No description available.

Parkinson's disease (PD) is the second most common neurodegenerative disorder (after Alzheimer's disease) and directly affects upto 5 million people worldwide. The stages (Hoehn and Yaar) of disease has been predicted by many methods which will be helpful for the doctors to give the dosage according to it. So these methods were brought up based on the data set which includes about seventy patients at nine clinics in Sweden. The purpose of the work is to analyze unsupervised technique with supervised neural network techniques in order to make sure the collected data sets are reliable to make decisions. The data which is available was preprocessed before calculating the features of it. One of the complex and efficient feature called wavelets has been calculated to present the data set to the network. The dimension of the final feature set has been reduced using principle component analysis. For unsupervised learning k-means gives the closer result around 76% while comparing with supervised techniques. Back propagation and J4 has been used as supervised model to classify the stages of Parkinson's disease where back propagation gives the variance percentage of 76-82%. The results of both these models have been analyzed. This proves that the data which are collected are reliable to predict the disease stages in Parkinson's disease.

The teratogenic drugs cytochalasin B and valproic acid have been shown to alter F-actin polymerization, an effect that is crucial in forming microfilaments. Microfilaments form important cytoskeletal structures that maintain the structural integrity of the cell, cause cell motility and cell migration. Microfilament alterations are known to cause neural tube defects such as spina bifida and anencephaly (Walmod et al., 1999). We here aim to show that disruption of microfilaments by cytochalasin B and valproic acid affects the tensile properties of the tissue. Biomechanics is an interdisciplinary field that allows mechanical concepts to help us understand embryo development. This project used a novel tissue stretching device that measures the tensile properties of neural and epidermal tissue. The instrument used a pair of cantilevered wires to which the specimen was glued. This device stretched the mid-neural and -lateral tissue anterior-posterior (AP) and medio-lateral (ML) unidirectionally. The tensile properties of the tissue were determined by Resultant Young’s Modulus that depends on the true stress and true strain in the tissue sample. The experiment was conducted at a strain rate of 50%. Axolotl embryos were treated with 5ug/mL and 2.5ug/mL cytochalasin B and 5mM valproic acid at stage 13 (early neurula) for an hour, washed, and allowed to develop to stage 15 before it was used in the uniaxial tissue stretcher. Changes in the F-actin filaments were analysed by phalloidin staining and viewed under a confocal microscope. The tests show that disruption of microfilaments by cytochalasin B increases the stiffness of the dorsal-tissue by as much as 101% for CB-treated tissues stretched in the AP direction and 298% when stretched in the ML direction. VA-treated neural plate tissue showed a stiffness increase of 278% when stretched in the AP direction and 319%, when stretched in the ML direction. Changes in the F-actin filaments are quantified by phalloidin staining viewed with confocal microscopy. These findings indicate that direction-dependent mechanical forces in the tissue are contributing factors in closure of the neural tube in axolotl embryos.

One of the most well-respected and widely used tools in the study of general intelligence is the Raven's Progressive Matrices test, a nonverbal task wherein subjects must induce the rules that govern the patterns in an arrangement of shapes and figures. This thesis describes the first neurally based, biologically plausible model that can dynamically generate the rules needed to solve Raven's matrices. We demonstrate the success and generality of the rules generated by the model, as well as interesting insights the model provides into the causes of individual differences, at both a low (neural capacity) and high (subject strategy) level. Throughout this discussion we place our research within the broader context of intelligence research, seeking to understand how the investigation and modelling of Raven's Progressive Matrices can contribute to our understanding of general intelligence.

Deep generative neural networks such as the Deep Belief Network and Deep Boltzmann Machines have been used successfully to model high dimensional visual data. However, they are not robust to common variations such as occlusion and random noise. In this thesis, we explore two strategies for improving the robustness of DBNs. First, we show that a DBN with sparse connections in the first layer is more robust to variations that are not in the training set. Second, we develop a probabilistic denoising algorithm to determine a subset of the hidden layer nodes to unclamp. We show that this can be applied to any feedforward network classifier with localized first layer connections. By utilizing the already available generative model for denoising prior to recognition, we show significantly better performance over the standard DBN implementations for various sources of noise on the standard and Variations MNIST databases.

Because of the highly complex structure of the load-sensing pump, its compensators and controlling elements, simulation of load-sensing pump system pose many challenges to researchers. One way to overcome some of the difficulties with creating complex computer model is the use of black box approach to create an approximation of the system behaviour by analyzing input/output relationships. That means the details of the physical phenomena are not so much of concern in the black box approach. Neural network can be used to implement the black box concept for system identification and it is proven that the neural network have the ability to model very complex behaviour and there is a well defined set of neural and neural network structures. Previous studies have shown the problems and limitations in dynamic system modeling using static neuron based neural networks. Some new neuron structures, Dynamic Neural Units (DNUs), have been developed which open a new area to the research associated with the system modelling.<p>The overall objective of this research was to investigate the feasibility of using a dynamic neural unit (DNU) based dynamic neural network (DNN) in modeling a hydraulic component (specifically a load-sensing pump), and the model could be used in a simulation with any other required component model to aid in hydraulic system design. To be truly representative of the component, the neural network model must be valid for both the steady state and the transient response. Due to three components (compensator, pump and control valve) in a load sensing pump system, there were three different pump model structures (the pump, compensator and valve model, the compensator and pump model, and the pump only model) from the practical point of view, and they were analysed thoroughly in this study. In this study, the DNU based DNN was used to model a pump only model which was a portion of a complete load sensing pump. After the trained DNN was tested with a wide variety of system inputs and due to the steady state error illustrated by the trained DNN, compensation equation approach and DNN and SNN combination approach were then adopted to overcome the steady state deviation. <p>It was verified, through this work, that the DNU based DNN can capture the dynamics of a nonlinear system, and the DNN and SNN combination can eliminate the steady state error which was generated by the trained DNN. <p>The first major contribution of this research was in investigating the feasibility of using the DNN to model a nonlinear system and eliminating the error accumulation problem encountered in the previous work. The second major contribution is exploring the combination of DNN and SNN to make the neural network model valid for both steady state and the transient response.

This dissertation presents a new type of fuel control algorithm for gaseous fuelled vehicles. Gaseous fuels such as hydrogen and natural gas have been shown to be less polluting than liquid fuels such as gasoline, both at the tailpipe and on a total cycle basis. Unfortunately, it can be expensive to convert vehicles to gaseous fuels, partially due to small production runs for these vehicles. One of major development costs for a new vehicle is the development and calibration of the fuel controller. The research presented here includes a fuel controller which does not require an expensive calibration phase.<p>The controller is based upon a two-part model, separating steady state and dynamic effects. This model is then used to estimate the optimum fuelling for the measured operating condition. The steady state model is calculated using an artificial neural network with an online learning scheme, allowing the model to continually update to improve the controller's performance. This is important during both the initial learning of the characteristics of a new engine, as well as tracking changes due to wear or damage.<p>The dynamic model of the system is concerned with the significant transport delay between the time the fuel is injected and when the exhaust gas oxygen sensor makes the reading. One significant result of this research is the realization that a previous commonly used model for this delay has become significantly less accurate due to the shift from carburettors or central point injection to port injection.<p>In addition to a description of the control scheme used, this dissertation includes a new method of algebraically inverting a neural network, avoiding computationally expensive iterative methods of optimizing the model. This can greatly speed up the control loop (or allow for less expensive, slower hardware).<p>An important feature of a fuel control scheme is that it produces a small, stable limit cycle between rich and lean fuel-air mixtures. This dissertation expands the currently available models for the limit cycle characteristics of a system with a linear controller as well as developing a similar model for the neural network controller by linearizing the learning scheme.<p>One of the most important aspects of this research is an experimental test, in which the controller was installed on a truck fuelled by natural gas. The tailpipe emissions of the truck with the new controller showed better results than the OEM controller on both carbon monoxide and nitrogen oxides, and the controller required no calibration and very little information about the properties of the engine.<p>The significant original contributions resulting from this research include:<br> -collection and summarization of previous work,<br> -development of a method of automatically determining the pure time delay between the fuel injection event and the feedback measurement,<br> -development of a more accurate model for the variability of the transport delay in modern port injection engines,<br> -developing a fuel-air controller requiring minimal knowledge of the engine's parameters,<br> -development of a method of algebraically inverting a neural network which is much faster than previous iterative methods,<br> -demonstrating how to initialize the neural model by taking advantage of some important characteristics of the system,<br> -expansion of the models available for the limit cycle produced by a system with a binary sensor and delay to include integral controllers with asymmetrical gains,<br> -development of a limit cycle model for the new neural controller, and<br> -experimental verification of the controller's tailpipe emissions performance, which compares favourably to the OEM controller.

Application of recently developed neural network based adaptive output feedback controllers to a diverse range of problems both in simulations and experiments is investigated in this thesis. The purpose is to evaluate the theory behind the development of these controllers numerically and experimentally, identify the needs for further development in practical applications, and to conduct further research in directions that are identified to ultimately enhance applicability of adaptive controllers to real world problems. We mainly focus our attention on adaptive controllers that augment existing fixed gain controllers. A recently developed approach holds great potential for successful implementations on real world applications due to its applicability to systems with minimal information concerning the plant model and the existing controller. In this thesis the formulation is extended to the multi-input multi-output case for distributed control of interconnected systems and successfully tested on a formation flight wind tunnel experiment. The command hedging method is formulated for the approach to further broaden the class of systems it can address by including systems with input nonlinearities. Also a formulation is adopted that allows the approach to be applied to non-minimum phase systems for which non-minimum phase characteristics are modeled with sufficient accuracy and treated properly in the design of the existing controller. It is shown that the approach can also be applied to augment nonlinear controllers under certain conditions and an example is presented where the nonlinear guidance law of a spinning projectile is augmented. Simulation results on a high fidelity 6 degrees-of-freedom nonlinear simulation code are presented. The thesis also presents a preliminary adaptive controller design for closed loop flight control with active flow actuators. Behavior of such actuators in dynamic flight conditions is not known. To test the adaptive controller design in simulation, a fictitious actuator model is developed that fits experimentally observed characteristics of flow control actuators in static flight conditions as well as possible coupling effects between actuation, the dynamics of flow field, and the rigid body dynamics of the vehicle.

Currently, sleep staging is accomplished is by clinical polysomnography (PSG). By extracting features from different combinations of electroencephalogram (EEG), electrooculogram (EOG) and electromyogram (EMG) signals, this study uses neural network to perform sleep staging. A whole night and complete sleep stage contains wake stage, rapid eye movement (REM) stage, stage 1, stage 2, and slow wave sleep (SWS) stage. This project focuses on the classification of wake stage and light-sleep (stage 1 and 2). These three stages are classified by a two-step process. At first, wake stage and light-sleep are divided into two parts. Second, light sleep is divided into stage 1 and stage 2. For a fixed number of channels, this work identifies the best combination of signal channels. In addition, by simultaneously considering the Neighboring epochs Rule classifier, this work also introduces an empirical rule to improve the classification accuracy. Among the tested databases which contain two Medicine center and sixteen sets of different signal channels, the best results are obtained from the group of patients with the low average RDI value. They include the group that has a mean 15% SWS and the group that uses CPAP. As a whole, the combinative features of four channels are better results of classification. For our best results, the sensitivity and PPV of wake and stage 2 varies from 85%~88%, and those of stage 1 are respective 44.84% and 53.61%. And the total classification of sleep staging is 84.59%. Apparently, the research has satisfactory results on sleep staging. Keywords: Sleep Medicine, Sleep stage, Neural Networks

In this thesis, a chorus detection and an emotion detection algorithm for popular music are proposed. First, a popular music is decomposed into chorus and verse segments based on its color representation and MFCCs (Mel-frequency cepstral coefficients). Four features including intensity, tempo and rhythm regularity are extracted from these structured segments for emotion detection. The emotion of a song is classified into four classes of emotions: happy, angry, depressed and relaxed via two classification methods. One is back-propagation neural network classifier and the other is Adaboost classifier. A test database consisting of 350 popular music songs is utilized in our experiment. Experimental results show that the average recall and precision of the proposed chorus detection are approximated to 95% and 84%, respectively; the average precision rate of emotion detection is 86% for neural network classifier and 92% for Adaboost classifier. The emotions of a song with different cover versions are also detected in our experiment. The precision rate is 92%.