Analysis and Classification of Multi-Criteria Recommender Systems

Recent studies have indicated that the application of Multi-Criteria Decision Making (MCDM) methods in recommender systems has yet to be systematically explored. This observation partially contradicts with the fact that in related literature, there exist several contributions describing recommender systems that engage some MCDM method. Such systems, which we refer to as multi-criteria recommender systems, have early demonstrated the potential of applying MCDM methods to facilitate recommendation, in numerous application domains. On the other hand, a comprehensive analysis of existing systems would facilitate their understanding and development. Towards this direction, this paper identifies a set of dimensions that distinguish, describe and categorize multi-criteria recommender systems, based on existing taxonomies and categorizations. These dimensions are integrated into an overall framework that is used for the analysis and classification of a sample of existing multi-criteria recommender systems. The results provide a comprehensive overview of the ways current multi-criteria recommender systems support the decision of online users.     

Efficient GA Based Techniques for Classification

A common approach to evaluating competing models in a classification context is via accuracy on a test set or on cross-validation sets. However, this can be computationally costly when using genetic algorithms with large datasets and the benefits of performing a wide search are compromised by the fact that estimates of the generalization abilities of competing models are subject to noise. This paper shows that clear advantages can be gained by using samples of the test set when evaluating competing models. Further, that applying statistical tests in combination with Occam's razor produces parsimonious models, matches the level of evaluation to the state of the search and retains the speed advantages of test set sampling.     

一类具有未知参变量的非线性系统的鲁棒故障诊断

讨论了一类含有状态和输入未知参变量的非线性系统的故障诊断问题,在满足一些几何条件的情况下,该类系统可化成两类不同的子系统。对于其中一类不受故障影响的子系统,得到了其非线性自适应观测器及参数自适应律的设计;另一类受故障影响的子系统的状态是可测的,给出了该类子系统的基于模型监测和故障诊断的观测方案。然后,给出了用于验证本文所提方案的数字示例。     

An Efficient Algorithm for Minimizing Real-Time Transition Systems

We address the problem of performing simultaneously reachability analysis and minimization of real-time transition systems represented by timed automata, i.e., automata extended with a finite set of clock variables. The transitions of the automaton may depend on the values of the clocks and may reset some of the clocks. An efficient algorithm is presented for minimizing a system with respect to a given initial partition that respects the enabling conditions of the transitions of the timed automaton. Our algorithm generates the portion of the minimized system that is reachable from a given initial configuration in time polynomial in the input and the size of the minimal reachable system.     

一种基于贝叶斯分类原理的动态系统故障检测与诊断方法

基于贝叶斯分类原理提出一种能够同时检测与诊断动态系统的过程故障和传感器故障的新方法。给出的算法是递推形式的。仿真结果表明具有灵敏度高和响应速度快等优点。     

基于协同进化算法的高维模糊分类系统的设计

基于协同进化算法,提出一种高维模糊分类系统的设计方法．首先定义系统的精确性指标,给出解释性的必要条件,利用聚类算法辨识初始模型．相互协作的3类种群分别代表系统的特征变量、规则前件和模型隶属函数的参数,适应度函数采用3类种群合作计算的策略,在算法运行中利用基于相似性的模型简化技术约简模糊系统,最后利用该方法对Wine问题进行研究．仿真结果表明该方法能够对高维分类问题的特征变量进行选择,同时利用较少规则和模糊集合数达到较高的识别率．     

动态系统的故障诊断技术

提出了一种全新的分类框架, 将故障诊断方法整体分为两大类, 即定性分析的方法和定量分析的方法. 对现有的方法在此框架下进行了划分, 并详细介绍了每种方法的基本思想、研究进展和典型应用, 其中重点讨论了数据驱动的方法. 最后, 简述了故障预测的研究现状, 并探讨了故障诊断研究存在的问题和未来的发展方向.     

Fuzzy Neural Network Models for Classification

In this paper, we combine neural networks with fuzzy logic techniques. We propose a fuzzy-neural network model for pattern recognition. The model consists of three layers. The first layer is an input layer. The second layer maps input features to the corresponding fuzzy membership values, and the third layer implements the inference engine. The learning process consists of two phases. During the first phase weights between the last two layers are updated using the gradient descent procedure, and during the second phase membership functions are updated or tuned. As an illustration the model is used to classify samples from a multispectral satellite image, a data set representing fruits, and Iris data set.     

文本倾向性分析技术在公安大情报系统中的应用研究

构建公安大情报平台是当前公安信息化中的一项重要工作,文章通过对现有文本倾向性分类技术的研究,探讨将这项技术应用到公安情报收集分析工作中的方式和难点,并设计一套能够融合到公安大情报平台中的文本倾向性分类器,以提高公安情报收集分析的效率。     

Methods for the Development of Distributed Real-Time Embedded Systems Using VDM

The development of distributed real-time embedded systems presents a signi-ffcant practical challenge both because of the complexity of distributed computation and because of the need to rapidly assess a wide variety of design alternatives in early stages when requirements are often volatile. Formal methods can address some of these challenges but are often thought to require greater initial investment and longer development cycles than is desirable for the development of noncritical systems in highly competitive markets.In this paper we propose an approach that takes advantage of formal modelling and analysis technology in a lightweight way, making signi cant use of readily available tools. We describe an incremental approach in which detail is progressively added to abstract system-level speci cations of functional and timing properties via intermediate models that express system architecture, concurrency and distribution. The approach is illustrated using a modelof a home automation system. The models are expressed using the Vienna Development Method (VDM) and are validated primarily by scenario-based tests.     

An Efficient Approach for Online Diagnosis of Discrete Event Systems

A novel approach to fault diagnosis of discrete event systems is presented in this paper. The standard approach is based on the offline computation of the set of fault events that may have occurred at each reachable state, providing a fast online diagnosis at a price of excessive memory requirements. A different approach is here adopted, which is based on the online computation of the set of possible fault events required to explain the last observed event. This is efficiently achieved by modelling the plant by Petri nets, since their mathematical representation permits to formulate the fault diagnosis problems in terms of mathematical programming, which is a standard tool. Moreover, the graphical representation of the net allows the diagnoser agent to compute off-line reduced portions of the net in order to improve the efficiency of the online computation, without a big increase in terms of memory requirement.     

A Suboptimal Dual Control Method for the Stochastic Systems with Parameters Drifting

This paper proposed a suboptimal dual control method for the stochastic systems with parameters drifting. Based on the consideration of the performance index control and the parameter estimation, the minimum variance of the system output and the estimated covariance matrix of the parameters estimation are both put into the performance index to evaluate the control quality. Furthermore, a dual control strategy is designed which is of the property of learning and control. Simulation results illustrate the effectiveness of the algorithm.     

一种基于Linux内核的高效包分类算法

针对iptables核心包分类算法的低效问题,提出一种符合Linux内核限制条件并充分利用已有内核机制的高效包分类算法。该算法具备动态更新、多维匹配、实施速度快等主流包分类算法的特点,适合实际应用。实验结果表明在规则库较大的情况下,算法性能有很大提高。     

动态系统的主动故障诊断技术

目前, 绝大多数动态系统的故障诊断方法仅利用系统的输入输出数据, 当数据中包含的故障特征不明显时, 诊断效果不佳. 动态系统的主动故障诊断方法通过向系统注入适当的辅助信号, 增强输入输出数据中特定故障的表现来提高对该故障的诊断能力. 主动故障诊断的研究不仅对于丰富与发展动态系统故障诊断理论具有重要价值, 还对故障诊断技术在实际中的推广应用具有重要意义. 本文阐述了主动故障诊断的思想, 介绍了用于增强故障表现的辅助信号所具有的特征, 分类概述了现有文献中的辅助信号设计方法, 分析了故障表现增强的形式与主动故障诊断技术的实现方式, 探讨了主动故障诊断中亟待解决的问题与未来的发展方向.     

Diagnosis of Discrete Event Systems Using Decentralized Architectures

Decentralized diagnosis of discrete event systems has received a lot of attention to deal with distributed systems or with systems that may be too large to be diagnosed by one centralized site. This paper casts the problem of decentralized diagnosis in a new hierarchical framework. A key feature is the exploitation of different local decisions together with appropriate rules for their fusion. This includes local diagnosis decisions that can be interpreted as “conditional decisions.” Under this new framework, a series of new decentralized architectures are defined and studied. The properties of their corresponding notions of decentralized diagnosability are characterized and their relationship with existing work described. Corresponding verification algorithms are also presented and on-line diagnosis strategies discussed.

深度强化学习的图像特征高效分类方法仿真

针对现有的图像特征分类方法收敛性差,分类无法满足日益增加的网络需求的现状,本文提出了一种基于深度强化学习的图像特征分类方法。通过对目标图像特征区域进行复域Contourlet分解,过滤处理分解结果,从而可以将目标图像子带系数矩阵提取出来,求取系数矩阵的相关特征。采取深度学习网络,使所选图像的特征向量直接经过已训练的层状网络深度模型,完成图像特征分类。实验结果表明,所提方法的误识率比现有方法明显降低,收敛速度明显提升。改进方法比传统方法更具优势,能够满足图像特征分类智能化处理的需要。     

一类非线性系统的自适应观测器

This paper investigates the means to design the ob- server for a class of nonlinear systems with Lipschitz conditions and unknown parameters.A new design approach of full-order state adaptive observer is proposed.The constructed observer could guarantee the error of state and the error of parameter estimation to asymptotically converge to zero.Furthermore,a numerical example is provided to verify the effectiveness of the observer.     

浅析分类方法的发展

分类是数据挖掘的重要任务之一,分类在实际应用中有广泛的应用,如医疗事业、信用等级等。近年来,分类方法得到了发展,本文对这些方法进行了归纳分析,总结了今后分类方法发展的方向。     

一类非线性系统的自适应观测器

研究一类非线性系统的观测器设计方法, 这类非线性系统满足 Lipschitz 条件且含有未知参数. 提出了全状态自适应观测器设计的新方法. 构造的观测器能保证状态估计误差及参数估计误差渐近收敛于零. 文中给出数值例验证了观测器的有效性.