Research

Research

81539 bookmarks
Newest
Towards Reinforcement Learning for In-Place Model Transformations | IEEE Conference Publication | IEEE Xplore
Towards Reinforcement Learning for In-Place Model Transformations | IEEE Conference Publication | IEEE Xplore
Model-driven optimization has gained much interest in the last years which resulted in several dedicated extensions for in-place model transformation engines. The main idea is to exploit domain-specific languages to define models which are optimized by applying a set of model transformation rules. Objectives are guiding the optimization processes which are currently mostly realized by meta-heuristic searchers such as different kinds of Genetic Algorithms. However, meta-heuristic search approaches are currently challenged by reinforcement learning approaches for solving optimization problems. In this new ideas paper, we apply for the first time reinforcement learning for in-place model transformations. In particular, we extend an existing model-driven optimization approach with reinforcement learning techniques. We experiment with value-based and policy-based techniques. We investigate several case studies for validating the feasibility of using reinforcement learning for model-driven optimization and compare the performance against existing approaches. The initial evaluation shows promising results but also helped in identifying future research lines for the whole model transformation community.
Towards Reinforcement Learning for In-Place Model Transformations | IEEE Conference Publication | IEEE Xplore
Midgar: Creation of a Graphic Domain-Specific Language to Generate Smart Objects for Internet of Things Scenarios Using Model-Driven Engineering | IEEE Journals & Magazine | IEEE Xplore
Midgar: Creation of a Graphic Domain-Specific Language to Generate Smart Objects for Internet of Things Scenarios Using Model-Driven Engineering | IEEE Journals & Magazine | IEEE Xplore
Currently, we have around us many Smart Objects. With the use of these objects, we can obtain benefits in our daily lives, as well as recommendations and help when we travel. Alternatively, we may increase and improve our industrial processes through the automation of certain tasks. Notwithstanding, we need to use specific software or to develop our own applications. Nevertheless, the main problem arises when we need to develop our own application because we need to save money, or in other cases, the existing applications are not adapted to us. In this case, it is possible that we need to learn new things, the money will then be spent, and such a process is likely to involve problems related to the Software Crisis. So, the main motivation is to create an environment which can reuse the previous knowledge and help people without knowledge about programming to create Smart Objects. Then, the research question of this paper is the following: Could we enable the creation of Smart Objects in an easy and efficient way for people who do not have programming skills? As a possible solution, we have developed a graphic Domain-Specific Language using the Midgar platform. In order to validate our proposal, we make an evaluation split into different phases; the first one consisted in measuring data obtained from participants when they were performing a specific task, and the second one consisted of a survey to collect their opinions about our proposal. Moreover, we also did a comparison of the measured data between two graphical editors and two different participant profiles according to their knowledge about Smart Objects.
Midgar: Creation of a Graphic Domain-Specific Language to Generate Smart Objects for Internet of Things Scenarios Using Model-Driven Engineering | IEEE Journals & Magazine | IEEE Xplore