252 research outputs found
Sparse discriminant analysis software (sparseLDA):Matlab and R packages
No full textReference: Clemmensen, L., Hastie, T., Ersbøll, B.,(2008), Sparse Discriminant Analysis
Wrist Angel - Qualitative Interview procedure
No full textDescribes qualitative interview procedure exploring experiences of OCD patients' and their parents' use of the E4 wristband for symptom monitoring.
The correct author list and order: Amalie Stougaard, Line Katrine Harder Clemmensen, Anne Katrine Pagsberg, & Nicole Nadine Lønfeld
Climatic changes and sea level response on north-west coast of Sardinia over the last 150 ky
No full textWhen iconicity stands in the way of abbreviation: No Zipfian effect for figurative signals - Fig 5
No full textChanges in frequency between our medieval corpus (Clemmensen) and our early modern corpus (Renesse) as a function of perimetric (left) or descriptive complexity (right). Iconic motifs are represented in blue, and non-iconic motifs in orange. The horizontal line (y = 0) indicates no change in relative frequency between Clemmensen and Renesse. Points above the line represent motifs that increased in frequency in our early modern corpus compared to our medieval corpus.</p
Data Driven Constraints for the SVM
No full textWe propose a generalized data driven constraint for support vector machines exemplified by classification of paired observations in general and specifically on the human ear canal. This is particularly interesting in dynamic cases such as tissue movement or pathologies developing over time. Assuming that two observations of the same subject in different states span a vector, we hypothesise that such structure of the data contains implicit information which can aid the classification, thus the name data driven constraints. We derive a constraint based on the data which allow for the use of the ℓ1-norm on the constraint while still allowing for the application of kernels. We specialize the proposed constraint to orthogonality of the vectors between paired observations and the estimated hyperplane. We show that imposing the constraint of orthogonality on the paired data yields a more robust classifier solution, compared to the SVM i.e. reduces variance and improves classification rates. We present a quantitative measure of the information level contained in the pairing and test the method on simulated as well as a high-dimensional paired data set of ear-canal surfaces
Anatomical comparison between Gilles de la Tourette syndrome patients and control subjects based on the framework of currents
Get PDFThe atlas construction method shown for the first time in the paper of Durrleman et al. and tested only on surfaces was successfully implemented also for fiber bundles modeled as 3D curves. We used this method on a dataset constituted by cortical surfaces, subcortical structures and fiber bundles (all represented by mathematical objects called “currents”) belonging to 27 controls and 47 patients with Gilles de la Tourette syndrome (GTS). The goal of this Master’s Thesis was to check the hypothesis presented in Worbe et al. which correlates GTS with the shapes of the anatomical objects constituting the cortico-striato-thalamo-cortical circuits. Given a population, we built a template (an average shape) for each kind of object considering all the subjects and we analyzed also the deformations of this template to each object in order to characterize its variability within the population. We compared the templates of each population and also their deformations showing the most different parts between the two populations. These areas can drive a deeper research for GTS biomarkersopenEmbargo per motivi di segretezza e di proprietà dei risultati e informazioni sensibil
Weight Sharing and Deep Learning for Spectral Data
No full textWe propose a novel method to co-train deep convolutional neural networks for data sets of differing position specific data. This is an advantage in chemometrics where individual measurements represent exact chemical compounds, e.g. for given wavelengths, and thus signals cannot be translated or resized without disturbing their interpretation. Our approach outperforms transfer learning for three small data sets co-trained with a medium sized data set.</p
Generalized requirements and decompositions for the design of test parts for micro additive manufacturing research
Get PDFThe design of experimental test parts to characterize micro additive manufacturing (AM) processes is challenging due to the influence of the manufacturing and metrology processes. This work builds on the lessons learned from a case study in the literature to derive generalized requirements and high level decompositions for the design of test parts and the design of experiments to characterize micro additive manufacturing processes. While the test parts and the experiments described are still work in progress, the generic requirements derived from them can serve as a starting point for the design of other micro additive manufacturing related studies and their decompositions can help structure future work
Towards an interpretable and transferable acoustic emotion recognition for the detection of mental disorders
No full textMotivation
Automatic speech emotion recognition (ASER) refers to a group of algorithms that deduce the emotional state of an individual from their speech utterances. The methods are deployed in a wide range of tasks, including the detection and intervention of mental disorders. State-of-the art ASER techniques have evolved from the more conventional ML based methods to the current advanced deep neural network based solutions. Despite the long history of research contributions in this domain, state-of-art methods still struggle to generalize across languages, between corpora with different recording conditions, etc. Furthermore, most of the methods lack in interpretation and transparency of the models and their decision making process. These aspects are especially crucial when the methods are deployed in applications with impact on human lives.
Contribution
Autoencoders and latent representation studies are useful tools in the exploration of interpretable and generalizable models. We present results on the benefits of using autoencoders and its variants for ASER, predominantly on emotional states like anger, sadness, happiness and the neutral state. We show that the clusters in the latent space are representative of the desired emotional clusters, although some classes of emotions are more discriminative than others. We take a step further to illustrate the use of DeepLIFT to gain insights into the feature subsets that contribute to the discriminative clustering of emotion classes in the latent space. Furthermore, we study the robustness of the methods by investigating the differences that occur in the latent representations when the underlying data conditions are modified. In other words, how the differences in the language of the corpus, recording conditions of the corpus~(acted, `in the wild') manifest in the latent space. In addition, we explore the discrete and continuous scales for their appropriateness in modelling speech emotions and their correspondence to each other
Data analysis in high-dimensional sparse spaces:Large p, small n problems
Get PDFThe present thesis considers data analysis of problems with many features in relation to the number of observations (large p, small n problems). The theoretical considerations for such problems are outlined including the curses and blessings of dimensionality, and the importance of dimension reduction. In this context the trade off between a rich solution which answers the questions at hand and a simple solution which generalizes to unseen data is described. For all of the given data examples labelled output exists and the analyses are therefore limited to supervised settings. Three novel classification techniques for high-dimensional problems are presented: Sparse discriminant analysis, sparse mixture discriminant analysis and orthogonality constrained support vector machines. The first two introduces sparseness to the well known linear and mixture discriminant analysis and thereby provide low-dimensional projections of data with few non-zero loadings which give improvements in classification. The latter adds a priori information of pairing between observations to the support vector machine and thereby give solutions with less variation and slight improvements in classification. The classification methods are applied to classifications of fish species, ear canal impressions used in the hearing aid industry, microbiological fungi species, and various cancerous tissues and healthy tissues. In addition, novel applications of sparse regressions (also called the elastic net) to the medical, concrete, and food industries via multi-spectral images for objective and automated systems are presented
- …
