In the present day, the music becomes more popular due to the following three reasons: (1) the evolution of the MP3 compression technology, (2) the growth of the public platform, and (3) the development of the MP3 portable discs. Most people follow the music to hum or follow the rhythm to tap sometimes. The meanings of a music style may be various if it is explained or felt by different people. Therefore we cannot obtain a very explicit answer if the notation of the music cannot be exactly made. We need some techniques and methods to analyze the music, and obtain some of its embedded information. Tempo and beats are very important elements in the perceptual music. Therefore, tempo estimation and beat tracking are fundamental techniques in automatic audio processing, which are crucial to multimedia applications. In this thesis, we first develop an artificial neural network to classify the music excerpts into the evaluation preference. And then, with the preference classification, we can obtain accurate estimation for tempo and beats, by either Ellis's method or Dixon's method. We test our method with a mixed data set which contains ten music genres extracted from the "ballroom dancer" database. Our experimental results show that the accuracy of our method is higher than that of only one individual Ellis's method or Dixon's method.

This thesis implemented a field programmable gate array (FPGA)-based face detector using a neural network (NN), as well as a bit-width reduced floating-point unit (FPU). An NN was used to easily separate face data and non-face data in the face detector. The NN performs time consuming repetitive calculation. This time consuming problem was solved by a Field Programmable Gate Array (FPGA) device and a bit-width reduced FPU in this thesis. A floating-point bit-width reduction provided a significant saving of hardware resources, such as area and power.<p>The analytical error model, using the maximum relative representation error (MRRE) and the average relative representation error (ARRE), was developed to obtain the maximum and average output errors for the bit-width reduced FPUs. After the development of the analytical error model, the bit-width reduced FPUs and an NN were designed using MATLAB and VHDL. Finally, the analytical (MATLAB) results, along with the experimental (VHDL) results, were compared. The analytical results and the experimental results showed conformity of shape. It was also found that while maintaining 94.1% detection accuracy, a reduction in bit-width from 32 bits to 16 bits reduced the size of memory and arithmetic units by 50%, and the total power consumption by 14.7%.

Composite materials are widely used in the aerospace industry because of their high strength-to-weight ratio. Although they have many advantages, their inhomogeneity and anisotropy pose problems. Because of these properties, machining of composites, unlike conventional metal working, needs more investigation. Conventional drilling of composites is one such field that requires extensive study and research. Among various parameters that determine the quality of a drilled hole, surface finish is of vital importance. The surface finish of a drilled hole depends on speed, feed-rate, material of the work piece, and geometry of the drill bit. This project studied the effect of speed and feed on surface finish and also the optimization of these parameters. Experiments were conducted based on Design of Experiment (DOE) and qualitative verification using Artificial Neural Network (ANN). Relevant behavior of surface finish was also studied. In this project, holes were drilled using a conventional twist drill at different cutting speeds (2,000 to 5,000 rpm) and feed rate was varied from 0.001 to 0.01 ipr for solid carbon fiber laminate (composite material). The other material drilled is BMS 8-276 form 3 (toughened resin system). Also five different drill bits were used to conduct experiments on BMS 8-276 form 3. Speed values were 5,000, 3,000, and 2,000 rpm and feed rates were 0.004, 0.006, and 0.01 ipr. The effect of speed, feed rate, and different drill geometries was analyzed with respect to surface finish in the drilled composites. / Thesis (M.S.)--Wichita State University, College of Engineering, Dept. of Mechanical Engineering. / "July 2006." / Includes bibliographic references (leaves 79-81).

<p>An on-line identifier using Functional Link Network (FLN) and Pole-shift (PS) controller for power system stabilizer (PSS) application are presented in this thesis. To have the satisfactory performance of the PSS controller, over a wide range of operating conditions, it is desirable to adapt PSS parameters in real time. Artificial Neural Networks (ANNs) transform the inputs in a low-dimensional space to high-dimensional nonlinear hidden unit space and they have the ability to model the nonlinear characteristics of the power system. The ability of ANNs to learn makes them more suitable for use in adaptive control techniques.</p> <p>On-line identification obtains a mathematical model at each sampling period to track the dynamic behavior of the plant. The ANN identifier consisting of a Functional link Network (FLN) is used for identifying the model parameters. A FLN model eliminates the need of hidden layer while retaining the nonlinear mapping capability of the neural network by using enhanced inputs. This network may be conveniently used for function approximation with faster convergence rate and lesser computational load.</p> <p>The most commonly used Pole Assignment (PA) algorithm for adaptive control purposes assign the pole locations to fixed locations within the unit circle in the z-plane. It may not be optimum for different operating conditions. In this thesis, PS type of adaptive control algorithm is used. This algorithm, instead of assigning the closed-loop poles to fixed locations within the unit circle in the z-plane, this algorithm assumes that the pole characteristic polynomial of the closed-loop system has the same form as the pole characteristic of the open-loop system and shifts the open-loop poles radially towards the centre of the unit circle in the z-plane by a shifting factor &alpha; according to some rules. In this control algorithm, no coefficients need to be tuned manually, so manual parameter tuning (which is a drawback in conventional power system stabilizer) is minimized. The PS control algorithm uses the on-line updated ARMA parameters to calculate the new closed-loop poles of the system that are always inside the unit circle in the z-plane.</p> <p>Simulation studies on a single-machine infinite bus and on a multi-machine power system for various operating condition changes, verify the effectiveness of the combined model of FLN identifier and PS control in damping the local and multi-mode oscillations occurring in the system. Simulation studies prove that the APSSs have significant benefits over conventional PSSs: performance improvement and no requirement for parameter tuning.</p>

No description available.

Large marine vessels carry their loads all over the world. It can be a container ship carrying over 10 000 containers filled with foods, textiles and electronics or a bulk freighter carrying 400 000 tons of coal. Vessels usually have a ballast system that pumps water into ballast tanks to stabilize the vessel. The ballast system can be used to change the vessel’s trim and list angles. Trim and list are the ship equivalents of pitch and roll. By changing the trim angle the water resistance can be reduced and thus also the fuel consumption. Since the vessel is consuming a couple of hundred tons of fuel per day, a small reduction in fuel consumption can save a considerable amount of money, and it is good for the environment. In this thesis, the ship’s power consumption has been estimated using an artificial neural network, which is a mathematical model based on data. The name refers to certain structural similarities with the neural synapse system in animals. The idea with neural networks has been to create brain-like systems. For applications such as learning to interpret sensor data, artificial neural networks are an effective learning method. The goal is to estimate the ship power using a artificial neural network and then use it to calculate the trim angle, to be able to save fuel. The data used in the artificial neural network come from sensor systems mounted on a container ship sailing between Europe and Asia. The sensor data have been thoroughly preprocessed and this includes for example removing the parts when the ship is docked in harbour, data patching and synchronisation and outlier detection based on a Kalman filter. A physical model of a marine craft including wind, wave, hydrodynamic and hydrostatic effects, has also been introduced to help analyse the performance and behaviour of the artificial neural network. The artificial neural network developed in this thesis could successfully estimate the power consumption of the ship. Based on the developed networks it can be seen that the fuel consumption is reduced by trimming the ship by bow, i.e., the ship is angled so the bow is closer to the water line than the stern. The method introduced here could also be applied on other marine vessels, such as bulk freighters or tank ships.

<p>An on-line identifier using Functional Link Network (FLN) and Pole-shift (PS) controller for power system stabilizer (PSS) application are presented in this thesis. To have the satisfactory performance of the PSS controller, over a wide range of operating conditions, it is desirable to adapt PSS parameters in real time. Artificial Neural Networks (ANNs) transform the inputs in a low-dimensional space to high-dimensional nonlinear hidden unit space and they have the ability to model the nonlinear characteristics of the power system. The ability of ANNs to learn makes them more suitable for use in adaptive control techniques.</p> <p>On-line identification obtains a mathematical model at each sampling period to track the dynamic behavior of the plant. The ANN identifier consisting of a Functional link Network (FLN) is used for identifying the model parameters. A FLN model eliminates the need of hidden layer while retaining the nonlinear mapping capability of the neural network by using enhanced inputs. This network may be conveniently used for function approximation with faster convergence rate and lesser computational load.</p> <p>The most commonly used Pole Assignment (PA) algorithm for adaptive control purposes assign the pole locations to fixed locations within the unit circle in the z-plane. It may not be optimum for different operating conditions. In this thesis, PS type of adaptive control algorithm is used. This algorithm, instead of assigning the closed-loop poles to fixed locations within the unit circle in the z-plane, this algorithm assumes that the pole characteristic polynomial of the closed-loop system has the same form as the pole characteristic of the open-loop system and shifts the open-loop poles radially towards the centre of the unit circle in the z-plane by a shifting factor &alpha; according to some rules. In this control algorithm, no coefficients need to be tuned manually, so manual parameter tuning (which is a drawback in conventional power system stabilizer) is minimized. The PS control algorithm uses the on-line updated ARMA parameters to calculate the new closed-loop poles of the system that are always inside the unit circle in the z-plane.</p> <p>Simulation studies on a single-machine infinite bus and on a multi-machine power system for various operating condition changes, verify the effectiveness of the combined model of FLN identifier and PS control in damping the local and multi-mode oscillations occurring in the system. Simulation studies prove that the APSSs have significant benefits over conventional PSSs: performance improvement and no requirement for parameter tuning.</p>

This thesis presents a fuzzy logic controller aimed at maintaining constant tension between two adjacent stands in tandem rolling mills. The fuzzy tension controller monitors tension variation by resorting to electric current comparison of different operation modes and sets the reference for speed controller of the upstream stand. Based on modeling the rolling stand as a single input single output linear discrete system, which works in the normal mode and is subject to internal and external noise, the element settings and parameter selections in the design of the fuzzy controller are discussed. To improve the performance of the fuzzy controller, a dynamic fuzzy controller is proposed. By switching the fuzzy controller elements in relation to the step response, both transient and stationary performances are enhanced. To endow the fuzzy controller with intelligence of generalization, flexibility and adaptivity, self-learning techniques are introduced to obtain fuzzy controller parameters. With the inclusion of supervision and concern for conventional control criteria, the parameters of the fuzzy inference system are tuned by a backward propagation algorithm or their optimal values are located by means of a genetic algorithm. In simulations, the neuro-fuzzy tension controller exhibits the real-time applicability, while the genetic fuzzy tension controller reveals an outstanding global optimization ability.

This thesis implemented a field programmable gate array (FPGA)-based face detector using a neural network (NN), as well as a bit-width reduced floating-point unit (FPU). An NN was used to easily separate face data and non-face data in the face detector. The NN performs time consuming repetitive calculation. This time consuming problem was solved by a Field Programmable Gate Array (FPGA) device and a bit-width reduced FPU in this thesis. A floating-point bit-width reduction provided a significant saving of hardware resources, such as area and power.<p>The analytical error model, using the maximum relative representation error (MRRE) and the average relative representation error (ARRE), was developed to obtain the maximum and average output errors for the bit-width reduced FPUs. After the development of the analytical error model, the bit-width reduced FPUs and an NN were designed using MATLAB and VHDL. Finally, the analytical (MATLAB) results, along with the experimental (VHDL) results, were compared. The analytical results and the experimental results showed conformity of shape. It was also found that while maintaining 94.1% detection accuracy, a reduction in bit-width from 32 bits to 16 bits reduced the size of memory and arithmetic units by 50%, and the total power consumption by 14.7%.

Die Modellierung natürlicher Neuronenpopulationen stellt den Versuch dar, komplizierte Wechselwirkungen und Ereignisabhängigkeiten in biologischen Systemen quantitativ erfassen zu wollen. Widersprüchlich erscheint dabei die Tatsache, daß ein einzelnes Neuron in einer Population ohne Signifikanz ist, daß sich die gesamte Population aber aus einer Vielzahl derartiger Neuronen zusammensetzt und eine, technischen Systemen überlegene funktionelle Vielfalt besitzt /ZUR 92/, /HOL 93/. Ergo setzt sich die Gesamtleistung eines Systems nicht aus der Summe der Leistungen seiner Komponenten "summarisch" zusammen, sondern resultiert vielmehr aus deren Wechselwirkungen. Technisch interessant erscheinen an dieser Stelle mindestens zwei Fragen: * Welcher Mechanismus begründet den genannten Widerspruch in Neuronenpopulationen? * Welche technische Anleihe bietet dieser Mechanismus? Die Modellierung einer Neuronenpopulation kann auf zweierlei Art und Weise erfolgen. Entweder durch die Aufklärung der Neuronenpopulation "von innen heraus", d.h. durch Beobachtung und mathematische Formulierung physiologischer Abläufe oder durch vergleichende Betrachtungen mit "konvergenten" Modellen, d.h. durch die Schaffung von Modellen mit vergleichbaren Phänomenen. Die nachfolgenden Ausführungen favorisieren die letztgenannte Vorgehensweise. Phänomene sind die ereignisabhängigen Schwellwertentwicklungen der Neuronen in Wechselwirkung mit den umgebenden Neuronen sowie die ereignisabhängigen Entwicklungen der synaptischen Verbindungsstärken zwischen den Neuronen, bezeichnet als "Leitwertentwicklung". Technische Anwendungen dieser Simulationsergebnisse werden erörtert, zum Beispiel die Nachbildung der Durchdringung diffusionsfähiger Medien mit Schadstoffen und die Objektvereinzelung.