一种基于离散Hopfield神经网络的RTOS功耗优化方法

RTOS(Real-Time Operating System,实时操作系统)是SoC(System-on-a-Chip,系统芯片或片上系统)的一个重要组成部分,其功耗一般约占整个系统功耗30～40%的比例,而基于软/硬件划分的RTOS功耗优化方法(简称RTOS-Power划分)能够明显地减少SoC的功耗.因此,文中首先引入了RTOS-Power划分问题的一个新模型,这有助于理解RTOS-Power划分的本质.然后,提出了一种基于离散Hopfield神经网络的RTOS-Power划分方法,重新定义了神经网络的神经元表示、能量函数、运行方程和系数.最后,对该方法进行了仿真实验,并同遗传算法和蚂蚁算法进行了性能比较.实验结果表明:该文提出的方法能够以相对较小的代价(FPGA开销小于4K个可编程逻辑块)取得高达60%的功耗节省,同时,与纯软件实现的RTOS相比,系统性能也得到了相应的提高.     

Dynamically reconfigurable hardware-software architecture for partitioning networking functions on the SoC platform

We present an issue of the dynamically reconfigurable hardware-software architecture which allows for partitioning networking functions on a SoC (System on Chip) platform. We address this issue as a partition problem of implementing network protocol functions into dynamically reconfigurable hardware and software modules. Such a partitioning technique can improve the co-design productivity of hardware and software modules. Practically, the proposed partitioning technique, which is called the ITC (Inter-Task Communication) technique incorporating the RT-IJC² (Real-Time Inter-Job Communication Channel), makes it possible to resolve the issue of partitioning networking functions into hardware and software modules on the SoC platform. Additionally, the proposed partitioning technique can support the modularity and reuse of complex network protocol functions, enabling a higher level of abstraction of future network protocol specifications onto the SoC platform. Especially, the RT-IJC² allows for more complex data transfers between hardware and software tasks as well as provides real-time data processing simultaneously for given application-specific real-time requirements. We conduct a variety of experiments to illustrate the application and efficiency of the proposed technique after implementing it on a commercial SoC platform based on the Altera’s Excalibur including the ARM922T core and up to 1 million gates of programmable logic.     

Soft computing framework for intelligent human–machine system design,simulation and optimization

 This paper proposes a novel soft-computing framework for human–machine system design and simulation based on the hybrid intelligent system techniques. The complex human–machine system is described by human and machine parameters within a comprehensive model. Based on this model, procedures and algorithms for human–machine system design, economical/ergonomic evaluation, and optimization are discussed in an integrated CAD and soft-computing framework. With a combination of individual neural and fuzzy techniques, the neuro-fuzzy hybrid soft-computing scheme implements a fuzzy if-then rules block for human–machine system design, evaluation and optimization by a trainable neural fuzzy network architecture. For training and test purposes, assembly tasks are simulated and carried out on a self-built multi-adjustable laboratory workstation with a flexible motion measurement and analysis system. The trained neural fuzzy network system is able to predict the operator's postures and joint angles of motion associated with a range of workstation configurations. It can also be used for design/layout and adjustment of human assembly workstations. The developed system provides a unified, intelligent computational framework for human–machine system design and simulation. Case studies for workstation system design and simulation are provided to illustrate and validate the developed system.     

一种针对动态部分可重构SoC软硬件划分的高效MILP模型

异构片上系统(System-on-Chip,SoC)在同一芯片上集成了多种类型的处理器,在处理能力、尺寸、重量、功耗等各方面有较大优势,因此在很多领域得到了应用。具有动态部分可重构特性的SoC(Dynamic Partial Reconfigurability SoC,DPR-SoC)是异构SoC的一种重要类型,这种系统兼具了软件的灵活性和硬件的高效性。此类系统的设计通常涉及到软硬件协同问题,其中如何进行应用的软硬件划分是保证系统实时性的关键技术。DPR-SoC中的软硬件划分问题可归类为组合优化问题,问题目标是获得调度长度最短的调度方案,包括任务映射、排序和定时。混合整数线性规划(Mixed Integer Linear Programming,MILP)是求解组合优化问题的一种有效方法;然而,将具体问题建模为MILP模型是求解问题的关键一环,不同建模方式对问题求解时间有重要影响。已有针对DPR-SoC软硬件划分问题的MILP模型存在大量变量和约束方程,对问题求解时间产生了不利影响;此外,其假设条件过多,使得求解结果与实际应用不符。针对这些问题,提出了一种新颖的MILP模型,其极大地降低了模型复杂度,提高了求解结果与实际应用的符合度。将应用建模成DAG图,并使用整数线性规划求解工具对问题进行求解。大量求解结果表明,新的模型能够有效地降低模型复杂度,缩短求解时间;并且随着问题规模的增大,所提模型在求解时间上的优势表现得更加显著。     

SoC设计中一种软硬件划分的性能评价方法

介绍了一种在SoC系统级设计中对软硬件划分进行评价的方法。系统层设计中，对设计方案的性能、成本和功耗的准确估计，是取得高质量设计的必要条件。讨论了基于平台的设计中，利用基于事务级仿真的方法对系统的软硬件划分结果进行评价的方法。     

A Simplified Neural Network for Linear Matrix Inequality Problems

A simplified neural network model is proposed to solve a class of linear matrix inequality problems. The stability and solvability of the proposed neural network are analyzed and discussed theoretically. In comparison with the previous neural network models (Lin and Huang, Neural Process Lett 11:153–169, 2000; Lin et al., IEEE Trans Neural Netw 11:1078–1092, 2000), the simplified one is composed of two layers rather than three layers, and the neuron array in each layer is triangular rather than square. The proposed approach can therefore reduce the complexity of the neural network architecture. In addition, the simplified neural network can also be extended to solve multiple linear matrix inequalities with specific constraints, which enlarges the application domain of the proposed approach. Finally, examples are given to illustrate the effectiveness and efficiency of the simplified neural network.     

Football Predictions Based on a Fuzzy Model with Genetic and Neural Tuning

A model is proposed for predicting the result of a football match from the previous results of both teams. This model underlies the method of identifying nonlinear dependencies by fuzzy knowledge bases. Acceptable simulation results can be obtained by tuning fuzzy rules using tournament data. The tuning procedure implies choosing the parameters of fuzzy-term membership functions and rule weights by a combination of genetic and neural optimization techniques. __________ Translated from Kibernetika i Sistemnyi Analiz, No. 4, pp. 171–184, July–August 2005.     

Bearing parameter identification of rotor–bearing system using clustering-based hybrid evolutionary algorithm

A new bearing parameter identification methodology based on global optimization scheme using measured unbalance response of rotor–bearing system is proposed. A new hybrid evolutionary algorithm which is a clustering-based hybrid evolutionary algorithm (CHEA), is proposed for global optimization scheme to improve the convergence speed and global search ability. Clustering of individuals by using a neural network is introduced to evaluate the degree of mature of genetic evolution. After clustering-based genetic algorithm (GA), local search is carried out for each cluster to judge the convexity of each cluster. Finally, random search is adapted for extrasearching to find a potential global candidate, which could be missed in GA and local search. The proposed methodology can identify not only unknown bearing parameters but also unbalance information of disk by simply setting them as unknown parameters. Numerical example and experimental results were used to verify the effectiveness of the proposed methodology.     

Learning and relocation capabilities of a CAM-brain machine

Two techniques to enhance the capabilities of a CAM-brain machine are proposed. The first is a learning capability that is realized by providing a “decay register” in each neuron cell. The second is a neural network relocation capability that makes it possible to compact the evolved neural network and make room for further evolution. Both techniques operate in an extrinsic manner and are considered supplementary to the intrinsic evolutionary capability of a CAM-brain. This work was presented, in part, at the Third International Symposium on Artificial Life and Robotics, Oita, Japan, January 19–21, 1998     

Design of intelligent power controller for DC–DC converters using CMAC neural network

DC–DC converters are the devices which can convert a certain electrical voltage to another level of electrical voltage. They are very popularly used because of the high efficiency and small size. This paper proposes an intelligent power controller for the DC–DC converters via cerebella model articulation controller (CMAC) neural network approach. The proposed intelligent power controller is composed of a CMAC neural controller and a robust controller. The CMAC neural controller uses a CMAC neural network to online mimic an ideal controller, and the robust controller is designed to achieve L ₂ tracking performance with desired attenuation level. Finally, a comparison among a PI control, adaptive neural control and the proposed intelligent power control is made. The experimental results are provided to demonstrate the proposed intelligent power controller can cope with the input voltage and load resistance variations to ensure the stability while providing fast transient response and simple computation.     

The Neural Network Approach to Input–Output Analysis for Economic Systems

Economic practitioners in China are giving up the classical Leontief’s Input–Output analysis methods. This paper offers an alternative method of input–output analysis. The proposed method is based on the layered neural network model. It shows that neural networks method can be useful for input–output analysis for a dynamic economic system.       

Least-cost design of singly and doubly reinforced concrete beam using genetic algorithm optimized artificial neural network based on Levenberg–Marquardt and quasi-Newton backpropagation learning techniques

In this work, least-cost design of singly and doubly reinforced beams with uniformly distributed and concentrated load was done by incorporating actual self-weight of beam, parabolic stress block, moment–equilibrium and serviceability constraint besides other constraints. Also, this design expertise was incorporated into a genetically optimized artificial neural network based on steepest descent, Levenberg–Marquardt, and quasi-Newton backpropagation learning techniques. The initial solution for the optimization procedure was obtained using limit state design as per IS: 456-2000.     

Prediction of quality using ANN based on Teaching‐Learning Optimization in component‐based software systems

The primary objective of our research work is to enhance the prediction of the quality of a component‐based software system and to develop an artificial neural network (ANN) model for the system reliability optimization problem. In this paper, we introduced the ANN‐supported Teaching‐Learning Optimization by transforming constraints to objective functions. Artificial neural network techniques are found to be powerful in the modeling software package quality metrics compared with the ancient statistical techniques. Therefore, by using the neural network, the quality characteristics of software components of the proposed work are predicted. A nonlinear differentiable transfer function of ANN used in the proposed approach is hyperbolic tangent sigmoid. A new efficient optimization methodology referred to as the Teaching‐Learning–based Optimization is proposed in this paper to optimize reliability and different cost functions. The weight values of the network are then adjusted consistent with a proposed optimization rule, therefore minimizing the network error. The proposed work is implemented in MATLAB by using the Neural Network Toolbox. The proposed work provides improved performance in terms of sensitivity, precision, specificity, negative predictive value, fall‐out or false positive rate, false discovery rate, accuracy, Matthews correlation coefficient, and rate of convergence.     

Implementation of multilayer neural network with threshold neurons and its analysis

In this paper, the implementation of new digital architecture for a multilayer neural network (MNN) with on-chip learning is discussed. The advantage of using the digital approach is that it can use state-of-the-art VLSI and ULSI implementation techniques. One of the major hard-ware problems in implementing a neural network is the activating function of the neurons. The proposed MNN uses a simple function as the neuron's activating function to reduce the circuit size. Moreover, the proposed MNN has an on-chip learning capability. As the learning algorithm, a backpropagation algorithm is modified for effective hard-wave implementation. The proposed MNN is implemented on a field-programmable gate array (FPGA) to evaluate the learning performance and circuit size. This work was presented, in part, at the Third International Symposium on Artificial Life and Robotics, Oita, Japan, January 19–21, 1998     

面向SoC任务分配的应用程序存储分析方法

存储设计是影响SoC系统性能和功耗的重要因素,分析、估计应用程序的存储需求量有助于SoC设计与优化。本文着重研究面向SoC任务分配时的应用程序存储需求量分析方法。首先介绍了面向任务分配的应用程序存储分析框架,然后较具体地论述了所提出的面向SoC任务分配的多粒度应用程序存储分析方法的原理和算法,最后通过一个应用实例论证了方法的有效性。     

改进的基于嵌入式SoC卷积神经网络识别模型

针对当前在FPGA上实现卷积神经网络模型时卷积计算消耗资源大,提高FPGA芯片性能代价较大等问题,提出一种改进的基于嵌入式SoC的优化设计方法。对卷积计算的实现方法和存储访问通道加以优化,以提高并行计算性能;将32位位宽的浮点数量化为16位定点数,加快前向传播的数据传输;结合硬件描述软件的高层次综合技术,将卷积神经网络映射到硬件平台成为一种同步数据流模型从而加快计算速度。通过实验证明,该方案较现有设计节约了89%的BRAM和72%的LUT,在工作频率为100 MHz的测试中,其处理速度比单独使用Cortex-A9的方案提升了42倍。     

Forecasting of Software Reliability Using Neighborhood Fuzzy Particle Swarm Optimization Based Novel Neural Network

This paper proposes an artificial neural network (ANN) based software reliability model trained by novel particle swarm optimization (PSO) algorithm for enhanced forecasting of the reliability of software. The proposed ANN is developed considering the fault generation phenomenon during software testing with the fault complexity of different levels. We demonstrate the proposed model considering three types of faults residing in the software. We propose a neighborhood based fuzzy PSO algorithm for competent learning of the proposed ANN using software failure data. Fitting and prediction performances of the neighborhood fuzzy PSO based proposed neural network model are compared with the standard PSO based proposed neural network model and existing ANN based software reliability models in the literature through three real software failure data sets. We also compare the performance of the proposed PSO algorithm with the standard PSO algorithm through learning of the proposed ANN. Statistical analysis shows that the neighborhood fuzzy PSO based proposed neural network model has comparatively better fitting and predictive ability than the standard PSO based proposed neural network model and other ANN based software reliability models. Faster release of software is achievable by applying the proposed PSO based neural network model during the testing period.      

Software defect prediction using cost-sensitive neural network

The software development life cycle generally includes analysis, design, implementation, test and release phases. The testing phase should be operated effectively in order to release bug-free software to end users. In the last two decades, academicians have taken an increasing interest in the software defect prediction problem, several machine learning techniques have been applied for more robust prediction. A different classification approach for this problem is proposed in this paper. A combination of traditional Artificial Neural Network (ANN) and the novel Artificial Bee Colony (ABC) algorithm are used in this study. Training the neural network is performed by ABC algorithm in order to find optimal weights. The False Positive Rate (FPR) and False Negative Rate (FNR) multiplied by parametric cost coefficients are the optimization task of the ABC algorithm. Software defect data in nature have a class imbalance because of the skewed distribution of defective and non-defective modules, so that conventional error functions of the neural network produce unbalanced FPR and FNR results. The proposed approach was applied to five publicly available datasets from the NASA Metrics Data Program repository. Accuracy, probability of detection, probability of false alarm, balance, Area Under Curve (AUC), and Normalized Expected Cost of Misclassification (NECM) are the main performance indicators of our classification approach. In order to prevent random results, the dataset was shuffled and the algorithm was executed 10 times with the use of n-fold cross-validation in each iteration. Our experimental results showed that a cost-sensitive neural network can be created successfully by using the ABC optimization algorithm for the purpose of software defect prediction.     

Rough Neural Network Based on Bottom-Up Fuzzy Rough Data Analysis

Based on bottom-up fuzzy rough data analysis, a new rough neural network decision-making model is proposed. Through supervised Gaustafason–Kessel (G–K) clustering algorithm, proper fuzzy clusters are found to partition the input data space. At the same time cluster number is searched by monotone increasing process. If the cluster number matches with that exactly exist in data sets then excellent fuzzy rough data modeling (FRDM) model can be built. And by integrating it with neural network technique, corresponding rough neural network is constructed. Our method overcomes the defects of conventional top-down based rough logic neural network (RLNN) method, and it also achieves adaptive learning ability and comprehensive soft decision-making ability compared with FRDM model. The experiment results indicate that our method has stronger generalization ability and more compact network structure than conventional RLNN.     

Network partitioning using harmony search and equivalencing for distributed computing

Power system has a highly interconnected network that requires intense computational effort and resources for centralized control. Distributed computing needs the systems to be partitioned optimally into clusters. The network partitioning is an optimization problem whose objective is to minimize the number of nodes in a cluster and the tie lines between the clusters. Harmony Search(HS) Algorithm is one of the recently developed meta heuristic algorithms that can be applied to optimization problems. In this work, the HS algorithm is applied to the network partitioning problem and power flow based equivalencing is done to represent the external system. Simulation is done on IEEE Standard Test Systems. The algorithm is found to be very effective in partitioning the system hierarchically and the equivalencing method gives accurate results in comparison to the centralized control.