Meta-Model Application

We can think of mem-modelling as concerning the discovery of models, and there has been rapidly increasing interest in applications over the last few years as practitioners look to exploit the wealth of alternative methods to improve 

In a typical QSAR publication it is now more usual to see some attempt to compare modelling methods against one or more datasets.Some workers have developed automated systems to do this, describing it as combi or combinatorial QSAR.  

The meta-modelling approach can automate the surveying of model space and partition local models. An ensemble of models can be more stable and reliably predictive. Since a key element of the QSAR practitioner s expertise is the selection of the appropriate method, meto-modelling can lead to more reliable automation of model discovery, as is often required in the context of large and continuously operated screening campaigns. 

In stacking, an ensemble of models is built, using different methods, and a model of the models is created, which weights the predictions from the different models. 

Temporal, or time-series, QSAR manages updating of QSAR models explicitly and is well suited to the continuous data generation processes built into the large pharmaceutical company infrastructure. 

---

Placed in a completely different and far more fixedly structured domain, the results of the DWQ project were not directly transferable to the CRC 476 IMPROVE. For the support of creative design processes, different approaches were - and are - necessary. Yet the approach of applying methods of meta modeling in domain and application models was expected to succeed there as well. Especially the use of ConceptBase, as described before, was used to achieve a sound conceptual and ontological basis for the modeling aspects, the process extensions to Data Warehousing as researched in the subproject Cl, and the meta process and product repository of the subproject B1. 

While the Meta Model is highly useful during model design, it is less relevant for practical applications. Under certain conditions, the Meta Model may even prove harmful, as its highly abstract concepts may confuse an inexperienced user rather than support him/her. For that reason, the interconnectivity between the Meta Model and the C EDM needs to be minimized such that they can be separated easily, once the design has been completed. To this end, the classes and relations defined in Meta Model are not directly used within the individual submodels of the C EDM. Rather, they are redefined and subsequently linked to the original concepts in the Meta Model. Thus, only the links to the Meta Model need to be disconnected if a stand-alone usage of the C EDM is desired. 

In principle, the model framework allows to include the entirety of aspects relevant to all possible applications in a single application-independent work process model, provided that its meta-model, i.e. the type-specific module, features all required model elements. This approach is not feasible because it would result in unmanageable complexity of the Process Ontology. Furthermore, a software application tailored to a certain task can offer better support for modeling application-specific aspects of a work process than a general-purpose work process modeling tool which aims at application-independent models. Thus, the application-independent work process model in the work process modeling tool should be restricted to those aspects which are relevant for several applications. 

When properly developed and implemented, ontologies can serve as the backbone for knowledge-based applications. They offer the possibility to stmcture the knowledge base by modelling the context in which knowledge is viewed. Domain (meta)models are made explicit and knowledge (re-)use is made possible... 

Safety cases have been increasingly accepted as an assurance technique by many industrial sectors, e.g. defence, air traffic control, railway, automobile and medical devices [1]. In the past decade, there are considerable research and application efforts placed on safety case notations, safety case life cycles, argument patterns, safety case tools and argument and evidence meta-models. However, a supportive element in the safety case development process, the strategy for describing the relationships between safety claims of different levels has not been emphasized as much as other key safety case elements, e.g. claims and evidence items. 

The main objective of this article is to promote the approach of meta-models or integrated-degradation models for the decision in the context of optimization of condition-based maintenance of structures and infrastructures. The construction of the state-dependent degradation model will be discussed within an application of the cracking of a submerged concrete structure subject to corrosion. Numerical experiments will be conducted for... 

In this article the Meta-Model approach (El Hajj et al. 2014) is apphed and discussed within an application to the cracking of a submerged concrete structure subject to corrosion. The degradation model is based on two correlated processes constructed by NDT data. Expert knowledge is introduced to reflect the main useful degradation properties that the model should tackle for decision-making. This allows both to simplify the construction and the fitness of the model to the data and to overcome some limits in the current practices in Civil Engineering (here the correlation between the crack width and the corrosion rate). We are aware that the construction of the model and, of course, the performance study is not based on field data, but we are confident in the philosophy of the approach and hope that it will help in the future data collection. 

Ghiorso M. S. and Carmichael L S. E. (1980). A regular solution model for meta-aluminous silicate liquids Applications to geothermometry, immiscibility, and the source regions of basic magma. Contrib. Mineral Petrol, 71 323-342. 

With regard to relevant statistical methodologies, it is possible to dehne 2 situations, which can be termed a meta-analysis context and a shrinkage estimation context. Similar statistical models, in particular random-effects models, may be applicable in both situations. However, the results of such a model will be used somewhat differently. 

The semi-specific, visualization uses additional information about certain concepts, instances and their relationships to achieve a more conclusive presentation. As an example, the ordered composition hierarchy (tree) in Fig. 4.10 displays the composition and realization hierarchy of an extruder. All information necessary for this presentation is stored as meta-level annotations of the appropriate concepts Extruder, Functional Zone and Screw Element), and their respective relations. Thus, the same presentation can be easily applied to any other model fragment that conforms to the same or a similar structure. Another possible application is to present a flowsheet as a network of devices and streams, by using a different kind of annotations. 

E. Bouzom, C. Laveille, H. Merdjan, and R. Jochemsen, Use of nonlinear mixed effect modeling for the meta-analysis of preclinical pharmacokinetic data application to S 20342 in the rat. J Pharm Sci 89 603-613 (2000). 

---