Property:Abstract
From ISLAB/CAISR
Jump to navigationJump to searchThis is a property of type Text.
A
<p>This paper is concerned with a general framework for designing afuzzy rule-based classifier. Structure and parameters of theclassifier are evolved through a two-stage genetic search. Theclassifier structure is constrained by a tree created using theevolving SOM tree algorithm. Salient input variables are specificfor each fuzzy rule and are found during the genetic search process.It is shown through computer simulations of four real world problemsthat a large number of rules and input variables can be eliminatedfrom the model without deteriorating the classification accuracy.</p> +
<p>This paper presents a general framework for designing a fuzzyrule-based classifier. Structure and parameters of the classifierare evolved through a two-stage genetic search. To reduce the searchspace, the classifier structure is constrained by a tree createdusing the evolving SOM tree algorithm. Salient input variables arespecific for each fuzzy rule and are found during the genetic searchprocess. It is shown through computer simulations of four real worldproblems that a large number of rules and input variables can beeliminated from the model without deteriorating the classificationaccuracy. By contrast, the classification accuracy of unseen data isincreased due to the elimination.This paper presents a general framework for designing a fuzzyrule-based classifier. Structure and parameters of the classifierare evolved through a two-stage genetic search. To reduce the searchspace, the classifier structure is constrained by a tree createdusing the evolving SOM tree algorithm. Salient input variables arespecific for each fuzzy rule and are found during the genetic searchprocess. It is shown through computer simulations of four real worldproblems that a large number of rules and input variables can beeliminated from the model without deteriorating the classificationaccuracy. By contrast, the classification accuracy of unseen data isincreased due to the elimination.</p> +
<p>An interactive tool is developed for the purpose of rapid exploration ofdiverse traffic scenario. The focus is on rapidity of design and evaluation rather thenon physical realism. Core aspects are the ability to define the essential elements fora traffic scenario such as a road network and vehicles. Cubic Bezier curves are usedto design the roads and vehicle trajectory. A prediction algorithm is used to visualizevehicle future poses and collisions and thus provide means for evaluation of saidscenario. Such a program was created using C++ with the help of Qt libraries.</p><p></p> +
<p>Artificial neural networks are used to model the offset printing process aiming to develop tools for on-line ink feed control. Inherent in the modelling data are outliers owing to sensor faults, measurement errors and impurity of materials used. It is fundamental to identify outliers in process data in order to avoid using these data points for updating the model. We present a hybrid, the process-model-network-based technique for outlier detection. The outliers can then be removed to improve the process model. Several diagnostic measures are aggregated via a neural network to categorize data points into the outlier and inlier classes. We demonstrate experimentally that a soft fuzzy expert can be configured to label data for training the categorization of neural network.</p> +
<p>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.</p> +
<p>Current practices in healthcare rely on expensive and labor-intensive procedures that are not adequate for future healthcare demands. Therefore, alternatives are required to complement or enhance healthcare services, both at clinical and home settings. Hospital and ordinary beds can be equipped with load cells to enable load sensing applications, such as for weight and sleep assessment. Beds with such functionalities represent a tangible alternative to expensive and obtrusive routines for sleep assessment, such as polysomnography. A finite-state machine is proposed as a lightweight on-line method to detect sleep-related activities, such as bed entrances and exits, awakenings, wakefulness, and sleep atonia. The proposed approach is evaluated with a dataset collected in real homes of older people receiving night-time home care services.</p> +
<p>There is evidence that many cognitive conditions affect the human motor system. Gait analysis has lately been used as a means of studying this physical-cognitive correlation. The development of gait analysis systems, able to record and analyze gait during normal daily activities and in uncontrolled environment, is an important addition to this area of research. Lately, linguistic approaches have been studied as means to achieve activity classification from vision sensors. The present work aims to extend the linguistic approach to achieve quantitative analysis of gait from accelerometer data. The proposed method can be used to extend the Human Activity Language framework to include the analysis of inertial sensors such as accelerometers. Results show that the proposed method is more accurate and robust than previous methods and can be used to extract a number of clinically relevant gait measurements. A novel symmetry index is presented to exemplify how the proposed method is able to extract more information from accelerometer signals than previous methods.</p> +
<p>In this paper we present a low-cost colour vision system mainly intended for robot design competitions, which nowadays is a popular, project-oriented, way of teaching mechatronics in engineering curriculums. The estimated cost is about 450 dollar inclusive colour camera and the system is small enough to be carried on-board relative small mobile robots. The system is build around a signal processor TMS C31. We also present and discuss the experiences made with the system in our robot design competition.</p> +
<p>This paper presents an autonomous agricultural mobile robot for mechanical weed control in outdoor environments. The robot employs two vision systems: one grey-level vision system that is able to recognise the row structure formed by the crops and to guide the robot along the rows and a second, colour-based vision system that is able to identify a single crop among weed plants. This vision system controls a weeding-tool that removes the weed within the row of crops. It has been shown that colour vision is feasible for single plant identification, i.e. discriminating between crops and weeds. The system as a whole has been verified, showing that the subsystems are able to work together effectively. A first trial in a greenhouse showed that the robot is able to manage weed control within a row of sugar beet plants.</p> +
<p>CBCT images suffer from acute shading artifacts primarily due to scatter. Numerous image-domain correction algorithms have been proposed in the literature that use patient-specific planning CT images to estimate shading contributions in CBCT images. However, in the context of radiosurgery applications such as gamma knife, planning images are often acquired through MRI which impedes the use of polynomial fitting approaches for shading correction. We present a new shading correction approach that is independent of planning CT images. Our algorithm is based on the assumption that true CBCT images follow a uniform volumetric intensity distribution per material, and scatter perturbs this uniform texture by contributing cupping and shading artifacts in the image domain. The framework is a combination of fuzzy C-means coupled with a neighborhood regularization term and Otsu’s method. Experimental results on artificially simulated craniofacial CBCT images are provided to demonstrate the effectiveness of our algorithm. Spatial non-uniformity is reduced from 16% to 7% in soft tissue and from 44% to 8% in bone regions. With shading-correction, thresholding based segmentation accuracy for bone pixels is improved from 85% to 91% when compared to thresholding without shading-correction. The proposed algorithm is thus practical and qualifies as a plug and play extension into any CBCT reconstruction software for shading correction.</p> +
<p>This paper describes the Halmstad University entry in the Grand Cooperative Driving Challenge, which is a competition in vehicle platooning. Cooperative platooning has the potential to improve traffic flow by mitigating shock wave effects, which otherwise may occur in dense traffic. A longitudinal controller that uses information exchanged via wireless communication with other cooperative vehicles to achieve string-stable platooning is developed. The controller is integrated into a production vehicle, together with a positioning system, communication system, and human–machine interface (HMI). A highly modular system architecture enabled rapid development and testing of the various subsystems. In the competition, which took place in May 2011 on a closed-off highway in The Netherlands, the Halmstad University team finished second among nine competing teams.</p> +
<p>A new system-architectural concept for trainable real-time control systems is based on resource adequacy both in processing and communication. Cyclically executing programs in distributed nodes communicate via a shared high-speed medium. Static scheduling of programs and communication implies that the maximum possible work-load can always be handled in a time-deterministic manner. The use of Artificial Neural Networks (ANN) algorithms and trainability implies a new system development strategy based on a Continuous Development paradigm. An implementation of the Architectural concept is presented. The communication speed is measured in Gbps and the access method is TDMA. An implementation of the system-development strategy is also presented. © 1993.</p> +
A multi-channel adaptive nonlinear filtering structure realizingsome properties of the hearing system +
<p>An adaptive nonlinear signal-filtering model of the cochlea is proposed based on the functional properties of the inner ear. The model consists of the cochlear filtering segments taking into account the longitudinal, transverse and radial pressure wave propagation. On the basis of an analytical description of different parts of the model and the results of computer modeling, the biological significance of the nonlinearity of signal transduction processes in the outer hair cells, their role in signal compression and adaptation, the efferent control over the characteristics of the filtering structures (frequency selectivity and sensitivity) are explained. © 2004 Elsevier Ltd. All rights reserved.</p> +
<p>Artificial neural networks are one of the most commonly used tools for character recognition problems, and usually they take gray values of 2D character images as inputs. In this paper, we propose a novel neural network classifier whose input is ID string patterns generated from the spatial relationships of primitive structures of Ethiopiccharacters. The spatial relationships of primitives are modeled by a special tree structure from which a unique set of string patterns are generated for each character. Training theneural network with string patterns of different font types and styles enables the classifier to handle variations in font types, sizes, and styles. We use a pair of directional filters forextracting primitives and their spatial relationships. The robustness of the proposed recognition system is tested by real life documents and experimental results are reported.</p> +
A new measure of movement symmetry in early Parkinson's disease patients using symbolic processing of inertial sensor data +
<p>Movement asymmetry is one of the motor symptoms associated with Parkinson's Disease (PD). Therefore, being able to detect and measure movement symmetry is important for monitoring the patient's condition.</p><p>The present paper introduces a novel symbol based symmetry index calculated from inertial sensor data. The method is explained, evaluated and compared to six other symmetry measures. These measures were used to determine the symmetry of both upper and lower limbs during walking of 11 early-to-mid-stage PD patients and 15 control subjects. The patients included in the study showed minimal motor abnormalities according to the Unified Parkinson's Disease Rating Scale (UPDRS).</p><p>The symmetry indices were used to classify subjects into two different groups corresponding to PD or control. The proposed method presented high sensitivity and specificity with an area under the Receiver Operating Characteristic (ROC) curve of 0.872, 9\% greater than the second best method. The proposed method also showed an excellent Intraclass Correlation Coefficient (ICC) of 0.949, 55\% greater than the second best method. Results suggest that the proposed symmetry index is appropriate for this particular group of patients.</p> +
<p>In the present paper, referring to known characteristics of the outer hair cells functioning in the cochlea of the inner ear, a functional model of the outer hair cells is constructed. It consists of a linear feed-forward circuit and a non-linear positive feedback circuit. The feed-forward circuit reflects the contribution of local basilar and tectorial membrane areas and passive outer hair cells’ physical parameters to the forming of low-selectivity resonance characteristics. The non-linear positive feedback circuit reflects the non-linear outer hair cell signal transduction processes and the active role of efferents from the medial superior olive in altering circuit sensitivity and selectivity.</p><p>Referring to an analytical description of the circuit model and computer simulation results, an explanation is given over the biological meaning of the outer hair cells’ non-linearities in signal transduction processes and the role of the non-linearities in achieving the following: signal compression, the dependency of circuit sensitivity and frequency selectivity upon the input signal amplitude, the compatibility of high-frequency selectivity and short transient response of the biological filtering circuits.</p> +
A novel approach to designing an adaptive committee applied to predicting company's future performance +
<p>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. © 2012 Elsevier Ltd. All rights reserved.</p> +
<p>A data proximity matrix is an important information source in random forests (RF) based data mining, including data clustering, visualization, outlier detection, substitution of missing values, and finding mislabeled data samples. A novel approach to estimate proximity is proposed in this work. The approach is based on measuring distance between two terminal nodes in a decision tree. To assess the consistency (quality) of data proximity estimate, we suggest using the proximity matrix as a kernel matrix in a support vector machine (SVM), under the assumption that a matrix of higher quality leads to higher classification accuracy. It is experimentally shown that the proposed approach improves the proximity estimate, especially when RF is made of a small number of trees. It is also demonstrated that, for some tasks, an SVM exploiting the suggested proximity matrix based kernel, outperforms an SVM based on a standard radial basis function kernel and the standard proximity matrix based kernel. © 2012 Elsevier Ltd. All rights reserved.</p> +
<p>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. © 2013 Elsevier Ltd. All rights reserved.</p> +
<p>Prediction of company’s life cycle stage change; creation of an ordered 2D map allowing to explore company’sfinancial soundness from a rating agency perspective; and prediction of trends of main valuationattributes usually used by investors are the main objectives of this article. The developed algorithms arebased on a random forest (RF) and a nonlinear data mapping technique ‘‘t-distributed stochastic neighborembedding’’.Information from five different perspectives, namely balance, income, cash flow, stock price, and risk indicatorswas aggregated via proximity matrices of RF to enable exploration of company’s financial soundnessfrom 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 increating ordered 2D maps of rated companies. The companies were well ordered according to the creditrisk rating assigned by the Moody’s rating agency.Results of experimental investigations substantiate that the developed models are capable of predictingshort term trends of the main valuation attributes, providing valuable information for investors, withlow error. The models reflect financial soundness of actions taken by company’s management team. Itwas also found that company’s life cycle stage change can be determined with the average accuracy of72.7%. Bearing in mind fuzziness of the transition moment, the obtained prediction accuracy is ratherencouraging.</p> +
