The generalization abilities of machine learning algorithms often depend on the algorithms' initialization, parameter settings, training sets, or feature selections. For instance, SVM classifier performance largely relies on whether the selected kernel functions are suitable for real application data. To enhance the performance of individual classifiers, this dissertation proposes classifier fu...

This paper proposes unconstrained functional networks classifier as a novel approach for solving pattern classification problems. Both initial topology and learning methodology of the new unconstrained functional networks classifier are presented. The performance of the new networks classifier is examined using both real-data and simulation studies. A comparative study with the most common clas...

In practical applications, machine learning algorithms are often needed to learn classifiers that optimize domain specific performance measures. In the past, the research has focused on learning the needed classifier in isolation, yet learning nonlinear classifier for nonlinear and nonsmooth performance measures is still hard. In this paper, rather than learning the needed classifier by optimiz...

This work presents a technique for the analysis of Facial Electromyogram signal activities to classify five different facial expressions for Computer-Muscle Interfacing applications. Facial Electromyogram (FEMG) is a technique for recording the asynchronous activation of neuronal inside the face muscles with non-invasive electrodes. FEMG pattern recognition is a difficult task for the researche...

This paper examines the use of minimal spanning trees as an alternative measure of classifier performance. The ability of this measure to capture classifier complexity is studied through the use of a gene expression dataset. The effect of distance metric on classifier performance is also detailed within.

The presented paper describes a methodology, how to perform benchmarking, when classifier performance measurements are sparse. The described methodology is based on missing value imputation and was demonstrated to work, even when 80% of measurements are missing, for example because of unavailable algorithm implementations or unavailable datasets. The methodology was then applied on 29 relationa...

UNLABELLED ROCR is a package for evaluating and visualizing the performance of scoring classifiers in the statistical language R. It features over 25 performance measures that can be freely combined to create two-dimensional performance curves. Standard methods for investigating trade-offs between specific performance measures are available within a uniform framework, including receiver operati...

This technical report gives details on the results obtained from evaluating the ANGEL Flow Classifier (FC) performance. Evaluation metrics comprise of accuracy, timeliness, stability, processing speed, and the efficiency of hardware resources usage.

The performance of multiple classifier systems varies with the performance of component classifiers as well as the method of combination. In this paper, informationtheoretic methods are proposed for constructing multiple classifier systems, provided that the number of component classifiers is constrained in advance. These proposed methods are applied to a classifier pool and examine the possibl...

We propose and investigate a non-parametric method for identifying regions of speech that have unexpected distortions not seen in the training data. The method does not require knowledge of correct labels and relies only on divergence between statistics of the test and training data. Our experiments show that the proposed method requires a relatively small amount of test data of the order of se...