Janusz Kacprzyk

Artificial Neural Networks: Biological Inspirations – ICANN 2005

Modeling the Brain and Cognitive Functions.- Novelty Analysis in Dynamic Scene for Autonomous Mental Development.- The Computational Model to Simulate the Progress of Perceiving Patterns in Neuron Population.- Short Term Memory and Pattern Matching with Simple Echo State Networks.- Analytical Solution for Dynamic of Neuronal Populations.- Dynamics of Cortical Columns - Sensitive Decision Making.- Dynamics of Cortical Columns - Self-organization of Receptive Fields.- Optimal Information Transmission Through Cortico-Cortical Synapses.- Ensemble of SVMs for Improving Brain Computer Interface P300 Speller Performances.- Modelling Path Integrator Recalibration Using Hippocampal Place Cells.- Coding of Objects in Low-Level Visual Cortical Areas.- A Gradient Rule for the Plasticity of a Neurons Intrinsic Excitability.- Building the Cerebellum in a Computer.- Special Session: The Development of Cognitive Powers in Embodied Systems.- Combining Attention and Value Maps.- Neural Network with Memory and Cognitive Functions.- Associative Learning in Hierarchical Self Organizing Learning Arrays.- A Review of Cognitive Processing in the Brain.- Spiking Neural Networks.- Neuronal Behavior with Sub-threshold Oscillations and Spiking/Bursting Activity Using a Piecewise Linear Two-Dimensional Map.- On-Line Real-Time Oriented Application for Neuronal Spike Sorting with Unsupervised Learning.- A Spiking Neural Sparse Distributed Memory Implementation for Learning and Predicting Temporal Sequences.- ANN-Based System for Sorting Spike Waveforms Employing Refractory Periods.- Emergence of Oriented Cell Assemblies Associated with Spike-Timing-Dependent Plasticity.- An Information Geometrical Analysis of Neural Spike Sequences.- Perceptual Binding by Coupled Oscillatory Neural Network.- Experimental Demonstration of Learning Properties of a New Supervised Learning Method for the Spiking Neural Networks.- Single-Unit Recordings Revisited: Activity in Recurrent Microcircuits.- A Hardware/Software Framework for Real-Time Spiking Systems.- Efficient Source Detection Using Integrate-and-Fire Neurons.- Associative Memory Models.- A Model for Hierarchical Associative Memories via Dynamically Coupled GBSB Neural Networks.- Balance Algorithm for Point-Feature Label Placement Problem.- Models of Self-correlation Type Complex-Valued Associative Memories and Their Dynamics.- Recovery of Performance in a Partially Connected Associative Memory Network Through Coding.- Optimal Triangle Stripifications as Minimum Energy States in Hopfield Nets.- Models of Biological Functions.- A Biophysical Model of Decision Making in an Antisaccade Task Through Variable Climbing Activity.- Can Dynamic Neural Filters Produce Pseudo-Random Sequences?.- Making Competition in Neural Fields Suitable for Computational Architectures.- Neural Network Computations with Negative Triggering Thresholds.- A Model for Delay Activity Without Recurrent Excitation.- Neuronal Coding Strategies for Two-Alternative Forced Choice Tasks.- Learning Features of Intermediate Complexity for the Recognition of Biological Motion.- Study of Nitric Oxide Effect in the Hebbian Learning: Towards a Diffusive Hebbs Law.- Special Session: Projects in the Area of NeuroIT.- Deterministic Modelling of Randomness with Recurrent Artificial Neural Networks.- Action Understanding and Imitation Learning in a Robot-Human Task.- Comparative Investigation into Classical and Spiking Neuron Implementations on FPGAs.- HYDRA: From Cellular Biology to Shape-Changing Artefacts.- The CIRCE Head: A Biomimetic Sonar System.- Tools for Address-Event-Representation Communication Systems and Debugging.- New Ears for a Robot Cricket.- Reinforcement Learning in MirrorBot.- Evolutionary and Other Biological Inspirations.- Varying the Population Size of Artificial Foraging Swarms on Time Varying Landscapes.- Lamarckian Clonal Selection Algorithm with Application.- Analysis for Characteristics of GA-Based Learning Method of Binary Neural Networks.- Immune Clonal Selection Wavelet Network Based Intrusion Detection.- Investigation of Evolving Populations of Adaptive Agents.- Enhancing Cellular Automata by an Embedded Generalized Multi-layer Perceptron.- Intelligent Pattern Generation for a Tactile Communication System.- Self-organizing Maps and Their Applications.- Self-organizing Map Initialization.- Principles of Employing a Self-organizing Map as a Frequent Itemset Miner.- Spatio-Temporal Organization Map: A Speech Recognition Application.- Residual Activity in the Neurons Allows SOMs to Learn Temporal Order.- Ordering of the RGB Space with a Growing Self-organizing Network. Application to Color Mathematical Morphology.- SOM of SOMs: Self-organizing Map Which Maps a Group of Self-organizing Maps.- The Topographic Product of Experts.- Self Organizing Map (SOM) Approach for Classification of Power Quality Events.- SOM-Based Method for Process State Monitoring and Optimization in Fluidized Bed Energy Plant.- A New Extension of Self-optimizing Neural Networks for Topology Optimization.- A Novel Technique for Data Visualization Based on SOM.- Statistical Properties of Lattices Affect Topographic Error in Self-organizing Maps.- Increasing Reliability of SOMs Neighbourhood Structure with a Bootstrap Process.- Computer Vision.- Artificial Neural Receptive Field for Stereovision.- Pattern Detection Using Fast Normalized Neural Networks.- Neural Network Model for Extracting Optic Flow.- A Modular Single-Hidden-Layer Perceptron for Letter Recognition.- Fast Color-Based Object Recognition Independent of Position and Orientation.- Class-Specific Sparse Coding for Learning of Object Representations.- Neural Network Based Adult Image Classification.- Online Learning for Object Recognition with a Hierarchical Visual Cortex Model.- Extended Hopfield Network for Sequence Learning: Application to Gesture Recognition.- Accurate and Robust Image Superresolution by Neural Processing of Local Image Representations.- The Emergence of Visual Object Recognition.- Implicit Relevance Feedback from Eye Movements.- Image Segmentation by Complex-Valued Units.- Cellular Neural Networks for Color Image Segmentation.- Image Segmentation Using Watershed Transform and Feed-Back Pulse Coupled Neural Network.- Adaptive Switching Median Filter with Neural Network Impulse Detection Step.- Face Recognition and Detection.- Human Face Detection Using New High Speed Modular Neural Networks.- Face Detection Using Convolutional Neural Networks and Gabor Filters.- Face Identification Performance Using Facial Expressions as Perturbation.- Discriminative Common Images for Face Recognition.- Classification of Face Images for Gender, Age, Facial Expression, and Identity.- Sound and Speech Recognition.- Classifying Unprompted Speech by Retraining LSTM Nets.- Temporal Sound Processing by Cochlear Nucleus Octopus Neurons.- A SOM Based 2500 - Isolated - Farsi - Word Speech Recognizer.- Training HMM/ANN Hybrid Speech Recognizers by Probabilistic Sampling.- Chord Classifications by Artificial Neural Networks Revisited: Internal Representations of Circles of Major Thirds and Minor Thirds.- Bioinformatics.- Biclustering Gene Expression Data in the Presence of Noise.- Gene Extraction for Cancer Diagnosis by Support Vector Machines.- High-Throughput Multi-dimensional Scaling (HiT-MDS) for cDNA-Array Expression Data.- Biomedical Applications.- Comparing Neural Network Architecture for Pattern Recognize System on Artificial Noses.- Medical Document Categorization Using a Priori Knowledge.- A Neurofuzzy Methodology for the Diagnosis of Wireless-Capsule Endoscopic Images.- Neural Network Use for the Identification of Factors Related to Common Mental Disorders.- Development and Realization of the Artificial Neural Network for Diagnostics of Stroke Type.- Special Session: Information-Theoretic Concepts in Biomedical Data Analysis.- A First Attempt at Constructing Genetic Programming Expressions for EEG Classification.- SOM-Based Wavelet Filtering for the Exploration of Medical Images.- Functional MRI Analysis by a Novel Spatiotemporal ICA Algorithm.- Early Detection of Alzheimers Disease by Blind Source Separation, Time Frequency Representation, and Bump Modeling of EEG Signals.

On Group Decision Making, Consensus Reaching, Voting and Voting Paradoxes under Fuzzy Preferences and a Fuzzy Majority: A Survey and some Perspectives

Group decision making, as meant in this chapter, is the following choice problem which proceeds in a multiperson setting. There is a group of individuals (decisionmakers, experts, ...) who provide their testimonies concerning an issue in question. These testimonies are assumed here to be individual preference relations over some set of option (alternatives, variants, ...). The problem is to find a solution, i.e. an alternative or a set of alternatives, from among the feasible ones, which best reflects the preferences of the group of individuals as a whole. We will survey main developments in group decision making under fuzziness. First, we will briefly outline some basic inconsistencies and negative results of group decision making and social choice, and show how they can be alleviated by some plausible modifications of underlying assumptions, mainly by introducing fuzzy preference relations and, to a lesser extent, a fuzzy majority. Then, we will concentrate on how to derive solutions under individual fuzzy preference relations, and a fuzzy majority equated with a fuzzy linguistic quantifier (e.g., most, almost all, ...) and dealt with in terms of a fuzzy logic based calculus of linguistically quantified statements or via the ordered weighted averaging (OWA) operators. We will briefly mention that one of solution concepts proposed can be a prototype for a wide class of group decision making choice functions. Then, we will discuss a related issue of how to define a “soft” degree of consensus in the group under individual fuzzy preference relations and a fuzzy majority. Finally, we will show how fuzzy preferences can help alleviate some voting paradoxes.

An Internet-based Group Decision and Consensus Reaching Support System

We present an idea of a group decision making and consensus reaching decision support system and its implementation within the framework of the Internet (WWW) service are presented. The focus is on the support of the consensus reaching process. The preferences are represented using linguistic terms and aggregation schemes employ various soft computing techniques. The point of departure is a multi-criteria evaluation of particular options given by each individual. These are processed to obtain various agreement assessment measures.

A novel text classification problem and its solution

A new text categorization problem is introduced. As in the classical problem, there is a set of documents and a set of categories. However, in addition to being assigned to a specific category, each document belongs to a certain sequence of documents, referred to as a case. It is assumed that all documents in the same case belong to the same category. An example may be a set of news articles. Their categories may be sport, politics, entertainment, etc. In each category there exist cases, i.e., sequences of documents describing, for example evolution of some events. The problem considered is how to classify a document to a proper category and a proper case within this category. In the paper we formalize the problem and discuss two approaches to its solution.

Linguistic Summaries of Time Series: On Some Additional Data Independent Quality Criteria

We further extend our approach on the linguistic summarization of time series (cf. Kacprzyk, Wilbik and Zadrozny) in which an approach based on a calculus of linguistically quantified propositions is employed, and the essence of the problem is equated with a linguistic quantifier driven aggregation of partial scores (trends). Basically, we present here some reformulation and extension of our works mainly by including a more complex evaluation of the linguistic summaries obtained. In addition to the basic criterion of a degree of truth (validity), we also use here as the additional criteria a degree of imprecision, specificity, fuzziness and focus. However, for simplicity and tractability, we use in the first shot the degrees of truth (validity) and focus, which usually reduce the space of possible linguistic summaries to a considerable extent, and then - for a usually much smaller set of linguistic summaries obtained - we use the remaining three degrees of imprecision, specificity and fuzziness for making a final choice of appropriate linguistic summaries. We show an application to the absolute performance type analysis of daily quotations of an investment fund.

Fuzzy Preferences as a Convenient Tool in Group Decision Making and a Remedy for Voting Paradoxes

In this section we will first discuss the very essence of group decision making and how fuzzy preferences can help alleviate some inherent difficulties and make models more realistic. Then, we will briefly present some tools to be used, notably how to deal with linguistically quantified statements, and with a linguistic quantifier driven aggregation.

A Novel View of Bipolarity in Linguistic Data Summaries

The problem of data summarization of a set of (numeric) data, notably a (relational) database is dealt with. We are concerned with how to devise a short, (quasi) natural language summary, in the form of a sentence, which would best grasp the very content of the set of data. For instance, for a personnel database with records corresponding to particular employees who are described by attributes like age, sex, salary, etc., such a linguistic summary with respect to age may be “most employees are middle aged”. We use as a point of departure a fuzzy logic based approach to linguistic summarization originated by Yager, and then developed by Kacprzyk and Zadrozny who have also indicated—first—an intrinsic connection between linguistic summarization and fuzzy querying, and—second—a crucial role of protoforms in Zadeh’s sense. The second point of departure is the concept of a bipolar query in the sense that the querying criteria may be mandatory and optional, i.e. those which must be satisfied and those which should be satisfied if possible, as initiated by Zadrozny, and then developed by Zadrozny, Kacprzyk and De Tre. In this paper we present the concept of a bipolar linguistic summary that combines the very concepts of a linguistic summary with that of bipolarity in the above sense, and also an analogous relation between the linguistic summaries and bipolar queries.

Trajectory Tracking Control of a Four-Wheeled Mobile Robot with Yaw Rate Linear Controller

The paper concerns the problem of trajectory tracking control of a four-wheeled PIAP SCOUT mobile robot with non-steered wheels. For this kind of wheeled robots, it is impossible to find kinematic relationship between robot’s body motion and motion of driven wheels, because of inherent sliding of wheels on the ground during turning. This is an important problem from the point of view of control of the robot. The approach followed in the present work relies on introducing a simple linear controller with feedback of actual yaw rate of robot’s body. The yaw velocity is measured by inexpensive MEMS gyroscope. Experiments were conducted on two kinds of floor typical for office buildings: PVC flooring and carpet flooring. Measurements of motion parameters were possible with INS technique. It was found that the proposed yaw rate controller significantly reduces the angular error of path tracking for 90 degrees turn maneuver.

Global path planning for a specialized autonomous robot for intrusion detection in wireless sensor networks (WSNs) using a new evolutionary algorithm

We present a new specialized evolutionary algorithm for the global path planning for mobile robots.We assume that multiple criteria are involved, notably the energy consumption, travel time and movement cost on dangerous areas, as well as constraints like the location obstacles, a limited minimal robot’s turning angle, a maximal energy (related to the capacity of batteries) and maximal time of travel. The new algorithm involves some new problem specific evolutionary operations. The simulation results using the V-REP platform involve obstacles, different surfaces and dangerous areas. The results are very encouraging, much better than those obtained using the traditional meta-heuristics, notably the widely used genetic algorithm. Moreover, a novel explicit involvement of energy consumption as a key factor, provides much new insight from both a theoretical and even more practical points of view.

Comparative Analysis of Posture Controllers for Tracking Control of a Four-Wheeled Skid-Steered Mobile Robot – Part 2. Dynamics Model of the Robot and Simulation Research of Posture Controllers

The paper is the second part of the work concerned with the problem of trajectory tracking control of a four-wheeled PIAP GRANITE mobile robot. The first part of the work was devoted to theoretical considerations. Research object and its kinematics were described. Robot motion control system structure comprising posture controller and drive unit controller was presented. Various solutions for posture controller were discussed and their modifications proposed. A methodology of posture controller tuning was introduced in which controller parameters for particular solutions are determined from conditions for maximum velocities of robot motion and maximum posture errors. In the present work dynamics model of the robot is described. It takes into account tire-ground contact conditions and wheel slips. The tire-ground contact conditions are characterized by coefficients of friction and rolling resistance. A simple form of the tire model, which includes only the most important effects of tire-ground interaction, is used. The robot dynamics model also contains the electromechanical model of a servomotor drive unit. The developed model of robot dynamics is used in the simulation studies in which the effectiveness of particular solutions of posture controller is benchmarked. Evaluation of the analyzed solutions is carried out using the introduced quality indexes.