Xiaoqin Zeng

Hohai University, Nan-ching, Jiangsu, China

Are you Xiaoqin Zeng?

Claim your profile

Publications (18)12.71 Total impact

  • Caigen Zhou · Xiaoqin Zeng · Jianjiang Yu · Haibo Jiang
    [Show abstract] [Hide abstract]
    ABSTRACT: A unified associative memory model with a novel method for designing associative memories is presented in this paper. Based on continuous recurrent neural networks, bipolar patterns inputted from external can cause the output of neural networks to be memorized patterns. In the method, two conditions relevant to external inputs are derived to ensure the network states converge to a stable interval, and an exponential stable criterion is proposed for the network being a bipolar associative memory with higher recall speed. By introducing a tunable slope activation function and considering time delay, the proposed model is general and can recall the memorized patterns in auto-associative and hetero-associative way, while higher robust and more flexible memory can be obtained through the proposed method. Experimental verification demonstrates the effectiveness and generalization of the proposed method.
    No preview · Article · Jan 2016 · Neurocomputing
  • Le Cheng · Lixin Han · Xiaoqin Zeng · Yuetang Bian · Hong Yan
    [Show abstract] [Hide abstract]
    ABSTRACT: Based on the Cockroach Swarm Optimization (CSO) algorithm, a new Cockroach Colony Optimization (CCO) algorithm is presented and applied to the Robot Path Planning (RPP) problem in this paper. In the CCO algorithm, an improved grid map is used for environment modeling, and 16-geometry and 8-geometry are introduced, respectively, in food division and cockroach search operation. Moreover, the CCO algorithm adopts a non-probabilistic search strategy, which avoids a lot of invalid searches. Furthermore, by introducing a novel rotation scheme in the above CCO algorithm, an Adaptive Cockroach Colony Optimization (ACCO) algorithm is presented for the 2-D Rod-Like Robot Path Planning (RLRPP) problem. The simulation results show that the CCO algorithm can plan an optimal or approximately optimal collision-free path with linear time complexities. With the ACCO algorithm, the robot can accomplish intelligent and adaptive rotations to avoid obstacles and pass through narrow passages along the better path.
    No preview · Article · Apr 2015 · Journal of Bionic Engineering
  • Caigen Zhou · Xiaoqin Zeng · Haibo Jiang · Lixin Han
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents a novel method for designing associative memories based on discrete recurrent neural networks to accurately memorize the networks’ external inputs. In the method, a generalized model is proposed for bipolar auto-associative memory and establishing an exponential stable criteria of the networks. The model is of generality with considering time delay and introducing a tunable slope activation function, and can robustly recall the memorized external input patterns in an auto-associative way. Experimental verification demonstrates that the proposed method is more effective and generalized than other existing ones.
    No preview · Article · Apr 2015 · Neurocomputing
  • Jiufeng Zhou · Lixin Han · Yuan Yao · Xiaoqin Zeng · Feng Xu
    [Show abstract] [Hide abstract]
    ABSTRACT: Analyzing the underlying social network is very important for the development of online applications. Owing to the increasingly growing size of these networks, parallel techniques play important roles in many network analysis tasks. In this paper, we explore the link sign prediction problem in large-scale online social networks, and propose a parallel approach, called PLSP, to solve the problem. Specifically, we first extract a set of features that serve as a base for prediction. Experiments on several real datasets show that these features outperform those proposed by existing methods in predictive accuracy. Next, we present two speedup strategies, i.e. dataset division and feature selection, to shorten the training time. Experimental evaluations show that our parallel approach is much faster than the traditional non-parallel method and achieves higher predictive accuracy than other methods at the same time.
    No preview · Article · Jun 2013 · The Computer Journal
  • Source
    Dataset: wu article
    Shengli Wu · Yaxin Bi · Xiaoqin Zeng

    Full-text · Dataset · Jun 2013
  • Yan Xu · Xiaoqin Zeng · Shuiming Zhong
    [Show abstract] [Hide abstract]
    ABSTRACT: The purpose of supervised learning with temporal encoding for spiking neurons is to make the neurons emit a specific spike train encoded by the precise firing times of spikes. If only running time is considered, the supervised learning for a spiking neuron is equivalent to distinguishing the times of desired output spikes and the other time during the running process of the neuron through adjusting synaptic weights, which can be regarded as a classification problem. Based on this idea, this letter proposes a new supervised learning method for spiking neurons with temporal encoding; it first transforms the supervised learning into a classification problem and then solves the problem by using the perceptron learning rule. The experiment results show that the proposed method has higher learning accuracy and efficiency over the existing learning methods, so it is more powerful for solving complex and real-time problems.
    No preview · Article · Mar 2013 · Neural Computation
  • Yan Xu · Xiaoqin Zeng · Lixin Han · Jing Yang
    [Show abstract] [Hide abstract]
    ABSTRACT: We use a supervised multi-spike learning algorithm for spiking neural networks (SNNs) with temporal encoding to simulate the learning mechanism of biological neurons in which the SNN output spike trains are encoded by firing times. We first analyze why existing gradient-descent-based learning methods for SNNs have difficulty in achieving multi-spike learning. We then propose a new multi-spike learning method for SNNs based on gradient descent that solves the problems of error function construction and interference among multiple output spikes during learning. The method could be widely applied to single spiking neurons to learn desired output spike trains and to multilayer SNNs to solve classification problems. By overcoming learning interference among multiple spikes, our method has high learning accuracy when there are a relatively large number of output spikes in need of learning. We also develop an output encoding strategy with respect to multiple spikes for classification problems. This effectively improves the classification accuracy of multi-spike learning compared to that of single-spike learning.
    No preview · Article · Feb 2013 · Neural networks: the official journal of the International Neural Network Society
  • Zhibin Liu · Xiaoqin Zeng · Huiyi Liu
    [Show abstract] [Hide abstract]
    ABSTRACT: How to improve the learning efficiency and optimize the encapsulation of subtasks is a key problem that hierarchical reinforcement learning needs to solve. This paper proposes a modular hierarchical reinforcement learning al-gorithm, named MHRL, in which the modularized hierarchical subtasks are trained by their independent reward systems. During learning, the MHRL pro-duces an optimization strategy for different modular layers, which makes inde-pendent modules be able to concurrently execute. In addition, this paper pre-sents some experimental results for solving application problems with nested learning processes. The results show that the MHRL can increase learning reus-ability and improve learning efficiency dramatically.
    No preview · Conference Paper · Jul 2012
  • Shengli Wu · Xiaoqin Zeng
    [Show abstract] [Hide abstract]
    ABSTRACT: Blogs have been popular social networking platforms in recent years. Blog opinion retrieval is one of the key issues that needs to be solved. In this paper, we investigate if the Condorcet fusion and the weighted Condorcet fusion can be used for effectiveness improvement of blog opinion retrieval. The experiments carried out with the data set from the TREC 2008 Blog track show that the Condorcet fusion is effective and the weighted Condorcet fusion, with its weights trained by linear discriminant analysis, is very effective. Both of them outperform the best component result by a clear margin.
    No preview · Conference Paper · Jan 2012
  • Source
    Shengli Wu · Yaxin Bi · Xiaoqin Zeng
    [Show abstract] [Hide abstract]
    ABSTRACT: In information retrieval systems and digital libraries, retrieval result evaluation is a very important aspect. Up to now, almost all commonly used metrics such as average precision and recall level precision are ranking based metrics. In this work, we investigate if it is a good option to use a score based method, the Euclidean distance, for retrieval evaluation. Two variations of it are discussed: one uses the linear model to estimate the relation between rank and relevance in resultant lists, and the other uses a more sophisticated cubic regression model for this. Our experiments with two groups of submitted results to TREC demonstrate that the introduced new metrics have strong correlation with ranking based metrics when we consider the average of all 50 queries. On the other hand, our experiments also show that one of the variations (the linear model) has better overall quality than all those ranking based metrics involved. Another surprising finding is that a commonly used metric, average precision, may not be as good as previously thought.
    Full-text · Conference Paper · Jul 2011
  • Source
    Shengli Wu · Yaxin Bi · Xiaoqin Zeng
    [Show abstract] [Hide abstract]
    ABSTRACT: In information retrieval, data fusion has been investigated by many researchers. Previous investigation and experimentation demonstrate that the linear combination method is an effective data fusion method for combining multiple information retrieval results. One advantage is its flexibility since different weights can be assigned to different component systems so as to obtain better fusion results. However, how to obtain suitable weights for all the component retrieval systems is still an open problem. In this paper, we use the multiple linear regression technique to obtain optimum weights for all involved component systems. Optimum is in the least squares sense that minimize the difference between the estimated scores of all documents by linear combination and the judged scores of those documents. Our experiments with four groups of runs submitted to TREC show that the linear combination method with such weights steadily outperforms the best component system and other major data fusion methods such as CombSum, CombMNZ, and the linear combination method with performance level/performance square weighting schemas by large margins.
    Full-text · Conference Paper · Jan 2011
  • Shuiming Zhong · Xiaoqin Zeng · Huiyi Liu · Yan Xu
    [Show abstract] [Hide abstract]
    ABSTRACT: The computation of the sensitivity of a Madaline’s output to its parameter perturbation is systematically discussed. Firstly, according to the discrete feature of Adalines, a method based on discrete stochastic technique is proposed, which derives some analytical formulas for the computation of Adalines’ sensitivity. The method can theoretically solve some problems that are unsolvable by the existing methods based on continuous stochastic techniques, release some unpractical constraints, and make it available to theoretically analyze the approximation error of Adalines’ sensitivity. Secondly, on the basis of the sensitivity of Adalines and the structural characteristics of Madalines, a new selection strategy depending on a type of dedication degree for computing Madalines’ sensitivity is proposed, which is superior to current popular way of simply averaging in both precision and complexity. The proposed formulas and algorithm have the advantages of simplicity, low computational complexity, small approximation error, and high generality, as have been verified by a great amount of experimental simulations.
    No preview · Article · Dec 2010 · Sciece China. Information Sciences
  • Shengli Wu · Yaxin Bi · Xiaoqin Zeng
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper we present a new data fusion method in information retrieval, which uses ranking information of resultant documents. Our method is based on the modelling of rank-probability of relevance of documents in resultant document list using logarithmic models. The proposed method is more effective than other data fusion methods which also use ranking information, and is as effective as some data fusion methods which rely on reliable scoring information.
    No preview · Conference Paper · Sep 2010
  • Source
    Jun Kong · Dianxiang Xu · Xiaoqin Zeng
    [Show abstract] [Hide abstract]
    ABSTRACT: Poor design has been a major source of software security problems. Rigorous and designer-friendly methodologies for modeling and analyzing secure software are highly desirable. A formal method for software development, however, often suffers from a gap between the rigidity of the method and the informal nature of system requirements. To narrow this gap, this paper presents a UML-based framework for modeling and analyzing security threats (i.e. potential security attacks) rigorously and visually. We model the intended functions of a software application with UML statechart diagrams and the security threats with sequence diagrams, respectively. Statechart diagrams are automatically converted into a graph transformation system, which has a well-established theoretical foundation. Method invocations in a sequence diagram of a security threat are interpreted as a sequence of paired graph transformations. Therefore, the analysis of a security threat is conducted through simulating the state transitions from an initial state to a final state triggered by method invocations. In our approach, designers directly work with UML diagrams to visually model system behaviors and security threats while threats can still be rigorously analyzed based on graph transformation.
    Full-text · Article · Sep 2010 · International Journal of Software Engineering and Knowledge Engineering
  • Xianming Chen · Xiaoqin Zeng · Rong Chu · Shuiming Zhong
    [Show abstract] [Hide abstract]
    ABSTRACT: The sensitivity of a neural network's output to its parameter variation is an important issue in both theoretical researches and practical applications of neural networks. This paper proposes a quantified sensitivity measure of the Radial Basis Function Neural Networks (RBFNNs) to input variation. The sensitivity is defined as the mathematical expectation of squared output deviations caused by input variations. In order to quantify the sensitivity, the input is treated as a statistical variable and a numerical integral technique is employed to approximately compute the expectation. Experimental verifications are run and the results show a very good agreement between the proposed sensitivity computation and computer simulation. The quantified sensitivity measure could be helpful as a general tool for evaluating RBFNNs' performance.
    No preview · Conference Paper · Jan 2010
  • Source
    Lei Lu · Xiaoqin Zeng · Shengli Wu · Shuiming Zhong
    [Show abstract] [Hide abstract]
    ABSTRACT: Ensemble learning is one of the main directions in machine learning and data mining, which allows learners to achieve higher training accuracy and better generalization ability. In this paper, with an aim at improving generalization performance, a novel approach to construct an ensemble of neural networks is proposed. The main contributions of the approach are its diversity measure for selecting diverse individual neural networks and weighted fusion technique for assigning proper weights to the selected individuals. Experimental results demonstrate that the proposed approach is effective.
    Full-text · Conference Paper · Jan 2008
  • Source
    Shengli Wu · Qili Zhou · Yaxin Bi · Xiaoqin Zeng
    [Show abstract] [Hide abstract]
    ABSTRACT: In information retrieval, the linear combination method is a very flexible and effective data fusion method, since different weights can be assigned to different component systems. However, it remains an open question which weighting schema is good. Previously, a simple weighting schema was very often used: for a system, its weight is assigned as its average performance over a group of training queries. In this paper, we investigate the weighting issue by extensive experiments. We find that, a series of power functions of average performance, which can be implemented as efficiently as the simple weighting schema, is more effective than the simple weighting schema for data fusion.
    Full-text · Conference Paper · Jan 2008
  • Jia Tang · Xiaoqin Zeng · Lei Lu
    [Show abstract] [Hide abstract]
    ABSTRACT: Ensemble learning to construct learners in regression and classification has practically and theoretically been proved to be able to improve the generalization capability of the learners. Nowadays, most neural network ensembles are obtained by manipulating training data and networks' architecture etc, such as Bagging, Boosting, and other methods like evolutionary techniques. In this paper, a new method to construct neural network ensembles is presented, which aims at selecting, by means of output sensitivity of an individual network, the most diverse members from a pool of trained networks. Conceptually, the sensitivity reflects a network's output behavior at a given data point, for example, the trend of the network's output nearby. So the sensitivity can be helpful to explicitly measure the output diversity among individuals in the pool. In our research, Multilayer Perceptrons (MLPs) are focused on, and the sensitivity is adopted as the partial derivative of an MLP's output to its input at data point. Based on the sensitivity, we developed four different measures for the selection of the most diverse individuals from a given pool of trained MLPs. Some experiments on the UCI benchmark data have been conducted, and the comparisons of our results with those from Bagging and Boosting show that our method has some advantages over the existing ensemble methods in ensemble size and generalization performance.
    No preview · Conference Paper · Aug 2007