Feature-based image fusion quality metrics

Image fusion quality metrics have evolved from image processing quality metrics. They measure the quality of fused images by estimating how much localized information has been transferred from the source images into the fused image. However, this technique assumes that it is actually possible to fuse two images into one without any loss. In practice, some features must be sacrificed and relaxed in both source images. Relaxed features might be very important, like edges, gradients and texture elements. The importance of a certain feature is application dependant. This paper presents a new method for image fusion quality assessment. It depends on estimating how much valuable information has not been transferred.

An ensemble of classifiers with genetic algorithmBased Feature Selection

Different data classification algorithms have been developed and applied in various areas to analyze and extract valuable information and patterns from large datasets with noise and missing values. However, none of them could consistently perform well over all datasets. To this end, ensemble methods have been suggested as the promising measures. This paper proposes a novel hybrid algorithm, which is the combination of a multi-objective Genetic Algorithm (GA) and an ensemble classifier. While the ensemble classifier, which consists of a decision tree classifier, an Artificial Neural Network (ANN) classifier, and a Support Vector Machine (SVM) classifier, is used as the classification committee, the multi-objective Genetic Algorithm is employed as the feature selector to facilitate the ensemble classifier to improve the overall sample classification accuracy while also identifying the most important features in the dataset of interest. The proposed GA-Ensemble method is tested on three benchmark datasets, and compared with each individual classifier as well as the methods based on mutual information theory, bagging and boosting. The results suggest that this GA-Ensemble method outperform other algorithms in comparison, and be a useful method for classification and feature selection problems.

Development and application of a microelectrode based scanning voltammetric detector

A large part of the work presented in this thesis describes the development and use of a novel electrochemical detector designed to allow the electrochemical characterisation of compounds in flowing solution by means of cyclic voltammetry. The detector was microprocessor controlled, which provides digital generation of the potential waveform and collection of data for subsequent analysis. Microdisk working electrodes are employed to permit both thermodynamic and kinetically controlled processes to be studied under steady-state conditions in flowing solutions without the distortion or hysteresis normally encountered with larger sized electrodes. The effect of electrode size, potential scan rate, and solution flow rate are studied extensively with the oxidation of ferrocene used as an example of a thermodynamically controlled process and a series of catecholamines as examples of a kinetically controlled process. The performance of the detector was best demonstrated when used as a HPLC post-column detector. The 3-dimensional chromatovoltammograms obtained allow on-line characterisation of each fraction as it elutes from the column. The rest of the work presented in this thesis involves the study of the oxidative degradation pathway of dithranol. The oxidative pathway was shown to involve a complex free radical mechanism, dependent on the presence of both oxygen and, in particular light. The pathway is further complicated by the fact that dithranol may exist in either a keto or enol form, the enol being most susceptible to oxidation. A likely mechanism is proposed from studies performed with cyclic voltammetry and controlled potential electrolysis, then defined by subsequent kinetic studies.

Qualitative and quantitative analysis of lipid classes in fish oils by thin-layer chromatography with an Iatroscan flame Ionization detector (TLC-FID) and liquid chromatography with an evaporative light scattering detector (LC-ELSD)

Combined effects of hydrogen and air flow rates on the peak response of selected neutral lipid classes (triacylglycerol, diacylglycerol, monoacylglycerol, free fatty acids, and ethyl esters) were studied to optimize and calibrate the Iatroscan Mk-6s Chromarod system for the qualitative and quantitative analysis of lipid classes by thin-layer chromatography (TLC) with flame ionization detection in fish oil during the transesterification process. Air flow rate of 2 L/min, hydrogen flow rate of 150-160 mL/min, and scan rate of 30 s/rod were found to be the optimum conditions. All samples were also analyzed by high performance liquid chromatography (HPLC) with evaporative light scattering detection. Quantitative results obtained by TLC with the flame ionization detection method were comparable to those obtained from HPLC with evaporative light scattering detection.

Feature extraction for animal fiber identification

Fiber identification has been a very important task in many industries such as wool growing, textile processing, archaeology, histochernical engineering, and zoology. Over the years, animal fibers have been identified using physical and chemical approaches. Recently, objective identification of animal fibers has been developed based on the cuticular information of fibers. Effective and accurate extraction of representative features is essential to animal fiber identification and classification. In the current work, two different strategies are developed for this purpose. In the first method, explicit features are extracted using image processing. However, only implicit features are used in the second method with an unsupervised artificial neural network. It is found that the use of explicit features increases the accuracy of fiber identification but requires more effort on processing images and solid knowledge of what features are representative ones.

Praxis modelling : an evaluation of and extension to feature based modelling

This thesis presents Relation Based Modelling as an extension to the Feature Based Modelling approach to student modelling. Relation Based Modelling dynamically creates new terms allowing the instructional designer to specify a set of primitives and operators from which the modelling system will create the necessary elements. Focal modelling is a new technique devised to manipulate and coordinate the addition of new terms. The thesis presents an evaluation of student modelling systems based on predictive accuracy.

An embedded two-layer feature selection approach for microarray data analysis

Feature selection is an important technique in dealing with application problems with large number of variables and limited training samples, such as image processing, combinatorial chemistry, and microarray analysis. Commonly employed feature selection strategies can be divided into filter and wrapper. In this study, we propose an embedded two-layer feature selection approach to combining the advantages of filter and wrapper algorithms while avoiding their drawbacks. The hybrid algorithm, called GAEF (Genetic Algorithm with embedded filter), divides the feature selection process into two stages. In the first stage, Genetic Algorithm (GA) is employed to pre-select features while in the second stage a filter selector is used to further identify a small feature subset for accurate sample classification. Three benchmark microarray datasets are used to evaluate the proposed algorithm. The experimental results suggest that this embedded two-layer feature selection strategy is able to improve the stability of the selection results as well as the sample classification accuracy.

Vehicle detection and classification by measuring and processing magnetic signal

This paper presents novel vehicle detection and classification method by measuring and processing magnetic signal based on single micro-electro- mechanical system (MEMS) magnetic sensor. When a vehicle moves over the ground, it generates a succession of impacts on the earth's magnetic field, which can be detected by single magnetic sensor. The magnetic signal measured by the magnetic sensor is related to the moving direction and the type of the vehicle. Generally, the recognition rate using single sensor detector is not high. In order to improve the recognition rate, a novel feature extraction algorithm and a novel vehicle classification and recognition algorithm are presented. The concavity and convexity areas, and the angles of concave and convex parts of the waveform are extracted. An improved support vector machine (ISVM) classifier is developed to perform vehicle classification and recognition. The effectiveness of the proposed approach is verified by outdoor experiments.

Classification of malware based on string and function feature selection

Anti-malware software producers are continually challenged to identify and counter new malware as it is released into the wild. A dramatic increase in malware production in recent years has rendered the conventional method of manually determining a signature for each new malware sample untenable. This paper presents a scalable, automated approach for detecting and classifying malware by using pattern recognition algorithms and statistical methods at various stages of the malware analysis life cycle. Our framework combines the static features of function length and printable string information extracted from malware samples into a single test which gives classification results better than those achieved by using either feature individually. In our testing we input feature information from close to 1400 unpacked malware samples to a number of different classification algorithms. Using k-fold cross validation on the malware, which includes Trojans and viruses, along with 151 clean files, we achieve an overall classification accuracy of over 98%.