Papers by Antanas Verikas
Expert Systems with Applications, 2016
A system for detecting deviating human behaviour in a smart home environment is the long-term goa... more A system for detecting deviating human behaviour in a smart home environment is the long-term goal of this work. Clearly, such systems will be very important in ambient assisted living services. A new approach to modelling human behaviour patterns is suggested in this paper. The approach reveals promising results in unsupervised modelling of human behaviour and detection of deviations by using such a model. Human behaviour/activity in a short time interval is represented in a novel fashion by responses of simple non-intrusive sensors. Deviating behaviour is revealed through data clustering and analysis of associations between clusters and data vectors representing adjacent time intervals (analysing transitions between clusters). To obtain clusters of human behaviour patterns, first, a random forest is trained without using beforehand defined teacher signals. Then information collected in the random forest data proximity matrix is mapped onto the 2D space and data clusters are revealed there by agglomerative clustering. Transitions between clusters are modelled by the third order Markov chain. Three types of deviations are considered: deviation in time, deviation in space and deviation in the transition between clusters of similar behaviour patterns. The proposed modelling approach does not make any assumptions about the position, type, and relationship of sensors but is nevertheless able to successfully create and use a model for deviation detectionthis is claimed as a significant result in the area of expert and intelligent systems. Results show that spatial and temporal deviations can be revealed through analysis of a 2D map of high dimensional data. It is demonstrated that such a map is stable in terms of the number of clusters formed. We show that the data clusters can be understood/explored by finding the most important variables and by analysing the structure of the most representative tree.
Clinical and Experimental Ophthalmology, 2009
Computers in Biology and Medicine, 2015
Automatic detection, recognition and geometric characterization of bacteriophages in electron mic... more Automatic detection, recognition and geometric characterization of bacteriophages in electron microscopy images was the main objective of this work. A novel technique, combining phase congruencybased image enhancement, Hough transform-, Radon transform-and open active contours with free boundary conditions-based object detection was developed to detect and recognize the bacteriophages associated with infection and lysis of cyanobacteria Aphanizomenon flos-aquae. A random forest classifier designed to recognize phage capsids provided higher than 99% accuracy, while measurable phage tails were detected and associated with a correct capsid with 81.35% accuracy. Automatically derived morphometric measurements of phage capsids and tails exhibited lower variability than the ones obtained manually. The technique allows performing precise and accurate quantitative (e.g. abundance estimation) and qualitative (e.g. diversity and capsid size) measurements for studying the interactions between host population and different phages that infect the same host.
International Journal of Pattern Recognition and Artificial Intelligence, 2006
An approach to integrating the global and local kernel-based automated analysis of vocal fold ima... more An approach to integrating the global and local kernel-based automated analysis of vocal fold images aiming to categorize laryngeal diseases is presented in this paper. The problem is treated as an image analysis and recognition task. A committee of support vector machines is employed for performing the categorization of vocal fold images into healthy, diffuse and nodular classes. Analysis of image color distribution, Gabor filtering, cooccurrence matrices, analysis of color edges, image segmentation into homogeneous regions from the image color, texture and geometry view point, analysis of the soft membership of the regions in the decision classes, the kernel principal components based feature extraction are the techniques employed for the global and local analysis of laryngeal images. Bearing in mind the high similarity of the decision classes, the correct classification rate of over 94% obtained when testing the system on 785 vocal fold images is rather encouraging.
Journal of voice : official journal of the Voice Foundation, Jan 17, 2015
The aim of the present study was to evaluate the reliability of the measurements of acoustic voic... more The aim of the present study was to evaluate the reliability of the measurements of acoustic voice parameters obtained simultaneously using oral and contact (throat) microphones and to investigate utility of combined use of these microphones for voice categorization. Voice samples of sustained vowel /a/ obtained from 157 subjects (105 healthy and 52 pathological voices) were recorded in a soundproof booth simultaneously through two microphones: oral AKG Perception 220 microphone (AKG Acoustics, Vienna, Austria) and contact (throat) Triumph PC microphone (Clearer Communications, Inc, Burnaby, Canada) placed on the lamina of thyroid cartilage. Acoustic voice signal data were measured for fundamental frequency, percent of jitter and shimmer, normalized noise energy, signal-to-noise ratio, and harmonic-to-noise ratio using Dr. Speech software (Tiger Electronics, Seattle, WA). The correlations of acoustic voice parameters in vocal performance were statistically significant and strong (r ...
Journal of Voice, 2011
Objectives. The aims of the present study were to evaluate the accuracy of an elaborated automate... more Objectives. The aims of the present study were to evaluate the accuracy of an elaborated automated voice categorization system that classified voice signal samples into healthy and pathological classes and to compare it with classification accuracy that was attained by human experts. Material and Methods. We investigated the effectiveness of 10 different feature sets in the classification of voice recordings of the sustained phonation of the vowel sound /a/ into the healthy and two pathological voice classes, and proposed a new approach to building a sequential committee of support vector machines (SVMs) for the classification. By applying ''genetic search'' (a search technique used to find solutions to optimization problems), we determined the optimal values of hyper-parameters of the committee and the feature sets that provided the best performance. Four experienced clinical voice specialists who evaluated the same voice recordings served as experts. The ''gold standard'' for classification was clinically and histologically proven diagnosis. Results. A considerable improvement in the classification accuracy was obtained from the committee when compared with the single feature type-based classifiers. In the experimental investigations that were performed using 444 voice recordings coming from 148 subjects, three recordings from each subject, we obtained the correct classification rate (CCR) of over 92% when classifying into the healthy-pathological voice classes, and over 90% when classifying into three classes (healthy voice and two nodular or diffuse lesion voice classes). The CCR obtained from human experts was about 74% and 60%, respectively. Conclusion. When operating under the same experimental conditions, the automated voice discrimination technique based on sequential committee of SVM was considerably more effective than the human experts.
Expert Systems with Applications, 2013
ABSTRACT Prediction of company’s life cycle stage change; creation of an ordered 2D map allowing ... more ABSTRACT Prediction of company’s life cycle stage change; creation of an ordered 2D map allowing to explore company’s financial soundness from a rating agency perspective; and prediction of trends of main valuation attributes usually used by investors are the main objectives of this article. The developed algorithms are based on a random forest (RF) and a nonlinear data mapping technique “t-distributed stochastic neighbor embedding”.Information from five different perspectives, namely balance, income, cash flow, stock price, and risk indicators was aggregated via proximity matrices of RF to enable exploration of company’s financial soundness from a rating agency perspective. The proposed use of information not only from companies’ financial statements but also from the stock price and risk indicators perspectives has proved useful in creating ordered 2D maps of rated companies. The companies were well ordered according to the credit risk rating assigned by the Moody’s rating agency.Results of experimental investigations substantiate that the developed models are capable of predicting short term trends of the main valuation attributes, providing valuable information for investors, with low error. The models reflect financial soundness of actions taken by company’s management team. It was also found that company’s life cycle stage change can be determined with the average accuracy of 72.7%. Bearing in mind fuzziness of the transition moment, the obtained prediction accuracy is rather encouraging.
Expert Systems with Applications, 2013
ABSTRACT This article presents an approach to designing an adaptive, data dependent, committee of... more ABSTRACT This article presents an approach to designing an adaptive, data dependent, committee of models applied to prediction of several financial attributes for assessing company’s future performance. Current liabilities/Current assets, Total liabilities/Total assets, Net income/Total assets, and Operating Income/Total liabilities are the attributes used in this paper. A self-organizing map (SOM) used for data mapping and analysis enables building committees, which are specific (committee size and aggregation weights) for each SOM node. The number of basic models aggregated into a committee and the aggregation weights depend on accuracy of basic models and their ability to generalize in the vicinity of the SOM node. A random forest is used a basic model in this study. The developed technique was tested on data concerning companies from ten sectors of the healthcare industry of the United States and compared with results obtained from averaging and weighted averaging committees. The proposed adaptivity of a committee size and aggregation weights led to a statistically significant increase in prediction accuracy if compared to other types of committees.
European Archives of Oto-Rhino-Laryngology, 2009
Imaging and image analysis became an important issue in laryngeal diagnostics. Various techniques... more Imaging and image analysis became an important issue in laryngeal diagnostics. Various techniques, such as videostroboscopy, videokymography, digital kymograpgy, or ultrasonography are available and are used in research and clinical practice. This paper reviews recent advances in imaging for laryngeal diagnostics.
Computerized Medical Imaging and Graphics, 2007
This paper is concerned with an approach to automated analysis of vocal fold images aiming to cat... more This paper is concerned with an approach to automated analysis of vocal fold images aiming to categorize laryngeal diseases. Colour, texture, and geometrical features are used to extract relevant information. A committee of support vector machines is then employed for performing the categorization of vocal fold images into healthy, diffuse, and nodular classes. The discrimination power of both, the original and the space obtained based on the kernel principal component analysis is investigated. A correct classification rate of over 92% was obtained when testing the system on 785 vocal fold images. Bearing in mind the high similarity of the decision classes, the correct classification rate obtained is rather encouraging.
Computer Methods and Programs in Biomedicine, 2007
This paper is concerned with an automated analysis of laryngeal images aiming to categorize the i... more This paper is concerned with an automated analysis of laryngeal images aiming to categorize the images into three decision classes, namely healthy, nodular, and diffuse. The problem is treated as an image analysis and classification task. Aiming to obtain a comprehensive description of laryngeal images, multiple feature sets exploiting information on image colour, texture, geometry, image intensity gradient direction, and frequency content are extracted. A separate support vector machine (SVM) is used to categorize features of each type into the decision classes. The final image categorization is then obtained based on the decisions provided by a committee of support vector machines. Bearing in mind a high similarity of the decision classes, the correct classification rate of over 94% obtained when testing the system on 785 laryngeal images recorded at the Department of Otolaryngology, Kaunas University of Medicine is rather promising.
Artificial Intelligence in Medicine, 2006
Objective: The objective of this work is to investigate a possibility of creating a computer-aide... more Objective: The objective of this work is to investigate a possibility of creating a computer-aided decision support system for an automated analysis of vocal cord images aiming to categorize diseases of vocal cords. Methodology: The problem is treated as a pattern recognition task. To obtain a concise and informative representation of a vocal cord image, colour, texture, and geometrical features are used. The representation is further analyzed by a pattern classifier categorizing the image into healthy, diffuse, and nodular classes. Results: The approach developed was tested on 785 vocal cord images collected at
This article is concerned with detection of objects in phytoplankton images, especially objects r... more This article is concerned with detection of objects in phytoplankton images, especially objects representing one invasive species-Prorocentrum minimum (P. minimum),-which is known to cause harmful blooms in many estuarine and coastal environments. A new technique, combining phase congruencybased detection of circular objects, stochastic optimization, and image segmentation was developed for solving the task. The developed algorithms were tested using 114 images of 1280 × 960 pixels size recorded by a colour camera. There were 2088 objects representing P. minimum cells in the images in total. The algorithms were able to detect 93.25% of the objects. The results are rather encouraging and may be applied for future development of the algorithms aimed at automated classification of objects into classes representing different phytoplankton species.
Speech Communication, 2012
In this paper identification of laryngeal disorders using cepstral parameters of human voice is r... more In this paper identification of laryngeal disorders using cepstral parameters of human voice is researched. Mel-frequency cepstral coefficients (MFCCs), extracted from audio recordings of patient's voice, are further approximated, using various strategies (sampling, averaging, and clustering by Gaussian mixture model). The effectiveness of similarity-based classification techniques in categorizing such pre-processed data into normal voice, nodular, and diffuse vocal fold lesion classes is explored and schemes to combine binary decisions of support vector machines (SVMs) are evaluated. Most practiced RBF kernel was compared to several constructed custom kernels: (i) a sequence kernel, defined over a pair of matrices, rather than over a pair of vectors and calculating the kernelized principal angle (KPA) between subspaces; (ii) a simple supervector kernel using only means of patient's GMM; (iii) two distance kernels, specifically tailored to exploit covariance matrices of GMM and using the approximation of the Kullback-Leibler divergence from the Monte-Carlo sampling (KL-MCS), and the Kullback-Leibler divergence combined with the Earth mover's distance (KL-EMD) as similarity metrics. The sequence kernel and the distance kernels both outperformed the popular RBF kernel, but the difference is statistically significant only in the distance kernels case. When tested on voice recordings, collected from 410 subjects (130 normal voice, 140 diffuse, and 140 nodular vocal fold lesions), the KL-MCS kernel, using GMM with full covariance matrices, and the KL-EMD kernel, using GMM with diagonal covariance matrices, provided the best overall performance. In most cases, SVM reached higher accuracy than least squares SVM, except for common binary classification using distance kernels. The results indicate that features, modeled with GMM, and kernel methods, exploiting this information, is an interesting fusion of generative (probabilistic) and discriminative (hyperplane) models for similarity-based classification.
Informatica
We consider that the outer hair cells of the inner ear together with the local structures of the ... more We consider that the outer hair cells of the inner ear together with the local structures of the basilar membrane, reticular lamina and tectorial membrane form the primary filters (PF) of the second order. Taking into account a delay in transmission of the excitation signal in the cochlea and the influence of the Reissner membrane, we design a signal filtering system consisting of the PF with the common PF of the neighboring channels. We assess the distribution of the central frequencies of the channels along the cochlea, optimal number of the PF constituting a channel, natural frequencies of the channels, damping factors and summation weights of the outputs of the PF. As an example, we present a filter bank comprising 20 Gaussian-type channels each consisting of five PF. The proposed filtering system can be useful for designing cochlear implants based on biological principles of signal processing in the cochlea.
Informatica
This paper is concerned with the problem of image analysis based detection of local defects embed... more This paper is concerned with the problem of image analysis based detection of local defects embedded in particleboard surfaces. Though simple, but efficient technique developed is based on the analysis of the discrete probability distribution of the image intensity values and the 2D discrete Walsh transform. Robust global features characterizing a surface texture are extracted and then analyzed by a pattern classifier. The classifier not only assigns the pattern into the quality or detective class, but also provides the certainty value attributed to the decision. A 100% correct classification accuracy was obtained when testing the technique proposed on a set of 200 images.
PloS one, 2017
This study investigates signals from sustained phonation and text-dependent speech modalities for... more This study investigates signals from sustained phonation and text-dependent speech modalities for Parkinson's disease screening. Phonation corresponds to the vowel /a/ voicing task and speech to the pronunciation of a short sentence in Lithuanian language. Signals were recorded through two channels simultaneously, namely, acoustic cardioid (AC) and smart phone (SP) microphones. Additional modalities were obtained by splitting speech recording into voiced and unvoiced parts. Information in each modality is summarized by 18 well-known audio feature sets. Random forest (RF) is used as a machine learning algorithm, both for individual feature sets and for decision-level fusion. Detection performance is measured by the out-of-bag equal error rate (EER) and the cost of log-likelihood-ratio. Essentia audio feature set was the best using the AC speech modality and YAAFE audio feature set was the best using the SP unvoiced modality, achieving EER of 20.30% and 25.57%, respectively. Fusio...
Journal of Advanced Computational Intelligence and Intelligent Informatics
In this paper, we propose quality function for an unsupervised neural classification. The functio... more In this paper, we propose quality function for an unsupervised neural classification. The function is based on the third order polynomials. The objective of the quality function is to find a place of the input space sparse in data points. By maximising the quality function, we find decision boundary between data clusters instead of centres of the clusters. The shape and place of the decision boundary are rather insensitive to the magnitude of the weight vector established during the maximisation process. A superiority of the proposed quality function over other similar functions as well as conventional clustering algorithms tested has been observed in the experiments. The proposed quality function has been successfully used for colour image segmentation.
Uploads
Papers by Antanas Verikas