## Towards New Languages for Systems Modelling

Venue: | Proceedings of the 42’nd Scandinavian Simulation Conference SIMS’02, September 26–27, 2002 |

Citations: | 3 - 0 self |

### BibTeX

@INPROCEEDINGS{Hyötyniemi_towardsnew,

author = {Heikki Hyötyniemi},

title = {Towards New Languages for Systems Modelling},

booktitle = {Proceedings of the 42’nd Scandinavian Simulation Conference SIMS’02, September 26–27, 2002},

year = {}

}

### OpenURL

### Abstract

This paper discusses what the future modeling environments could look like. To tackle with ever increasing complexity of process models, higher level of abstraction needs to be exploited. It is noticed that the most natural way to connect low-level models to high-level tools is simulation. Based on such semantic grounding, new description formalisms can perhaps be implemented. 1. NEW CHALLENGES Because of the fieldbuses, and because of the modern sensor technology, etc., the availability of the industrial processes has been enhanced considerably. There is an explosion of structureless data facing us. The problem is that there do not exist enough domain area experts that could analyze the data and rewrite the models for the processes appropriately. Automatic modeling systems would be invaluable – systems that could not only adapt the model parameters within a predetermined structural framework, but also determine the structures themselves without too much human intervention. The modeling problems are attacked by utilizing different kinds of description formalisms. One major approach is to define more and more general formalisms (like Java language) for system description: In such environments, anything can be expressed, but this means that large numbers of expressions are needed

### Citations

3969 |
Artificial intelligence: A modern approach. Upper Saddle River
- Russell, Norvig
- 2003
(Show Context)
Citation Context ...n be adapted according to the observed data, so that the numeric weights can change more or less automatically to better match the real behavior. This facilitates getting nearer to the agent paradigm =-=[1]-=-: Independent actors outside the environment can be integrated in the model as long as they deliver the data promptly. The consequences of this are elaborated on below. 2 Perhaps this similarity betwe... |

1659 |
The sciences of the artificial
- Simon
- 1962
(Show Context)
Citation Context ...rominent view is offered by Herbert A. Simon: A complex system consists of a hierarchy, where the structural elements are more or less independent and interact only through some well-defined channels =-=[2]-=-. How to bind the above kinds of substructures into a manageable hierarchical structure? There seems to exist a close connection between automation systems and cognitive systems what comes to the unde... |

118 |
A New Kind of Science. Wolfram
- Wolfram
- 2002
(Show Context)
Citation Context ...f multivariate statistical structures – these issues are discussed next. First, let us look at the modeling problem from a wider perspective. 2. COMPLEX SYSTEMS AND EMERGENCE Stephen Wolfram proposes =-=[10]-=- that everything in the Nature could be explained in terms of simple “programs” that are just iterated long enough – complexity is an emergent phenomenon. However, despite his intuitively appealing cl... |

10 |
Multivariate regression – techniques and tools
- Hyötyniemi
- 2001
(Show Context)
Citation Context ...tomation engineering. If one is lucky, the dependencies are (clusterwise) linear (or linearizable), and the very efficient multivariate statistical methods like PCA, PLS and CCR can be exploited (see =-=[7]-=-). Rather than searching the underlying latent variables explaining the connections between u and y, as is normally done in multivariate analysis, “latent parameters”, meaningful combinations of the u... |

7 |
On mental images and “computational semantics
- Hyötyniemi
(Show Context)
Citation Context ...ion between automation systems and cognitive systems what comes to the underlying data structures – many of the mysteries of the mental machinery can be attacked in this framework 2 . As explained in =-=[4]-=-, for example, in a cognitive domain the data clusters within the observation space can be interpreted as categories or concepts and the substructure dimensions as attributes or chunks modifying the c... |

3 |
From Intelligent Models to Smart Ones
- Hyötyniemi
(Show Context)
Citation Context ...he assumption of local linearity also often holds: The effect of small parameter changes in the final behavioral phenomena can be modeled using piecewise linear approximations. It can be claimed (see =-=[5]-=-) that at all levels of process analysis, the meaningful phenomena can be characterized in the high-dimensional observation data space as follows: There exist clusters with linear substructures. The c... |

3 |
Emergent Phenomena and Optimization of Parameters
- Hyötyniemi
(Show Context)
Citation Context ...g latent variables explaining the connections between u and y, as is normally done in multivariate analysis, “latent parameters”, meaningful combinations of the underlying parameters are modeled (see =-=[9]-=-). 4. STRUCTURE IN PROCESS DATA This far, what has been reached is a statistical data mining problem – is this the best one can do, or can we reach higher levels in the dialectic hierarchy between sto... |

2 |
On unsolvability of nonlinear systems stability
- Hyötyniemi
- 1997
(Show Context)
Citation Context ...t possible to avoid crispness? At least in principle, some kind of numeric languages can be defined – but it seems that continuity on the low level does not assure continuity on the larger scale (see =-=[3]-=-). Extensions of fuzzy logic, like “computing with words”, seem to lack the expressional power of symbolic representations when the conceptual structures are collapsed ontothe real axis. Simple pruni... |

2 |
Explorations in “Naturalistic Formalisms
- Hyötyniemi
(Show Context)
Citation Context ...is also inherent in the structures – indeed, one way to formalize the underlying ontology assumption is in terms of fuzzy subsets, where the one-way hierarchy changes into a two-way relationship (see =-=[6]-=-). The language is more like a static data description formalism rather than a traditional algorithmic programming language, facilitating some kind of pattern matching rather than procedural, sequenti... |

2 |
Reality and Truth in the Semantic Web
- Hyötyniemi
(Show Context)
Citation Context ...haps even automatic (self)organization of the process structures and parameters. On a still wider scale, the Semantic Web initiative can perhaps offer access to the global resources of expertise (see =-=[8]-=-). On the lower level, when studying individual subprocess, the presented approach makes it possible to implement new kinds of model optimization strategies and controller tuning schemes (see [9]). 7.... |