Browsing by Author "Nair, Arvind"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Integrating recommender systems into domain specific modeling tools
    (2017-03-09) Nair, Arvind; Hill, James Haswell; Ning, Xia N.; Raje, Rajeev R.; Fang, Shiaofen
    This thesis investigates integrating recommender systems into model-driven engineering tools powered by domain-specific modeling languages. The objective of integrating recommender systems into such tools is overcome a shortcoming of proactive modeling where the modeler must inform the model intelligence engine how to progress when it cannot automatically determine the next modeling action to execute (e.g., add, delete, or edit). To evaluate our objective, we integrated a recommender system into the Proactive Modeling Engine, which is a add-on for the Generic Modeling Environment (GME). We then conducted experiments to both subjective and objectively evaluate the enhancements to the Proactive Modeling Engine. The results of our experiments show that integrating recommender system into the Proactive Modeling Engine results in an Average Reciprocal Hit-Rank (ARHR) of 0.871. Likewise, the integration results in System Usability Scale (SUS) rating of 77. Finally, user feedback shows that the integration of the recommender system to the Proactive Modeling Engine increases the usability and learnability of domain-speci c modeling tools.
  • Thumbnail Image
    Item
    A VERY FAST CONSTRAINT SOLVER INTERPRETER FOR EVALUATING MODEL CONSTRAINTS
    (Office of the Vice Chancellor for Research, 2016-04-08) Nair, Arvind; Hill, James H.
    Model-Driven Engineering (MDE) facilitates building solutions in many enterprise application domains through the systematic use of graphical languages called domain-specific modeling languages (DSMLs). MDE tools, such as the Generic Modeling Environment (GME) and the Generic Eclipse Modeling System (GEMS), enable end-users to rapidly create such custom DSMLs. One advantage of using DSMLs is its correct-by-construction characteristics, which is provided by domain-specific constraints defined within these custom languages. The constraints, written in Object Constraint Language (OCL), are evaluated during and after model construction using a constraint checker. For example, GME provides a Constraint Manager (CM) that evaluate the constraints defined by a DSMLs against its models. Unfortunately, our experience has shown that the constraint checkers provided by MDE tools do not scale to large models (i.e., models that have 10s of 1000s of model elements and 10s of 100s of constraints). Our research therefore focuses on developing a very fast OCL constraint solver that can address the current shortcomings of existing OCL constraint solvers in the context of GME. Our design approach leverages best practices in software design patterns, caching, and multi-threading to improve its performance and scalability. Initial results of our work show that for small models (e.g., 10s to 100s of elements), the traditional constraint solvers run slightly faster than our approach. For models with more than 1000s of elements, our approach is twice as fast, and performs exponential better as the size and complexity of the models increase.