Comprehensive evaluation of results obtained using acoustic and contact microphones in screening for laryngeal disorders through analysis of sustained phonation is the main objective of this study. Aiming to obtain a versatile characterization of voice samples recorded using microphones of both types, 14 different sets of features are extracted and used to build an accurate classifier to distinguish between normal and pathological cases. We propose a new, data dependent random forests-based, way to combine information available from the different feature sets. An approach to exploring data and decisions made by a random forest is also presented. Experimental investigations using a mixed gender database of 273 subjects have shown that the perceptual linear predictive cepstral coefficients (PLPCC) was the best feature set for both microphones. However, the linear predictive coefficients (LPC) and linear predictive cosine transform coefficients (LPCTC) exhibited good performance in the acoustic microphone case only. Models designed using the acoustic microphone data significantly outperformed the ones built using data recorded by the contact microphone. The contact microphone did not bring any additional information useful for the classification. The proposed data dependent random forest significantly outperformed the traditional random forest. (C) 2015 IPEM. Published by Elsevier Ltd. All rights reserved.

Topic of this study is exploration and fusion o fnon-invasive measurements for an accurate detection of pathological larynx. Measurements for human subject encompass answers to items of a specific survey and information extracted by the openSMILE toolkit from several audio recordings of sustained phonation (vowel/a/).

Topic of the research is exploration and fusion of non-invasive measurements for an accurate detection of pathological larynx. Measurements for human subject encompass results of a specific survey and information extracted by openSMILE toolkit from several audio recordings of sustained phonation (vowel/a/). Clinical diagnosis, assigned by medical specialist, is a target attribute for binary classification into healthy and pathological cases. Random forest (RF) is used here as a base-learner and also as a meta-learner for decision-level fusion. Fusion combines decisions from ensemble of 5 RF classifiers built on 3 variants of audio recording data (raw and after two types of voice activity detection) and 2 variants of questionnaire (with 9 and 26 questions) data. Out-of-bag equal error rate (EER) was found to be higher for audio data and lower for querry, but each variant was outperformed by the fusion where the lowest EER of 4.8% was achieved. Finally, due to noteworthy performance of the querry data, 22 association rules (11 healthy + 11 pathological) using 17 questions were obtained for comprehensible insights.

During 2013, an evaluation of all the research conducted at Halmstad University was carried out. The purpose was to assess the quality of the research, coproduction, and collaboration in research, as well as the impact of the research. The evaluation was dubbed the Assessment of Research and Coproduction 2013, or ARC13. (Extract from Executive Summary)

Exploration of various features and different structures of data dependent random forests in screening for laryngeal disorders through analysis of sustained phonation recorded by acoustic and contact microphones is the main objective of this study. To obtain a versatile characterization of voice samples, 14 different sets of features were extracted and used to build an accurate classifier to distinguish between normal and pathological cases. We proposed a new, data dependent random forest-based, way to combine information available from the different feature sets. An approach to exploring data and decisions made by a random forest was also presented. Experimental investigations using a mixed gender database of 273 subjects have shown that the Perceptual linear predictive cepstral coefficients (PLPCC) was the best feature set for both microphones. However, the LP-coefficients and LPCT-coefficients feature sets exhibited good performance in the acoustic microphone case only. Models designed using the acoustic microphone data significantly outperformed the ones built using data recorded by the contact microphone. The contact microphone did not bring any additional information useful for classification. The proposed data dependent random forest significantly outperformed traditional designs. © 2014 IEEE.

The objective of this work is to identify the main parameters of the printing press, the printing process, and the paper affecting the occurrence of web breaks in a pressroom. Two approaches are explored. The first one treats the problem as a task of data classification into "break" and "non-break" classes. The procedures of classifier design and selection of relevant input variables are integrated into one process based on genetic search. The second approach, targeted for data visualization and also based on genetic search, combines procedures of input variable selection and data mapping into a two-dimensional space. The genetic search-based analysis has shown that the web tension parameters are amongst the most important ones. It was also found that the group of paper related parameters recorded online contain more information for predicting the occurrence of web breaks than the group of traditional parameters recorded off-line at a paper lab. Using the selected set of parameters, on average, 93.7% of the test set data were classified correctly. The average classification accuracy of web break cases was equal to 76.7%. (C) 2010 Elsevier B. V. All rights reserved.

Objective: This paper is concerned with soft computing techniques for categorizing laryngeal disorders based on information extracted from an image of patient's vocal folds, a voice signal, and questionnaire data.

Methods: Multiple feature sets are exploited to characterize images and voice signals. To characterize colour, texture, and geometry of biological structures seen in colour images of vocal folds, eight feature sets are used. Twelve feature sets are used to obtain a comprehensive characterization of a voice signal (the sustained phonation of the vowel sound /a/). Answers to 14 questions constitute the questionnaire feature set. A committee of support vector machines is designed for categorizing the image, voice, and query data represented by the multiple feature sets into the healthy, nodular and diffuse classes. Five alternatives to aggregate separate SVMs into a committee are explored. Feature selection and classifier design are combined into the same learning process based on genetic search.

Results: Data of all the three modalities were available from 240 patients. Among those, 151 patients belong to the nodular class, 64 to the diffuse class and 25 to the healthy class. When using a single feature set to characterize each modality, the test set data classification accuracy of 75.0%, 72.1%, and 85.0% was obtained for the image, voice and questionnaire data, respectively. The use of multiple feature sets allowed to increase the accuracy to 89.5% and 87.7% for the image and voice data, respectively. The test set data classification accuracy of over 98.0% was obtained from a committee exploiting multiple feature sets from all the three modalities. The highest classification accuracy was achieved when using the SVM-based aggregation with hyper parameters of the SVM determined by genetic search. Bearing in mind the difficulty of the task, the obtained classification accuracy is rather encouraging.

Conclusions: Combination of both multiple feature sets characterizing a single modality and the three modalities allowed to substantially improve the classification accuracy if compared to the highest accuracy obtained from a single feature set and a single modality. In spite of the unbalanced data sets used, the error rates obtained for the three classes were rather similar.

This paper is concerned with a technique for detecting and monitoring abnormal paper formation variations in machine direction online in various frequency regions. A paper web is illuminated by two red diode lasers and the reflected light recorded as two time series of high resolution measurements constitute the input signal to the papermaking process monitoring system. The time series are divided into blocks and each block is analyzed separately. The task is treated as kernel based novelty detection applied to a multi-resolution time series representation obtained from the band-pass filtering of the Fourier power spectrum of the time series block. The frequency content of each frequency region is characterized by a feature vector, which is transformed using the kernel canonical correlation analysis and then categorized into the inlier or outlier class by the novelty detector. The ratio of outlying data points, significantly exceeding the predetermined value, indicates abnormalities in the paper formation. The experimental investigations performed have shown good repetitiveness and stability of the paper formation abnormalities detection results. The tools developed are used for online paper formation monitoring in a paper mill.

This paper is concerned with data mining techniques for identifying the main parameters of the printing press, the printing process and paper affecting the occurrence of paper web breaks in a pressroom.Two approaches are explored. The first one treats the problem as a task of data classification into “break” and “non break” classes. The procedures of classifier design and selection of relevant input variables are integrated into one process based on genetic search. The search process results in a set of input variables providing the lowest average loss incurred in taking decisions. The second approach, also based on genetic search, combines procedures of input variable selection and data mapping into a low dimensional space. The tests have shown that the web tension parameters are amongst the most important ones. It was also found that, provided the basic off-line paper parameters are in an acceptable range, the paper related parameters recorded online contain more information for predicting the occurrence of web breaks than the off-line ones. Using the selected set of parameters, on average, 93.7% of the test set data were classified correctly. The average classification accuracy of the break cases was equal to 76.7%.

A measurement platform for online studies of print runnability in a full-scale four-high web offset printing press is described. Results from two trial runs showed no effect of reel tightness on print runnability. Differences were, however, found for so called edge reels.