海量数据库迁移与升级

目前数据库中数据越来越多,应用对数据库在线时间的要求也越来越高,使得数据库迁移和数据库升级成为了一件非常困难的事情.为此,介绍了几种迁移和升级的方法,用以实现以尽可能少的停机时间对TB级数据库完成数据库的迁移和升级.     

Stock Price Forecasting: An Echo State Network Approach

Forecasting stock prices using deep learning models suffers from problems such as low accuracy, slow convergence, and complex network structures. This study developed an echo state network (ESN) model to mitigate such problems. We compared our ESN with a long short-term memory (LSTM) network by forecasting the stock data of Kweichow Moutai, a leading enterprise in China’s liquor industry. By analyzing data for 120, 240, and 300 days, we generated forecast data for the next 40, 80, and 100 days, respectively, using both ESN and LSTM. In terms of accuracy, ESN had the unique advantage of capturing nonlinear data. Mean absolute error (MAE) was used to present the accuracy results. The MAEs of the data forecast by ESN were 0.024, 0.024, and 0.025, which were, respectively, 0.065, 0.007, and 0.009 less than those of LSTM. In terms of convergence, ESN has a reservoir state-space structure, which makes it perform faster than other models. Root-mean-square error (RMSE) was used to present the convergence time. In our experiment, the RMSEs of ESN were 0.22, 0.27, and 0.26, which were, respectively, 0.08, 0.01, and 0.12 less than those of LSTM. In terms of network structure, ESN consists only of input, reservoir, and output spaces, making it a much simpler model than the others. The proposed ESN was found to be an effective model that, compared to others, converges faster, forecasts more accurately, and builds time-series analyses more easily.     

A conditional classification recurrent RBM for improved series mid-term forecasting

In the context of human-robot and robot-robot interactions, the better cooperation can be achieved by predicting the other party’s subsequent actions based on the current action of the other party. The time duration for adjustment is not sufficient provided by short term forecasting models to robots. A longer duration can by achieved by mid-term forecasting. But the mid-term forecasting models introduce the previous errors into the follow-up forecasting and amplified gradually, eventually invalidating the forecasting. A new mid-term forecasting with error suppression based on restricted Boltzmann machine(RBM) is proposed in this paper. The proposed model can suppress the error amplification by replacing the previous inputs with their features, which are retrieved by a deep belief network(DBN). Furthermore, a new mechanism is proposed to decide whether the forecasting result is accepted or not. The model is evaluated with several datasets. The reported experiments demonstrate the superior performance of the proposed model compared to the state-of-the-art approaches.

     

SESF-Fuse: an unsupervised deep model for multi-focus image fusion

Neural Computing and Applications - Muti-focus image fusion is the extraction of focused regions from different images to create one all-in-focus fused image. The key point is that only objects...     

用于自动测试系统继电器矩阵开关的设计

针对目前现有的矩阵开关在性价比、可靠性以及通用性等方面不尽如人意,无法满足中小型自动测试系统的实际要求这一问题;设计了一种用于自动测试系统的继电器矩阵开关,给出了其设计原理、硬件电路图以及主程序流程图;系统搭建完成后,进行8次独立重复试验,测试结果显示:该继电器矩阵开关测试数据的最大误差为±0.3％,同时具有性价比高、通用性好、可靠性较高等优点,特别适合于中小型测试系统的电源通道和信号通道的切换与控制.     

坦克炮控系统摩擦扰动补偿研究

针对坦克水平向炮控伺服系统中存在的摩擦不确定因素及未建模动态,首先建立水平向炮控伺服系统的数学模型,将摩擦扰动和未建模动态视为一个综合扰动项,然后利用扩张状态观测器对综合扰动项进行观测和补偿,并将扩张状态观测器(ESO)补偿回路作为经典PID控制方法的内回路,实现ESO-PID的复合控制;最后对所用方法进行仿真,结果表明,在原有控制方法的基础上设计控制器,集合了PID控制算法的"被动抗扰"和自抗扰控制方法中扩张状态观测器的"主动抗扰"特性,能够在保持控制系统原有特性的基础上大幅度提高炮控系统的稳定精度以及低速性能。     

Analysis and control of general logical networks – An algebraic approach

Since Boolean network is a powerful tool in describing the genetic regulatory networks, accompanying the development of systems biology, the analysis and control of Boolean networks have attracted much attention from biologists, physicists, and systems scientists. From mathematical point of view, the dynamics of a Boolean (control) network is a discrete-time logical dynamic process. This paper surveys a recently developed technique, called the algebraic approach, based on semi-tensor product. The new technique can deal with not only Boolean networks, which allow each node to take two values, but also k-valued networks, which allow each node to take k different values, and mix-valued networks, which allow nodes to take different numbers of values.The paper provides a comprehensive introduction to the new technique, including (1) mathematical background of this new technique – semi-tensor product of matrices and the matrix expression of logic; (2) dynamic models of Boolean networks, and general (multi- or mix-valued) logical networks; (3) the topological structure of Boolean networks and general networks; (4) the basic control problems of Boolean/general control networks, which include the controllability, observability, realization, stability and stabilization, disturbance decoupling, identification and optimization, etc.; (5) some other related applications.     

Network traffic classification via HMM under the guidance of syntactic structure

Network traffic classification is the basis of many network technologies including intrusion detection, traffic scheduling, and quality of service. Given the limitations of existing classification approaches based on the port number, the packet-payload and statistical characteristics of network traffic, in this paper we propose a novel classification method via a hidden Markov model. With the analysis about the time series characteristics and statistical properties of network traffic, we use a hidden Markov model to model for a type of traffic under the guidance of syntactic structure of it. And then a classification approach is presented based on the model. Experiment results on several typical network applications indicate that the combination of time series characteristics and the statistical properties not only make the established model more precise, but also improve the accuracy of network traffic classification.     

Learning-enhanced differential evolution for numerical optimization

Differential evolution (DE) is a simple and powerful population-based search algorithm, successfully used in various scientific and engineering fields. However, DE is not free from the problems of stagnation and premature convergence. Hence, designing more effective search strategies to enhance the performance of DE is one of the most salient and active topics. This paper proposes a new method, called learning-enhanced DE (LeDE) that promotes individuals to exchange information systematically. Distinct from the existing DE variants, LeDE adopts a novel learning strategy, namely clustering-based learning strategy (CLS). In CLS, there are two levels of learning strategies, intra-cluster learning strategy and inter-cluster learning strategy. They are adopted for exchanging information within the same cluster and between different clusters, respectively. Experimental studies over 23 benchmark functions show that LeDE significantly outperforms the conventional DE. Compared with other clustering-based DE algorithms, LeDE can obtain better solutions. In addition, LeDE is also shown to be significantly better than or at least comparable to several state-of-art DE variants as well as some other evolutionary algorithms.     

Surface characterization of 6H-SiC (0001) substrates in indentation and abrasive machining

Surface characterization of 6H-SiC (0001) substrates in indentation and abrasive machining was carried out to investigate microfracture, residual damage, and surface roughness associated with material removal and surface generation. Brittle versus plastic deformation was studied using Vickers indention and nano-indentation. To characterize the abrasive machining response, the 6H-SiC (0001) substrates were ground using diamond wheels with grit sizes of 25, 15 and 7 μm, and then polished with diamond suspensions of 3 and 0.05 μm. It is found that in indentation, there was a scale effect for brittle versus plastic deformation in 6H-SiC substrates. Also, in grinding, the scales of fracture and surface roughness of the substrates decreased with a decrease in diamond grit size. However, in polishing, a reduction in grit size of diamond suspensions gave no significant improvement in surface roughness. Furthermore, the results showed that fracture-free 6H-SiC (0001) surfaces were generated in polishing with the existence of the residual crystal defects, which were associated with the origin of defects in single crystal growth.