Property:Abstract
From ISLAB/CAISR
Jump to navigationJump to searchThis is a property of type Text.
U
<p>Knowledge of the precise position of crop plants is a prerequisite for effective mechanical weed control in robotic weeding application such as in crops like sugar beets which are sensitive to mechanical stress. Visual detection and recognition of crop plants based on their shapes has been described many times in the literature. In this paper the potential of using knowledge about the crop seed pattern is investigated based on simulated output from a perception system. The reliability of position–based crop plant detection is shown to depend on the weed density (ρ, measured in weed plants per square metre) and the crop plant pattern position uncertainty (σ<sub>x</sub> and σ<sub>y</sub>, measured in metres along and perpendicular to the crop row, respectively). The recognition reliability can be described with the positive predictive value (PPV), which is limited by the seeding pattern uncertainty and the weed density according to the inequality: PPV ≤ (1 + 2πρσ<sub>x</sub>σ<sub>y</sub>)<sup>−1</sup>. This result matches computer simulations of two novel methods for position–based crop recognition as well as earlier reported field–based trials. © 2016 IAgrE</p> +
<p>Cost effective methods for predictive maintenance are increasingly demanded in the automotive industry. One solution is to utilize the on-board signals streams on each vehicle and build self-organizing systems that discover data deviations within a fleet. In this paper we evaluate histograms as features for describing and comparing individual vehicles. The results are based on a long-term field test with nineteen city buses operating around Kungsbacka in Halland. The purpose of this work is to investigate ways of discovering abnormal behaviors and irregularities between histograms of on-board signals, here specifically focusing on air pressure. We compare a number of distance measures and analyze the variability of histograms collected over different time spans. Clustering algorithms are used to discover structure in the data and track how this changes over time. As data are compared across the fleet, observed deviations should be matched against (often imperfect) reference data coming from workshop maintenance and repair databases.</p> +
Using Labelled and Unlabelled Data to Train a Multilayer Perceptron for Colour Classification in Graphic Arts +
<p>This paper presents an approach to using both labelled and unlabelled data to train a multi-layer perceptron. The unlabelled data are iteratively pre-processed by a perceptron being trained to obtain the soft class label estimates. It is demonstrated that substantial gains in classification performance may be achieved from the use of the approach when the labelled data do not adequately represent the entire class distributions. The experimental investigations performed have shown that the approach proposed may be successfully used to train networks for colour classification in graphic arts.</p> +
<p>Estimation of combustion variability can be performed by using ion currents measured at the spark plug. A scheme is here proposed that exploits the potential of using measurements from multiple cylinders to improve the estimation accuracy of combustion variability (measured by the coefficient of variation of IMEP). This is realised by dividing combustion variability into categories and having one classifier running for each cylinder with the ion current as input signal. The final estimate of combustion variability is then formed by a majority vote among the classifiers. This scheme is shown to improve estimation accuracy by up to 15% on measurements taken from highway driving in a production vehicle.</p> +
<p>This paper presents an approach to using both labelled and unlabelled data to train a multilayer perceptron. The unlabelled data are iteratively pre-processed by a perceptron being trained to obtain the soft class label estimates. It is demonstrated that substantial gains in classification performance may be achieved from the use of the approach when the labelled data do not represent adequately the entire class distributions. The experimental investigations performed have shown that the approach proposed may be successfully used to train neural networks for learning different classification problems. © Springer-Verlag Berlin Heidelberg 2001.</p> +
<p>This letter concerns several papers, devoted to neural network-based process and system modelling, recently published in the Chemometrics and Intelligent Laboratory Systems journal. Artificial neural networks have proved themselves to be very useful in various modelling applications, because they can represent complex mapping functions and discover the representations using powerful learning algorithms. An optimal set of parameters for defining the functions is learned from examples by minimizing an error functional. In various practical applications, the number of examples available for estimating parameters of the models is rather limited. Moreover, to discover the best model, numerous candidate models must be trained and evaluated. In such thin-data situations, special precautions are to be taken to avoid erroneous conclusions. In this letter, we discuss three important issues, namely network initialization, over-fitting, and model selection, the right consideration of which can be of tremendous help in successful network design and can make neural modelling results more valuable.</p> +
<p>This paper presents the idea to use linear symmetry properties as a feature based pre-processing step for fingerprint images. These features contain structural information of the local patterns. The linear symmetry can be computed by using separable spatial filtering and therefore has the potential to be a fast pre-processing step. Our results indicate that minutiae can be located as well as can be assigned a certain class type. The type of minutiae matching in combination with geometrical matching increases the matching efficiency as compared to the pure geometrical matching. </p> +
<p>This paper is concerned with soft computing techniques for screening laryngeal disorders based on patient's questionnaire data. By applying the genetic search, the most important questionnaire statements are determined and a support vector machine (SVM) classifier is designed for categorizing the questionnaire data into the healthy, nodular and diffuse classes. To explore the obtained automated decisions, the curvilinear component analysis (CCA) in the space of decisions as well as questionnaire statements is applied. When testing the developed tools on the set of data collected from 180 patients, the classification accuracy of 85.0% was obtained. Bearing in mind the subjective nature of the data, the obtained classification accuracy is rather encouraging. The CCA allows obtaining ordered two-dimensional maps of the data in various spaces and facilitates the exploration of automated decisions provided by the system and determination of relevant groups of patients for various comparisons.</p> +
<p>This Letter presents an approach to using both labelled and unlabelled data to train a multilayer perceptron. The unlabelled data are iteratively pre-processed by a perceptron being trained to obtain the soft class label estimates. It is demonstrated that substantial gains in classification performance may be achieved from the use of the approach when the labelled data do not adequately represent the entire class distributions. The experimental investigations performed have shown that the approach proposed may be successfully used to train neural networks for learning different classification problems.</p> +
V
<p>A new approach is proposed for fault detection. It builds on using the relationships between sensor values on vehicles to detect deviating sensor readings and trends in the system performance. However, in contrast to previous approaches based on such sensor relations, our approach uses a fleet of vehicles to define the normal conditions and relations. The relationships between the sensors are also determined automatically in a self-organized way on each vehicle, i.e. no off-line modeling is required. The proposed method is the first step in a remote diagnostics and maintenance service where error detection is done automatically, followed by a download of special purpose diagnostics software for the particular subsystem where the possible fault was detected.</p> +
<p>Resisting spoofing attempts via photographs and video playbacks is a vital issue for the success of face biometrics. Yet, the “liveness ” topic has only been partially studied in the past. In this paper we are suggesting a holistic liveness detection paradigm that collaborates with standard techniques in 2D face biometrics. The experiments show that many attacks are avertible via a combination of antispoofing measures. We have investigated the topic using real-time techniques and applied them to real-life spoofing scenarios in an indoor, yet uncontrolled environment.</p> +
<p>The use of computer-based signal processing and sensor technology to guide and control different types of agricultural field implements increases the performance of traditional implements and even makes it possible to create new ones. This thesis increases the knowledge on vision-based perception for mechatronic weed control. The contributions are of four different kinds:</p><p>First, a vision-based system for row guidance of agricultural field machinery has been proposed. The system uses a novel method, based on the Hough transform, for row recognition of crop rows.</p><p>Second is a proposal for a vision-based perception system to discriminate between crops and weeds, using images from real situations in the field. Most crops are cultivated in rows and sown in a defined pattern, i.e. with a constant inter-plant distance. The proposed method introduces the concept of using these geometrical properties of the scene (context) for single plant recognition and localization. A mathematical model of a crop row has been derived that models the probability for the positions of consecutive crops in a row. Based on this mathematical model two novel methods for context-based classification between crops and weeds have been developed. Furthermore, a novel method that combines geometrical features of the scene (context) and individual plant features has been proposed. The method has been evaluated in two datasets of images of sugar beet rows. The classification rate was 92 % and 98 %, respectively.</p><p>The third contribution is the design of a mobile agricultural robot equipped with these perception systems and a mechanical weeding tool intended for intra-row weed control in ecologically cultivated crops.</p><p>The fourth contribution is a demonstration of the feasibility of the perception systems in real field environments, especially with respect to robustness and real-time performance. The row guidance system has been implemented in three different row cultivators and performed inter-row weed control at two commercial farms. The robot has proven to be able to follow a row structure by itself, while performing weed control within the seed line of a crop row, i.e. intra-row cultivation. </p>
J. Bigun +
<p>Presents a systematic, mathematically rigorous examination of modern signal processing concepts used in computer vision and image analysis. This book is illustrated with 4-color graphics and applications, including biometric person authentication, texture analysis, optical character recognition, motion estimation and tracking.</p> +
<p>In this paper we propose a simple method for low-level navigation for autonomous mobile robots, employing an artificial neural network. Both corridor following and obstacle avoidance in indoor environments are managed by the same network. Raw grayscale images of size 32 x 23 pixels are processed one at a time by a feed-forward neural network. The output signals from the network directly control the motor control system of the robot. The feed-forward network is trained using the RPROP algorithm. Experiments in both familiar and unfamiliar environments are reported.</p> +
<p>The use of popular and effective robot-design competitions in teaching system integration in engineering curricula was discussed. Such robot competitions give students open-ended problem spaces, teaches them to work in groups and stimulates creativity. The technical and pedagogical aspects of robot competitions along with their experiences and shortcomings were also discussed.</p> +
<p>In this paper we present a visual odometry system for agricultural field robots that is not sensitive to uneven terrain. A stereo camera system is mounted perpendicular to the ground and height and traveled distance are calculated using normalized cross correlation. A method for evaluating the system is developed, where flower boxes containing representative surfaces are placed in a metal-working lathe. The cameras are mounted on the carriage which can be positioned manually with 0.1 mm accuracy. Images are captured every 10 mm over 700 mm. The tests are performed on eight different surfaces representing real world situations. The resulting error is less than 0.6% of traveled distance on surfaces where the maximum height variation is measured to 96 mm. The variance is measured for eight test runs, total 5.6 m, to 0.040 mm. This accuracy is sufficient for crop-scale agricultural operations.</p> +
W
<p>Early detection of anomalies, trends and emerging patterns can be exploited to reduce the number and severity of quality problems in vehicles. This is crucially important since having a good understanding of the quality of the product leads to better designs in the future, and better maintenance to solve the current issues. To this end, the integration of large amounts of data that are logged during the vehicle operation can be used to build the model of usage patterns for early prediction. In this study, we have developed a machine learning system for warranty claims by integrating available information sources: Logged Vehicle Data (LVD) and Warranty Claims (WCs). The experimental results obtained from a large data set of heavy duty trucks are used to demonstrate the effectiveness of the proposed system to predict the warranty claims. © Springer Nature Switzerland AG 2019.</p> +
<p>Several papers have been published where non-linear machine learning algorithms, e.g. artificial neural networks, support vector machines and decision trees, have been used to model the specificity of the HIV-1 protease and extract specificity rules. We show that the dataset used in these studies is linearly separable and that it is a misuse of nonlinear classifiers to apply them to this problem. The best solution on this dataset is achieved using a linear classifier like the simple perceptron or the linear support vector machine, and it is straightforward to extract rules from these linear models. We identify key residues in peptides that are efficiently cleaved by the HIV-1 protease and list the most prominent rules, relating them to experimental results for the HIV-1 protease. Motivation: Understanding HIV-1 protease specificity is important when designing HIV inhibitors and several different machine learning algorithms have been applied to the problem. However, little progress has been made in understanding the specificity because nonlinear and overly complex models have been used. Results: We show that the problem is much easier than what has previously been reported and that linear classifiers like the simple perceptron or linear support vector machines are at least as good predictors as nonlinear algorithms. We also show how sets of specificity rules can be generated from the resulting linear classifiers.</p> +
<p>An approach is presented and experimentally demonstrated where consensus among distributed self-organized agents is used for intelligent monitoring of mobile cyberphysical systems (in this case vehicles). The demonstration is done on test data from a 30 month long field test with a city bus fleet under real operating conditions. The self-organized models operate on-board the systems, like embedded agents, communicate their states over a wireless communication link, and their states are compared off-line to find systems that deviate from the consensus. In this way is the group (the fleet) of systems used to detect errors that actually occur. This can be used to build up a knowledge base that can be accumulated over the life-time of the systems.</p> +
