A multilayer perceptron-based medical decision support system for heart disease diagnosis

The medical diagnosis by nature is a complex and fuzzy cognitive process, and soft computing methods, such as neural networks, have shown great potential to be applied in the development of medical decision support systems (MDSS). In this paper, a multiplayer perceptron-based decision support system is developed to support the diagnosis of heart diseases. The input layer of the system includes 40 input variables, categorized into four groups and then encoded using the proposed coding schemes. The number of nodes in the hidden layer is determined through a cascade learning process. Each of the 5 nodes in the output layer corresponds to one heart disease of interest. In the system, the missing data of a patient are handled using the substituting mean method. Furthermore, an improved back propagation algorithm is used to train the system. A total of 352 medical records collected from the patients suffering from five heart diseases have been used to train and test the system. In particular, three assessment methods, cross validation, holdout and bootstrapping, are applied to assess the generalization of the system. The results show that the proposed MLP-based decision support system can achieve very high diagnosis accuracy (>90%) and comparably small intervals (<5%), proving its usefulness in support of clinic decision process of heart diseases.     

A perceptron-based replication scheme for managing the shared last level cache

The shared last level cache (SLLC), which provides large effective cache capacity, is widely adopted in modern chip multiprocessors (CMPs). But, long on-chip access latency in the SLLC is a key problem that hurts system performance. Replication is an effective way to relieve this problem through storing a replica of L1 victims in the near local LLC slice. However, previous replication schemes either blindly create replicas based on no feature of cache blocks or select replicas based on a single feature (such as data type, access count, etc.), which will affect the replication accuracy and limit the system performance improvements. In this paper, according to the successful application of machine learning (ML) in the field of computer architecture optimization in recent years, we develop a novel perceptron-based replication scheme (PBR) for effectively managing the SLLC in CMPs. Unlike existing single-feature-based schemes, this scheme effectively combines four features related to the reuse behavior of L1 victims, which are address (Addr), program counter (PC), data type (DT), and access count (AC), through perceptron to facilitate the accuracy of replica selection. Experimental results show that compared with the two previously proposed single-feature-based replication schemes: ASR and LADR, PBR decreases the execution time by 6.59% and 18.27%, and reduces the network traffic by 10.35% and 13.18% respectively with negligible energy consumption, hardware and area overhead.     

对象格产生概念格

通过在对象集内引入两个偏序关系≤′和C′及一种新的交运算∩′来建立改进的对象格,然后通过此对象格产生概念格。此概念格与由通常对象集合的交运算∩产生的概念格相比,其产生的概念节点不仅包括由通常对象集合的交运算∩产生的概念格的子节点的对象,还包括产生的新对象。     

基于UKF的自适应DFE信道均衡

针对信道的线性和非线性失真,在分析简化的非线性滤波的基础上,利用判决反馈的结构特点对其进行扩展,提出了基于UKF滤波的判决反馈均衡器,仿真表明,UKF滤波算法能降低系统均方误差性能。     

On the stability structure for lattice Boltzmann schemes

The stability structure for lattice Boltzmann schemes has been introduced in Banda et al. (2006) [16], Junk and Yong (2007) [14] to analyze the stability of numerical algorithms. The first purpose of this paper is to discuss the stability structure from the perspective of matrix analysis. Its second goal is to illustrate and apply the results to different classes of lattice Boltzmann collision operators. In particular we formulate an equivalence condition–just recently also reported in Yong (2008) [18]–that guarantees the existence of a pre-stability structure. It is then illustrated by several examples, how this equivalence condition can be effectively employed for the systematic verification and construction of stable collision operators. Finally, we point out some shortcomings of the stability structure approach arising in certain cases.     

A multi-agent approach using perceptron-based learning for robust operation of distributed chemical reactor networks

Controlling the individual reactors of a chemical reactor network producing different grades of a product requires intelligent reconfiguration strategies. Agent-based approaches are ideal for such distributed manufacturing processes, since they provide flexible, robust, and emergent solutions under dynamically changing process conditions. This paper proposes a multi-layered, multi-agent framework based on a decentralized online learning approach for the supervision of grade transitions in autocatalytic reactor networks. The values for the manipulated variables and the path to the target reactor are determined to give the least disturbance to the system. Case studies illustrate the performance of the approach in managing grade transition and disturbance rejection in a reactor network.     

A framework for integrating information sources under lattice structure

Different observations over one and the same natural phenomenon often lead to different collections of information elements describing that phenomenon. Such collections of information elements, which we call information sources, can be heterogeneous, redundant, complementary, or even contradictory. In general, the information elements describing the phenomenon can be unified and related in a hierarchical structure, using existing methods for data integration and ontology merging. In this paper, we consider the problem of redundancy, complementarity, and consistency of information sources, under the assumption that the information elements of each source are related in a lattice structure. We propose various methods for integrating information sources and establish relationships between these methods. Applications of the framework are illustrated through examples in the areas of geographic information and battlefield target identification.     

基于参数曲面的增材制造保形晶格结构生成方法

晶格结构因其具备特殊的机械性能,已成为增材制造复杂结构设计和制造的重要研究领域之一.针对传统的模型晶格结构生成方法需要通过对参数化建模的晶格结构网格进行裁剪或对其网格进行保形变形实现,且生成效率较低的问题,提出一种基于参数曲面的增材制造保形晶格结构生成方法,实现晶格结构对曲面空间的适应和高效生成.首先,基于一种矩阵方法...     

Prediction of interfacial reaction products between metals with same lattice structure through thermodynamic modeling

Interfacial reactions exert crucial effect on the performance of soldering joints. Prediction of the first phase formed at the interface between metals benefit the design of electronic packaging. Based on our previous work, a new scheme is developed in this paper, which aims at predicting phase formation of the interface reaction between metals with the same lattice structure. In the new scheme, the conventional principle considering both the thermodynamic and kinetic factors is employed. A criterion is introduced for the case where a spinodal decomposition exists in the starting solution when the local equilibrium assumption is still valid. Another new criterion involving only nucleation driving force and entropy change is proposed for the case where no spinodal decomposition occurs and the assumption of local equilibrium is no longer valid. The validity of these criteria has been confirmed when applied to predict the intermetallic compound (IMC) formed in the binary diffusion couples such as Al/Cu, Al/Pt, Al/Au, and Co/Zn.     

Multilayer discrete-time neural-net controller with guaranteedperformance

A family of novel multilayer discrete-time neural-net (NN) controllers is presented for the control of a class of multi-input multi-output (MIMO) dynamical systems. The neural net controller includes modified delta rule weight tuning and exhibits a learning while-functioning-features. The structure of the NN controller is derived using a filtered error/passivity approach. Linearity in the parameters is not required and certainty equivalence is not used. This overcomes several limitations of standard adaptive control. The notion of persistency of excitation (PE) for multilayer NN is defined and explored. New online improved tuning algorithms for discrete-time systems are derived, which are similar to sigma or epsilon-modification for the case of continuous-time systems, that include a modification to the learning rate parameter plus a correction term. These algorithms guarantee tracking as well as bounded NN weights in nonideal situations so that PE is not needed. An extension of these novel weight tuning updates to NN with an arbitrary number of hidden layers is discussed. The notions of discrete-time passive NN, dissipative NN, and robust NN are introduced. The NN makes the closed-loop system passive.     

The Galois lattice as a hierarchical structure for topological relations

This paper presents the construction and the comparison of Galois lattices of topological relations for qualitative spatial representation and reasoning. The lattices rely on a correspondence between computational operations working on quantitative data, on the one hand, and topological relations working on qualitative knowledge units, on the other hand. After introducing the context of the present research work, i.e. the RCC-8 model of topological relations, we present computational operations for checking topological relations on spatial regions. From these operations are derived two sets of computational conditions that can be associated to topological relations through a Galois connection. The associated Galois lattices are presented and compared. Elements on the practical use of the lattices for representing spatial knowledge and for reasoning are also introduced and discussed.     

Ab initio lattice stability in comparison with CALPHAD lattice stability

A systematic first-principles calculation for the total energies of 78 pure elemental solids has been performed at zero Kelvin using the projector augmented-wave method within the generalized gradient approximation. The total energy differences, i.e. lattice stabilities, among the face-centered-cubic (fcc), body-centered-cubic (bcc), and hexagonal-close-packed (hcp) crystal structures are studied and compared with the Scientific Group Thermodata Europe (SGTE) database developed by the CALPHAD method. For non-transitional elements, favorable comparison is observed, while for the majority of transition elements, particularly the V, Cr, Mn, Fe, and Co group elements, significant discrepancies exist. The Bain/tetragonal distortion analysis between fcc and bcc structures shows that when one structure is stable, the other is unstable, and the higher the energy of the unstable structure, the larger the discrepancy. Through analysis of the alloying effect in binary systems, we conclude that the lattice stability of unstable structures obtained through extrapolation of first-principles calculations in binary systems is close to the SGTE lattice stability obtained by the CALPHAD method.     

Efficient algorithms for mining closed itemsets and their lattice structure

The set of frequent closed itemsets uniquely determines the exact frequency of all itemsets, yet it can be orders of magnitude smaller than the set of all frequent itemsets. In this paper, we present CHARM, an efficient algorithm for mining all frequent closed itemsets. It enumerates closed sets using a dual itemset-tidset search tree, using an efficient hybrid search that skips many levels. It also uses a technique called diffsets to reduce the memory footprint of intermediate computations. Finally, it uses a fast hash-based approach to remove any "nonclosed" sets found during computation. We also present CHARM-L, an algorithm that outputs the closed itemset lattice, which is very useful for rule generation and visualization. An extensive experimental evaluation on a number of real and synthetic databases shows that CHARM is a state-of-the-art algorithm that outperforms previous methods. Further, CHARM-L explicitly generates the frequent closed itemset lattice.     

短波多径衰落信道下的判决反馈均衡器研究

判决反馈均衡器(DFE)主要有两种基本类型:直接调整抽头系数的传统DFE和通过估计信道冲激响应直接计算均衡器抽头系数的基于信道估计DFE.研究两种基本的DFE和一种改进的基于信道估计DFE在短波多径衰落信道下的性能.仿真结果显示,基于信道估计DFE尤其是改进的基于信道估计DFE,在对抗信道的时变性方面与传统DFE相比,具有更强的鲁棒性,更适合在短波通信中使用.     

Multilayer neural-net robot controller with guaranteed trackingperformance

A multilayer neural-net (NN) controller for a general serial-link rigid robot arm is developed. The structure of the NN controller is derived using a filtered error/passivity approach. No off-line learning phase is needed for the proposed NN controller and the weights are easily initialized. The nonlinear nature of the NN, plus NN functional reconstruction inaccuracies and robot disturbances, mean that the standard delta rule using backpropagation tuning does not suffice for closed-loop dynamic control. Novel online weight tuning algorithms, including correction terms to the delta rule plus an added robust signal, guarantee bounded tracking errors as well as bounded NN weights. Specific bounds are determined, and the tracking error bound can be made arbitrarily small by increasing a certain feedback gain. The correction terms involve a second-order forward-propagated wave in the backpropagation network. New NN properties including the notions of a passive NN, a dissipative NN, and a robust NN are introduced.     

Multilayer feedforward networks with adaptive spline activationfunction

In this paper, a new adaptive spline activation function neural network (ASNN) is presented. Due to the ASNN's high representation capabilities, networks with a small number of interconnections can be trained to solve both pattern recognition and data processing real-time problems. The main idea is to use a Catmull-Rom cubic spline as the neuron's activation function, which ensures a simple structure suitable for both software and hardware implementation. Experimental results demonstrate improvements in terms of generalization capability and of learning speed in both pattern recognition and data processing tasks.     

DFE3D: 双重特征增强的三维点云类增量学习

随着点云采集技术的发展和三维应用需求的增加, 实际场景要求针对流动数据持续动态地更新点云分析网络. 对此, 提出了双重特征增强的三维点云类增量学习方法, 通过增量学习使点云目标分类技术能够适应新数据中不断出现新类别目标的场景. 该方法通过对点云数据特性和旧类信息的研究分别提出了差异性局部增强模块和知识注入网络, 以缓解类增量学习中的新类偏好问题. 具体而言, 差异性局部增强模块通过感知丰富的局部语义, 表征出三维点云物体中不同的局部结构特性. 随后, 根据目标中每个局部结构的全局信息获得各个局部的重要性权重, 强化对差异性局部特征的感知, 从而提高新旧类特征差异性. 另外, 知识注入网络将旧模型中的旧知识注入新模型的特征学习过程中, 增强后的混合特征能够更有效缓解旧类信息不足导致的新类偏好加剧现象. 在三维点云数据集ModelNet40, ScanObjectNN, ScanNet, ShapeNet上的实验表明, 该方法与现有最优方法相比, 在4个数据集上的平均增量准确率有2.03%、2.18%、1.65%、1.28% 提升.     

树状结构组织的属性优先的概念格渐进式算法

通过对概念格渐进式构造过程的分析,采用树结构对概念格节点进行组织,研究了利用这种树状组织的渐进式生成属性优先的概念格的构造算法。并结合实例说明了概念格的树结构组织在属性优先的渐进式生成概念格时,能有效地缩小产生子格节点的搜索范围和新增格节点的父节点和子节点的搜索范围,从而能快速生成概念格。     

DFE: efficient IoT network intrusion detection using deep feature extraction

Neural Computing and Applications - In recent years, the Internet of Things (IoT) has received a lot of attention. It has been used in many applications such as the control industry, industrial...     

Design and simulate the properties of triangular periodic nanoparticle arrays with the structure of bi-layer hexagonal lattice

Microsystem Technologies - In this study, the discrete dipole approximation (DDA) method was used to simulate the hybrid bi-layer hexagonal lattice of triangular periodic nanoparticle arrays...