Property:Abstract
From ISLAB/CAISR
Jump to navigationJump to searchThis is a property of type Text.
O
<p>There is a strong trend for increasingly sophisticated Advanced Driver Assistance Systems (ADAS) such as Autonomous Emergency Braking (AEB) systems, Lane Keeping Aid (LKA) systems, or indeed autonomous driving. This trend generates a need for online maneuver generation, for which numerous approaches can be found in the large body of work related to path planning and obstacle avoidance. In order to ease the challenge of choosing a method, this paper reports quantitative and qualitative insights about three different path planning methods: a state lattice planner, model predictive control, and spline-based search tree. Each method is described, implemented and compared on two specific traffic situations. In addition, qualitative merits and drawbacks are discussed for each method. The paper will not provide a final answer about which method is best. This depends on several factors such as computational constraints and the formulation of maneuver optimality that is appropriate for a given assistance or safety function. Instead, the conclusions will provide guidance for choosing a method for a specific application.</p> +
<p>The ever increasing complexity of modern systems and equipment make the task of monitoring their health quite challenging. Traditional methods such as expert defined thresholds, physics based models and process history based techniques have certain drawbacks. Thresholds defined by experts require deep knowledge about the system and are often too conservative. Physics driven approaches are costly to develop and maintain. Finally, process history based models require large amount of data that may not be available at design time of a system. Moreover, the focus of these traditional approaches has been system specific. Hence, when industrial systems are deployed on a large scale, their monitoring becomes a new challenge. Under these conditions, this paper demonstrates the use of a group-based selfmonitoring approach that learns over time from similar systems subject to similar conditions. The approach is based on conformal anomaly detection coupled with an exchangeability test that uses martingales. This allows setting a threshold value based on sound theoretical justification. A hypothesis test based on this threshold is used to decide on if a system has deviated from its group. We demonstrate the feasibility of this approach through a real case study of monitoring a group of heat-pumps where it can detect a faulty hot-water switch-valve and a broken outdoor temperature sensor without previously observing these faults.</p> +
<p>A study of the dimensionality of the Face Authentication problem using Principal Component Analysis (PCA) and a novel dimensionality reduction algorithm that we call Support Vector Features (SVF) is presented. Starting from a Gabor feature space, we show that PCA and SVF identify distinct subspaces with comparable authentication and generalisation performance. Experiments using KNN classifiers and Support Vector Machines (SVMs) indicate that the number of PCs or SVF required for the authentication performance to saturate heavily depends on the choice of the classifier. SVMs appear to be vulnerable to excessive PCA-based compression.</p> +
<p>The paper is an experimental study of using the rough sets based rule induction algorithm MODLEM in the framework of multiple classifiers. Particular attention is paid to using a meta-classifier called combiner, which learns how to aggregate answers of component classifiers. The experimental results confirm that the range of classification improvement for the combiner depends on the independence of errors made by the component classifiers. Moreover, we summarize the experience with using MODLEM in other multiple classifiers, namely the bagging and n <sup>2</sup> classifiers. © 2005 IEEE.</p> +
<p>The integration of microcontrollers within mechanical systems is a current trend. However, decreasing the size of the system and satisfying higher precision requirements make it necessary to reevaluate the common signal processing techniques for controller implementations, because limited controller size, computation speed, and power consumption become major topics. In this paper, we demonstrate that serial computations with the most significant digits first, that is, on-line arithmetic, offer an important potential for real-time control. They enable a combination of traditional functions, such as analog-to-digital converters and control data computations. This leads to very efficient controller implementations with small size, high speed, and low power consumption. After a brief description of the requirements and challenges of microsystem controller design, the use of on-line arithmetic for real-time control is proposed. A short introduction to on-line arithmetic is given and control-specific implementation guidelines are presented and finally applied to a simple test system.</p> +
<p>Online recognition of handwritten characters is gaining a renewed interest as it provides a natural way of data entry for a wide variety of handheld devices. In this paper, we present online handwriting recognition system for Ethiopic script based on the structural and syntactical analysis of the strokes forming characters. The complex structures of characters are represented by the spatio- temporal relationships of simple-shaped strokes called primitives. A special tree structure is used to model spatio- temporal relationships of the strokes. The tree generates a unique set of primitive stroke sequences for each character, and for recognition each stroke sequence is matched against a stored knowledge base. Characters are also classified based on their structural similarity to select a plausible set of characters for un unknown input, which improves recognition and processing time. We also present a dataset collected for training and testing online recognition systems for Ethiopic script. The dataset is prepared in accordance with the international standard UNIPEN format. The recognition system is tested with the collected dataset and experimental results are reported.</p> +
<p>Whole-body operational space control is a powerful compliant control approach for robots that physically interact with their environment. The underlying mathematical and algorithmic principles have been laid in a large body of published work, and novel research keeps advancing its formulation and variations. However, the lack of a reusable and robust shared implementation has hindered its widespread adoption. To fill this gap, we present an open-source implementation of whole-body operational space control that provides runtime configurability, ease of reuse and extension, and independence from specific middlewares or operating systems. Our libraries are highly portable. Decoupling from specific runtime platforms (such as RTAI or ROS) is achieved by containing application code in a thin adaptation layer. In this paper, we briefly survey the foundations of whole-body control for mobile manipulation, describe the structure of our software, very briefly present experiments on two quite different robots, and then delve into the bundled tutorials to help prospective new users.</p> +
<p>The maximization of biomass productivity in the fed-batch fermentation of Saccharomyces cerevisiae is analyzed. Due to metabolic bottleneck, often attributed to limited oxygen capacity, ethanol is formed when the substrate concentration is above a critical value, which results in a decrease in biomass productivity. Thus, to maximize the production of biomass, the substrate concentration should be kept at the critical value. However, this value is unknown a priori and may change from experiment to experiment. A way to overcome this lack of knowledge is to allow the cells to produce a very small amount of ethanol. This way, the problem of maximizing the production of biomass is converted into that of regulating the concentration of ethanol, for which cell growth can be viewed as a perturbation. A novel adaptive control methodology based on the internal model principle is used to maintain the desired ethanol setpoint and reject the perturbation. Only a single parameter needs to be estimated on-line. Experimental results demonstrate the effectiveness of the proposed control methodology.</p> +
<p>We suggest a set of complex differential operators, symmetry derivatives, that can be used for matching and pattern recognition. We present results on the invariance properties of these. These show that all orders of symmetry derivatives of Gaussians yield a remarkable invariance : they are obtained by replacing the original differential polynomial with the same polynomial but using ordinary scalars. Moreover, these functions are closed under convolution and they are invariant to the Fourier transform. The revealed properties have practical consequences for local orientation based feature extraction. This is shown by two applications: i) tracking markers in vehicle tests ii) alignment of fingerprints.</p> +
<p>While standard compression methods available include complex source encoding schemes, the scanning of the image is often performed by a horizontal (row-by-row) or vertical scanning. In this work a new scanning method, called ridge scanning, for lossless compression of fingerprint images is presented. By using ridge scanning our goal is to increase the redundancy in data and thereby increase the compression rate. By using orientations, estimated from the linear symmetry property of local neighbourhoods in the fingerprint, a scanning algorithm which follows the ridges and valleys is developed. The properties of linear symmetry are also used for a segmentation of the fingerprint into two parts, one part which lacks orientation and one that has it. We demonstrate that ridge scanning increases the compression ratio for Lempel-Ziv coding as well as recursive Huffman coding with approximately 3% in average. Compared to JPEG-LS, using ridge scanning and recursive Huffman the gain is 10% in average.</p> +
<p>Smart grids are advanced power grids that use modern hardware and software technologies to provide clean, safe, secure, reliable, ecient and sustainable energy. However, there are many challenges in the eld of smart grids in terms of communication, reliability, interoperability, and big data that should be considered. In this paper we present a brief overview of some of the challenges and solutions in the smart grids, focusing especially on the Swedish point of view. We discuss thirty articles, from 2006 until 2013, with the main interest on datarelated challenges.</p> +
P
<p>Piums®, a new protein identification tool for peptide fingerprints, is presented. Piums includes both a peak extraction tool (Pepex®) and a new protein scoring algorithm (Piped®). The basic ideas underlying the scoring algorithm are presented and it is demonstrated on some real sample spectra. It is shown, using simulated peak lists, how the scoring performance varies with contamination levels and protein sequence coverage, and that there is a boundary for when scoring is possible. Piums is fully scriptable and modularised. Each individual module can be used by itself, with input and output in XML format, to e.g. include it in an analysis chain. Piums is benchmarked against the Mascot software from Matrix Science LLC, The results indicate that Piums is more precise than the Mascot score, and about 5-10% more efficient than Mascot for real peak lists, for the same level of false positives.</p> +
<p>Application of deep learning tends to outperform hand-crafted features in many domains. This study uses convolutional neural networks to explore effectiveness of various segments of a speech signal,? – text-dependent pronunciation of a short sentence, – in Parkinson’s disease detection task. Besides the common Mel-frequency spectrogram and its first and second derivatives, inclusion of various other input feature maps is also considered. Image interpolation is investigated as a solution to obtain a spectrogram of fixed length. The equal error rate (EER) for sentence segments varied from 20.3% to 29.5%. Fusion of decisions from sentence segments achieved EER of 14.1%, whereas the best result when using the full sentence exhibited EER of 16.8%. Therefore, splitting speech into segments could be recommended for Parkinson’s disease detection. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2018.</p> +
<p>Minutia based matching scheme is the most widely accepted method for both automated as well as manual (forensic) fingerprint matching. The scenario of comparing a partial fingerprint minutia set against a full fingerprint minutia set is a challenging problem. In this work, we propose a method to register the orientation field of the partial fingerprint minutia set to that of the orientation field of full fingerprint minutia set. As a consequence of registering the partial fingerprint orientation field, we obtain extra information that can augment a minutia based matcher by reducing the search space of minutiae in the full fingerprint. We present the accuracy of our registration algorithm on NIST-SD27 database, reporting separately for both subjective and quantitative quality classification of NIST-SD27. The registration performance accuracy is measured in terms of percentage of ground truth minutiae present in the reduced minutiae search space generated by our algorithm. ©2014 IEEE.</p> +
PastVision+ : Thermovisual Inference of Recent Medicine Intake by Detecting Heated Objects and Cooled Lips +
<p>This article addresses the problem of how a robot can infer what a person has done recently, with a focus on checking oral medicine intake in dementia patients. We present PastVision+, an approach showing how thermovisual cues in objects and humans can be leveraged to infer recent unobserved human-object interactions. Our expectation is that this approach can provide enhanced speed and robustness compared to existing methods, because our approach can draw inferences from single images without needing to wait to observe ongoing actions and can deal with short-lasting occlusions; when combined, we expect a potential improvement in accuracy due to the extra information from knowing what a person has recently done. To evaluate our approach, we obtained some data in which an experimenter touched medicine packages and a glass of water to simulate intake of oral medicine, for a challenging scenario in which some touches were conducted in front of a warm background. Results were promising, with a detection accuracy of touched objects of 50% at the 15 s mark and 0% at the 60 s mark, and a detection accuracy of cooled lips of about 100 and 60% at the 15 s mark for cold and tepid water, respectively. Furthermore, we conducted a follow-up check for another challenging scenario in which some participants pretended to take medicine or otherwise touched a medicine package: accuracies of inferring object touches, mouth touches, and actions were 72.2, 80.3, and 58.3% initially, and 50.0, 81.7, and 50.0% at the 15 s mark, with a rate of 89.0% for person identification. The results suggested some areas in which further improvements would be possible, toward facilitating robot inference of human actions, in the context of medicine intake monitoring.</p> +
PastVision: Exploring "Seeing" into the Near Past with Thermal Touch Sensing and Object Detection -- For Robot Monitoring of Medicine Intake by Dementia Patients +
<p>We present PastVision, a proof-of-concept approach that explores combining thermal touch sensing and object detection to infer recent actions by a person which have not been directly observed by a system. Inferring such past actions has received little attention yet in the literature, but would be highly useful in scenarios in which sensing can fail (e.g., due to occlusions) and the cost of not recognizing an action is high. In particular, we focus on one such application, involving a robot which should monitor if an elderly person with dementia has taken medicine. For this application, we explore how to combine detection of touches and objects, as well as how heat traces vary based on materials and a person’s grip, and how robot motions and activity models can be leveraged. The observed results indicate promise for the proposed approach.</p> +
<p>This paper addresses the path following problem for autonomous Ackermann-like vehicle navigation. A control strategy that takes into account both kinodynamic and configuration space constraints of the vehicle, denoted as Traversability-Anchored Dynamic Path Following (TADPF) controller is presented. It ensures secure vehicle commands in presence of obstacles, based on traversability information given by a global navigation function. By additionally using a reference point on the global smooth path, the local vicinity path configuration with respect to the vehicle is taken explicitly into account to ensure smooth and stable path following. Furthermore, a previously developed Sliding Mode Path Following (SMPF) controller that results in fast convergence rate and low path following error but which does not consider kinodynamic constraints, is augmented by the the kinodynamic and configuration space constraints check of the TADPF controller. The new proposed control strategy denoted as TADPF-SMPF controller thus combines advantageous characteristics of both original control strategies for path following, yielding inherent safety and vehicle dynamics margin. All three control strategies are verified in simulation, whereas the TADPF and TADPF-SMPF path following schemes are also verified experimentally. © 2008 IEEE.</p> +
<p>We present an autonomous driving system that iscapable of planning, replanning, and executing paths for drivingin urban and offroad environments. For planning, we rely onthe E algorithm which computes a smooth navigation functionthat takes into account traversibility information extracted fromlaser scans. The path execution algorithm is centered arounda kinodynamic controller which follows the gradient of thenavigation function. This work is based on prior experience withthe SmartTer vehicle, which we are in the process of updating,and the focus is on integration.</p> +
<p>Periocular biometrics has been established as an independent modality due to concerns on the performance of iris or face systems in uncontrolled conditions. Periocular refers to the facial region in the eye vicinity, including eyelids, lashes and eyebrows. It is available over a wide range of acquisition distances, representing a trade-off between the whole face (which can be occluded at close distances) and the iris texture (which do not have enough resolution at long distances). Since the periocular region appears in face or iris images, it can be used also in conjunction with these modalities. Features extracted from the periocular region have been also used successfully for gender classification and ethnicity classification, and to study the impact of gender transformation or plastic surgery in the recognition performance. This paper presents a review of the state of the art in periocular biometric research, providing an insight of the most relevant issues and giving a thorough coverage of the existing literature. Future research trends are also briefly discussed. © 2016 IEEE.</p> +
<p>Periocular refers to the region around the eye, including sclera, eyelids, lashes, brows and skin. With a surprisingly high discrimination ability, it is the ocular modality requiring the least constrained acquisition. Here, we apply existing pre-trained architectures, proposed in the context of the ImageNet Large Scale Visual Recognition Challenge, to the task of periocular recognition. These have proven to be very successful for many other computer vision tasks apart from the detection and classification tasks for which they were designed. Experiments are done with a database of periocular images captured with a digital camera. We demonstrate that these offthe-shelf CNN features can effectively recognize individuals based on periocular images, despite being trained to classify generic objects. Compared against reference periocular features, they show an EER reduction of up to ~40%, with the fusion of CNN and traditional features providing additional improvements.</p> +
