Comparative testing of a miniature diffusion size classifier to assess airborne ultrafine particles under field conditions

Miniature diffusion size classifiers (miniDiSC) are novel handheld devices to measure ultrafine particles (UFP). UFP have been linked to the development of cardiovascular and pulmonary diseases; thus, detection and quantification of these particles are important for evaluating their potential health hazards. As part of the UFP exposure assessments of highwaymaintenance workers in western Switzerland, we compared a miniDiSC with a portable condensation particle counter (P-TRAK). In addition, we performed stationary measurements with a miniDiSC and a scanning mobility particle sizer (SMPS) at a site immediately adjacent to a highway. Measurements with miniDiSC and P-TRAK correlated well (correlation of r = 0.84) but average particle numbers of the miniDiSC were 30%âeuro"60% higher. This difference was significantly increased for mean particle diameters below 40 nm. The correlation between theminiDiSC and the SMPSduring stationary measurements was very high (r = 0.98) although particle numbers from the miniDiSC were 30% lower. Differences between the three devices were attributed to the different cutoff diameters for detection. Correction for this size dependent effect led to very similar results across all counters.We did not observe any significant influence of other particle characteristics. Our results suggest that the miniDiSC provides accurate particle number concentrations and geometric mean diameters at traffic-influenced sites, making it a useful tool for personal exposure assessment in such settings.

An Efficient Segmentation Method for Ultrasound Images based on a Semi-supervised Approach and Patch-based Features

Segmenting ultrasound images is a challenging problemwhere standard unsupervised segmentation methods such asthe well-known Chan-Vese method fail. We propose in thispaper an efficient segmentation method for this class ofimages. Our proposed algorithm is based on asemi-supervised approach (user labels) and the use ofimage patches as data features. We also consider thePearson distance between patches, which has been shown tobe robust w.r.t speckle noise present in ultrasoundimages. Our results on phantom and clinical data show avery high similarity agreement with the ground truthprovided by a medical expert.

Semi-supervised remote sensing image classification with cluster kernels

A semisupervised support vector machine is presented for the classification of remote sensing images. The method exploits the wealth of unlabeled samples for regularizing the training kernel representation locally by means of cluster kernels. The method learns a suitable kernel directly from the image and thus avoids assuming a priori signal relations by using a predefined kernel structure. Good results are obtained in image classification examples when few labeled samples are available. The method scales almost linearly with the number of unlabeled samples and provides out-of-sample predictions.

Domain Adaptation in remote sensing: increasing the portability of land-cover classifiers

Among the types of remote sensing acquisitions, optical images are certainly one of the most widely relied upon data sources for Earth observation. They provide detailed measurements of the electromagnetic radiation reflected or emitted by each pixel in the scene. Through a process termed supervised land-cover classification, this allows to automatically yet accurately distinguish objects at the surface of our planet. In this respect, when producing a land-cover map of the surveyed area, the availability of training examples representative of each thematic class is crucial for the success of the classification procedure. However, in real applications, due to several constraints on the sample collection process, labeled pixels are usually scarce. When analyzing an image for which those key samples are unavailable, a viable solution consists in resorting to the ground truth data of other previously acquired images. This option is attractive but several factors such as atmospheric, ground and acquisition conditions can cause radiometric differences between the images, hindering therefore the transfer of knowledge from one image to another. The goal of this Thesis is to supply remote sensing image analysts with suitable processing techniques to ensure a robust portability of the classification models across different images. The ultimate purpose is to map the land-cover classes over large spatial and temporal extents with minimal ground information. To overcome, or simply quantify, the observed shifts in the statistical distribution of the spectra of the materials, we study four approaches issued from the field of machine learning. First, we propose a strategy to intelligently sample the image of interest to collect the labels only in correspondence of the most useful pixels. This iterative routine is based on a constant evaluation of the pertinence to the new image of the initial training data actually belonging to a different image. Second, an approach to reduce the radiometric differences among the images by projecting the respective pixels in a common new data space is presented. We analyze a kernel-based feature extraction framework suited for such problems, showing that, after this relative normalization, the cross-image generalization abilities of a classifier are highly increased. Third, we test a new data-driven measure of distance between probability distributions to assess the distortions caused by differences in the acquisition geometry affecting series of multi-angle images. Also, we gauge the portability of classification models through the sequences. In both exercises, the efficacy of classic physically- and statistically-based normalization methods is discussed. Finally, we explore a new family of approaches based on sparse representations of the samples to reciprocally convert the data space of two images. The projection function bridging the images allows a synthesis of new pixels with more similar characteristics ultimately facilitating the land-cover mapping across images.

Geomodelling of a fluvial system with semi-supervised support vector regression

Fluvial deposits are a challenge for modelling flow in sub-surface reservoirs. Connectivity and continuity of permeable bodies have a major impact on fluid flow in porous media. Contemporary object-based and multipoint statistics methods face a problem of robust representation of connected structures. An alternative approach to model petrophysical properties is based on machine learning algorithm ? Support Vector Regression (SVR). Semi-supervised SVR is able to establish spatial connectivity taking into account the prior knowledge on natural similarities. SVR as a learning algorithm is robust to noise and captures dependencies from all available data. Semi-supervised SVR applied to a synthetic fluvial reservoir demonstrated robust results, which are well matched to the flow performance

Supervised injection services : what has been demonstrated? A systematic literature review

BACKGROUND: Supervised injection services (SISs) have been developed to promote safer drug injection practices, enhance health-related behaviors among people who inject drugs (PWID), and connect PWID with external health and social services. Nevertheless, SISs have also been accused of fostering drug use and drug trafficking. AIMS: To systematically collect and synthesize the currently available evidence regarding SIS-induced benefits and harm. METHODS: A systematic review was performed via the PubMed, Web of Science, and ScienceDirect databases using the keyword algorithm [("supervised" or "safer") and ("injection" or "injecting" or "shooting" or "consumption") and ("facility" or "facilities" or "room" or "gallery" or "centre" or "site")]. RESULTS: Seventy-five relevant articles were found. All studies converged to find that SISs were efficacious in attracting the most marginalized PWID, promoting safer injection conditions, enhancing access to primary health care, and reducing the overdose frequency. SISs were not found to increase drug injecting, drug trafficking or crime in the surrounding environments. SISs were found to be associated with reduced levels of public drug injections and dropped syringes. Of the articles, 85% originated from Vancouver or Sydney. CONCLUSION: SISs have largely fulfilled their initial objectives without enhancing drug use or drug trafficking. Almost all of the studies found in this review were performed in Canada or Australia, whereas the majority of SISs are located in Europe. The implementation of new SISs in places with high rates of injection drug use and associated harms appears to be supported by evidence.

Deep learning via semi-supervised embedding

We show how nonlinear embedding algorithms popular for use with shallow semi-supervised learning techniques such as kernel methods can be applied to deep multilayer architectures, either as a regularizer at the output layer, or on each layer of the architecture. This provides a simple alternative to existing approaches to deep learning whilst yielding competitive error rates compared to those methods, and existing shallow semi-supervised techniques.

Multispectral remote sensing for site-specific nitrogen fertilizer management

The objective of this work was to evaluate the use of multispectral remote sensing for site-specific nitrogen fertilizer management. Satellite imagery from the advanced spaceborne thermal emission and reflection radiometer (Aster) was acquired in a 23 ha corn-planted area in Iran. For the collection of field samples, a total of 53 pixels were selected by systematic randomized sampling. The total nitrogen content in corn leaf tissues in these pixels was evaluated. To predict corn canopy nitrogen content, different vegetation indices, such as normalized difference vegetation index (NDVI), soil-adjusted vegetation index (Savi), optimized soil-adjusted vegetation index (Osavi), modified chlorophyll absorption ratio index 2 (MCARI2), and modified triangle vegetation index 2 (MTVI2), were investigated. The supervised classification technique using the spectral angle mapper classifier (SAM) was performed to generate a nitrogen fertilization map. The MTVI2 presented the highest correlation (R²=0.87) and is a good predictor of corn canopy nitrogen content in the V13 stage, at 60 days after cultivating. Aster imagery can be used to predict nitrogen status in corn canopy. Classification results indicate three levels of required nitrogen per pixel: low (0-2.5 kg), medium (2.5-3 kg), and high (3-3.3 kg).

Intelligent Internet Data Searching

In this thesis author approaches the problem of automated text classification, which is one of basic tasks for building Intelligent Internet Search Agent. The work discusses various approaches to solving sub-problems of automated text classification, such as feature extraction and machine learning on text sources. Author also describes her own multiword approach to feature extraction and pres-ents the results of testing this approach using linear discriminant analysis based classifier, and classifier combining unsupervised learning for etalon extraction with supervised learning using common backpropagation algorithm for multilevel perceptron.

Spontaneous Speech and Emotional Response modeling based on One-class classifier oriented to Alzheimer Disease diagnosis

The purpose of our project is to contribute to earlier diagnosis of AD and better estimates of its severity by using automatic analysis performed through new biomarkers extracted from non-invasive intelligent methods. The methods selected in this case are speech biomarkers oriented to Sponta-neous Speech and Emotional Response Analysis. Thus the main goal of the present work is feature search in Spontaneous Speech oriented to pre-clinical evaluation for the definition of test for AD diagnosis by One-class classifier. One-class classifi-cation problem differs from multi-class classifier in one essen-tial aspect. In one-class classification it is assumed that only information of one of the classes, the target class, is available. In this work we explore the problem of imbalanced datasets that is particularly crucial in applications where the goal is to maximize recognition of the minority class as in medical diag-nosis. The use of information about outlier and Fractal Dimen-sion features improves the system performance.

Classifier combination for in vivo magnetic resonance spectra of brain tumours

Peer-reviewed

Classifier combination for in vivo magnetic resonance spectra of brain tumours

In this paper we present a multi-stage classifier for magnetic resonance spectra of human brain tumours which is being developed as part of a decision support system for radiologists. The basic idea is to decompose a complex classification scheme into a sequence of classifiers, each specialising in different classes of tumours and trying to reproducepart of the WHO classification hierarchy. Each stage uses a particular set of classification features, which are selected using a combination of classical statistical analysis, splitting performance and previous knowledge.Classifiers with different behaviour are combined using a simple voting scheme in order to extract different error patterns: LDA, decision trees and the k-NN classifier. A special label named "unknown¿ is used when the outcomes of the different classifiers disagree. Cascading is alsoused to incorporate class distances computed using LDA into decision trees. Both cascading and voting are effective tools to improve classification accuracy. Experiments also show that it is possible to extract useful information from the classification process itself in order to helpusers (clinicians and radiologists) to make more accurate predictions and reduce the number of possible classification mistakes.

Shared feature extraction for nearest neighbor face recognition

In this paper, we propose a new supervised linearfeature extraction technique for multiclass classification problemsthat is specially suited to the nearest neighbor classifier (NN).The problem of finding the optimal linear projection matrix isdefined as a classification problem and the Adaboost algorithmis used to compute it in an iterative way. This strategy allowsthe introduction of a multitask learning (MTL) criterion in themethod and results in a solution that makes no assumptions aboutthe data distribution and that is specially appropriated to solvethe small sample size problem. The performance of the methodis illustrated by an application to the face recognition problem.The experiments show that the representation obtained followingthe multitask approach improves the classic feature extractionalgorithms when using the NN classifier, especially when we havea few examples from each class