The article presents the walking robot control system project. A ROBONOVA-I robot is used as a base mechanics and servo research platform. The possibilities of this platform allow to control the robot's limbs with...
详细信息
ISBN:
(纸本)9783319023090
The article presents the walking robot control system project. A ROBONOVA-I robot is used as a base mechanics and servo research platform. The possibilities of this platform allow to control the robot's limbs with 16 degrees of freedom. Designed control system supports force sensors and three-axis gyroscope with triaxial accelerometer, all in one ADIS16360 system by Analog Device. A PC software is made, which allows to test the pre-developed algorithms. User is able to wirelessly communicate with the robot via XBee module and also to track, online, information from sensors. Article concludes with a simple algorithm for sequentially walking robot.
Pairwise dissimilarity representations are frequently used as an alternative to feature vectors in pattern recognition. One of the problems encountered in the analysis of such data, is that the dissimilarities are rar...
详细信息
ISBN:
(纸本)9783319023090
Pairwise dissimilarity representations are frequently used as an alternative to feature vectors in pattern recognition. One of the problems encountered in the analysis of such data, is that the dissimilarities are rarely Euclidean, while statistical learning algorithms often rely on Euclidean distances. Such non-Euclidean dissimilarities are often corrected or imposed geometry via embedding. This talk reviews and and extends the field of analysing non-Euclidean dissimilarity data.
Protein-protein interactions are important for the majority of biological processes. A significant number of computational methods have been developed to predict protein-protein interactions using proteins' sequen...
详细信息
ISBN:
(纸本)9783319023090
Protein-protein interactions are important for the majority of biological processes. A significant number of computational methods have been developed to predict protein-protein interactions using proteins' sequence, structural and genomic data. Hence, this fact motivated us to perform a comparative study of various machine learning methods, training them on the set of known protein-protein interactions, using proteins' global and local attributes. The results of the classifiers were evaluated through cross-validation and several performance measures were computed. It was noticed from the results that support vector machine outperformed other classifiers. This fact has also been established through statistical test, called Wilcoxon rank sum test, at 5% significance level.
The problem of comparison of genomic sequences is of great importance. There are various measures of similarity of sequences. One of the most popular is the length of the longest common subsequence (LCS). We propose t...
详细信息
ISBN:
(纸本)9783319023090
The problem of comparison of genomic sequences is of great importance. There are various measures of similarity of sequences. One of the most popular is the length of the longest common subsequence (LCS). We propose the first bit-parallel algorithm for the variant of the LCS problem, block merged LCS, which was recently formulated in the studies on the whole genome duplication hypothesis. Practical experiments show that our proposal is from 10 to over 100 times faster than existing algorithms.
In an embedded approach to feature selection and reduction, a mechanism determining their choice constitutes a part of an inductive learning algorithm, as happens for example in construction of decision trees, artific...
详细信息
ISBN:
(纸本)9783319023090
In an embedded approach to feature selection and reduction, a mechanism determining their choice constitutes a part of an inductive learning algorithm, as happens for example in construction of decision trees, artificial neural networks with pruning, or rough sets with activated relative reducts. The paper presents the embedded solution based on assumed weights for reducts and measures defined for conditional attributes, where weighting of these attributes was used in their backward elimination for rule classifiers induced in Dominance-Based Rough Set Approach. The methodology is illustrated with a binary classification case of authorship attribution.
Recently MALDI-ToF mass spectrometry has become major technique for the analysis of complex protein mixtures. For large studies or when data from different machines are compared, a problem of shifts of peaks between s...
详细信息
ISBN:
(纸本)9783319023090
Recently MALDI-ToF mass spectrometry has become major technique for the analysis of complex protein mixtures. For large studies or when data from different machines are compared, a problem of shifts of peaks between spectra becomes very urgent, especially in low resolution data. In our study we compare different profile-based alignment algorithms using a virtual instrument. We investigate the performance of algorithms through different simulation scenarios and indicate their weaknesses and strengths by a few commonly used statistical measures. We propose a modification of the peak alignment by fast Fourier transform algorithm, which significantly improved its robustness by reducing alignment artefacts and over alignments. Spectral alignment is an indispensable element in the MS data pre-processing. PAFFT algorithm with our modification may be a good MS spectra pre-processing tool, by achieving high sensitivity and keeping false discovery rate at a reasonably low level.
This article describes a problem of spatial query optimization. The processing of such queries is a new area of rapidly developing domain of spatial databases. The main scope of considerations is the impact of constra...
详细信息
ISBN:
(纸本)9783319023090
This article describes a problem of spatial query optimization. The processing of such queries is a new area of rapidly developing domain of spatial databases. The main scope of considerations is the impact of constraints type on the speed of execution. Transformation of logical formulas is proposed for some kind of queries as a method of optimization. Proposed decompositions of queries were done according to the logic and set theory. It is experimentally proved that the presented way of optimization is efficient.
The article presents a problem of 3D and 2D heterogenic data visualization. The data come from different devices installed on the robot platform. The data include 3D point cloud, 2D images, 3D and 2D occupancy grids, ...
详细信息
ISBN:
(纸本)9783319023090
The article presents a problem of 3D and 2D heterogenic data visualization. The data come from different devices installed on the robot platform. The data include 3D point cloud, 2D images, 3D and 2D occupancy grids, obtained from laser scanning device, stereocameras and calculated using data from laser 3D scanner.
Unmanned aerial systems have become recently a rapidly developing research area. The most popular platforms are undoubtedly multirotors with an ability to vertical take-off and land. These are often controlled by huma...
详细信息
ISBN:
(纸本)9783319023090
Unmanned aerial systems have become recently a rapidly developing research area. The most popular platforms are undoubtedly multirotors with an ability to vertical take-off and land. These are often controlled by human pilots using some basic apparatus. In this paper the mechanical architecture, hardware components, and software structure of the ground control station have been described. These components create an interface between an operator and the flying machine allowing to perform an operation with a different level of complexity. Furthermore the main purpose of designing this device is to obtain a user friendly system that can be used by a medium experienced user with limited training time.
We present a generic model of a cognitive system, which is based on a population of communicating agents. Following the earlier models (Steels and Belpaeme, 2005) we give communication an important role in shaping the...
详细信息
ISBN:
(纸本)9783319023090
We present a generic model of a cognitive system, which is based on a population of communicating agents. Following the earlier models (Steels and Belpaeme, 2005) we give communication an important role in shaping the cognitive categories of individual agents. Yet in this paper we underscore the importance of other constraints on cognition: the structure of the environment, in which a system evolves and learns and the learning capacities of individual agents. Thus our agent-based model of cultural emergence of colour categories shows that boundaries might be seen as a product of agent's communication in a given environment. We discuss the methodological issues related to real data characterization, as well as to the process of modeling the emergence of perceptual categories in human subjects.
暂无评论