Sensor-based Control of Chewing and Rumination Behavior of Dairy Cows

The measurement of feed intake, feeding time and rumination time, summarized by the term feeding behavior, are helpful indicators for early recognition of animals which show deviations in their behavior. The overall objective of this work was the development of an early warning system for inadequate feeding rations and digestive and metabolic disorders, which prevention constitutes the basis for health, performance, and reproduction. In a literature review, the current state of the art and the suitability of different measurement tools to determine feeding behavior of ruminants was discussed. Five measurement methods based on different methodological approaches (visual observance, pressure transducer, electrical switches, electrical deformation sensors and acoustic biotelemetry), and three selected measurement techniques (the IGER Behavior Recorder, the Hi-Tag rumination monitoring system and RumiWatchSystem) were described, assessed and compared to each other within this review. In the second study, the new system for measuring feeding behavior of dairy cows was evaluated. The measurement of feeding behavior ensues through electromyography (EMG). For validation, the feeding behavior of 14 cows was determined by both the EMG system and by visual observation. The high correlation coefficients indicate that the current system is a reliable and suitable tool for monitoring the feeding behavior of dairy cows. The aim of a further study was to compare the DairyCheck (DC) system and two additional measurement systems for measuring rumination behavior in relation to efficiency, reliability and reproducibility, with respect to each other. The two additional systems were labeled as the Lely Qwes HR (HR) sensor, and the RumiWatchSystem (RW). Results of accordance of RW and DC to each other were high. The last study examined whether rumination time (RT) is affected by the onset of calving and if it might be a useful indicator for the prediction of imminent birth. Data analysis referred to the final 72h before the onset of calving, which were divided into twelve 6h-blocks. The results showed that RT was significantly reduced in the final 6h before imminent birth.

Optimization of the Mechanical and Optical Properties of Tunable Optical Sensor Arrays (TOSA) for a Nanospectrometer in the Visible and Near Infrared Spectral Range

Tunable Optical Sensor Arrays (TOSA) based on Fabry-Pérot (FP) filters, for high quality spectroscopic applications in the visible and near infrared spectral range are investigated within this work. The optical performance of the FP filters is improved by using ion beam sputtered niobium pentoxide (Nb2O5) and silicon dioxide (SiO2) Distributed Bragg Reflectors (DBRs) as mirrors. Due to their high refractive index contrast, only a few alternating pairs of Nb2O5 and SiO2 films can achieve DBRs with high reflectivity in a wide spectral range, while ion beam sputter deposition (IBSD) is utilized due to its ability to produce films with high optical purity. However, IBSD films are highly stressed; resulting in stress induced mirror curvature and suspension bending in the free standing filter suspensions of the MEMS (Micro-Electro-Mechanical Systems) FP filters. Stress induced mirror curvature results in filter transmission line degradation, while suspension bending results in high required filter tuning voltages. Moreover, stress induced suspension bending results in higher order mode filter operation which in turn degrades the optical resolution of the filter. Therefore, the deposition process is optimized to achieve both near zero absorption and low residual stress. High energy ion bombardment during film deposition is utilized to reduce the film density, and hence the film compressive stress. Utilizing this technique, the compressive stress of Nb2O5 is reduced by ~43%, while that for SiO2 is reduced by ~40%. Filters fabricated with stress reduced films show curvatures as low as 100 nm for 70 μm mirrors. To reduce the stress induced bending in the free standing filter suspensions, a stress optimized multi-layer suspension design is presented; with a tensile stressed metal sandwiched between two compressively stressed films. The stress in Physical Vapor Deposited (PVD) metals is therefore characterized for use as filter top-electrode and stress compensating layer. Surface micromachining is used to fabricate tunable FP filters in the visible spectral range using the above mentioned design. The upward bending of the suspensions is reduced from several micrometers to less than 100 nm and 250 nm for two different suspension layer combinations. Mechanical tuning of up to 188 nm is obtained by applying 40 V of actuation voltage. Alternatively, a filter line with transmission of 65.5%, Full Width at Half Maximum (FWHM) of 10.5 nm and a stopband of 170 nm (at an output wavelength of 594 nm) is achieved. Numerical model simulations are also performed to study the validity of the stress optimized suspension design for the near infrared spectral range, wherein membrane displacement and suspension deformation due to material residual stress is studied. Two bandpass filter designs based on quarter-wave and non-quarter-wave layers are presented as integral components of the TOSA. With a filter passband of 135 nm and a broad stopband of over 650 nm, high average filter transmission of 88% is achieved inside the passband, while maximum filter transmission of less than 1.6% outside the passband is achieved.

Interferometrisch messender faseroptischer Sensor mit mechanisch oszillierender Sonde

Punktförmig messende optische Sensoren zum Erfassen von Oberflächentopografien im Nanometerbereich werden in der Forschung und Industrie benötigt. Dennoch ist die Auswahl unterschiedlicher Technologien und kommerziell verfügbarer Sensoren gering. In dieser Dissertationsschrift werden die wesentlichen Aspekte eines Messsystems untersucht das über das Potenzial verfügt, zu den künftigen Standardmessmethoden zu gehören. Das Messprinzip beruht auf einem Common-Path-Interferometer. In einer mikrooptischen Sonde wird das Laserlicht auf die zu untersuchende Oberfläche gerichtet. Das vom Messobjekt reflektierte Licht interferiert sondenintern mit einem Referenzreflex. Die kompakte Bauweise bewirkt kurze optische Wege und eine gewisse Robustheit gegen Störeinflüsse. Die Abstandsinformation wird durch eine mechanische Oszillation in eine Phasenmodulation überführt. Die Phasenmodulation ermöglicht eine robuste Auswertung des Interferenzsignals, auch wenn eine zusätzliche Amplitudenmodulation vorhanden ist. Dies bietet den Vorteil, unterschiedlich geartete Oberflächen messen zu können, z. B. raue, teilweise transparente und geneigte Oberflächen. Es können wiederholbar Messungen mit einer Standardabweichung unter einem Nanometer erzielt werden. Die beschriebene mechanische Oszillation wird durch ein periodisches elektrisches Signal an einem piezoelektrischen Aktor hervorgerufen, der in einem Biegebalken integriert ist. Die Bauform des Balkens gestattet eine Hybridisierung von optischen und mechanischen Komponenten zu einer Einheit, welche den Weg zur weiteren Miniaturisierung aufzeigt. Im Rahmen dieser Arbeit konnte so u. a. eine Sonde mit einer Bauhöhe unter 10 mm gefertigt werden. Durch eine zweite optische Wellenlänge lässt sich der eingeschränkte Eindeutigkeitsbereich des Laserinterferometers nachweislich vergrößern. Die hierfür eingesetzte Methode, die Stand der Technik ist, konnte erfolgreich problemspezifisch angepasst werden. Um das volle Potenzial des Sensors nutzen zu können, wurden zudem zahlreiche Algorithmen entworfen und erfolgreich getestet. Anhand von hier dokumentierten Messergebnissen können die Möglichkeiten, als auch die Schwächen des Messsystems abgeschätzt werden.

Optimierung von Betriebsstrategien für elektrifizierte Antriebskonzepte

Im Rahmen dieser Arbeit wird eine gemeinsame Optimierung der Hybrid-Betriebsstrategie und des Verhaltens des Verbrennungsmotors vorgestellt. Die Übernahme von den im Steuergerät verwendeten Funktionsmodulen in die Simulationsumgebung für Fahrzeuglängsdynamik stellt eine effiziente Applikationsmöglichkeit der Originalparametrierung dar. Gleichzeitig ist es notwendig, das Verhalten des Verbrennungsmotors derart nachzubilden, dass das stationäre und das dynamische Verhalten, inklusive aller relevanten Einflussmöglichkeiten, wiedergegeben werden kann. Das entwickelte Werkzeug zur Übertragung der in Ascet definierten Steurgerätefunktionen in die Simulink-Simulationsumgebung ermöglicht nicht nur die Simulation der relevanten Funktionsmodule, sondern es erfüllt auch weitere wichtige Eigenschaften. Eine erhöhte Flexibilität bezüglich der Daten- und Funktionsstandänderungen, sowie die Parametrierbarkeit der Funktionsmodule sind Verbesserungen die an dieser Stelle zu nennen sind. Bei der Modellierung des stationären Systemverhaltens des Verbrennungsmotors erfolgt der Einsatz von künstlichen neuronalen Netzen. Die Auswahl der optimalen Neuronenanzahl erfolgt durch die Betrachtung des SSE für die Trainings- und die Verifikationsdaten. Falls notwendig, wird zur Sicherstellung der angestrebten Modellqualität, das Interpolationsverhalten durch Hinzunahme von Gauß-Prozess-Modellen verbessert. Mit den Gauß-Prozess-Modellen werden hierbei zusätzliche Stützpunkte erzeugt und mit einer verminderten Priorität in die Modellierung eingebunden. Für die Modellierung des dynamischen Systemverhaltens werden lineare Übertragungsfunktionen verwendet. Bei der Minimierung der Abweichung zwischen dem Modellausgang und den Messergebnissen wird zusätzlich zum SSE das 2σ-Intervall der relativen Fehlerverteilung betrachtet. Die Implementierung der Steuergerätefunktionsmodule und der erstellten Steller-Sensor-Streckenmodelle in der Simulationsumgebung für Fahrzeuglängsdynamik führt zum Anstieg der Simulationszeit und einer Vergrößerung des Parameterraums. Das aus Regelungstechnik bekannte Verfahren der Gütevektoroptimierung trägt entscheidend zu einer systematischen Betrachtung und Optimierung der Zielgrößen bei. Das Ergebnis des Verfahrens ist durch das Optimum der Paretofront der einzelnen Entwurfsspezifikationen gekennzeichnet. Die steigenden Simulationszeiten benachteiligen Minimumsuchverfahren, die eine Vielzahl an Iterationen benötigen. Um die Verwendung einer Zufallsvariablen, die maßgeblich zur Steigerung der Iterationanzahl beiträgt, zu vermeiden und gleichzeitig eine Globalisierung der Suche im Parameterraum zu ermöglichen wird die entwickelte Methode DelaunaySearch eingesetzt. Im Gegensatz zu den bekannten Algorithmen, wie die Partikelschwarmoptimierung oder die evolutionären Algorithmen, setzt die neu entwickelte Methode bei der Suche nach dem Minimum einer Kostenfunktion auf eine systematische Analyse der durchgeführten Simulationsergebnisse. Mit Hilfe der bei der Analyse gewonnenen Informationen werden Bereiche mit den bestmöglichen Voraussetzungen für ein Minimum identifiziert. Somit verzichtet das iterative Verfahren bei der Bestimmung des nächsten Iterationsschrittes auf die Verwendung einer Zufallsvariable. Als Ergebnis der Berechnungen steht ein gut gewählter Startwert für eine lokale Optimierung zur Verfügung. Aufbauend auf der Simulation der Fahrzeuglängsdynamik, der Steuergerätefunktionen und der Steller-Sensor-Streckenmodelle in einer Simulationsumgebung wird die Hybrid-Betriebsstrategie gemeinsam mit der Steuerung des Verbrennungsmotors optimiert. Mit der Entwicklung und Implementierung einer neuen Funktion wird weiterhin die Verbindung zwischen der Betriebsstrategie und der Motorsteuerung erweitert. Die vorgestellten Werkzeuge ermöglichten hierbei nicht nur einen Test der neuen Funktionalitäten, sondern auch eine Abschätzung der Verbesserungspotentiale beim Verbrauch und Abgasemissionen. Insgesamt konnte eine effiziente Testumgebung für eine gemeinsame Optimierung der Betriebsstrategie und des Verbrennungsmotorverhaltens eines Hybridfahrzeugs realisiert werden.

A Vector Signal Processing Approach to Color

Surface (Lambertain) color is a useful visual cue for analyzing material composition of scenes. This thesis adopts a signal processing approach to color vision. It represents color images as fields of 3D vectors, from which we extract region and boundary information. The first problem we face is one of secondary imaging effects that makes image color different from surface color. We demonstrate a simple but effective polarization based technique that corrects for these effects. We then propose a systematic approach of scalarizing color, that allows us to augment classical image processing tools and concepts for multi-dimensional color signals.

Comparing Support Vector Machines with Gaussian Kernels to Radial Basis Function Classifiers

The Support Vector (SV) machine is a novel type of learning machine, based on statistical learning theory, which contains polynomial classifiers, neural networks, and radial basis function (RBF) networks as special cases. In the RBF case, the SV algorithm automatically determines centers, weights and threshold such as to minimize an upper bound on the expected test error. The present study is devoted to an experimental comparison of these machines with a classical approach, where the centers are determined by $k$--means clustering and the weights are found using error backpropagation. We consider three machines, namely a classical RBF machine, an SV machine with Gaussian kernel, and a hybrid system with the centers determined by the SV method and the weights trained by error backpropagation. Our results show that on the US postal service database of handwritten digits, the SV machine achieves the highest test accuracy, followed by the hybrid approach. The SV approach is thus not only theoretically well--founded, but also superior in a practical application.

Vector-Based Integration of Local and Long-Range Information in Visual Cortex

Integration of inputs by cortical neurons provides the basis for the complex information processing performed in the cerebral cortex. Here, we propose a new analytic framework for understanding integration within cortical neuronal receptive fields. Based on the synaptic organization of cortex, we argue that neuronal integration is a systems--level process better studied in terms of local cortical circuitry than at the level of single neurons, and we present a method for constructing self-contained modules which capture (nonlinear) local circuit interactions. In this framework, receptive field elements naturally have dual (rather than the traditional unitary influence since they drive both excitatory and inhibitory cortical neurons. This vector-based analysis, in contrast to scalarsapproaches, greatly simplifies integration by permitting linear summation of inputs from both "classical" and "extraclassical" receptive field regions. We illustrate this by explaining two complex visual cortical phenomena, which are incompatible with scalar notions of neuronal integration.

Improving Multiclass Text Classification with the Support Vector Machine

We compare Naive Bayes and Support Vector Machines on the task of multiclass text classification. Using a variety of approaches to combine the underlying binary classifiers, we find that SVMs substantially outperform Naive Bayes. We present full multiclass results on two well-known text data sets, including the lowest error to date on both data sets. We develop a new indicator of binary performance to show that the SVM's lower multiclass error is a result of its improved binary performance. Furthermore, we demonstrate and explore the surprising result that one-vs-all classification performs favorably compared to other approaches even though it has no error-correcting properties.

Properties of Support Vector Machines

Support Vector Machines (SVMs) perform pattern recognition between two point classes by finding a decision surface determined by certain points of the training set, termed Support Vectors (SV). This surface, which in some feature space of possibly infinite dimension can be regarded as a hyperplane, is obtained from the solution of a problem of quadratic programming that depends on a regularization parameter. In this paper we study some mathematical properties of support vectors and show that the decision surface can be written as the sum of two orthogonal terms, the first depending only on the margin vectors (which are SVs lying on the margin), the second proportional to the regularization parameter. For almost all values of the parameter, this enables us to predict how the decision surface varies for small parameter changes. In the special but important case of feature space of finite dimension m, we also show that there are at most m+1 margin vectors and observe that m+1 SVs are usually sufficient to fully determine the decision surface. For relatively small m this latter result leads to a consistent reduction of the SV number.

Notes on PCA, Regularization, Sparsity and Support Vector Machines

We derive a new representation for a function as a linear combination of local correlation kernels at optimal sparse locations and discuss its relation to PCA, regularization, sparsity principles and Support Vector Machines. We first review previous results for the approximation of a function from discrete data (Girosi, 1998) in the context of Vapnik"s feature space and dual representation (Vapnik, 1995). We apply them to show 1) that a standard regularization functional with a stabilizer defined in terms of the correlation function induces a regression function in the span of the feature space of classical Principal Components and 2) that there exist a dual representations of the regression function in terms of a regularization network with a kernel equal to a generalized correlation function. We then describe the main observation of the paper: the dual representation in terms of the correlation function can be sparsified using the Support Vector Machines (Vapnik, 1982) technique and this operation is equivalent to sparsify a large dictionary of basis functions adapted to the task, using a variation of Basis Pursuit De-Noising (Chen, Donoho and Saunders, 1995; see also related work by Donahue and Geiger, 1994; Olshausen and Field, 1995; Lewicki and Sejnowski, 1998). In addition to extending the close relations between regularization, Support Vector Machines and sparsity, our work also illuminates and formalizes the LFA concept of Penev and Atick (1996). We discuss the relation between our results, which are about regression, and the different problem of pattern classification.

From Regression to Classification in Support Vector Machines

We study the relation between support vector machines (SVMs) for regression (SVMR) and SVM for classification (SVMC). We show that for a given SVMC solution there exists a SVMR solution which is equivalent for a certain choice of the parameters. In particular our result is that for $epsilon$ sufficiently close to one, the optimal hyperplane and threshold for the SVMC problem with regularization parameter C_c are equal to (1-epsilon)^{- 1} times the optimal hyperplane and threshold for SVMR with regularization parameter C_r = (1-epsilon)C_c. A direct consequence of this result is that SVMC can be seen as a special case of SVMR.

On the Noise Model of Support Vector Machine Regression

Support Vector Machines Regression (SVMR) is a regression technique which has been recently introduced by V. Vapnik and his collaborators (Vapnik, 1995; Vapnik, Golowich and Smola, 1996). In SVMR the goodness of fit is measured not by the usual quadratic loss function (the mean square error), but by a different loss function called Vapnik"s $epsilon$- insensitive loss function, which is similar to the "robust" loss functions introduced by Huber (Huber, 1981). The quadratic loss function is well justified under the assumption of Gaussian additive noise. However, the noise model underlying the choice of Vapnik's loss function is less clear. In this paper the use of Vapnik's loss function is shown to be equivalent to a model of additive and Gaussian noise, where the variance and mean of the Gaussian are random variables. The probability distributions for the variance and mean will be stated explicitly. While this work is presented in the framework of SVMR, it can be extended to justify non-quadratic loss functions in any Maximum Likelihood or Maximum A Posteriori approach. It applies not only to Vapnik's loss function, but to a much broader class of loss functions.

A Unified Framework for Regularization Networks and Support Vector Machines

Regularization Networks and Support Vector Machines are techniques for solving certain problems of learning from examples -- in particular the regression problem of approximating a multivariate function from sparse data. We present both formulations in a unified framework, namely in the context of Vapnik's theory of statistical learning which provides a general foundation for the learning problem, combining functional analysis and statistics.

An Equivalence Between Sparse Approximation and Support Vector Machines

In the first part of this paper we show a similarity between the principle of Structural Risk Minimization Principle (SRM) (Vapnik, 1982) and the idea of Sparse Approximation, as defined in (Chen, Donoho and Saunders, 1995) and Olshausen and Field (1996). Then we focus on two specific (approximate) implementations of SRM and Sparse Approximation, which have been used to solve the problem of function approximation. For SRM we consider the Support Vector Machine technique proposed by V. Vapnik and his team at AT&T Bell Labs, and for Sparse Approximation we consider a modification of the Basis Pursuit De-Noising algorithm proposed by Chen, Donoho and Saunders (1995). We show that, under certain conditions, these two techniques are equivalent: they give the same solution and they require the solution of the same quadratic programming problem.

Support Vector Machines: Training and Applications

The Support Vector Machine (SVM) is a new and very promising classification technique developed by Vapnik and his group at AT&T Bell Labs. This new learning algorithm can be seen as an alternative training technique for Polynomial, Radial Basis Function and Multi-Layer Perceptron classifiers. An interesting property of this approach is that it is an approximate implementation of the Structural Risk Minimization (SRM) induction principle. The derivation of Support Vector Machines, its relationship with SRM, and its geometrical insight, are discussed in this paper. Training a SVM is equivalent to solve a quadratic programming problem with linear and box constraints in a number of variables equal to the number of data points. When the number of data points exceeds few thousands the problem is very challenging, because the quadratic form is completely dense, so the memory needed to store the problem grows with the square of the number of data points. Therefore, training problems arising in some real applications with large data sets are impossible to load into memory, and cannot be solved using standard non-linear constrained optimization algorithms. We present a decomposition algorithm that can be used to train SVM's over large data sets. The main idea behind the decomposition is the iterative solution of sub-problems and the evaluation of, and also establish the stopping criteria for the algorithm. We present previous approaches, as well as results and important details of our implementation of the algorithm using a second-order variant of the Reduced Gradient Method as the solver of the sub-problems. As an application of SVM's, we present preliminary results we obtained applying SVM to the problem of detecting frontal human faces in real images.