Speeding up AdaBoost Classifier with Random Projection

The development of techniques for scaling up classifiers so that they can be applied to problems with large datasets of training examples is one of the objectives of data mining. Recently, AdaBoost has become popular among machine learning community thanks to its promising results across a variety of applications. However, training AdaBoost on large datasets is a major problem, especially when the dimensionality of the data is very high. This paper discusses the effect of high dimensionality on the training process of AdaBoost. Two preprocessing options to reduce dimensionality, namely the principal component analysis and random projection are briefly examined. Random projection subject to a probabilistic length preserving transformation is explored further as a computationally light preprocessing step. The experimental results obtained demonstrate the effectiveness of the proposed training process for handling high dimensional large datasets.

Geometry Of Proline And Hydroxyproline .1. An Analysis Of X-Ray Crystal-Structure Data

We have carried out an analysis of crystal structure data on prolyl and hydroxyprolyl moieties in small molecules. The flexibility of the pyrrolidine ring due to the pyramidal character of nitrogen has been defined in terms of two projection angles δ1 and δ2. The distribution of these parameters in the crystal structures is found to be consistent with results of the energy calculations carried out on prolyl moieties in our laboratory.

Image reconstruction with laterally truncated projections in helical cone-beam CT: Linear prediction based projection completion techniques

Lateral or transaxial truncation of cone-beam data can occur either due to the field of view limitation of the scanning apparatus or iregion-of-interest tomography. In this paper, we Suggest two new methods to handle lateral truncation in helical scan CT. It is seen that reconstruction with laterally truncated projection data, assuming it to be complete, gives severe artifacts which even penetrates into the field of view. A row-by-row data completion approach using linear prediction is introduced for helical scan truncated data. An extension of this technique known as windowed linear prediction approach is introduced. Efficacy of the two techniques are shown using simulation with standard phantoms. A quantitative image quality measure of the resulting reconstructed images are used to evaluate the performance of the proposed methods against an extension of a standard existing technique.

Unsupervised Domain Adaptation by Domain Invariant Projection

Domain-invariant representations are key to addressing the domain shift problem where the training and test exam- ples follow different distributions. Existing techniques that have attempted to match the distributions of the source and target domains typically compare these distributions in the original feature space. This space, however, may not be di- rectly suitable for such a comparison, since some of the fea- tures may have been distorted by the domain shift, or may be domain specific. In this paper, we introduce a Domain Invariant Projection approach: An unsupervised domain adaptation method that overcomes this issue by extracting the information that is invariant across the source and tar- get domains. More specifically, we learn a projection of the data to a low-dimensional latent space where the distance between the empirical distributions of the source and target examples is minimized. We demonstrate the effectiveness of our approach on the task of visual object recognition and show that it outperforms state-of-the-art methods on a stan- dard domain adaptation benchmark dataset

Patient doses in ct, dental cone beam ct and projection radiography in Finland, with emphasis on paediatric patients

Diagnostic radiology represents the largest man-made contribution to population radiation doses in Europe. To be able to keep the diagnostic benefit versus radiation risk ratio as high as possible, it is important to understand the quantitative relationship between the patient radiation dose and the various factors which affect the dose, such as the scan parameters, scan mode, and patient size. Paediatric patients have a higher probability for late radiation effects, since longer life expectancy is combined with the higher radiation sensitivity of the developing organs. The experience with particular paediatric examinations may be very limited and paediatric acquisition protocols may not be optimised. The purpose of this thesis was to enhance and compare different dosimetric protocols, to promote the establishment of the paediatric diagnostic reference levels (DRLs), and to provide new data on patient doses for optimisation purposes in computed tomography (with new applications for dental imaging) and in paediatric radiography. Large variations in radiation exposure in paediatric skull, sinus, chest, pelvic and abdominal radiography examinations were discovered in patient dose surveys. There were variations between different hospitals and examination rooms, between different sized patients, and between imaging techniques; emphasising the need for harmonisation of the examination protocols. For computed tomography, a correction coefficient, which takes individual patient size into account in patient dosimetry, was created. The presented patient size correction method can be used for both adult and paediatric purposes. Dental cone beam CT scanners provided adequate image quality for dentomaxillofacial examinations while delivering considerably smaller effective doses to patient compared to the multi slice CT. However, large dose differences between cone beam CT scanners were not explained by differences in image quality, which indicated the lack of optimisation. For paediatric radiography, a graphical method was created for setting the diagnostic reference levels in chest examinations, and the DRLs were given as a function of patient projection thickness. Paediatric DRLs were also given for sinus radiography. The detailed information about the patient data, exposure parameters and procedures provided tools for reducing the patient doses in paediatric radiography. The mean tissue doses presented for paediatric radiography enabled future risk assessments to be done. The calculated effective doses can be used for comparing different diagnostic procedures, as well as for comparing the use of similar technologies and procedures in different hospitals and countries.

New phase unwrapping strategy for rapid and dense 3D data acquisition in structured light approach

Sinusoidal structured light projection (SSLP) technique, specifically-phase stepping method, is in widespread use to obtain accurate, dense 3-D data. But, if the object under investigation possesses surface discontinuities, phase unwrapping (an intermediate step in SSLP) stage mandatorily require several additional images, of the object with projected fringes (of different spatial frequencies), as input to generate a reliable 3D shape. On the other hand, Color-coded structured light projection (CSLP) technique is known to require a single image as in put, but generates sparse 3D data. Thus we propose the use of CSLP in conjunction with SSLP to obtain dense 3D data with minimum number of images as input. This approach is shown to be significantly faster and reliable than temporal phase unwrapping procedure that uses a complete exponential sequence. For example, if a measurement with the accuracy obtained by interrogating the object with 32 fringes in the projected pattern is carried out with both the methods, new strategy proposed requires only 5 frames as compared to 24 frames required by the later method.

Population projection for Namibia 2011-2020 - With an estimation of the impact of HIV/AIDS

This study presents a population projection for Namibia for years 2011–2020. In many countries of sub-Saharan Africa, including Namibia, the population growth is still continuing even though the fertility rates have declined. However, many of these countries suffer from a large HIV epidemic that is slowing down the population growth. In Namibia, the epidemic has been severe. Therefore, it is important to assess the effect of HIV/AIDS on the population of Namibia in the future. Demographic research on Namibia has not been very extensive, and data on population is not widely available. According to the studies made, fertility has been shown to be generally declining and mortality has been significantly increasing due to AIDS. Previous population projections predict population growth for Namibia in the near future, yet HIV/AIDS is affecting the future population developments. For the projection constructed in this study, data on population is taken from the two most recent censuses, from 1991 and 2001. Data on HIV is available from HIV Sentinel Surveys 1992–2008, which test pregnant women for HIV in antenatal clinics. Additional data are collected from different sources and recent studies. The projection is made with software (EPP and Spectrum) specially designed for developing countries with scarce data. The projection includes two main scenarios which have different assumptions concerning the development of the HIV epidemic. In addition, two hypothetical scenarios are made: the first considering the case where HIV epidemic would never have existed and the second considering the case where HIV treatment would never have existed. The results indicate population growth for Namibia. Population in the 2001 census was 1.83 million and is projected to result in 2.38/2.39 million in 2020 in the first two scenarios. Without HIV, population would be 2.61 million and without treatment 2.30 million in 2020. Urban population is growing faster than rural. Even though AIDS is increasing mortality, the past high fertility rates still keep young adult age groups quite large. The HIV epidemic shows to be slowing down, but it is still increasing the mortality of the working-aged population. The initiation of HIV treatment in 2004 in the public sector seems to have had an effect on many projected indicators, diminishing the impact of HIV on the population. For example, the rise of mortality is slowing down.

Image reconstruction from incomplete projections data: A multiresolution modeling approach

Computerized tomography is an imaging technique which produces cross sectional map of an object from its line integrals. Image reconstruction algorithms require collection of line integrals covering the whole measurement range. However, in many practical situations part of projection data is inaccurately measured or not measured at all. In such incomplete projection data situations, conventional image reconstruction algorithms like the convolution back projection algorithm (CBP) and the Fourier reconstruction algorithm, assuming the projection data to be complete, produce degraded images. In this paper, a multiresolution multiscale modeling using the wavelet transform coefficients of projections is proposed for projection completion. The missing coefficients are then predicted based on these models at each scale followed by inverse wavelet transform to obtain the estimated projection data.

A Unified Approach to Encoding and Classification Using Bimodal Projection-Based Features

In general the objective of accurately encoding the input data and the objective of extracting good features to facilitate classification are not consistent with each other. As a result, good encoding methods may not be effective mechanisms for classification. In this paper, an earlier proposed unsupervised feature extraction mechanism for pattern classification has been extended to obtain an invertible map. The method of bimodal projection-based features was inspired by the general class of methods called projection pursuit. The principle of projection pursuit concentrates on projections that discriminate between clusters and not faithful representations. The basic feature map obtained by the method of bimodal projections has been extended to overcome this. The extended feature map is an embedding of the input space in the feature space. As a result, the inverse map exists and hence the representation of the input space in the feature space is exact. This map can be naturally expressed as a feedforward neural network.

A numerical study of variable coefficient elliptic Cauchy problem via projection method

In this paper, we investigate a numerical method for the solution of an inverse problem of recovering lacking data on some part of the boundary of a domain from the Cauchy data on other part for a variable coefficient elliptic Cauchy problem. In the process, the Cauchy problem is transformed into the problem of solving a compact linear operator equation. As a remedy to the ill-posedness of the problem, we use a projection method which allows regularization solely by discretization. The discretization level plays the role of regularization parameter in the case of projection method. The balancing principle is used for the choice of an appropriate discretization level. Several numerical examples show that the method produces a stable good approximate solution.

A NEAR OPTIMAL PROJECTION FOR SPARSE REPRESENTATION BASED CLASSIFICATION

Sparse representation based classification (SRC) is one of the most successful methods that has been developed in recent times for face recognition. Optimal projection for Sparse representation based classification (OPSRC)1] provides a dimensionality reduction map that is supposed to give optimum performance for SRC framework. However, the computational complexity involved in this method is too high. Here, we propose a new projection technique using the data scatter matrix which is computationally superior to the optimal projection method with comparable classification accuracy with respect OPSRC. The performance of the proposed approach is benchmarked with various publicly available face database.

Projection Error Propagation-based Regularization (PEPR) method for resistivity reconstruction in Electrical Impedance Tomography (EIT)

A novel Projection Error Propagation-based Regularization (PEPR) method is proposed to improve the image quality in Electrical Impedance Tomography (EIT). PEPR method defines the regularization parameter as a function of the projection error developed by difference between experimental measurements and calculated data. The regularization parameter in the reconstruction algorithm gets modified automatically according to the noise level in measured data and ill-posedness of the Hessian matrix. Resistivity imaging of practical phantoms in a Model Based Iterative Image Reconstruction (MoBIIR) algorithm as well as with Electrical Impedance Diffuse Optical Reconstruction Software (EIDORS) with PEPR. The effect of PEPR method is also studied with phantoms with different configurations and with different current injection methods. All the resistivity images reconstructed with PEPR method are compared with the single step regularization (STR) and Modified Levenberg Regularization (LMR) techniques. The results show that, the PEPR technique reduces the projection error and solution error in each iterations both for simulated and experimental data in both the algorithms and improves the reconstructed images with better contrast to noise ratio (CNR), percentage of contrast recovery (PCR), coefficient of contrast (COC) and diametric resistivity profile (DRP). (C) 2013 Elsevier Ltd. All rights reserved.

Action Recognition from Motion Capture Data using Meta-cognitive RBF Network Classifier

Action recognition plays an important role in various applications, including smart homes and personal assistive robotics. In this paper, we propose an algorithm for recognizing human actions using motion capture action data. Motion capture data provides accurate three dimensional positions of joints which constitute the human skeleton. We model the movement of the skeletal joints temporally in order to classify the action. The skeleton in each frame of an action sequence is represented as a 129 dimensional vector, of which each component is a 31) angle made by each joint with a fixed point on the skeleton. Finally, the video is represented as a histogram over a codebook obtained from all action sequences. Along with this, the temporal variance of the skeletal joints is used as additional feature. The actions are classified using Meta-Cognitive Radial Basis Function Network (McRBFN) and its Projection Based Learning (PBL) algorithm. We achieve over 97% recognition accuracy on the widely used Berkeley Multimodal Human Action Database (MHAD).

A high pressure xenon time projection chamber for double beta decay

This thesis describes the design, construction and performance of a high-pressure, xenon, gas time projection chamber (TPC) for the study of double beta decay in ^(136) Xe. The TPC when operating at 5 atm can accommodate 28 moles of 60% enriched ^(136) Xe. The TPC has operated as a detector at Caltech since 1986. It is capable of reconstructing a charged particle trajectory and can easily distinguish between different kinds of charged particles. A gas purification and xenon gas recovery system were developed. The electronics for the 338 channels of readout was developed along with a data acquistion system. Currently, the detector is being prepared at the University of Neuchatel for installation in the low background laboratory situated in the St. Gotthard tunnel, Switzerland. In one year of runtime the detector should be sensitive to a 0ν lifetime of the order of 10^(24) y, which corresponds to a neutrino mass in the range 0.3 to 3.3 eV.

Restructuring Sparse High Dimensional Data for Effective Retrieval

The task in text retrieval is to find the subset of a collection of documents relevant to a user's information request, usually expressed as a set of words. Classically, documents and queries are represented as vectors of word counts. In its simplest form, relevance is defined to be the dot product between a document and a query vector--a measure of the number of common terms. A central difficulty in text retrieval is that the presence or absence of a word is not sufficient to determine relevance to a query. Linear dimensionality reduction has been proposed as a technique for extracting underlying structure from the document collection. In some domains (such as vision) dimensionality reduction reduces computational complexity. In text retrieval it is more often used to improve retrieval performance. We propose an alternative and novel technique that produces sparse representations constructed from sets of highly-related words. Documents and queries are represented by their distance to these sets. and relevance is measured by the number of common clusters. This technique significantly improves retrieval performance, is efficient to compute and shares properties with the optimal linear projection operator and the independent components of documents.