Intelligent Systems Engineering

Intelligent Systems Engineering

Online ISSN 2054-0345
Print ISSN 0963-9640

Published from 1992-1994, Intelligent Systems Engineering provided an international forum for reporting significant work on the application of artificial intelligence techniques to engineering systems. It reported on the emerging scientific principles behind the development of intelligent systems, described advances in tools and techniques relevant to engineering, and reported the practical application of such methods to industrial problems. The scope of the journal was categorised by the main tasks for which intelligent systems are built: control, diagnosis, design, planning and scheduling, sensor interpretation, simulation and training. In each of these categories, original contributions to principles, tools and techniques, and applications were published.

Volumes & issues:

Show / Hide details

Latest content

Scheduling theory and practice: Minsk group results
- Author(s): Yu.N. Sotskov and V.S. Tanaev
- + Show details - Hide details
- p. 1 –8 (8)
  The paper surveys scheduling theory results obtained mainly at the Institute of Engineering Cybernetics of the Academy of Sciences of Belarus, and published on the whole in Russian. The survey deals with the job-shop, flow-shop and open-shop scheduling problems, and with sequencing jobs on one machine and on a set of parallel machines. The more complicated problems and applied aspects of scheduling theory are also observed. Some trends of further research in scheduling and sequencing are outlined.
Responsibility modelling as a technique for organisational requirements definition
- Author(s): Ros Strens and John Dobson
- + Show details - Hide details
- p. 20 –26 (7)
  The paper proposes that the concept of responsibility provides a means of identifying and specifying, in a way that is meaningful both to users and systems designers, the organisational requirements that arise when a technical system is placed in a social context. The paper shows how organisational structure may be represented as a network of responsibility relationships, how requirements arise from the discharge of obligations associated with responsibilities, and how these concepts have been applied to the particular example of specifying user requirements for clinical workstations in acute hospitals.
Neural network-based classification system for texture images with its applications
- Author(s): Changjing Shang and Keith Brown
- + Show details - Hide details
- p. 27 –36 (10)
  A new approach to interconnecting multi-layer feedforward neural networks for tackling the problems of texture classification is proposed. The resulting classification system classifies textures via two stages; one to compress original co-occurrence feature patterns of high dimensionality to lower dimensional principal feature patterns, and the other to perform actual classification of textures using the principal features. Each stage is efficiently implemented by a trained multi-layer feedforward neural network. Such a cascaded use of neural networks significantly reduces the computational complexity that is otherwise encountered in classifying large-scale texture images. Two practical applications of the system are provided, showing the direct applicability of the approach for real problem-solving.
On-line process fault diagnosis using fuzzy neural networks
- Author(s): J. Zhang and A.J. Morris
- + Show details - Hide details
- p. 37 –47 (11)
  The paper describes a new technique for on-line process fault diagnosis using fuzzy neural networks. The fuzzy neural network considered in this paper is obtained by adding a fuzzification layer to a conventional feed-forward neural network. The fuzzification layer converts the increment in each on-line measurement and controller output into three fuzzy sets; ‘increase’, ‘steady’ and ‘decrease’ with corresponding membership functions. The feed-forward neural network then classifies abnormalities, represented by fuzzy increments in on-line measurements and controller outputs, into various categories. The fuzzification layer can compress training data, and thereby ease training effort. Robustness of the diagnosis system is enhanced by adopting a fuzzy approach in representing abnormalities in the process. Applications of the proposed technique to the fault diagnosis of a continuous stirred tank reactor system demonstrate that the technique is robust to measurement noise, capable of diagnosing incipient faults, and requires fewer training data examples than a conventional network approach.
Robotic Systems: Advanced Techniques and Applications
- Author(s): Ranjan Vepa
- + Show details - Hide details
- p. 48 –49 (2)

Most cited content for this Journal

We currently have no most cited data available for this content.

Login

Not registered yet?

Share

Tools

Login to add to favourites

Key

Intelligent Systems Engineering

Volumes & issues:

Volume 3 (1994)

Volume 2 (1993)

Volume 1 (1992)

Latest content

Scheduling theory and practice: Minsk group results

Responsibility modelling as a technique for organisational requirements definition

Neural network-based classification system for texture images with its applications

On-line process fault diagnosis using fuzzy neural networks

Robotic Systems: Advanced Techniques and Applications

Most viewed content for this Magazine

Most cited content for this Journal