Abstract
Due to the large amount of pages in Websites it is important to collect knowledge about users' previous visits in order to provide patterns that allow the customization of the Website. In previous work we proposed a multi-agent approach using agents with two different algorithms (associative rules and collaborative filtering) and showed the results of the offline tests. Both algorithms are incremental and work with binary data. In this paper we present the results of experiments held online. Results show that this multi-agent approach combining different algorithms is capable of improving user's satisfaction.

Abstract
The traditional approach for specifying adaptive behavior in embedded applications requires developers to engage in error-prone programming tasks. This results in long design cycles and in the inherent inability to explore and evaluate a wide variety of alternative adaptation behaviors, critical for systems exposed to dynamic operational and situational environments. In this paper, we introduce a domain-specific language (DSL) for specifying and implementing run-time adaptable application behavior. We illustrate our approach using a real-life stereo navigation application as a case study, highlighting the impact and benefits of dynamically adapting algorithm parameters. The experiments reveal our approach effective, as such run-time adaptations are easily specified in a higher level by the DSL, and thus at a lower programming effort than when using a general-purpose language such as C.

Abstract
Due to the large number of optimizations provided in modern compilers and to compiler optimization specific opportunities, a Design Space Exploration (DSE) is necessary to search for the best sequence of compiler optimizations for a given code fragment (e. g., function). As this exploration is a complex and time consuming task, in this paper we present DSE strategies to select optimization sequences to both improve the performance of each function and reduce the exploration time. The DSE is based on a clustering approach which groups functions with similarities and then explore the reduced search space provided by the optimizations previously suggested for the functions in each group. The identification of similarities between functions uses a data mining method which is applied to a symbolic code representation of the source code. The DSE process uses the reduced set identified by clustering in two ways: as the design space or as the initial configuration. In both ways, the adoption of a pre-selection based on clustering allows the use of simple and fast DSE algorithms. Our experiments for evaluating the effectiveness of the proposed approach address the exploration of compiler optimization sequences considering 49 compilation passes and targeting a Xilinx MicroBlaze processor, and were performed aiming performance improvements for 41 functions. Experimental results reveal that the use of our new clustering-based DSE approach achieved a significant reduction on the total exploration time of the search space (18 x over a Genetic Algorithm approach for DSE) at the same time that important performance speedups (43% over the baseline) were obtained by the optimized codes.

Abstract
A common migration path for applications to high-performance multicore architectures relies on code annotations with concurrent semantics. Some annotations, however, are very target architecture specific and thus highly non-portable. In this paper we describe a source-to-source code transformation system that allows programmers to specify transformations using an aspect-oriented domain specific language - LARA. LARA allows programmers to specify strategies to search large code transformation design spaces while preserving the original source code. As the experimental results reveal, this approach leads to a substantial reduction in code maintenance costs, and promotes the portability of both programmers and performance. Copyright © 2014 ACM.

Abstract
Embedded systems are severely resource constrained and thus can benefit from adaptations to enhance their functionality in highly dynamic operating conditions. Adaptations, however, often require additional programming effort or complex architectural solutions, resulting in long design cycles, troublesome maintenance, and impractical use for legacy applications. In this letter, we introduce an adaptation logic for the dynamic reconfiguration of embedded applications and its implementation via a domain-specific language. We illustrate the approach in a real-world case study of a navigation application for avionics. © 2014 IEEE.

Abstract
In this paper we present a clustering-based selection approach for reducing the number of compilation passes used in search space during the exploration of optimizations aiming at increasing the performance of a given function and/or code fragment. The basic idea is to identify similarities among functions and to use the passes previously explored each time a new function is being compiled. This subset of compiler optimizations is then used by a Design Space Exploration (DSE) process. The identification of similarities is obtained by a data mining method which is applied to a symbolic code representation that translates the main structures of the source code to a sequence of symbols based on transformation rules. Experiments were performed for evaluating the effectiveness of the proposed approach. The selection of compiler optimization sequences considering a set. of 49 compilation passes and targeting a Xilinx Nlicrofilaze processor was performed aiming at latency improvements for 41 functions from Texas Instruments benchmarks. The results reveal that the passes selection based on our clustering method achieves a significant gain on execution time over the full search space still achieving important performance speedups.