Abstract

Abstract
This paper presents a novel approach to accelerate program execution by mapping repetitive traces of executed instructions, called Megablocks, to a runtime reconfigurable array of functional units. An offline tool suite extracts Megablocks from microprocessor instruction traces and generates a Reconfigurable Processing Unit (RPU) tailored for the execution of those Megablocks. The system is able to transparently movebcomputations from the microprocessor to the RPU at runtime. A prototype implementation of the system using a cacheless MicroBlaze microprocessor running code located in external memory reaches speedups from 2.2x to 18.2x for a set of 14 benchmark kernels. For a system setup which maximizes microprocessor performance by having the application code located in internal block RAMs, speedups from 1.4x to 2.8x were estimated.

Abstract

Abstract
Recommender Systems are a hot application area these days, made popular by well known web sites. The problem of predicting user preferences is very demanding from the data mining algorithm design point of view, but it also poses challenges to evaluation and monitoring. Moreover, there is a lot of information that can be exploited, from clickstreams and background information to musical content and social interaction. As data grows and recommendation requests must be answered in a split second, online and agile solutions must be implemented. In this talk we will give a brief introduction to binary recommender systems, describe a particular hybrid application to music recommendation - from algorithm to online evaluation, and refer to context aware and online recommender algorithms. © 2013 ACM.

Abstract
Medical information produced in hospitals is, simultaneously, used (1) to support health care provided to patients, (2) in research work performed by internal and external health professionals, and (3) as legal proof with various objectives. The co-existence of electronic and paper health information, the integration constraints of the various computer applications, and the storage of massive volumes of retrospective paper-based patient records are dominant concerns for São João Hospital Center (SJHC). These problems must be considered in the adoption of an Electronic Patient Record (EPR) in order to ensure that hospitals and patients fully benefit from the technological investments. The contribution of this chapter is the design and conduction of a (re)use study, which consisted of an analysis of the paper-based records management activities and of the patients' records content. A survey on the (re) use of the paper-based patient records has been conducted in order to characterize the (re)use in terms of objective and type of hospital encounter, and documents accessed were identified and organized in an access frequency table. The results support the paper-based patient records strategy to implement in SJHC integrated in the Hospital EPR adoption project. © 2013, IGI Global.

Abstract
In this paper a new heuristic is proposed to solve general multi-level lot-sizing and scheduling problems. The idea is to cross-fertilize the principles of the meta-heuristic Variable Neighborhood Decomposition Search (VNDS) with those of the MIP-based Fix&Optimize heuristic. This combination will make it possible to solve the kind of problems that typically arise in the consumer goods industry due to sequence-dependent setups and shifting bottlenecks. In order to demonstrate the strength of this procedure, a GLSP variant for multiple production stages is chosen as a representative. With the help of artificial and real-world instances, the quality of the solution as well as the computational performance of the new procedure is tested and compared to a standard MIP-solver.