An unsupervised approach to feature discretization and selection

Many learning problems require handling high dimensional datasets with a relatively small number of instances. Learning algorithms are thus confronted with the curse of dimensionality, and need to address it in order to be effective. Examples of these types of data include the bag-of-words representation in text classification problems and gene expression data for tumor detection/classification. Usually, among the high number of features characterizing the instances, many may be irrelevant (or even detrimental) for the learning tasks. It is thus clear that there is a need for adequate techniques for feature representation, reduction, and selection, to improve both the classification accuracy and the memory requirements. In this paper, we propose combined unsupervised feature discretization and feature selection techniques, suitable for medium and high-dimensional datasets. The experimental results on several standard datasets, with both sparse and dense features, show the efficiency of the proposed techniques as well as improvements over previous related techniques.

Facial feature extraction and selection by Gabor wavelets and boosting

In this paper, we present a feature selection approach based on Gabor wavelet feature and boosting for face verification. By convolution with a group of Gabor wavelets, the original images are transformed into vectors of Gabor wavelet features. Then for individual person, a small set of significant features are selected by the boosting algorithm from a large set of Gabor wavelet features. The experiment results have shown that the approach successfully selects meaningful and explainable features for face verification. The experiments also suggest that for the common characteristics such as eyes, noses, mouths may not be as important as some unique characteristic when training set is small. When training set is large, the unique characteristics and the common characteristics are both important.

Integrated project evaluation and selection using multiple-attribute decision-making technique

The evaluation and selection of industrial projects before investment decision is customarily done using marketing, technical and financial information. Subsequently, environmental impact assessment and social impact assessment are carried out mainly to satisfy the statutory agencies. Because of stricter environment regulations in developed and developing countries, quite often impact assessment suggests alternate sites, technologies, designs, and implementation methods as mitigating measures. This causes considerable delay to complete project feasibility analysis and selection as complete analysis requires to be taken up again and again till the statutory regulatory authority approves the project. Moreover, project analysis through above process often results sub-optimal project as financial analysis may eliminate better options, as more environment friendly alternative will always be cost intensive. In this circumstance, this study proposes a decision support system, which analyses projects with respect to market, technicalities, and social and environmental impact in an integrated framework using analytic hierarchy process, a multiple-attribute decision-making technique. This not only reduces duration of project evaluation and selection, but also helps select optimal project for the organization for sustainable development. The entire methodology has been applied to a cross-country oil pipeline project in India and its effectiveness has been demonstrated. © 2005 Elsevier B.V. All rights reserved.

Multi-criteria decision making approaches for supplier evaluation and selection:a literature review

Supplier evaluation and selection problem has been studied extensively. Various decision making approaches have been proposed to tackle the problem. In contemporary supply chain management, the performance of potential suppliers is evaluated against multiple criteria rather than considering a single factor-cost. This paper reviews the literature of the multi-criteria decision making approaches for supplier evaluation and selection. Related articles appearing in the international journals from 2000 to 2008 are gathered and analyzed so that the following three questions can be answered: (i) Which approaches were prevalently applied? (ii) Which evaluating criteria were paid more attention to? (iii) Is there any inadequacy of the approaches? Based on the inadequacy, if any, some improvements and possible future work are recommended. This research not only provides evidence that the multi-criteria decision making approaches are better than the traditional cost-based approach, but also aids the researchers and decision makers in applying the approaches effectively.

Forage peanut (Arachis spp.) genetic evaluation and selection.

Forage peanut improvement for use in grass?legume mixtures is expected to have a great impact on the sustainability of Brazilian livestock production. Eighteen cloned Arachis spp. ecotypes were evaluated under clipping in a Brazilian Cerrado region and results analysed using a mixed model methodology. The objective was to estimate genetic and phenotypic parameters and to select the best ecotypes based on selection index applied on their predicted genotypic value. The traits of total dry-matter (DM) and leaf DM yield presented moderate (0_30 < h2g < 0_50) to high (>0_50) broad-sense heritability, in contrast to the low genetic variability in nutritional quality-associated traits. Ecotypes of Arachis spp. contained average crude protein concentrations of 224 g kg _1 DM in leaves and 138 g kg _1 DM in stems, supporting the potential role of these species to overcome the low protein content in Cerrado pastures. The correlations between yield traits and traits associated with low nutritional value in leaves were consistently significant and positive. Genetic correlations among all the yield traits evaluated during the rainy or dry seasons were significant and positive. The ecotypes were ranked based on selection index. The next step is to validate long-term selection of grass?Arachis in combination with pastures under competition and adjusted grazing in the Cerrado region.

Generating segmented meshes from textured color images

This paper presents a new framework for generating triangular meshes from textured color images. The proposed framework combines a texture classification technique, called W-operator, with Imesh, a method originally conceived to generate simplicial meshes from gray scale images. An extension of W-operators to handle textured color images is proposed, which employs a combination of RGB and HSV channels and Sequential Floating Forward Search guided by mean conditional entropy criterion to extract features from the training data. The W-operator is built into the local error estimation used by Imesh to choose the mesh vertices. Furthermore, the W-operator also enables to assign a label to the triangles during the mesh construction, thus allowing to obtain a segmented mesh at the end of the process. The presented results show that the combination of W-operators with Imesh gives rise to a texture classification-based triangle mesh generation framework that outperforms pixel based methods. Crown Copyright (C) 2009 Published by Elsevier Inc. All rights reserved.

Raspberry (Rubus idaeus L.) wine: Yeast selection, sensory evaluation and instrumental analysis of volatile and other compounds

To evaluate the potential for fermentation of raspberry pulp, sixteen yeast strains (S. cerevisiae and S. bayanus) were studied. Volatile compounds were determined by GC-MS, GC-FID, and GC-PFPD. Ethanol. glycerol and organic acids were determined by HPLC. HPLC-DAD was used to analyse phenolic acids. Sensory analysis was performed by trained panellists. After a screening step, CAT-1, UFLA FW 15 and S. bayanus CBS 1505 were previously selected based on their fermentative characteristics and profile of the metabolites identified. The beverage produced with CAT-1 showed the highest volatile fatty acid concentration (1542.6 mu g/L), whereas the beverage produced with UFLA FIN 15 showed the highest concentration of acetates (2211.1 mu g/L) and total volatile compounds (5835 mu g/L). For volatile sulphur compounds. 566.5 mu g/L were found in the beverage produced with S. bayanus CBS 1505. The lowest concentration of volatile sulphur compounds (151.9 mu g/L) was found for the beverage produced with UFLA FW 15. In the sensory analysis, the beverage produced with UFLA FW 15 was characterised by the descriptors raspberry, cherry, sweet, strawberry, floral and violet. In conclusion, strain UFLA FW 15 was the yeast that produced a raspberry wine with a good chemical and sensory quality. (C) 2010 Elsevier Ltd. All rights reserved.

Evaluation of various pre-treatments for the dehydration of banana and selection of suitable drying models

The thin-layer drying behaviour of bananas in a beat pump dehumidifier dryer was examined. Four pre-treatments (blanching, chilling, freezing and combined blanching and freezing) were applied to the bananas, which were dried at 50 degreesC with an air velocity of 3.1 m s(-1) and with the relative humidity of the inlet air of 10-35%. Three drying models, the simple model, the two-term exponential model and the Page model were examined. All models were evaluated using three statistical measures, correlation coefficient, root means square error, and mean absolute percent error. Moisture diffusivity was calculated based on the diffusion equation for an infinite cylindrical shape using the slope method. The rate of drying was higher for the pre-treatments involving freezing. The sample which was blanched only did not show any improvement in drying rate. In fact, a longer drying time resulted due to water absorption during blanching. There was no change in the rate for the chilled sample compared with the control. While all models closely fitted the drying data, the simple model showed greatest deviation from the experimental results. The two-term exponential model was found to be the best model for describing the drying curves of bananas because its parameters represent better the physical characteristics of the drying process. Moisture diffusivities of bananas were in the range 4.3-13.2 x 10(-10) m(2)s(-1). (C) 2002 Published by Elsevier Science Ltd.

User Profile Management and Selection in Context-Aware Service Platforms for Networks Beyond 3G

In recent years, progress in the area of mobile telecommunications has changed our way of life, in the private as well as the business domain. Mobile and wireless networks have ever increasing bit rates, mobile network operators provide more and more services, and at the same time costs for the usage of mobile services and bit rates are decreasing. However, mobile services today still lack functions that seamlessly integrate into users’ everyday life. That is, service attributes such as context-awareness and personalisation are often either proprietary, limited or not available at all. In order to overcome this deficiency, telecommunications companies are heavily engaged in the research and development of service platforms for networks beyond 3G for the provisioning of innovative mobile services. These service platforms are to support such service attributes. Service platforms are to provide basic service-independent functions such as billing, identity management, context management, user profile management, etc. Instead of developing own solutions, developers of end-user services such as innovative messaging services or location-based services can utilise the platform-side functions for their own purposes. In doing so, the platform-side support for such functions takes away complexity, development time and development costs from service developers. Context-awareness and personalisation are two of the most important aspects of service platforms in telecommunications environments. The combination of context-awareness and personalisation features can also be described as situation-dependent personalisation of services. The support for this feature requires several processing steps. The focus of this doctoral thesis is on the processing step, in which the user’s current context is matched against situation-dependent user preferences to find the matching user preferences for the current user’s situation. However, to achieve this, a user profile management system and corresponding functionality is required. These parts are also covered by this thesis. Altogether, this thesis provides the following contributions: The first part of the contribution is mainly architecture-oriented. First and foremost, we provide a user profile management system that addresses the specific requirements of service platforms in telecommunications environments. In particular, the user profile management system has to deal with situation-specific user preferences and with user information for various services. In order to structure the user information, we also propose a user profile structure and the corresponding user profile ontology as part of an ontology infrastructure in a service platform. The second part of the contribution is the selection mechanism for finding matching situation-dependent user preferences for the personalisation of services. This functionality is provided as a sub-module of the user profile management system. Contrary to existing solutions, our selection mechanism is based on ontology reasoning. This mechanism is evaluated in terms of runtime performance and in terms of supported functionality compared to other approaches. The results of the evaluation show the benefits and the drawbacks of ontology modelling and ontology reasoning in practical applications.

Fingerprint Recognition: Enhancement, Feature Extraction and Automatic Evaluation of Algorithms

The identification of people by measuring some traits of individual anatomy or physiology has led to a specific research area called biometric recognition. This thesis is focused on improving fingerprint recognition systems considering three important problems: fingerprint enhancement, fingerprint orientation extraction and automatic evaluation of fingerprint algorithms. An effective extraction of salient fingerprint features depends on the quality of the input fingerprint. If the fingerprint is very noisy, we are not able to detect a reliable set of features. A new fingerprint enhancement method, which is both iterative and contextual, is proposed. This approach detects high-quality regions in fingerprints, selectively applies contextual filtering and iteratively expands like wildfire toward low-quality ones. A precise estimation of the orientation field would greatly simplify the estimation of other fingerprint features (singular points, minutiae) and improve the performance of a fingerprint recognition system. The fingerprint orientation extraction is improved following two directions. First, after the introduction of a new taxonomy of fingerprint orientation extraction methods, several variants of baseline methods are implemented and, pointing out the role of pre- and post- processing, we show how to improve the extraction. Second, the introduction of a new hybrid orientation extraction method, which follows an adaptive scheme, allows to improve significantly the orientation extraction in noisy fingerprints. Scientific papers typically propose recognition systems that integrate many modules and therefore an automatic evaluation of fingerprint algorithms is needed to isolate the contributions that determine an actual progress in the state-of-the-art. The lack of a publicly available framework to compare fingerprint orientation extraction algorithms, motivates the introduction of a new benchmark area called FOE (including fingerprints and manually-marked orientation ground-truth) along with fingerprint matching benchmarks in the FVC-onGoing framework. The success of such framework is discussed by providing relevant statistics: more than 1450 algorithms submitted and two international competitions.

Procurement : Proposal evaluation and source selection /

"This pamphlet supersedes AMCP 715-3, 31 March 1966, including C1, 29 November 1968."

Biometrical analysis and selection of tetraploid progenies of Panicum maximum using mixed model methods

The objectives of this work were to estimate the genetic and phenotypic parameters and to predict the genetic and genotypic values of the selection candidates obtained from intraspecific crosses in Panicum maximum as well as the performance of the hybrid progeny of the existing and projected crosses. Seventy-nine intraspecific hybrids obtained from artificial crosses among five apomictic and three sexual autotetraploid individuals were evaluated in a clonal test with two replications and ten plants per plot. Green matter yield, total and leaf dry matter yields and leaf percentage were evaluated in five cuts per year during three years. Genetic parameters were estimated and breeding and genotypic values were predicted using the restricted maximum likelihood/best linear unbiased prediction procedure (REML/BLUP). The dominant genetic variance was estimated by adjusting the effect of full-sib families. Low magnitude individual narrow sense heritabilities (0.02-0.05), individual broad sense heritabilities (0.14-0.20) and repeatability measured on an individual basis (0.15-0.21) were obtained. Dominance effects for all evaluated characteristics indicated that breeding strategies that explore heterosis must be adopted. Less than 5% increase in the parameter repeatability was obtained for a three-year evaluation period and may be the criterion to determine the maximum number of years of evaluation to be adopted, without compromising gain per cycle of selection. The identification of hybrid candidates for future cultivars and of those that can be incorporated into the breeding program was based on the genotypic and breeding values, respectively. The prediction of the performance of the hybrid progeny, based on the breeding values of the progenitors, permitted the identification of the best crosses and indicated the best parents to use in crosses.

Evaluation and comparison of current fetal ultrasound image segmentation methods for biometric measurements: a grand challenge.

This paper presents the evaluation results of the methods submitted to Challenge US: Biometric Measurements from Fetal Ultrasound Images, a segmentation challenge held at the IEEE International Symposium on Biomedical Imaging 2012. The challenge was set to compare and evaluate current fetal ultrasound image segmentation methods. It consisted of automatically segmenting fetal anatomical structures to measure standard obstetric biometric parameters, from 2D fetal ultrasound images taken on fetuses at different gestational ages (21 weeks, 28 weeks, and 33 weeks) and with varying image quality to reflect data encountered in real clinical environments. Four independent sub-challenges were proposed, according to the objects of interest measured in clinical practice: abdomen, head, femur, and whole fetus. Five teams participated in the head sub-challenge and two teams in the femur sub-challenge, including one team who tackled both. Nobody attempted the abdomen and whole fetus sub-challenges. The challenge goals were two-fold and the participants were asked to submit the segmentation results as well as the measurements derived from the segmented objects. Extensive quantitative (region-based, distance-based, and Bland-Altman measurements) and qualitative evaluation was performed to compare the results from a representative selection of current methods submitted to the challenge. Several experts (three for the head sub-challenge and two for the femur sub-challenge), with different degrees of expertise, manually delineated the objects of interest to define the ground truth used within the evaluation framework. For the head sub-challenge, several groups produced results that could be potentially used in clinical settings, with comparable performance to manual delineations. The femur sub-challenge had inferior performance to the head sub-challenge due to the fact that it is a harder segmentation problem and that the techniques presented relied more on the femur's appearance.

R&D Performance Analysis: Case Studies on the Challenges and Promotion of the Evaluation and Measurement of R&D

Due to the intense international competition, demanding, and sophisticated customers, and diverse transforming technological change, organizations need to renew their products and services by allocating resources on research and development (R&D). Managing R&D is complex, but vital for many organizations to survive in the dynamic, turbulent environment. Thus, the increased interest among decision-makers towards finding the right performance measures for R&D is understandable. The measures or evaluation methods of R&D performance can be utilized for multiple purposes; for strategic control, for justifying the existence of R&D, for providing information and improving activities, as well as for the purposes of motivating and benchmarking. The earlier research in the field of R&D performance analysis has generally focused on either the activities and considerable factors and dimensions - e.g. strategic perspectives, purposes of measurement, levels of analysis, types of R&D or phases of R&D process - prior to the selection of R&Dperformance measures, or on proposed principles or actual implementation of theselection or design processes of R&D performance measures or measurement systems. This study aims at integrating the consideration of essential factors anddimensions of R&D performance analysis to developed selection processes of R&D measures, which have been applied in real-world organizations. The earlier models for corporate performance measurement that can be found in the literature, are to some extent adaptable also to the development of measurement systemsand selecting the measures in R&D activities. However, it is necessary to emphasize the special aspects related to the measurement of R&D performance in a way that make the development of new approaches for especially R&D performance measure selection necessary: First, the special characteristics of R&D - such as the long time lag between the inputs and outcomes, as well as the overall complexity and difficult coordination of activities - influence the R&D performance analysis problems, such as the need for more systematic, objective, balanced and multi-dimensional approaches for R&D measure selection, as well as the incompatibility of R&D measurement systems to other corporate measurement systems and vice versa. Secondly, the above-mentioned characteristics and challenges bring forth the significance of the influencing factors and dimensions that need to be recognized in order to derive the selection criteria for measures and choose the right R&D metrics, which is the most crucial step in the measurement system development process. The main purpose of this study is to support the management and control of the research and development activities of organizations by increasing the understanding of R&D performance analysis, clarifying the main factors related to the selection of R&D measures and by providing novel types of approaches and methods for systematizing the whole strategy- and business-based selection and development process of R&D indicators.The final aim of the research is to support the management in their decision making of R&D with suitable, systematically chosen measures or evaluation methods of R&D performance. Thus, the emphasis in most sub-areas of the present research has been on the promotion of the selection and development process of R&D indicators with the help of the different tools and decision support systems, i.e. the research has normative features through providing guidelines by novel types of approaches. The gathering of data and conducting case studies in metal and electronic industry companies, in the information and communications technology (ICT) sector, and in non-profit organizations helped us to formulate a comprehensive picture of the main challenges of R&D performance analysis in different organizations, which is essential, as recognition of the most importantproblem areas is a very crucial element in the constructive research approach utilized in this study. Multiple practical benefits regarding the defined problemareas could be found in the various constructed approaches presented in this dissertation: 1) the selection of R&D measures became more systematic when compared to the empirical analysis, as it was common that there were no systematic approaches utilized in the studied organizations earlier; 2) the evaluation methods or measures of R&D chosen with the help of the developed approaches can be more directly utilized in the decision-making, because of the thorough consideration of the purpose of measurement, as well as other dimensions of measurement; 3) more balance to the set of R&D measures was desired and gained throughthe holistic approaches to the selection processes; and 4) more objectivity wasgained through organizing the selection processes, as the earlier systems were considered subjective in many organizations. Scientifically, this dissertation aims to make a contribution to the present body of knowledge of R&D performance analysis by facilitating dealing with the versatility and challenges of R&D performance analysis, as well as the factors and dimensions influencing the selection of R&D performance measures, and by integrating these aspects to the developed novel types of approaches, methods and tools in the selection processes of R&D measures, applied in real-world organizations. In the whole research, facilitation of dealing with the versatility and challenges in R&D performance analysis, as well as the factors and dimensions influencing the R&D performance measure selection are strongly integrated with the constructed approaches. Thus, the research meets the above-mentioned purposes and objectives of the dissertation from the scientific as well as from the practical point of view.