekniikkaan keskittynyt yksikkö Oulun yliopistossa. Yksittäiselle opetusryhmän kuitukuvalle laskettiin keskiarvot ja keskihajonnat kolmesta eri piirteestä, jotka olivat pituus, leveys ja kaarevuus. Lisäksi laskettiin, kuinka monta kuitua kuvasta löydettiin. Näiden piirteiden eri yhdistelmien avulla testattiin tunnistamisen tarkkuutta käyttämällä k:n lähimmän naapurin menetelmää ja Naiivi Bayes -luokitinta testausryhmän kuville. Testeistä saatiin lupaavia tuloksia muun muassa pituuden ja leveyden keskiarvoja käytettäessä saavutettiin jopa noin 98 %:n tarkkuus molemmilla algoritmeilla. Tunnistuksessa kuitujen keskimäärinen pituus vaikutti olevan kuitukuvia parhaiten kuvaava piirre. Käytettyjen algoritmien välillä ei ollut suurta vaihtelua tarkkuudessa. Testeissä saatujen tulosten perusteella voidaan todeta, että kuitukuvien tunnistaminen on mahdollista. Testien perusteella kuitukuvista tarvitsee laskea vain kaksi piirrettä, joilla kuidut voidaan tunnistaa tarkasti. Käytetyt lajittelualgoritmit olivat hyvin yksinkertaisia, mutta ne toimivat testeissä hyvin.

Pretraining Convolutional Neural Networks for Visual Recognition

Convolutional Neural Networks (CNN) have become the state-of-the-art methods on many large scale visual recognition tasks. For a lot of practical applications, CNN architectures have a restrictive requirement: A huge amount of labeled data are needed for training. The idea of generative pretraining is to obtain initial weights of the network by training the network in a completely unsupervised way and then fine-tune the weights for the task at hand using supervised learning. In this thesis, a general introduction to Deep Neural Networks and algorithms are given and these methods are applied to classification tasks of handwritten digits and natural images for developing unsupervised feature learning. The goal of this thesis is to find out if the effect of pretraining is damped by recent practical advances in optimization and regularization of CNN. The experimental results show that pretraining is still a substantial regularizer, however, not a necessary step in training Convolutional Neural Networks with rectified activations. On handwritten digits, the proposed pretraining model achieved a classification accuracy comparable to the state-of-the-art methods.