No description available.

none

Circuit breaker is an important interrupting device in power system network. It usually has a lifetime about 20 to 40 years. During breaker's service time, maintenance and inspection are imperative duties to achieve its reliable operation. To automate the diagnostic practice for circuit breaker operation and reduce the utility company's workload, Wavelet based analysis software of circuit breaker operation is developed here. Combined with circuit breaker monitoring system, the analysis software processes the original circuit breaker information, speeds up the analysis time and provides stable and consistent evaluation for the circuit breaker operation.

High-throughput technologies for rapid measurement of vast numbers of biolog- ical variables offer the potential for highly discriminatory diagnosis and prognosis; however, high dimensionality together with small samples creates the need for fea- ture selection, while at the same time making feature-selection algorithms less reliable. Feature selection is required to avoid overfitting, and the combinatorial nature of the problem demands a suboptimal feature-selection algorithm. In this dissertation, we have found that feature selection is problematic in small- sample settings via three different approaches. First we examined the feature-ranking performance of several kinds of error estimators for different classification rules, by considering all feature subsets and using 2 measures of performance. The results show that their ranking is strongly affected by inaccurate error estimation. Secondly, since enumerating all feature subsets is computationally impossible in practice, a suboptimal feature-selection algorithm is often employed to find from a large set of potential features a small subset with which to classify the samples. If error estimation is required for a feature-selection algorithm, then the impact of error estimation can be greater than the choice of algorithm. Lastly, we took a regression approach by comparing the classification errors for the optimal feature sets and the errors for the feature sets found by feature-selection algorithms. Our study shows that it is unlikely that feature selection will yield a feature set whose error is close to that of the optimal feature set, and the inability to find a good feature set should not lead to the conclusion that good feature sets do not exist.

An experimental approach to traffic flow analysis is presented in which methodology from pattern recognition is applied to a specific dataset to examine its utility in determining traffic patterns. The selected dataset for this work, taken from a 1985 study by JHK and Associates (traffic research) for the Federal Highway Administration, covers an hour long time period over a quarter mile section and includes nine different identifying features for traffic at any given time. The initial step is to select the most pertinent of these features as a target for extraction and local storage during the experiment. The tools created for this approach, a two-level hierarchical group of operators, are used to extract features from the dataset to create a feature space; this is done to minimize the experimental set to a matrix of desirable attributes from the vehicles on the roadway. The application is to identify if this data can be readily parsed into four distinct traffic states; in this case, the state of a vehicle is defined by its velocity and acceleration at a selected timestamp. A three-dimensional plot is used, with color as the third dimension and seen from a top-down perspective, to initially identify vehicle states in a section of roadway over a selected section of time. This is followed by applying k-means clustering, in this case with k=4 to match the four distinct traffic states, to the feature space to examine its viability in determining the states of vehicles in a time section. The method's accuracy is viewed through silhouette plots. Finally, a group of experiments run through a decision-tree architecture is compared to the kmeans clustering approach. Each decision-tree format uses sets of predefined values for velocity and acceleration to parse the data into the four states; modifications are made to acceleration and deceleration values to examine different results. The three-dimensional plots provide a visual example of congested traffic for use in performing visual comparisons of the clustering results. The silhouette plot results of the k-means experiments show inaccuracy for certain clusters; on the other hand, the decision-tree work shows promise for future work.

The protein fold recognition problem is one of the important topics in biophysics. It is believed that the primary structure of a protein is helpful to drawing its three-dimensional (3D) structure. Given a target protein (a sequence of amino acids), the protein fold recognition problem is to decide which fold group of some protein structure database the target protein belongs to. Since more than two fold groups are to be located in this problem, it is a multi-class classification problem. Recently, many researchers have solved this problem by using the popular machine learning tools, such as neural networks (NN) and support vector machines (SVM). In this thesis, we use the SVM tool to solve this problem. Our strategy is to find out the effective features which can be used as an efficient guide to the classification problem. We build the feature preference table to help us to find out effective feature combinations quickly. We take 27 well-known fold groups in SCOP (Structural Classification of Proteins) as our data set. Our experimental results show that our method achieves the overall prediction accuracy of 61.4%, which is better than the previous method (56.5%). With the same feature combinations, our prediction accuracy is also higher than the previous results. These results show that our method is indeed effective for the fold recognition problem.

In the traditional login systems, we use the username and the password to identify the legalities of users. It is a simple and convenient way to identify, but passwords could be stolen or copied by someone who tries to invade the system illegally. Adding one protective mechanism to identify users, the way of biometrics are brought out, such as keystroke dynamics, fingerprints, DNA, retinas and so on that are unique characteristics of each individuals, it could be more effective in preventing trespassing. This thesis uses keystroke biometrics as research aspects of user authentication. The advantages of this system are low-cost and high security to identify users using keyboard to calculate the time of keystrokes. In this thesis, we use statistical way to examine the researches and experiments. Chosen length of the username and password are greater than or equal to 9 characters, and learning sample sizes are 20 and adapting the sample adaptation mechanism, the results show that we achieved by False Acceptance Rate of 0.85%, False Rejection Rate of 1.51% and Average False Rate of 1.18%; all reach the high levels of safeties.

In login systems, a user is asked to enter his correct account and password in order to be allowed to enter to the system. The safety of systems is at the risk of leaking out the information, hence, the single mechanism of identity verification has not filled the bill at present. We study the personal typing behavior to get one¡¦s own specific features. In our thesis , we compare three methods and anlysis the advantages and shortcomings of those three. First one is to sort the twenty study data, and distribute the weights into the proper region. If the total weights is less than the threshold then this test data will be accepted, otherwise, it will be rejected. The second and third method are similar. Both of them are trying to rescale the data. The spirit of them is that the typing rate of a person will be faster when they type frequently and will be sloer when they are out of practice. However the relative positions of those keys, the lengths of ons¡¦s fingers, and the time that people making pauses in reading unpunctuated are unique. Those factors can be one¡¦s typing rhythm. There are twenty two individuals involved in this experiment. Each one choose his own proficient account and password to type and set up his typing model. The imposters are randomly choose legal user to imitate.

We live in a visually rich environment yet our brains are only equipped to process a small fraction of all available information at any point in time. For successful and efficient perception, the brain relies on attention to differentiate and select specific stimuli for further analysis. Attention can be directed to features – feature based attention – which enhances the processing of other similar features independent of spatial location. I have recently shown that the benefits of feature-based attention not only apply to lower-level features, but also to processes of object perception. The aim of the thesis was to examine the behavioural and electrophysiological correlates underlying the influence of feature-based attention on object perception. Chapter 1 measured the electric field activity associated with attending to higher-level features (object contours) and comparing it with the neural activity while attending to motion stimuli. We found temporally later effects for contours relative to motion, suggesting that feature-based attention to objects might be mediated by higher-tier visual areas, such as the lateral occipital cortex. In Chapter 2, I describe a study designed to investigate the time course of neural activity while cueing attention within the feature dimension of shape that more directly targets higher-tier visual areas. Consistent with Chapter 1, I iii found temporally late modulation, but behavioural effects that were weaker than expected. To account for these findings, I proposed a “wrong-turn” model which explains the perceptual benefits and costs coupled to expecting the correct or incorrect feature by taking into consideration the hierarchical structure of the visual system. Moreover, the model also makes specific predictions about the pattern of behavioural and electrophysiological activity while attending to features of varying complexity during object perception. The aim of Chapter 3 was to test the predictions of the model; I cued attention to colour, a lower-level feature essential to perceiving the object. I found much stronger behavioural cueing effects, and a biphasic pattern (early and late) electric brain activity that confirmed the predictions of the model. Together the results indicate that feature-based attention plays an important role in object perception that is mediated by a flexible perceptual system.

We live in a visually rich environment yet our brains are only equipped to process a small fraction of all available information at any point in time. For successful and efficient perception, the brain relies on attention to differentiate and select specific stimuli for further analysis. Attention can be directed to features – feature based attention – which enhances the processing of other similar features independent of spatial location. I have recently shown that the benefits of feature-based attention not only apply to lower-level features, but also to processes of object perception. The aim of the thesis was to examine the behavioural and electrophysiological correlates underlying the influence of feature-based attention on object perception. Chapter 1 measured the electric field activity associated with attending to higher-level features (object contours) and comparing it with the neural activity while attending to motion stimuli. We found temporally later effects for contours relative to motion, suggesting that feature-based attention to objects might be mediated by higher-tier visual areas, such as the lateral occipital cortex. In Chapter 2, I describe a study designed to investigate the time course of neural activity while cueing attention within the feature dimension of shape that more directly targets higher-tier visual areas. Consistent with Chapter 1, I iii found temporally late modulation, but behavioural effects that were weaker than expected. To account for these findings, I proposed a “wrong-turn” model which explains the perceptual benefits and costs coupled to expecting the correct or incorrect feature by taking into consideration the hierarchical structure of the visual system. Moreover, the model also makes specific predictions about the pattern of behavioural and electrophysiological activity while attending to features of varying complexity during object perception. The aim of Chapter 3 was to test the predictions of the model; I cued attention to colour, a lower-level feature essential to perceiving the object. I found much stronger behavioural cueing effects, and a biphasic pattern (early and late) electric brain activity that confirmed the predictions of the model. Together the results indicate that feature-based attention plays an important role in object perception that is mediated by a flexible perceptual system.