Maciej Majewski

Sentence recognition using artificial neural networks

The paper describes an application of artificial neural networks (ANN) for natural language text reasoning. The task of knowledge discovery in text from a database, represented with a database file consisting of sentences with similar meanings but different lexico-grammatical patterns, was solved with ANNs which recognize the meaning of the text using training files with limited dictionary. The paper features recognition algorithms of text meaning from a selected source using 3-layer ANNs. Tests of the new method have also been described.

New intelligent interactive automated systems for design of machine elements and assemblies

This paper presents a new concept of intelligent interactive automated systems for design of machine elements and assemblies on the basis of its features described in a natural language. In the proposed system, computational intelligence methods allow for communication by speech and handwriting, meaning analyses of design engineers messages, analyses of constructions, encoding and assessments of constructions, CAD system controlling and visualizations. The system uses an intelligent subsystem for assessment of engineers ability for efficient designing. It is capable of control, supervision and optimization of the designing process. The system consists of spoken natural language and handwriting interfaces between the designing system and design engineers. They are equipped with several adaptive intelligent layers for human biometric identification, recognition of speech and handwriting, recognition of words, analyses and recognition of messages, meaning analyses of messages, and assessments of human reactions. The paper also makes a comparison of the proposed new automated designing system with the present system of realization of designing tasks. In the system also proposed are new concepts of a system of symbolic notation of construction features and language for notation, archiving and processing of construction description data (object oriented language for construction).

Intelligent semantic-based system for corpus analysis through hybrid probabilistic neural networks

The paper describes the application of hybrid probabilistic neural networks for corpus analysis which consists of intelligent semanticbased methods of analysis and recognition of word clusters and their meaning. The task of analyzing a corpus of academic articles was resolved with hybrid probabilistic neural networks and developed word clusters. The created prototypes of word clusters provide the probabilistic neural networks with possibilities of recognizing corpus clusters. The established corpus comprises 1376 articles, from specialist leading SCIindexed journals, and provides representative samples of the language of science and technology. In this paper, a review of selected issues is carried out with regards to computational approaches to language modelling as well as semantic patterns of language. The paper features semanticbased recognition algorithms of word clusters of similar meanings but different lexico-grammatical patterns from the established corpus using multilayer neural networks. The paper also presents experimental results of word cluster semantic-based recognition in the context of phrase meaning analysis.

Intelligent e-learning systems for evaluation of user's knowledge and skills with efficient information processing

This paper presents a new concept of an e-learning system with intelligent two-way speech communication between the system and its users. Computational intelligence methods allow for analysis, evaluation and assessment of users knowledge and skills and users ability for efficient information processing. The system is also capable of control, supervision and optimization of the e-learning process. Developed as a prototype for mobile technologies, the communication system by speech and natural language between the e-learning system and external users consists of biometric user identification, speech recognition, word and sentence recognition, sentence meaning analysis, and user reaction assessment. Also discussed are selected new concepts of intelligent e-learning systems using speech communication. The discussion focuses on recognition and evaluation of spoken natural language sentences with hybrid neural networks.

Natural language human-robot interface using evolvable fuzzy neural networks for mobile technology

In this paper, a human-robot speech interface for mobile technology is described which consists of intelligent mechanisms of human identification, speech recognition, word and command recognition, command meaning and effect analysis, command safety assessment, process supervision as well as human reaction assessment. A review of selected issues is carried out with regards to recognition and evaluation of speech commands in natural language using hybrid neural networks. The paper presents experimental results of automatic recognition and evaluation of spoken commands of a manufacturing robot model simulating the execution of laser processing tasks in a virtual production process.

Intelligent natural language processing

In this paper, a natural language interface is presented which consists of the intelligent mechanisms of human identification, speech recognition, word and command recognition, command syntax and result analysis, command safety assessment, technological process supervision as well as human reaction assessment. In this paper, a review is carried out of selected issues with regards to recognition of speech commands in natural language given by the operator of the technological device. A view is offered of the complexity of the recognition process of the operators words and commands using neural networks made up of a few layers of neurons. The paper presents research results of speech recognition and automatic recognition of commands in natural language using artificial neural networks.

Human-Machine Speech-Based Interfaces with Augmented Reality and Interactive Systems for Controlling Mobile Cranes

In this paper, an overview of human-machine interactive communication for controlling lifting devices is presented, covering also the integration with vision and sensorial systems. Following a general concept, and motivation towards intelligent human-machine communication through artificial neural networks, selected methods are proposed, which provide further directions both of recent as well as of future research on human-machine interaction. The aim of the experimental research is to design a prototype of an innovative interaction system, equipped with a speech interface in a natural language, augmented reality and interactive manipulators with force feedback.

Intelligent Layer of Two-Way Voice Communication of the Technological Device with the Operator

In this paper there is a review of the selected issues on recognition and safety estimation of voice commands in natural language given by the operator of the technological device. A view is offered of the complexity of the recognition process of words and commands using neural networks made of a few layers of neurons. The paper presents some research results of speech recognition and automatic command recognition with artificial neural networks. The first part of the paper introduces a new conception of an intelligent layer of two-way voice communication of the technological device with the operator and discusses the general topics and issues. The second part is devoted to a discussion of more specific topics of the automatic command recognition and safety estimation that have led to interesting new approaches and techniques.

Conceptual Design of Innovative Speech Interfaces with Augmented Reality and Interactive Systems for Controlling Loader Cranes

The paper presents a concept of implementation of augmented reality, interactive systems and an operator’s speech interface for controlling lifting devices. The aim of the experimental research is to design a prototype of an innovative system for controlling a mobile crane, equipped with a vision and sensorial system, interactive manipulators with force feedback, as well as a system for bi-directional voice communication through speech and natural language between an operator and the controlled lifting device. The system is equipped with several adaptive intelligent layers for human biometric identification, speech recognition, word recognition, analysis and recognition of commands and messages, sentence meaning analysis, command effect analysis and safety assessment, process supervision and human reaction assessment. The article presents the designed structure of an innovative system for interaction of lifting devices with their operators, which provides versatility in terms of application of the system when used for controlling and supervising modern machines and devices in conditions of difficulty or increased risk.

Intelligent Speech Interaction of Devices and Human Operators

The article describes research and development of intelligent speech interaction systems between mobile lifting devices and their human operators. A general processing scheme, using several functional modules, for the interaction has been presented. The paper proposes an intelligent subsystem for assessment of human operator’s ability for efficient processing of information streams from many sources. The paper also formulates rigorously developed concepts of process information mining and assessment of task execution and correlated working conditions using hybrid neural networks. These methods enable a variety of analyzes of task parameters and working conditions and allow us to classify different process quality classes and safety condition types. Furthermore, the methodology allows us to determine regression of task execution quality assessment. The presented research offers the possibility of motivating and inspiring further development of the intelligent speech interaction system and methods that have been elaborated in this paper.