Property:Abstract
From ISLAB/CAISR
Jump to navigationJump to searchThis is a property of type Text.
F
<p>Fake iris detection has been studied so far using near-infrared sensors (NIR), which provide grey scale-images, i.e. With luminance information only. Here, we incorporate into the analysis images captured in visible range, with color information, and perform comparative experiments between the two types of data. We employ Gray-Level Cocurrence textural features and SVM classifiers. These features analyze various image properties related with contrast, pixel regularity, and pixel co-occurrence statistics. We select the best features with the Sequential Forward Floating Selection (SFFS) algorithm. We also study the effect of extracting features from selected (eye or periocular) regions only. Our experiments are done with fake samples obtained from printed images, which are then presented to the same sensor than the real ones. Results show that fake images captured in NIR range are easier to detect than visible images (even if we down sample NIR images to equate the average size of the iris region between the two databases). We also observe that the best performance with both sensors can be obtained with features extracted from the whole image, showing that not only the eye region, but also the surrounding periocular texture is relevant for fake iris detection. An additional source of improvement with the visible sensor also comes from the use of the three RGB channels, in comparison with the luminance image only. A further analysis also reveals that some features are best suited to one particular sensor than the others. © 2014 IEEE</p> +
<p>A point-symmetry function based on autoconvolution is described which makes it possible to track the position of point-symmetric objects with sub-pixel accuracy. The method is insensitive to grey level and was developed in order to have a fast and robust algorithm for real-time tracking of small magnetic particles in a light microscopc. The phase contrast microscope image of the 4.5 mu m diameter spherical particle consisted of concentric light and dark fringes where the shape of the fringes were dependent on the focus. The position of the particle could be monitored in real-time at 25 Hz with a lateral accuracy of +/- 20 nm corresponding to less than +/- 0.1 pixel. To determine the vertical or z-position a new parameter was defined representing a measure of the second derivative of the intensity function. The vertical position could thus be determined with an accuracy of +/-50 nm. The magnetic particle could be tracked acid guided by applied magnetic fields to remain in a fixed position or programmed to scan either horizontal or vertical surfaces. Forces down to 10(-14) N could be measured by monitoring the applied magnetic forces. One and two-dimensional Brownian motion could be studied by regulating the particle to a fixed z-position and monitoring the lateral position.</p> +
<p>The ubiquitous computing paradigm is becoming a reality; we are reaching a level of automation and computing in which people and devices interact seamlessly. However, one of the main challenges is the difficulty users have in interacting with these increasingly complex systems. Ultimately, endowing machines with the ability to perceive users' emotions will enable a more intuitive and reliable interaction. Consequently, using the electroencephalogram (EEG) as a bio-signal sensor, the affective state of a user can be modelled and subsequently utilised in order to achieve a system that can recognise and react to the users emotions. In this context, this paper investigates feature vector generation from EEG signals for the purpose of affective state modelling based on Russells Circumplex Model. Investigations are presented that aim to provide the foundation for future work in modelling user affect and interaction experiences through exploitation of different input modalities. The DEAP dataset was used within this work, along with a Support Vector Machine, which yielded reasonable classification accuracies for Valence and Arousal using feature vectors based on statistical measurements, band power from the α, β, δ and θ waves, and High Order Crossing of the EEG signal. © 2016 IEEE.</p> +
<p>We present a neural network based approach for identifying salient features for classification in feedforward neural networks. Our approach involves neural network training with an augmented cross-entropy error function. The augmented error function forces the neural network to keep low derivatives of the transfer functions of neurons when learning a classification task. Such an approach reduces output sensitivity to the input changes. Feature selection is based on the reaction of the cross-validation data set classification error due to the removal of the individual features. We demonstrate the usefulness of the proposed approach on one artificial and three real-world classification problems. We compared the approach with five other feature selection methods, each of which banks on a different concept. The algorithm developed outperformed the other methods by achieving higher classification accuracy on all the problems tested.</p> +
<p>Improving the performance of systems is a goal pursued in all areas and vehicles are no exception. In places like Europe, where the majority of goods are transported over land, it is imperative for fleet operators to have the best efficiency, which results in efforts to improve all aspects of truck operations. We focus on drivers and their performance with respect to fuel consumption. Some of relevant factors are not accounted for inavailable naturalistic data, since it is not feasible to measure them. An alternative is to set up experiments to investigate driver performance but these are expensive and the results are not always conclusive. For example, drivers are usually aware of the experiment’s parameters and adapt their behavior.</p><p>This paper proposes a method that addresses some of the challenges related to categorizing driver performance with respect to fuel consumption in a naturalistic environment. We use expert knowledge to transform the data and explore the resulting structure in a new space. We also show that the regions found in APPES provide useful information related to fuel consumption. The connection between APPES patterns and fuel consumption can be used to, for example, cluster drivers in groups that correspond to high or low performance.</p> +
<p>With the introduction of low-cost wireless communication many new applications have been made possible; applications where systems can collaboratively learn and get wiser without human supervision. One potential application is automated monitoring for fault isolation in mobile mechatronic systems such as commercial vehicles. The paper proposes an agent design that is based on uploading software agents to a fleet of mechatronic systems. Each agent searches for interesting state representations of a system and reports them to a central server application. The states from the fleet of systems can then be used to form a consensus from which it can be possible to detect deviations and even locating a fault.</p> +
<p>Recently, image quality awareness has been found to increase recognition rates and to supportdecisions in multimodal authentication systems significantly. Nevertheless, automatic quality assessmentis still an open issue, especially with regard to biometric authentication tasks. Here we analyze theorientation tensor of fingerprint images with a set of symmetry descriptors, in order to detect fingerprintimage quality impairments like noise, lack of structure, blur, etc. Allowed classes of local shapes area priori application information for the proposed quality measures, therefore no training or explicitimage reference information is required. Our quality assessment method is compared to an existingautomatic method and a human opinion in numerous experiments involving several public databases.Once the quality of an image is determined, it can be exploited in several ways, one of which is toadapt fusion parameters in a monomodal multi-algorithm environment, here a number of fingerprintrecognition systems. In this work, several trained and non-trained fusion schemes applied to the scoresof these matchers are compared. A Bayes-based strategy for combining experts with weights on theirpast performances, able to readapt to each identity claim based on the input quality is developed andevaluated. To show some of the advantages of quality-driven multi-algorithm fusion, such as boostingrecognition rates, increasing computational efficiency, etc., a novel cascade fusion and simple fusionrules are employed in comparison as well.</p> +
<p>Signal-quality awareness has been found to increase recognition rates and to support decisions in multisensor environments significantly. Nevertheless, automatic quality assessment is still an open issue. Here, we study the orientation tensor of fingerprint images to quantify signal impairments, such as noise, lack of structure, blur, with the help of symmetry descriptors. A strongly reduced reference is especially favorable in biometrics, but less information is not sufficient for the approach. This is also supported by numerous experiments involving a simpler quality estimator, a trained method (NFIQ), as well as the human perception of fingerprint quality on several public databases. Furthermore, quality measurements are extensively reused to adapt fusion parameters in a monomodal multialgorithm fingerprint recognition environment. In this study, several trained and nontrained score-level fusion schemes are investigated. A Bayes-based strategy for incorporating experts' past performances and current quality conditions, a novel cascaded scheme for computational efficiency, besides simple fusion rules, is presented. The quantitative results favor quality awareness under all aspects, boosting recognition rates and fusing differently skilled experts efficiently as well as effectively (by training).</p> +
<p>First, an overview of the state of the art in fingerprint recognition is presented, including current issues and challenges. Fingerprint databases and evaluation campaigns, are also summarized. This is followed by the description of the BioSecure Benchmarking Framework for Fingerprints, using the NIST Fingerpint Image Software (NFIS2), the publicly available MCYT-100 database, and two evaluation protocols. Two research systems are compared within the proposed framework. The evaluated systems follow different approaches for fingerprint processing and are discussed in detail. Fusion experiments involving different combinations of the presented systems are also given. The NFIS2 software is also used to obtain the fingerprint scores for the multimodal experiments conducted within the BioSecure Multimodal Evaluation Campaign(BMEC’2007) reported in Chap.11.</p> +
<p>The flipped classroom format involves swapping activities traditionally performed inside and outside the classroom. The expected effectsfrom this swap include increased student engagement and peer-to-peer interaction in the classroom, as well as more flexible access to learning materials. Key criteria for successful outcomes from these effects include improved test scores and enhanced student satisfaction. Unfortunately, while many researchers have reported positive outcomes from the approach, some instructors can still encounter difficulties in reproducing this success.</p><p>In this paper we report our experiences with flipping a first course on Cyber-Physical Systems at Halmstad University. The course is required for a Masters level program and is available as an elective for undergraduates. The focus of this report is on three separate editions of the course taught over three years. In the first year, lectures were recorded. In the second, the same instructor taught the course using the flipped format. In the third, new instructors taught it using the flipped classroom format.</p><p>Our experience suggests that flipping a classroom can lead to improved student performance and satisfaction from the first edition. It can also enable new instructors to take over the course and perform at a level comparable to an experienced instructor. On the other hand, it also suggests that the format may require more effort to prepare for, and to teach, than the traditional format, and that a higher level of attention to detail is needed to execute it with positive outcomes. Thus, the format can be demanding for instructors. It is also the case that not all students preferred this format.</p> +
<p>A portable gait measurement system for foot dynamic analysis is proposed. Portable cheap sensors are suitable in active control rehabilitation equipments such as prostheses and orthoses. A system of one gyroscope and two accelerometers was used to measure the foot movement in the sagital plane. Both ground inclination during stance and foot angle relative to ground during swing are estimated. This enables fast detection of changing environments such as hills and stairs.</p> +
<p>An embedded measurement system for foot orthosis during gait is proposed. In this paper strain gauge sensors are mounted on a foot orthosis in order to give information about strain in the sagital plane. The ankle angle of the orthosis is fixed. Strain characteristics are therefore changed when walking on slopes. It is investigated if strain information can be used for detection of inclination and estimation of inclination angle. Also walking speed influence is studied. It is shown that strain sensing only gives significant information about up hill walking. At a known walking speed ground angle can be estimated for up hill walking.</p> +
<p>Increasingly, absolute frequency and orientation maps are needed, e.g. for forensics. We introduce a non-linear scale space via the logarithm of trace of the Structure Tensor. Therein, frequency estimation becomes an orientation estimation problem. We show that this offers significant advantages, including construction of efficient isotropic estimations of dense maps of frequency. In fingerprints, both maps are shown to improve each other in an enhancement scheme via Gabor filtering. We suggest a novel continuous ridge counting method, relying only on dense absolute frequency and orientation maps, without ridge detection, thinning, etc. Furthermore, we present new evidence that frequency maps are useful attributes of minutiae. We verify that the suggested method compares favorably with state of the art using forensic fingerprints as test bed, and test images where the ground truth is known. In evaluations, we use public data sets and published methods only.</p> +
Fusing Various Audio Feature Sets for Detection of Parkinson's Disease from Sustained Voice and Speech Recordings +
<p>The aim of this study is the analysis of voice and speech recordings for the task of Parkinson’s disease detection. Voice modality corresponds to sustained phonation /a/ and speech modality to a short sentence in Lithuanian language. Diverse information from recordings is extracted by 22 well-known audio feature sets. Random forest is used as a learner, both for individual feature sets and for decision-level fusion. Essentia descriptors were found as the best individual feature set, achieving equal error rate of 16.3 % for voice and 13.3 % for speech. Fusion of feature sets and modalities improved detection and achieved equal error rate of 10.8 %. Variable importance in fusion revealed speech modality as more important than voice. © Springer International Publishing Switzerland 2016</p> +
<p>To improve recognition results, decisions of multiple neural networks can be aggregated into a committee decision. Aggregation weights assigned to neural networks or groups of networks can be the same in the entire data space or can be different (data dependent) in various regions of the space. In this paper, we propose a method for obtaining data dependent aggregation weights. The proposed approach is tested in two aggregation schemes, namely aggregation through neural network selection, and aggregation by the Choquet integral with respect to the lambda-fuzzy measure. The effectiveness of the approach is demonstrated on two artificial and three real data sets.</p> +
<p>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/).</p> +
<p>Detection of mild laryngeal disorders using acoustic parameters of human voice is the main objective in this study. Observations of sustained phonation (audio recordings of vocalized /a/) are labeled by clinical diagnosis and rated by severity (from 0 to 3). Research is exclusively constrained to healthy (severity 0) and mildly pathological (severity 1) cases - two the most difficult classes to distinguish between. Comprehensive voice signal characterization and information fusion constitute the approach adopted here. Characterization is obtained through diverse feature set, containing 26 feature subsets of varying size, extracted from the voice signal. Usefulness of feature-level and decision-level fusion is explored using support vector machine (SVM) and random forest (RF) as basic classifiers. For both types of fusion we also investigate the influence of feature selection on model accuracy. To improve the decision-level fusion we introduce a simple unsupervised technique for ensemble design, which is based on partitioning the feature set by k-means clustering, where the parameter k controls the size and diversity of the prospective ensemble. All types of the fusion resulted in an evident improvement over the best individual feature subset. However, none of the types, including fusion setups comprising feature selection, proved to be significantly superior over the rest. The proposed ensemble design by feature set decomposition discernibly enhanced decision-level and significantly outperformed feature-level fusion. Ensemble of RF classifiers, induced from a cluster-based partitioning of the feature set, achieved equal error rate of 13.1 ± 1.8% in the detection of mildly pathological larynx. This is a very encouraging result, considering that detection of mild laryngeal disorder is a more challenging task than a common discrimination between healthy and a wide spectrum of pathological cases. © 2014 Elsevier B.V.</p> +
<p>In this paper, we discuss some new methods for combining different outputs from several feed forward neural networks into a final output. We generalize the BADD defuzzification method (G-BADD) to obtain substantial improvement in system output. It is compared with the ordinary BADD-, Sugeno- and the MOM-methods. The use of the fuzzy integral, as a selection tool when deciding which networks are to be used in the combination, is introduced.</p> +
G
Gait Event Detection in Real-World Environment for Long-Term Applications : Incorporating Domain Knowledge into Time-Frequency Analysis +
<p>Detecting gait events is the key to many gait analysis applications that would benefit from continuous monitoring or long-term analysis. Most gait event detection algorithms using wearable sensors that offer a potential for use in daily living have been developed from data collected in controlled indoor experiments. However, for real-word applications, it is essential that the analysis is carried out in humansâ natural environment; that involves different gait speeds, changing walking terrains, varying surface inclinations and regular turns among other factors. Existing domain knowledge in the form of principles or underlying fundamental gait relationships can be utilized to drive and support the data analysis in order to develop robust algorithms that can tackle real-world challenges in gait analysis. This paper presents a novel approach that exhibits how domain knowledge about human gait can be incorporated into time-frequency analysis to detect gait events from longterm accelerometer signals. The accuracy and robustness of the proposed algorithm are validated by experiments done in indoor and outdoor environments with approximately 93,600 gait events in total. The proposed algorithm exhibits consistently high performance scores across all datasets in both, indoor and outdoor environments. © Copyright 2016 IEEE</p> +
<p>Healthy gait requires a balance between various neuro-physiological systems and is considered an important indicator of a subject's physical and cognitive health status. As such, health-related applications would immensely benefit by performing long-term or continuous monitoring of subjects' gait in their natural environment and everyday lives. In contrast to stationary sensors such as motion capture systems and force plates, inertial sensors provide a good alternative for such gait analysis applications as they are miniature, cheap, mobile and can be easily integrated into wearable systems.</p><p>This thesis focuses on improving overall gait analysis using inertial sensors by providing a methodology for detecting gait events in real-world settings. Although the experimental protocols for such analysis have been restricted to only highly-controlled lab-like indoor settings; this thesis presents a new gait database that consists of data from gait activities carried out in both, indoor and outdoor environments. The thesis shows how domain knowledge about gait could be formulated and utilized to develop methods that are robust and can tackle real-world challenges. It also shows how the proposed approach can be generalized to estimate gait events from multiple body locations. Another aspect of this thesis is to demonstrate that the traditionally used temporal error metrics are not enough for presenting the overall performance of gait event detection methods. The thesis introduces how non-parametric tests can be used to complement them and provide a better overview.</p><p>The results of comparing the proposed methodology to state-of-the-art methods showed that the approach of incorporating domain knowledge into the time-frequency analysis of the signal was robust across different real-world scenarios and outperformed other methods, especially for the scenario involving variable gait speeds in outdoor settings. The methodology was also benchmarked on publicly available gait databases yielding good performance for estimating events from different body locations. To conclude, this thesis presents a road map for the development of gait analysis systems in real-world settings.</p>
