Mariofanna G. Milanova

Computational Intelligence in Biomedicine and Bioinformatics

The purpose of this book is to provide an overview of powerful state-of-the-art methodologies that are currently utilized for biomedicine and/ or bioinformatics-oriented applications, so that researchers working in those fields could learn of new methods to help them tackle their problems. On the other hand, the CI community will find this book useful by discovering a new and intriguing area of applications. In order to help fill the gap between the scientists on both sides of this spectrum, the editors have solicited contributions from researchers actively applying computational intelligence techniques to important problems in biomedicine and bioinformatics.

Computational Intelligence in Solving Bioinformatics Problems: Reviews, Perspectives, and Challenges

This chapter presents a broad overview of Computational Intelligence (CI) techniques including Artificial Neural Networks (ANN), Particle Swarm Optimization (PSO), Genetic Algorithms (GA), Fuzzy Sets (FS), and Rough Sets (RS). We review a number of applications of computational intelligence to problems in bioinformatics and computational biology, including gene expression, gene selection, cancer classification, protein function prediction, multiple sequence alignment, and DNA fragment assembly. We discuss some representative methods to provide inspiring examples to illustrate how CI could be applied to solve bioinformatic problems and how bioinformatics could be analyzed, processed, and characterized by computational intelligence. Challenges to be addressed and future directions of research are presented. An extensive bibliography is also included.

Recognition of Emotional states in Natural Human-Computer Interaction

In this paper we present a non-invasive method for extracting facial expression components from video sequences. We propose a contextual analysis of user state and guide appropriate system actuation. The approach proposed hereafter combines the advantages of MPEG-4 and an active contour model to extract the contours of the facial objects such as: eyes, eyebrows, nose, lips and dimples. The first stage applies a local statistics to distinguish the objects subject of interest. The second stage runs an existing active contour model to define the contours of the objects. Further the facial control points could be spotted on the contours and used for emotion recognition. To distinguish geometric facial features an approach is proposed to compare multiple closed polygons. To validate the theoretical concepts experiments were performed using a normal and a smiling face. A comparison with an existing approach underlines the advantages and disadvantages of the present work.

Documents Image Compression with IDP and Adaptive RLE

In the paper is presented a new method for efficient lossless documents image compression, based on the inverse difference pyramid (IDP) decomposition. The method is aimed at the processing of graphic and text grayscale and color images. The IDP decomposition is presented in brief and the method ability to process efficiently different kinds of images are presented. In the paper are included the results of the compression of graphics and texts and they are compared with those obtained with JPEG2000 and other widely used lossless compression methods

Hybridization of independent component analysis, rough sets, and multi-objective evolutionary algorithms for classificatory decomposition of cortical evoked potentials

This article presents a continuation of our research aiming at improving the effectiveness of signal decomposition algorithms by providing them with “classification-awareness.” We investigate hybridization of multi-objective evolutionary algorithms (MOEA) and rough sets (RS) to perform the task of decomposition in the light of the underlying classification problem itself. In this part of the study, we also investigate the idea of utilizing the Independent Component Analysis (ICA) to initialize the population in the MOEA.

Multimedia watermarking with complex Hadamard transform in the inverse pyramid decomposition

A new method for digital watermarking of multimedia signals (audio signals and images) is offered, based on decomposition with inverse difference pyramid (IDP), whose coefficients are obtained with complex Hadamard transform (CHT). Advantages of the method, compared with those based on DFT or DWT transform, are that there is no quantization of the values of the transform coefficients; it has lower computational complexity and permits insertion of different watermark in every consecutive pyramid level. The method ensures practical invisibility (insensibility) of the inserted watermark, and high resistance against tampering, compression, affine transforms, filtration, dithering and other kinds of processing. Together with this, the method permits sure detection of the inserted watermark and low probability for mistakes in the water mark extraction.

Cellular neural networks for motion estimation

The cellular neural networks (CNN) model is now a paradigm of cellular analogue programmable multidimensional processor array with distributed local logic and memory. CNNs consist of many parallel analogue processors computing in realtime. One desirable feature is that these processors arranged in a two dimensional grid only have local connections, which lend themselves easily to VLSI implementations. We present a new algorithm for motion estimation using a CNN. We start from a mathematical viewpoint (i.e., statistical regularisation based on a Markov random field) and proceed by mapping the algorithm onto a cellular neural network. Because of the temporal dynamics inherent in the cells of the CNN it is well suited to processing time-varying images. A robust motion estimation algorithm is achieved by using a spatio-temporal neighbourhood for modelling pixel interactions.

EEG Signal Processing for Brain–Computer Interfaces

This chapter is focused on recent advances in electroencephalogram (EEG) signal processing for brain computer interface (BCI) design. A general overview of BCI technologies is first presented, and then the protocol for motor imagery noninvasive BCI for mobile robot control is discussed. Our ongoing research on noninvasive BCI design based not on recorded EEG but on the brain sources that originated the EEG signal is also introduced. We propose a solution to EEG-based brain source recovering by combining two techniques, a sequential Monte Carlo method for source localization and spatial filtering by beamforming for the respective source signal estimation. The EEG inverse problem is previously studded assuming that the source localization is known. In this work for the first time the problem of inverse modeling is solved simultaneously with the problem of the respective source space localization.

Adaptive Compression of Compound Images

In the paper is presented new method for efficient compression of compound still images, containing pictures and texts/graphics. The method is based on the inverse difference pyramid (IDP) image decomposition and lossless coding of the obtained data. The method permits the recognition of texts and graphics in compound images, the setting of corresponding regions of interest (ROI) and their coding with the most efficient tools. The method ensures easy access and transfer of visual information via Internet aimed at distance learning applications.

Resistant image watermarking in the phases of the Complex Hadamard Transform coefficients

In the paper a new method is presented for digital content protection based on watermark data insertion in the image transform domain. For this, the still digital image is transformed using Complex Hadamard Transform (CHT), and the watermark data is then inserted in the imaginary part of the transform coefficients. The selection of the suitable for watermarking transform coefficients is done in accordance with pre-defined rules. The so inserted watermark is perceptually invisible. The method permits the insertion of relatively large amount of data, retaining the high quality of the protected image. The main advantages of the algorithm for digital watermarking, based on the CHT are that it is resistant against attacks, based on high-frequency filtration (JPEG compression); it permits the insertion of significant amount of data, and the watermark detection could be done without using the original image.