Tomasz Orzechowski

LDA for Face Profile Detection

This paper presents a new approach to face profile classification. It was shown that the Linear Discriminant Analysis combined with the Principal Component Analysis can be used to construct an accurate face profile predictor. Proposed classifier achieves 85% accuracy in face profile prediction.

Secure data harvesting in the federation of repositories managed by Multi Agent Systems

Multi Agent Systems (MAS) are used for efficient data processing on hardware resources. We decided to take benefits of such a system to establish an efficient intelligent fast search system, which will offer advanced search facilities needed by large distributed systems consisting of metadata repositories. In this article we present troubleshooting of organizing such a system with high security.

Diurnal variability of human operator attention disengagement and chronotype: an fMRI-based case study

The main objective of this study was to analyse diurnal variations during attention disengagement operations on a neuronal level in a group of subjects representing extreme chronotypes. The parietal lobes of the participants were scanned four times per day for activity changes using functional magnetic resonance imaging (fMRI), while the subjects performed the task at hand. The findings provide credible evidence of the existence of variability in the activity patterns and levels of the parietal lobes. The activity patterns and levels depend on both the participants’ chronotype as well as time of day. The morning type showed stronger activation of the left parietal lobe, while the evening type showed stronger activation of the right parietal lobe. There was a visible decrease in parietal lobe activity during the post-lunch dip, independent of the subjects’ chronotype. Such variability of parietal lobe activity may suggest that humans are more likely to make errors during task performance at certain times of the day as opposed to others.

TMO: time and memory optimized algorithm applicable for more accurate alignment of trinucleotide repeat disorders associated genes

ABSTRACT In this study, time and memory optimized (TMO) algorithm is presented. Compared with Smith–Watermans algorithm, TMO is applicable for a more accurate detection of continuous insertion/deletions (indels) in genes’ fragments, associated with disorders caused by over-repetition of a certain codon. The improvement comes from the tendency to pinpoint indels in the least preserved nucleotide pairs. All nucleotide pairs that occur less frequently are classified as less preserved and they are considered as mutated codons whose mid-nucleotides were deleted. Other benefit of the proposed algorithm is its general tendency to maximize the number of matching nucleotides included per alignment, regardless of any specific alignment metrics. Since the structure of the solution, when applying Smith–Waterman, depends on the adjustment of the alignment parameters and, therefore, an incomplete (shortened) solution may be derived, our algorithm does not reject any of the consistent matching nucleotides that can be included in the final solution. In terms of computational aspects, our algorithm runs faster than Smith–Waterman for very similar DNA and requires less memory than the most memory efficient dynamic programming algorithms. The speed up comes from the reduced number of nucleotide comparisons that have to be performed, without having to imperil the completeness of the solution. Due to the fact that four integers (16 Bytes) are required for tracking matching fragment, regardless its length, our algorithm requires less memory than Huangs algorithm.

Framework for integration of police repositories

The main purpose of this article is to present a structure of a multi interfaces system, which can be used for the integration of different repositories consisting of personal data, with any additional data storage. The brokerage-oriented architecture with its functionalities, can allow the detection of new areas of information that may allow a better protection against variety ofmalicious acts.

Face Occurrence Verification Using Haar Cascades - Comparison of Two Approaches

Face occurrence verification is mandatory stage for color based face detection systems. Facial features extraction using Haar cascades is one of the possible way to classify regions as faces. The purpose of this paper is to provide novel and valuable comparison of two approaches for using Haar cascades in face occurrence verification stage. Performance and accuracy tests have been carried out to decide which of approaches described in the article is more suitable. Results might be crucial while implementing similar face detection system based on skin detection and facial features localization.