Active Magnetic Bearing uses electromagnetic force, generated by current carrying coils to levitate the rotor freely. The application of active magnetic bearing embedded devices like Maglev Train, Fly wheel based ener...
详细信息
ISBN:
(纸本)9781538684931
Active Magnetic Bearing uses electromagnetic force, generated by current carrying coils to levitate the rotor freely. The application of active magnetic bearing embedded devices like Maglev Train, Fly wheel based energy storage system, Micro precision devices, Blood pump etc. are increasing in industries because of rapid progress happened in the electronics sector and controller structure. Finite Element is a method which allows numerical modelling and analysis of this kind of systems. In this paper, a 2D computersimulation of an axial active magnetic bearing system has been carried out using finite element software COMSOL. The changes in flux density and force are plotted.
The proceedings contain 6 papers. The topics discussed include: on the power consumption modeling for the simulation of heterogeneous HPC clouds;cloudlightning simulation and evaluation roadmap;a self-healing approach...
ISBN:
(纸本)9781450327145
The proceedings contain 6 papers. The topics discussed include: on the power consumption modeling for the simulation of heterogeneous HPC clouds;cloudlightning simulation and evaluation roadmap;a self-healing approach towards autonomic cloud services;the cloudlightning approach to cloud-user interaction;integrating dataflow engines in self-organization self-management cloud architectures;and imaging data management system.
Modern computing architectures exhibit increasing parallelism. Therefore, dynamic loop scheduling (DLS) plays an increasing role in the performance optimization of parallel applications executing on the modern computi...
详细信息
ISBN:
(纸本)9781538625880
Modern computing architectures exhibit increasing parallelism. Therefore, dynamic loop scheduling (DLS) plays an increasing role in the performance optimization of parallel applications executing on the modern computing architectures. In the previous decades, there was a large body of research concerning DLS techniques. Reproduction of the DLS experiments is significant for ensuring the trustworthiness of the DLS techniques implementation in modern scheduling tools or within new scientific applications. The results of executing the implemented DLS techniques are expected to be in agreement with the results reported in earlier work. The present work is a step towards the reproduction of the experiments that introduced the well-known DLS technique named factoring (FAC). Studying scheduling techniques via simulation is favorable compared to native execution to have control over all the factors that may affect the performance. The use of simulation in this work is essential for the reproduction of the scheduling experiments performed on computing systems that no longer exist. This work shows that the self scheduling technique with matrix multiplication kernel has a significantly poorer performance on the modern system considered in this study than on the past system.
For the sake of better accuracy, the face recognition model is becoming larger and larger, which makes them difficult to be deployed on embeddedsystems. This work proposes an effective model compression method using ...
详细信息
For the sake of better accuracy, the face recognition model is becoming larger and larger, which makes them difficult to be deployed on embeddedsystems. This work proposes an effective model compression method using knowledge distillation, where a fast student model is trained under the guidance of a complex teacher model. Firstly, different loss combinations and network architectures are analyzed through comprehensive experiments to find the most effective approach. To augment the performance, the feature layer is further normalized to make the optimization objective consistent with cosine similarity metric. Moreover, a teacher weighting strategy is proposed to address the issue when teacher provides wrong guidance. Experimental results show that the student model built by our approach can surpass the teacher model while achieving 3× acceleration.
The proceedings contain 46 papers. The topics discussed include: cycle-accurate performance modeling in an ultra-fast just-in-time dynamic binary translation instruction set simulator;a trace-based scenario database f...
ISBN:
(纸本)9781424479382
The proceedings contain 46 papers. The topics discussed include: cycle-accurate performance modeling in an ultra-fast just-in-time dynamic binary translation instruction set simulator;a trace-based scenario database for high-level simulation of multimedia MP-SoCs;a library of dual-clock FIFOs for cost-effective and flexible MPSoCs design;transparent sampling;design of a flexible high-speed FPGA-based flow monitor for next generation networks;a fully programmable FSM-based processing engine for gigabytes/s header parsing;empirical evaluation of data transformations for network infrastructure applications;design environment for the support of configurable network interfaces in NoC-based platforms;an efficient realization of forward integer transform in H.264/AVC intra-frame encoder;SIMD performance in software based mobile video coding;and real-time stereo vision system using semi-global matching disparity estimation: architecture and FPGA-implementation.
In the last decade, different computing paradigms and modelling frameworks for the description and simulation of biochemical systems based on stochastic modelling have been proposed. From a computational point of view...
详细信息
ISBN:
(纸本)9781509060580
In the last decade, different computing paradigms and modelling frameworks for the description and simulation of biochemical systems based on stochastic modelling have been proposed. From a computational point of view, many simulations of the model are necessary to identify the behaviour of the system. The execution of thousands of simulations can require huge amount of time, therefore the parallelization of these algorithms is highly desirable. In particular, models that consider the size of volumes and objects involved in the reaction are very time-consuming, since many rules should be considered to take into account the position of the different molecules. In this work we present an implementation of a stochastic space-aware simulator which exploits the benefit and features of hybrid low-power computing architectures. This work shows that the simulator dynamic probabilistic approach to select possible chemical reactions can be applied and implemented in hybrid low-power low-cost architectures as well as current industry high-end servers.
The main function of range sensory systems under a given dynamic environment is to detect, discriminate and track a particular target for surveillance in case of a friendly target or an enemy target interception. The ...
详细信息
The main function of range sensory systems under a given dynamic environment is to detect, discriminate and track a particular target for surveillance in case of a friendly target or an enemy target interception. The combination of two or more sensors will provide better position estimate than a single sensor. In this paper, the advantages of the multi sensor data fusion is presented and compared over conventional single sensor tracking. The state estimation techniques are utilized to enhance position accuracy in a single and multi-sensor environment. The performance of each state estimator is evaluated by considering different target motions along with their nonlinear characteristics. The state estimators presented here varies from simple linear filters such as fixed gain and Kalman filters to complex nonlinear filters such as Particle filter. Two widely used Extended Kalman filter based fusion architectures such as measurement fusion and state vector fusion are explored. The data is simulated from two ground based sensors RADAR and FLIR (forward looking infra red) to examine the fusion process. The RMS error is computed in range, azimuth, and elevation angles. A complete mathematical modeling and simulation is implemented in MATLAB. It is found that fusion architectures have demonstrated better performance in tracking accuracy.
Summary form only given, as follows. The complete presentation was not made available for publication as part of the conference proceedings. The pervasive diffusion of embedded and cyberphysical systems connected to f...
详细信息
ISBN:
(纸本)9781538634387;9781538634370
Summary form only given, as follows. The complete presentation was not made available for publication as part of the conference proceedings. The pervasive diffusion of embedded and cyberphysical systems connected to form the internet of things brings new security challenges. These devices are usually deployed in a hostile environment, where an attacker could easily have physical access, and their life span can be pretty long, thus posing the problem of long term security. Yet, security functionalities should fit the tight area and energy budget available in these devices. To address these challenges, researchers are investigating several research directions, including novel constructions withstanding future attacks carried out by quantum computational power, novel and more powerful physical attacks and new approaches to defeat them. It is thus of crucial importance that designers of embeddedsystems are aware of the most important security challenges which need to be addressed during design and that they have the proper basic blocks and tools to solve them in a correct and effective way. This special session covers challenges and opportunities related with design and deployment of secure embeddedsystems in several platforms. Talks in the session will present more targeted side channel attacks, more efficient architectures for implementing elliptic curve cryptography (ECC) and number theoretic transform (NTT), a crucial block for implementing quantum resistant algorithms, and will summarize current research effort in secure processors design and in the use of reconfigurable architectures for secure applications.
Many safety and infotainment applications of Vehicular Ad hoc Networks (VANETs) depend on the robustness and reliability of the routing protocols. There are many routing protocols proposed for VANETs in the literature...
详细信息
Vector matrix multiplication computation underlies major applications in machine vision, deep learning and scientific simulation. These applications require high computational speed and are run on platforms that are s...
详细信息
Vector matrix multiplication computation underlies major applications in machine vision, deep learning and scientific simulation. These applications require high computational speed and are run on platforms that are size, weight and power constrained. With the transistor scaling coming to an end, existing digital hardware architectures will not be able to meet this increasing demand. Analog computation with its rich set of primitives and inherent parallel architecture can be faster, more efficient and compact for some of these applications. One such primitive is a memristor-CMOS crossbar array based vector matrix multiplication. In this paper, we develop a memristor-CMOS analog co-processor architecture that can handle floating point computation. The crossbar array is based on a TaOx memristor device. To demonstrate the working of the analog co-processor at a system level, we use a new tool developed by Cadence and Mathworks called PSpice systems Option which performs integrated co-simulation of MATLAB/Simulink and PSpice. It is shown that the analog co-processor has a superior performance when compared to other processors. Using the new PSpice systems Option tool, various application simulations for image processing and solution to partial differential equations are performed on the analog coprocessor model.
暂无评论