An Efficient Value Predictor Dynamically Using Loop and Locality Properties

Value prediction, a technique to break data dependency, is important in enhancing instruction-level parallelism and processor performance. A new value predictor utilizing both the loop and locality properties of data values has been proposed in this paper to pursue desirable prediction accuracy at reasonable cost. The proposed value predictor, called the Dynamic Loop and Locality-based (DLL) predictor, makes predictions by dynamically practicing the loop or locality-based prediction policy according to the state. With certain simple designs, the DLL predictor gains prediction accuracy in an efficient way. To secure more comprehensive experimental evaluation of value predictors, a new performance measure, accuracy improvement per cost, briefed as the A/C ratio, is introduced in the paper. Simulation results show that, compared with other existing value predictors, the proposed DLL predictor produces better A/C ratios in almost all situations due to flexible application of different prediction policies and reduced cost.     

Limits of Data Value Predictability

The predictability of data values is studied at a fundamental level. Two basic predictor models are defined: Computational predictors perform an operation on previous values to yield predicted next values. Examples we study are stride value prediction and last value prediction; Context-Based predictors match recent value history (context) with previous value history and predict values based entirely on previously observed patterns. To understand the potential of value prediction we perform simulations with unbounded prediction tables that are immediately updated using correct data values. Simulations of integer SPEC95 benchmarks show that data values can be highly predictable. Best performance is obtained with context-based predictors; overall prediction accuracies are between 56% and 92%. The context based predictor typically has an accuracy about 20% better than the computational predictors (last value and stride). Results with bounded tables suggest the feasibility of context-based predictors that approximate the performance with unbounded tables.     

非负局部约束线性编码图像分类算法

基于特征提取的图像分类算法的核心问题是如何对特征进行有效编码. 局部约束线性编码(Locality-constrained linear coding, LLC) 因其良好的特征重构性与局部平滑稀疏性, 已取得了很好的分类性能. 然而, LLC编码的分类性能对编码过程中的近邻数k的大小比较敏感, 随着k的增大, 编码中的某些负值元素与正值元素的差值绝对值也可能增大, 这使得LLC越来越不稳定. 本文通过在LLC优化模型的目标方程中引入非负约束, 提出了一种新型编码方式, 称为非负局部约束线性编码(Non-negative locality-constrained linear coding, NNLLC). 该模型一般采取迭代优化算法进行求解, 但其计算复杂度较大. 因此, 本文提出两种近似非负编码算法, 其编码速度与LLC一样快速. 实验结果表明, 在多个广泛使用的图像数据集上, 相比于LLC, NNLLC编码方式不仅在分类精确率上提高了近1%～4%, 而且对k的选取具有更强的鲁棒性.     

参数独立的加权局部均值伪近邻分类算法

针对局部均值伪近邻（LMPNN）算法对k值敏感且忽略了每个属性对分类结果的不同影响等问题,提出了一种参数独立的加权局部均值伪近邻分类（PIW-LMPNN）算法。首先,利用差分进化算法的最新变体——基于成功历史记录的自适应参数差分进化（SHADE）算法对训练集样本进行优化,从而得到最佳k值和一组与类别相关的最佳权重;其次,计算样本间的距离时赋予每类的每个属性不同的权重,并对测试集样本进行分类。在15个实际数据集上进行了仿真实验,并把所提算法与其他8种分类算法进行了比较,实验结果表明,所提算法的分类准确率和F1值分别最大提高了约28个百分点和23.1个百分点;同时Wilcoxon符号秩检验、Friedman秩方差检验以及Hollander-Wolfe两处理的比较结果表明,所提出的改进算法在分类精度以及k值选择方面相较其他8种分类算法具有明显优势。     

On distributed catenation

We introduce a new operation between words and languages, called distributed catenation. The distributed catenation is a natural extension of the well-known catenation operation. As for partial shuffle operation the introduction of this operation is motivated by the theory of concurrency. At the same time the distributed catenation is a powerful operation. For instance, any Turing machine can be simulated by a pushdown automaton that uses distributed catenation for the pushdown memory.     

基于类型预测的甚块预测器

高性能的甚块预测器是保证EDGE体系结构性能的关键手段.为研究性能更好的甚块预测器,文中通过仿真实验发现甚块的出口类型独立于甚块的出口个数和甚块的动态执行结果而存在.以此为据,提出了基于类型预测的甚块预测器.该预测器摈弃了甚块出口号,直接对甚块出口类型进行预测.随后,根据对甚块出口类型可预测性的分析,通过实验证明甚块出口类型与历史和路径信息相关.仿真结果显示,与经典的基于出口预测的甚块预测器相比,文中提出的基于类型预测的甚块预测器能够将每千条指令误预测次数平均降低约10％.     

空间调制系统下改进的QRD-M检测算法

空间调制（SM）系统中性能最优的最大似然（ML）检测算法复杂度很高,用基于信道矩阵QR分解的M算法（QRD-M）可以降低复杂度,但传统QRD-M算法检测时,每层都保留固定的M个节点,仍会造成额外的计算量。针对传统QRD-M算法中存在的问题,提出一种低复杂度的动态M值QRD-M检测算法——LC-QRD-dM。LC-QRD-dM算法利用设计的阈值与累积分支度量值进行比较,每层自适应地选择不超过M的保留节点数,相对于传统QRD-M算法以牺牲少量性能为代价大大降低了复杂度。接着又针对该改进算法在信道衰落较深时会产生较大误码率的问题,进一步提出一种基于信道状态的动态M值QRD-M检测算法——CS-QRD-dM。CS-QRD-dM利用LC-QRD-dM的原理,在低信噪比（SNR）时,每层根据阈值选择不小于M的保留节点数;在高信噪比时,每层则选择不超过M的保留节点数。理论分析和仿真结果表明：相比传统QRD-M,CS-QRD-dM在低信噪比时有约1.3 dB的信噪比增益（误码率为10^-2）,以增加少量复杂度为代价,显著地改善了检测性能;在高信噪比时,其检测性能及复杂度与LC-QRD-dM相同。     

Selective Branch Inversion: Confidence Estimation for Branch Predictors

This paper describes a family of branch predictors that use confidence estimation to improve the performance of an underlying branch predictor. This method, referred to as Selective Branch Inversion (SBI), uses a confidence estimator to determine when the branch direction prediction is likely to be incorrect; branch decisions for these low-confidence branches are inverted. SBI with an underlying Gshare branch predictor outperforms other equal sized predictors such as the best history length Gshare predictor, as well as equally complex McFarling and Bi-Mode predictors. Our analysis shows that SBI achieves its performance through conflict detection and correction, rather than through conflict avoidance as some of the previously proposed predictors such as Bi-Mode and Agree. We also show that SBI is applicable to other underlying predictors, such as the McFarling Combined predictor. Finally we show that Dynamic Inversion Monitoring (DIM) can be used as a safeguard to turn off SBI in cases where it degrades the overall performance.     

Performance Evaluation of Data Value Prediction Schemes

Data value prediction has been widely accepted as an effective mechanism to break data hazards for high performance processor design. Several works have reported promising performance potential. However, there is hardly enough information that is presented in a clear way about performance comparison of these prediction mechanisms. This paper investigates the performance impact of four previously proposed value predictors, namely last value predictor, stride value predictor, two-level value predictor and hybrid (stride two-level) predictor. The impact of misprediction penalty, which has been frequently ignored, is discussed in detail. Several other implementation issues, including instruction window size, issue width and branch predictor are also addressed and simulated. Simulation results indicate that data value predictors act differently under different configurations. In some cases, simpler schemes may be more beneficial than complicated ones. In some particular cases, value prediction may have negative impact on performance.     

基于Kappa系数的数据流分类算法

数据流挖掘已经成为数据挖掘领域一个热门的研究方向,由于数据流中概念漂移现象的存在,使得传统的分类算法无法直接应用于数据流中。为了能有效地应对数据流中的概念漂移,提出了一种基于Kappa系数的数据流分类算法。该算法采用集成式分类技术,以Kappa系数度量系统的分类性能,根据Kappa系数来动态地调整分类器,当发生概念漂移时,系统能利用已有的知识很快删除不符合要求的分类器来适应新概念。实验结果表明,相对于实验中参与比较的BWE,AE和AWE算法,该算法不但具有较好的分类性能,而且在一定程度上能较为有效地降低时间开销。     

黎曼流形上半调图像的协方差建模与贝叶斯分类方法

针对半调图像分类问题,提出黎曼流形上的协方差建模方法和贝叶斯分类策略.根据半调图像傅立叶频谱的特点,提出一种基于模板矩阵的特征获取方法,并结合频谱信息形成协方差矩阵描述方法.通过引入有效图像判决规则和分块技术,提出一种协方差矩阵提取算法.利用样本的局部特性和核密度估计方法,实现黎曼流形上的贝叶斯分类策略.实验中研究阈值参数的选择策略,与5个相似方法进行分类性能比较,探讨有关参数对性能的影响.实验结果表明,所提出的方法在Q=32或64和L=10~15时其分类错误率低于4%,建模时间开销低于100ms,且优于5个相似方法.     

Multi-kernel one class link prediction in heterogeneous complex networks

The heterogeneity of a network causes major challenges for link prediction in heterogeneous complex networks. To deal with this problem, supervised link prediction could be applied to integrate heterogeneous features extracted from different nodes/relations. However, supervised link prediction might be faced with highly imbalanced data issues which results in undesirable false prediction rate. In this paper, we propose a new kernel-based one-class link predictor in heterogeneous complex networks. Assuming a set of available meta-paths, a graph kernel is extracted based on each meta-path. Then, they are combined to form a single kernel function. Afterwards, one class support vector machine (OC-SVM) would be applied on the positive node pairs to train the link predictor. The proposed method has been compared with popular link predictors using DBLP network. The results show that the method outperforms other conventional link predictors in terms of prediction performances.     

Combined classifier for cross-project defect prediction: an extended empirical study

To facilitate developers in effective allocation of their testing and debugging efforts, many software defect prediction techniques have been proposed in the literature. These techniques can be used to predict classes that are more likely to be buggy based on the past history of classes, methods, or certain other code elements. These techniques are effective provided that a sufficient amount of data is available to train a prediction model. However, sufficient training data are rarely available for new software projects. To resolve this problem, cross-project defect prediction, which transfers a prediction model trained using data from one project to another, was proposed and is regarded as a new challenge in the area of defect prediction. Thus far, only a few cross-project defect prediction techniques have been proposed. To advance the state of the art, in this study, we investigated seven composite algorithms that integrate multiple machine learning classifiers to improve cross-project defect prediction. To evaluate the performance of the composite algorithms, we performed experiments on 10 open-source software systems from the PROMISE repository, which contain a total of 5,305 instances labeled as defective or clean. We compared the composite algorithms with the combined defect predictor where logistic regression is used as the meta classification algorithm (CODEP _Logistic ), which is the most recent cross-project defect prediction algorithm in terms of two standard evaluation metrics: cost effectiveness and F-measure. Our experimental results show that several algorithms outperform CODEP _Logistic : Maximum voting shows the best performance in terms of F-measure and its average F-measure is superior to that of CODEP _Logistic by 36.88%. Bootstrap aggregation (Bagging_J48) shows the best performance in terms of cost effectiveness and its average cost effectiveness is superior to that of CODEP _Logistic by 15.34%.     

基于权值多样性的半监督分类算法

在实际生活中,可以很容易地获得大量系统数据样本,却只能获得很小一部分的准确标签。为了获得更好的分类学习模型,引入半监督学习的处理方式,对基于未标注数据强化集成多样性（UDEED）算法进行改进,提出了UDEED⁺——一种基于权值多样性的半监督分类算法。UDEED⁺主要的思路是在基学习器对未标注数据的预测分歧的基础上提出权值多样性损失,通过引入基学习器权值的余弦相似度来表示基学习器之间的分歧,并且从损失函数的不同角度充分扩展模型的多样性,使用未标注数据在模型训练过程中鼓励集成学习器的多样性的表示,以此达到提升分类学习模型性能和泛化性的目的。在8个UCI公开数据集上,与UDEED算法、S4VM（Safe Semi-Supervised Support Vector Machine）和SSWL（Semi-Supervised Weak-Label）半监督算法进行了对比,相较于UDEED算法,UDEED⁺在正确率和F1分数上分别提升了1.4个百分点和1.1个百分点;相较于S4VM,UDEED⁺在正确率和F1分数上分别提升了1.3个百分点和3.1个百分点;相较于SSWL,UDEED⁺在正确率和F1分数上分别提升了0.7个百分点和1.5个百分点。实验结果表明,权值多样性的提升可以改善UDEED⁺算法的分类性能,验证了其对所提算法UDEED⁺的分类性能提升的正向效果。     

Fuzzy predictive PI control for processes with large time delays

This paper presents the design, tuning and performance analysis of a new predictive fuzzy controller structure for higher order plants with large time delays. The designed controller consists of a fuzzy proportional-integral (PI) part and a fuzzy predictor. The fuzzy predictive PI controller combines the advantages of fuzzy control while maintaining the simplicity and robustness of a conventional PI controller. The dynamics of the prediction term are adaptive to the system's time delay. The prediction term has two parts: a fuzzy predictor that uses the system time delay as an input for calculating the prediction horizon and an exponential term that uses the prediction horizon as its positive power. The prediction term also introduces phase lead into the system which compensates for the phase lag due to the time delay in the plant, thereby stabilizing the closed-loop configuration. The performance of the proposed controller is compared with the responses of the conventional predictive PI controller, showing many advantages of the new design over its conventional counterpart.     

Improving the effectiveness of RBF classifier based on a hybrid cost function

This paper presents a new minimum classification error (MCE)–mean square error (MSE) hybrid cost function to enhance the classification ability and speed up the learning process of radial basis function (RBF)-based classifier. Contributed by the MCE function, the proposed cost function enables the RBF-based classifier to achieve an excellent classification performance compared with the conventional MSE function. In addition, certain learning difficulties experienced by the MCE algorithm can be solved in an efficient and simple way. The presented results show that the proposed method exhibits a substantially higher convergence rate compared with the MCE function.     

Modulo Path History for the Reduction of Pipeline Overheads in Path-based Neural Branch Predictors

Neural-inspired branch predictors achieve very low branch misprediction rates. However, previously proposed implementations have a variety of characteristics that make them challenging to implement in future high-performance processors. In particular, the path-based neural predictor (PBNP) and the piecewise-linear (PWL) predictor require deep pipelining and additional area to support checkpointing for misprediction recovery. The complexity of the PBNP predictor stems from the fact that the path history length, which determines the number of tables and pipeline stages, is equal to the history length, which is typically very long for high accuracy. We propose to decouple the path-history length from the outcome-history length through a new technique called modulo-path history. By allowing a shorter path history, we can implement the PBNP and PWL predictors with significantly fewer tables and pipeline stages while still exploiting a traditional long branch outcome history.     

基于局部信息的WLAN位置预测器

分析了移动路径预测的已有方案,尤其针对k阶Markov预测器中存在的状态空间膨胀以及知识更新较慢问题,提出了一种新的WLAN位置预测器模型,并在1200个实际WLAN用户的移动跟踪数据集上对Markov预测器和新预测器的预测精度进行了比较分析。分析结果表明,新的预测器模型比k阶Markov预测器中复杂度最低的一阶Markov预测器更节省空间和搜索时间,并且比预测效果最好的二阶Markov预测器有更好的预测精度和普适性。该模型以很小的代价获得更好的性能,具有较高的实用价值。     

基于CenterNet的实时行人检测模型

针对传统目标检测模型不能同时兼顾检测速度和准确度的问题,提出一种新的PD-CenterNet模型。在CenterNet的基础上对网络结构和损失函数进行改进,在网络结构的上采路径中,设计基于注意力机制的特征融合模块,对低级特征和高级特性进行融合,在损失函数中通过设计α、γ、δ 3个影响因子来提高正样本与降低负样本的损失,以平衡正负样本的损失。实验结果表明,相比CenterNet模型,该模型在网络结构和损失函数上的准确度分别提高5.1%、9.81%。     

增量式SVM的数据流异常检测模型

针对网络数据流异常检测,既要保证分类准确率,又要提高检测速度的问题,在原有数据流挖掘技术的基础上提出一种改进的增量式学习算法.算法中建立多模型轮转结构,在每次训练中从几何角度出发求出当前训练样本集的支持向量,选择出分布于超平面间隔中的支持向量进行增量SVM训练.使用UCI标准数据库中的数据进行实验,并且与另外两种经典分类模型进行比较,结果表明了方法的有效性.