An investigation into feature construction to assist word sense disambiguation

Identifying the correct sense of a word in context is crucial for many tasks in natural language processing (machine translation is an example). State-of-the art methods for Word Sense Disambiguation (WSD) build models using hand-crafted features that usually capturing shallow linguistic information. Complex background knowledge, such as semantic relationships, are typically either not used, or used in specialised manner, due to the limitations of the feature-based modelling techniques used. On the other hand, empirical results from the use of Inductive Logic Programming (ILP) systems have repeatedly shown that they can use diverse sources of background knowledge when constructing models. In this paper, we investigate whether this ability of ILP systems could be used to improve the predictive accuracy of models for WSD. Specifically, we examine the use of a general-purpose ILP system as a method to construct a set of features using semantic, syntactic and lexical information. This feature-set is then used by a common modelling technique in the field (a support vector machine) to construct a classifier for predicting the sense of a word. In our investigation we examine one-shot and incremental approaches to feature-set construction applied to monolingual and bilingual WSD tasks. The monolingual tasks use 32 verbs and 85 verbs and nouns (in English) from the SENSEVAL-3 and SemEval-2007 benchmarks; while the bilingual WSD task consists of 7 highly ambiguous verbs in translating from English to Portuguese. The results are encouraging: the ILP-assisted models show substantial improvements over those that simply use shallow features. In addition, incremental feature-set construction appears to identify smaller and better sets of features. Taken together, the results suggest that the use of ILP with diverse sources of background knowledge provide a way for making substantial progress in the field of WSD.

A Road Following Approach Using Artificial Neural Networks Combinations

Navigation is a broad topic that has been receiving considerable attention from the mobile robotic community over the years. In order to execute autonomous driving in outdoor urban environments it is necessary to identify parts of the terrain that can be traversed and parts that should be avoided. This paper describes an analyses of terrain identification based on different visual information using a MLP artificial neural network and combining responses of many classifiers. Experimental tests using a vehicle and a video camera have been conducted in real scenarios to evaluate the proposed approach.

An Information Theory framework for two-stage binary image operator design

The design of translation invariant and locally defined binary image operators over large windows is made difficult by decreased statistical precision and increased training time. We present a complete framework for the application of stacked design, a recently proposed technique to create two-stage operators that circumvents that difficulty. We propose a novel algorithm, based on Information Theory, to find groups of pixels that should be used together to predict the Output Value. We employ this algorithm to automate the process of creating a set of first-level operators that are later combined in a global operator. We also propose a principled way to guide this combination, by using feature selection and model comparison. Experimental results Show that the proposed framework leads to better results than single stage design. (C) 2009 Elsevier B.V. All rights reserved.

Multilevel Training of Binary Morphological Operators

The design of binary morphological operators that are translation-invariant and locally defined by a finite neighborhood window corresponds to the problem of designing Boolean functions. As in any supervised classification problem, morphological operators designed from a training sample also suffer from overfitting. Large neighborhood tends to lead to performance degradation of the designed operator. This work proposes a multilevel design approach to deal with the issue of designing large neighborhood-based operators. The main idea is inspired by stacked generalization (a multilevel classifier design approach) and consists of, at each training level, combining the outcomes of the previous level operators. The final operator is a multilevel operator that ultimately depends on a larger neighborhood than of the individual operators that have been combined. Experimental results show that two-level operators obtained by combining operators designed on subwindows of a large window consistently outperform the single-level operators designed on the full window. They also show that iterating two-level operators is an effective multilevel approach to obtain better results.

Measuring time series predictability using support vector regression

Most studies involving statistical time series analysis rely on assumptions of linearity, which by its simplicity facilitates parameter interpretation and estimation. However, the linearity assumption may be too restrictive for many practical applications. The implementation of nonlinear models in time series analysis involves the estimation of a large set of parameters, frequently leading to overfitting problems. In this article, a predictability coefficient is estimated using a combination of nonlinear autoregressive models and the use of support vector regression in this model is explored. We illustrate the usefulness and interpretability of results by using electroencephalographic records of an epileptic patient.

Road and Traffic Signs Recognition using Vector Machines

Intelligent Transportation System (ITS) is a system that builds a safe, effective and integrated transportation environment based on advanced technologies. Road signs detection and recognition is an important part of ITS, which offer ways to collect the real time traffic data for processing at a central facility.This project is to implement a road sign recognition model based on AI and image analysis technologies, which applies a machine learning method, Support Vector Machines, to recognize road signs. We focus on recognizing seven categories of road sign shapes and five categories of speed limit signs. Two kinds of features, binary image and Zernike moments, are used for representing the data to the SVM for training and test. We compared and analyzed the performances of SVM recognition model using different features and different kernels. Moreover, the performances using different recognition models, SVM and Fuzzy ARTMAP, are observed.

Computerized identification of motor complications in Parkinson's disease

Objective: To investigate whether spirography-based objective measures are able to effectively characterize the severity of unwanted symptom states (Off and dyskinesia) and discriminate them from motor state of healthy elderly subjects. Background: Sixty-five patients with advanced Parkinson’s disease (PD) and 10 healthy elderly (HE) subjects performed repeated assessments of spirography, using a touch screen telemetry device in their home environments. On inclusion, the patients were either treated with levodopa-carbidopa intestinal gel or were candidates for switching to this treatment. On each test occasion, the subjects were asked trace a pre-drawn Archimedes spiral shown on the screen, using an ergonomic pen stylus. The test was repeated three times and was performed using dominant hand. A clinician used a web interface which animated the spiral drawings, allowing him to observe different kinematic features, like accelerations and spatial changes, during the drawing process and to rate different motor impairments. Initially, the motor impairments of drawing speed, irregularity and hesitation were rated on a 0 (normal) to 4 (extremely severe) scales followed by marking the momentary motor state of the patient into 2 categories that is Off and Dyskinesia. A sample of spirals drawn by HE subjects was randomly selected and used in subsequent analysis. Methods: The raw spiral data, consisting of stylus position and timestamp, were processed using time series analysis techniques like discrete wavelet transform, approximate entropy and dynamic time warping in order to extract 13 quantitative measures for representing meaningful motor impairment information. A principal component analysis (PCA) was used to reduce the dimensions of the quantitative measures into 4 principal components (PC). In order to classify the motor states into 3 categories that is Off, HE and dyskinesia, a logistic regression model was used as a classifier to map the 4 PCs to the corresponding clinically assigned motor state categories. A stratified 10-fold cross-validation (also known as rotation estimation) was applied to assess the generalization ability of the logistic regression classifier to future independent data sets. To investigate mean differences of the 4 PCs across the three categories, a one-way ANOVA test followed by Tukey multiple comparisons was used. Results: The agreements between computed and clinician ratings were very good with a weighted area under the receiver operating characteristic curve (AUC) coefficient of 0.91. The mean PC scores were different across the three motor state categories, only at different levels. The first 2 PCs were good at discriminating between the motor states whereas the PC3 was good at discriminating between HE subjects and PD patients. The mean scores of PC4 showed a trend across the three states but without significant differences. The Spearman’s rank correlations between the first 2 PCs and clinically assessed motor impairments were as follows: drawing speed (PC1, 0.34; PC2, 0.83), irregularity (PC1, 0.17; PC2, 0.17), and hesitation (PC1, 0.27; PC2, 0.77). Conclusions: These findings suggest that spirography-based objective measures are valid measures of spatial- and time-dependent deficits and can be used to distinguish drug-related motor dysfunctions between Off and dyskinesia in PD. These measures can be potentially useful during clinical evaluation of individualized drug-related complications such as over- and under-medications thus maximizing the amount of time the patients spend in the On state.

Visualization of spirography-based objective measures in Parkinson's disease

Objective: To investigate whether advanced visualizations of spirography-based objective measures are useful in differentiating drug-related motor dysfunctions between Off and dyskinesia in Parkinson’s disease (PD). Background: During the course of a 3 year longitudinal clinical study, in total 65 patients (43 males and 22 females with mean age of 65) with advanced PD and 10 healthy elderly (HE) subjects (5 males and 5 females with mean age of 61) were assessed. Both patients and HE subjects performed repeated and time-stamped assessments of their objective health indicators using a test battery implemented on a telemetry touch screen handheld computer, in their home environment settings. Among other tasks, the subjects were asked to trace a pre-drawn Archimedes spiral using the dominant hand and repeat the test three times per test occasion. Methods: A web-based framework was developed to enable a visual exploration of relevant spirography-based kinematic features by clinicians so they can in turn evaluate the motor states of the patients i.e. Off and dyskinesia. The system uses different visualization techniques such as time series plots, animation, and interaction and organizes them into different views to aid clinicians in measuring spatial and time-dependent irregularities that could be associated with the motor states. Along with the animation view, the system displays two time series plots for representing drawing speed (blue line) and displacement from ideal trajectory (orange line). The views are coordinated and linked i.e. user interactions in one of the views will be reflected in other views. For instance, when the user points in one of the pixels in the spiral view, the circle size of the underlying pixel increases and a vertical line appears in the time series views to depict the corresponding position. In addition, in order to enable clinicians to observe erratic movements more clearly and thus improve the detection of irregularities, the system displays a color-map which gives an idea of the longevity of the spirography task. Figure 2 shows single randomly selected spirals drawn by a: A) patient who experienced dyskinesias, B) HE subject, and C) patient in Off state. Results: According to a domain expert (DN), the spirals drawn in the Off and dyskinesia motor states are characterized by different spatial and time features. For instance, the spiral shown in Fig. 2A was drawn by a patient who showed symptoms of dyskinesia; the drawing speed was relatively high (cf. blue-colored time series plot and the short timestamp scale in the x axis) and the spatial displacement was high (cf. orange-colored time series plot) associated with smooth deviations as a result of uncontrollable movements. The patient also exhibited low amount of hesitation which could be reflected both in the animation of the spiral as well as time series plots. In contrast, the patient who was in the Off state exhibited different kinematic features, as shown in Fig. 2C. In the case of spirals drawn by a HE subject, there was a great precision during the drawing process as well as unchanging levels of time-dependent features over the test trial, as seen in Fig. 2B. Conclusions: Visualizing spirography-based objective measures enables identification of trends and patterns of drug-related motor dysfunctions at the patient’s individual level. Dynamic access of visualized motor tests may be useful during the evaluation of drug-related complications such as under- and over-medications, providing decision support to clinicians during evaluation of treatment effects as well as improve the quality of life of patients and their caregivers. In future, we plan to evaluate the proposed approach by assessing within- and between-clinician variability in ratings in order to determine its actual usefulness and then use these ratings as target outcomes in supervised machine learning, similarly as it was previously done in the study performed by Memedi et al. (2013).

First-principle data-driven models for assessment of motor disorders in Parkinson’s disease

Parkinson’s disease (PD) is an increasing neurological disorder in an aging society. The motor and non-motor symptoms of PD advance with the disease progression and occur in varying frequency and duration. In order to affirm the full extent of a patient’s condition, repeated assessments are necessary to adjust medical prescription. In clinical studies, symptoms are assessed using the unified Parkinson’s disease rating scale (UPDRS). On one hand, the subjective rating using UPDRS relies on clinical expertise. On the other hand, it requires the physical presence of patients in clinics which implies high logistical costs. Another limitation of clinical assessment is that the observation in hospital may not accurately represent a patient’s situation at home. For such reasons, the practical frequency of tracking PD symptoms may under-represent the true time scale of PD fluctuations and may result in an overall inaccurate assessment. Current technologies for at-home PD treatment are based on data-driven approaches for which the interpretation and reproduction of results are problematic.  The overall objective of this thesis is to develop and evaluate unobtrusive computer methods for enabling remote monitoring of patients with PD. It investigates first-principle data-driven model based novel signal and image processing techniques for extraction of clinically useful information from audio recordings of speech (in texts read aloud) and video recordings of gait and finger-tapping motor examinations. The aim is to map between PD symptoms severities estimated using novel computer methods and the clinical ratings based on UPDRS part-III (motor examination). A web-based test battery system consisting of self-assessment of symptoms and motor function tests was previously constructed for a touch screen mobile device. A comprehensive speech framework has been developed for this device to analyze text-dependent running speech by: (1) extracting novel signal features that are able to represent PD deficits in each individual component of the speech system, (2) mapping between clinical ratings and feature estimates of speech symptom severity, and (3) classifying between UPDRS part-III severity levels using speech features and statistical machine learning tools. A novel speech processing method called cepstral separation difference showed stronger ability to classify between speech symptom severities as compared to existing features of PD speech. In the case of finger tapping, the recorded videos of rapid finger tapping examination were processed using a novel computer-vision (CV) algorithm that extracts symptom information from video-based tapping signals using motion analysis of the index-finger which incorporates a face detection module for signal calibration. This algorithm was able to discriminate between UPDRS part III severity levels of finger tapping with high classification rates. Further analysis was performed on novel CV based gait features constructed using a standard human model to discriminate between a healthy gait and a Parkinsonian gait. The findings of this study suggest that the symptom severity levels in PD can be discriminated with high accuracies by involving a combination of first-principle (features) and data-driven (classification) approaches. The processing of audio and video recordings on one hand allows remote monitoring of speech, gait and finger-tapping examinations by the clinical staff. On the other hand, the first-principles approach eases the understanding of symptom estimates for clinicians. We have demonstrated that the selected features of speech, gait and finger tapping were able to discriminate between symptom severity levels, as well as, between healthy controls and PD patients with high classification rates. The findings support suitability of these methods to be used as decision support tools in the context of PD assessment.

Automatic spiral analysis for objective assessment of motor symptoms in Parkinson's disease

Objective: To develop a method for objective quantification of PD motor symptoms related to Off episodes and peak dose dyskinesias, using spiral data gathered by using a touch screen telemetry device. The aim was to objectively characterize predominant motor phenotypes (bradykinesia and dyskinesia), to help in automating the process of visual interpretation of movement anomalies in spirals as rated by movement disorder specialists. Background: A retrospective analysis was conducted on recordings from 65 patients with advanced idiopathic PD from nine different clinics in Sweden, recruited from January 2006 until August 2010. In addition to the patient group, 10 healthy elderly subjects were recruited. Upper limb movement data were collected using a touch screen telemetry device from home environments of the subjects. Measurements with the device were performed four times per day during week-long test periods. On each test occasion, the subjects were asked to trace pre-drawn Archimedean spirals, using the dominant hand. The pre-drawn spiral was shown on the screen of the device. The spiral test was repeated three times per test occasion and they were instructed to complete it within 10 seconds. The device had a sampling rate of 10Hz and measured both position and time-stamps (in milliseconds) of the pen tip. Methods: Four independent raters (FB, DH, AJ and DN) used a web interface that animated the spiral drawings and allowed them to observe different kinematic features during the drawing process and to rate task performance. Initially, a number of kinematic features were assessed including ‘impairment’, ‘speed’, ‘irregularity’ and ‘hesitation’ followed by marking the predominant motor phenotype on a 3-category scale: tremor, bradykinesia and/or choreatic dyskinesia. There were only 2 test occasions for which all the four raters either classified them as tremor or could not identify the motor phenotype. Therefore, the two main motor phenotype categories were bradykinesia and dyskinesia. ‘Impairment’ was rated on a scale from 0 (no impairment) to 10 (extremely severe) whereas ‘speed’, ‘irregularity’ and ‘hesitation’ were rated on a scale from 0 (normal) to 4 (extremely severe). The proposed data-driven method consisted of the following steps. Initially, 28 spatiotemporal features were extracted from the time series signals before being presented to a Multilayer Perceptron (MLP) classifier. The features were based on different kinematic quantities of spirals including radius, angle, speed and velocity with the aim of measuring the severity of involuntary symptoms and discriminate between PD-specific (bradykinesia) and/or treatment-induced symptoms (dyskinesia). A Principal Component Analysis was applied on the features to reduce their dimensions where 4 relevant principal components (PCs) were retained and used as inputs to the MLP classifier. Finally, the MLP classifier mapped these components to the corresponding visually assessed motor phenotype scores for automating the process of scoring the bradykinesia and dyskinesia in PD patients whilst they draw spirals using the touch screen device. For motor phenotype (bradykinesia vs. dyskinesia) classification, the stratified 10-fold cross validation technique was employed. Results: There were good agreements between the four raters when rating the individual kinematic features with intra-class correlation coefficient (ICC) of 0.88 for ‘impairment’, 0.74 for ‘speed’, 0.70 for ‘irregularity’, and moderate agreements when rating ‘hesitation’ with an ICC of 0.49. When assessing the two main motor phenotype categories (bradykinesia or dyskinesia) in animated spirals the agreements between the four raters ranged from fair to moderate. There were good correlations between mean ratings of the four raters on individual kinematic features and computed scores. The MLP classifier classified the motor phenotype that is bradykinesia or dyskinesia with an accuracy of 85% in relation to visual classifications of the four movement disorder specialists. The test-retest reliability of the four PCs across the three spiral test trials was good with Cronbach’s Alpha coefficients of 0.80, 0.82, 0.54 and 0.49, respectively. These results indicate that the computed scores are stable and consistent over time. Significant differences were found between the two groups (patients and healthy elderly subjects) in all the PCs, except for the PC3. Conclusions: The proposed method automatically assessed the severity of unwanted symptoms and could reasonably well discriminate between PD-specific and/or treatment-induced motor symptoms, in relation to visual assessments of movement disorder specialists. The objective assessments could provide a time-effect summary score that could be useful for improving decision-making during symptom evaluation of individualized treatment when the goal is to maximize functional On time for patients while minimizing their Off episodes and troublesome dyskinesias.

Automatic spiral analysis for objective assessment of motor symptoms in Parkinson's disease

A challenge for the clinical management of advanced Parkinson’s disease (PD) patients is the emergence of fluctuations in motor performance, which represents a significant source of disability during activities of daily living of the patients. There is a lack of objective measurement of treatment effects for in-clinic and at-home use that can provide an overview of the treatment response. The objective of this paper was to develop a method for objective quantification of advanced PD motor symptoms related to off episodes and peak dose dyskinesia, using spiral data gathered by a touch screen telemetry device. More specifically, the aim was to objectively characterize motor symptoms (bradykinesia and dyskinesia), to help in automating the process of visual interpretation of movement anomalies in spirals as rated by movement disorder specialists. Digitized upper limb movement data of 65 advanced PD patients and 10 healthy (HE) subjects were recorded as they performed spiral drawing tasks on a touch screen device in their home environment settings. Several spatiotemporal features were extracted from the time series and used as inputs to machine learning methods. The methods were validated against ratings on animated spirals scored by four movement disorder specialists who visually assessed a set of kinematic features and the motor symptom. The ability of the method to discriminate between PD patients and HE subjects and the test-retest reliability of the computed scores were also evaluated. Computed scores correlated well with mean visual ratings of individual kinematic features. The best performing classifier (Multilayer Perceptron) classified the motor symptom (bradykinesia or dyskinesia) with an accuracy of 84% and area under the receiver operating characteristics curve of 0.86 in relation to visual classifications of the raters. In addition, the method provided high discriminating power when distinguishing between PD patients and HE subjects as well as had good test-retest reliability. This study demonstrated the potential of using digital spiral analysis for objective quantification of PD-specific and/or treatment-induced motor symptoms.

Automating condition monitoring of vegetation on railway trackbeds and embankments

Vegetation growing on railway trackbeds and embankments present potential problems. The presence of vegetation threatens the safety of personnel inspecting the railway infrastructure. In addition vegetation growth clogs the ballast and results in inadequate track drainage which in turn could lead to the collapse of the railway embankment. Assessing vegetation within the realm of railway maintenance is mainly carried out manually by making visual inspections along the track. This is done either on-site or by watching videos recorded by maintenance vehicles mainly operated by the national railway administrative body. A need for the automated detection and characterisation of vegetation on railways (a subset of vegetation control/management) has been identified in collaboration with local railway maintenance subcontractors and Trafikverket, the Swedish Transport Administration (STA). The latter is responsible for long-term planning of the transport system for all types of traffic, as well as for the building, operation and maintenance of public roads and railways. The purpose of this research project was to investigate how vegetation can be measured and quantified by human raters and how machine vision can automate the same process. Data were acquired at railway trackbeds and embankments during field measurement experiments. All field data (such as images) in this thesis work was acquired on operational, lightly trafficked railway tracks, mostly trafficked by goods trains. Data were also generated by letting (human) raters conduct visual estimates of plant cover and/or count the number of plants, either on-site or in-house by making visual estimates of the images acquired from the field experiments. Later, the degree of reliability of(human) raters’ visual estimates were investigated and compared against machine vision algorithms. The overall results of the investigations involving human raters showed inconsistency in their estimates, and are therefore unreliable. As a result of the exploration of machine vision, computational methods and algorithms enabling automatic detection and characterisation of vegetation along railways were developed. The results achieved in the current work have shown that the use of image data for detecting vegetation is indeed possible and that such results could form the base for decisions regarding vegetation control. The performance of the machine vision algorithm which quantifies the vegetation cover was able to process 98% of the im-age data. Investigations of classifying plants from images were conducted in in order to recognise the specie. The classification rate accuracy was 95%.Objective measurements such as the ones proposed in thesis offers easy access to the measurements to all the involved parties and makes the subcontracting process easier i.e., both the subcontractors and the national railway administration are given the same reference framework concerning vegetation before signing a contract, which can then be crosschecked post maintenance.A very important issue which comes with an increasing ability to recognise species is the maintenance of biological diversity. Biological diversity along the trackbeds and embankments can be mapped, and maintained, through better and robust monitoring procedures. Continuously monitoring the state of vegetation along railways is highly recommended in order to identify a need for maintenance actions, and in addition to keep track of biodiversity. The computational methods or algorithms developed form the foundation of an automatic inspection system capable of objectively supporting manual inspections, or replacing manual inspections.

Aplicação de modelos gráficos probabilísticos computacionais em economia

O objetivo deste trabalho é testar a aplicação de um modelo gráfico probabilístico, denominado genericamente de Redes Bayesianas, para desenvolver modelos computacionais que possam ser utilizados para auxiliar a compreensão de problemas e/ou na previsão de variáveis de natureza econômica. Com este propósito, escolheu-se um problema amplamente abordado na literatura e comparou-se os resultados teóricos e experimentais já consolidados com os obtidos utilizando a técnica proposta. Para tanto,foi construído um modelo para a classificação da tendência do "risco país" para o Brasil a partir de uma base de dados composta por variáveis macroeconômicas e financeiras. Como medida do risco adotou-se o EMBI+ (Emerging Markets Bond Index Plus), por ser um indicador amplamente utilizado pelo mercado.

Redes bayesianas aplicadas à modelagem de fraudes em cartão de crédito

Modelos para detecção de fraude são utilizados para identificar se uma transação é legítima ou fraudulenta com base em informações cadastrais e transacionais. A técnica proposta no estudo apresentado, nesta dissertação, consiste na de Redes Bayesianas (RB); seus resultados foram comparados à técnica de Regressão Logística (RL), amplamente utilizada pelo mercado. As Redes Bayesianas avaliadas foram os classificadores bayesianos, com a estrutura Naive Bayes. As estruturas das redes bayesianas foram obtidas a partir de dados reais, fornecidos por uma instituição financeira. A base de dados foi separada em amostras de desenvolvimento e validação por cross validation com dez partições. Naive Bayes foram os classificadores escolhidos devido à simplicidade e a sua eficiência. O desempenho do modelo foi avaliado levando-se em conta a matriz de confusão e a área abaixo da curva ROC. As análises dos modelos revelaram desempenho, levemente, superior da regressão logística quando comparado aos classificadores bayesianos. A regressão logística foi escolhida como modelo mais adequado por ter apresentado melhor desempenho na previsão das operações fraudulentas, em relação à matriz de confusão. Baseada na área abaixo da curva ROC, a regressão logística demonstrou maior habilidade em discriminar as operações que estão sendo classificadas corretamente, daquelas que não estão.