This work proposes three different methods to automatically characterize heterogeneous MPSoCs composed of a variable number of masters (in the form of processors) and hardware accelerators (HWaccs). These hardware accelerators are given as Behavioral IPs (BIPs) mapped as loosely coupled accelerators on a shared bus system (i.e AHB, AXI). BIPs have a distinct advantage over traditional RT-level based IPs given VHDL or Verilog: The ability to generate micro-architectures with different area vs. performance trade-offs from the same description. This is usually done by specifying different synthesis directives in the form of pragmas. This in turn implies that using different mixes of the accelerators’ micro-architectures lead to SoCs with unique area vs. performance trade-offs. Two of the three methods proposed are based on cycle-accurate simulations of the complete MPSoC, while the third method accelerates this exploration by performing it on a Configurable SoC FPGA. Extensive experimental results compare these three methods and highlight their strengths and weaknesses.
The emergence of new horizons in the field of travel assistant management leads to the development of cutting-edge systems focused on improving the existing ones. Moreover, new opportunities are being also presented since systems trend to be more reliable and autonomous. In this paper, a self-learning embedded system for object identification based on adaptive-cooperative dynamic approaches is presented for intelligent sensor’s infrastructures. The proposed system is able to detect and identify moving objects using a dynamic decision tree. Consequently, it combines machine learning algorithms and cooperative strategies in order to make the system more adaptive to changing environments. Therefore, the proposed system may be very useful for many applications like shadow tolls since several types of vehicles may be distinguished, parking optimization systems, improved traffic conditions systems, etc.
27 July 2019 in International Journal of Distributed Sensor Networks
In this work, a two-stage architecture is used to analyze the information collected from several sensors. The first stage makes classifications from partial information of the entire target (i.e. from different points of view or from different kind of measures) using a simple artificial neural network as a classifier. In addition, the second stage aggregates all the estimations given by the ensemble in order to obtain the final classification. Four different ensembles methods are compared in the second stage: artificial neural network, plurality majority, basic weighted majority, and stochastic weighted majority. However, not only reliability is an important factor but also adaptation is critical when the ensemble is working in changing environments. Therefore, the artificial neural network and the plurality majority algorithm are compared against our two proposed adaptive algorithms. Unlike artificial neural network, majority methods do not require previous training. The effects of improving the first stage and how the system behaves when different perturbations are presented have been measured. Results have been obtained from two applications: a realistic one and another simpler one, with more training examples for a more accurate comparison. These results show that artificial neural network is the most accurate proposal, whereas the most innovative proposed stochastic weighted voting is the most adaptive one.
Los robots industriales de seis grados de libertad son empleados, de manera habitual, en células flexibles de fabricación para carga y descarga de máquinas y manipulación de piezas y otros elementos o en células de mecanizado. En este último caso, los robots, al no alcanzar precisiones de posicionamiento elevadas, se relegan a la realización de tareas de pre-mecanizado y desbarbado, o para tareas de manipulación. Para poder mejorar la productividad de las células de mecanizado mediante la redistribución de tareas entre los centros de mecanizado y el robot o entre fases previas de conformado y el robot, es necesario establecer la capacidad real de trabajo del robot considerando las fuerzas del proceso a realizar y teniendo en cuenta la precisión especificada del producto a fabricar mediante el modelado específico de su comportamiento. Para ello, se requiere conocer los parámetros dinámicos del robot, información que no está disponible por parte de los fabricantes. En el trabajo que se presenta, se propone un método experimental para determinar los parámetros dinámicos del robot. El método desarrollado utiliza la señal del movimiento angular que el controlador envía a cada motor como consigna y la compara con el movimiento angular de salidaque realiza el robot, medido con un sensor de alta precisión. De esta manera, se obtiene la función de transferencia para dos grados de libertad, caracterizando la rigidez y el amortiguamiento dinámico de cada articulación. La verificación se ha realizado simulando una célula que mecaniza piezas de aluminio mediante el método de sistemas multicuerpo con formulación en coordenadas naturales mixtas (MBSmc) y considerando una rigidez variable en las articulaciones del robot. En el robot utilizado, se ha montado un husillo que permite realizar fresados periféricos y taladrados. La simulación muestra los resultados con el modelado del proceso completo sin la influencia de los parámetros dinámicos y con ellos. Como resultado del trabajo, se espera determinar el incremento de productividad que se puede conseguir en aplicaciones de mecanizado robotizado o en células de fabricación flexibles.