基于TDT技术的Web主题搜索分析与设计

提出了一种结合最新TDT技术、基于增强学习的优先Web环境主题搜索策略,并以此设计主题搜索器系统。该系统通过引入基于领域知识的TDT文本分类技术,大大改进了基于关键字的Naive Bayes模型主题相似性判别的准确性;通过引入基于增强学习的页面评估函数特征化主题Web环境,有效地提高了稀有信息的搜索能力。试验结果表明,该系统具有较高的实用性。     

Hierarchical bayesian models for regularisation in sequential learning

We show that a hierarchical Bayesian modeling approach allows us to perform regularization in sequential learning. We identify three inference levels within this hierarchy: model selection, parameter estimation, and noise estimation. In environments where data arrive sequentially, techniques such as cross validation to achieve regularization or model selection are not possible. The Bayesian approach, with extended Kalman filtering at the parameter estimation level, allows for regularization within a minimum variance framework. A multilayer perceptron is used to generate the extended Kalman filter nonlinear measurements mapping. We describe several algorithms at the noise estimation level that allow us to implement on-line regularization. We also show the theoretical links between adaptive noise estimation in extended Kalman filtering, multiple adaptive learning rates, and multiple smoothing regularization coefficients.     

一种基于强化学习的学习Agent

强化学习通过感知环境状态和从环境中获得不确定奖赏值来学习动态系统的最优行为策略,是构造智能Agent的核心技术之一,在面向Agent的开发环境AODE中扩充BDI模型,引入策略和能力心智成分,采用强化学习技术实现策略构造函数,从而提出一种基于强化学习技术的学习Agent,研究AODE中自适应Agent物结构和运行方式,使智能Agent具有动态环境的在线学习能力,有效期能够有效地满足Agent各种心智要求。     

Concept mapping your Web searches: a design rationale and Web-enabled application

Although it has become very common to use World Wide Web‐based information in many educational settings, there has been little research on how to better search and organize Web‐based information. This paper discusses the shortcomings of Web search engines and Web browsers as learning environments and describes an alternative Web search environment that combines a concept mapping and a data mining technique to address their drawbacks.     

An adaptive bi-flight cuckoo search with variable nests for continuous dynamic optimization problems

This paper presents an adaptive bi-flight cuckoo search algorithm for continuous dynamic optimization problems. Unlike the standard cuckoo search which relies on Levy flight, the proposed method uses two types of flight that are chosen adaptively by a learning automaton to control the global and local search ability of the method during the run. Furthermore, a variable nest scheme and a new cuckoo addition mechanism are introduced. A greedy local search method is also integrated to refine the best found solution. An extensive set of experiments is conducted on a variety of dynamic environments generated by the moving peaks benchmark, to evaluate the performance of the proposed approach. Results are also compared with those of other state-of-the-art algorithms from the literature. The experimental results indicate the effectiveness of the proposed approach.     

A feature-free search query classification approach using semantic distance

When classifying search queries into a set of target categories, machine learning based conventional approaches usually make use of external sources of information to obtain additional features for search queries and training data for target categories. Unfortunately, these approaches rely on large amount of training data for high classification precision. Moreover, they are known to suffer from inability to adapt to different target categories which may be caused by the dynamic changes observed in both Web topic taxonomy and Web content. In this paper, we propose a feature-free classification approach using semantic distance. We analyze queries and categories themselves and utilizes the number of Web pages containing both a query and a category as a semantic distance to determine their similarity. The most attractive feature of our approach is that it only utilizes the Web page counts estimated by a search engine to provide the search query classification with respectable accuracy. In addition, it can be easily adaptive to the changes in the target categories, since machine learning based approaches require extensive updating process, e.g., re-labeling outdated training data, re-training classifiers, to name a few, which is time consuming and high-cost. We conduct experimental study on the effectiveness of our approach using a set of rank measures and show that our approach performs competitively to some popular state-of-the-art solutions which, however, frequently use external sources and are inherently insufficient in flexibility.     

Searching the Web with Queries

In this paper we study the problem of searching the Web with online learning algorithms. We consider that Web documents can be represented by vectors of n boolean attributes. A search engine is viewed as a learner, and a user is viewed as a teacher. We investigate the number of queries a search engine needs from the user to search for a collection of Web documents. We design several efficient learning algorithms to search for any collection of documents represented by a disjunction (or a conjunction) of relevant attributes with the help of membership queries or equivalence queries.     

自适应最优搜索算法的网络蜘蛛的设计与实现

主题搜索引擎NonHogSearch改进了采用最优搜索算法的网络蜘蛛的搜索过程,控制了搜索的贪婪程度;并引入网页信噪比概念,从而判断网页是否属于所要搜索的主题页面;进一步,NonHogSearch在爬行过程中自动更新链接的权重,当得到主题相关页面时产生回报,将回报沿链接链路逆向反馈,更新链路上所有链接的Q值,这样避免了网络蜘蛛过早陷入Web搜索空间中局部最优子空间的陷阱,并通过并行方式实现多条链路的同时搜索,改进了搜索引擎的性能。实验证实了该算法在查全率与查准率两方面都有一定的优越性。     

Towards adaptive Web sites: conceptual framework and case study

The creation of a complex Web site is a thorny problem in user interface design. In this paper we explore the notion of adaptive Web sites: sites that semi-automatically improve their organization and presentation by learning from visitor access patterns. It is easy to imagine and implement Web sites that offer shortcuts to popular pages. Are more sophisticated adaptive Web sites feasible? What degree of automation can we achieve?To address the questions above, we describe the design space of adaptive Web sites and consider a case study: the problem of synthesizing new index pages that facilitate navigation of a Web site. We present the PageGather algorithm, which automatically identifies candidate link sets to include in index pages based on user access logs. We demonstrate experimentally that PageGather outperforms the Apriori data mining algorithm on this task. In addition, we compare PageGather's link sets to pre-existing, human-authored index pages.     

Incidental memory and navigation in panoramic virtual reality for electronic commerce

Recently much effort has been dedicated to designing and implementing World Wide Web sites for virtual shopping and e-commerce. Despite this effort, relatively little empirical work has been done to determine the effectiveness with which different site designs sell products. We report three experiments in which participants were asked to search for products in various experimental e-commerce sites. Across the experiments participants were asked to search in either QTVR (QuickTime Virtual Reality), hypertext, or pictorially rich hypertext environments; they were then tested for their ability to recall the products seen and to recognize product locations. The experiments demonstrated that when using QTVR (Experiments 1, 2, and 3) or pictorial environments (Experiment 2), participants retained more information about products that were incidental to their goals. In two of the experiments it was shown that participants navigated more efficiently when using a QTVR environment. The costs and benefits of using 3D virtual environments for on-line shops are discussed. Actual or potential applications of this research include support for the development of e-commerce design guidelines.     

A hybridisation of adaptive variable neighbourhood search and large neighbourhood search: Application to the vehicle routing problem

In this paper, an adaptive variable neighbourhood search (AVNS) algorithm that incorporates large neighbourhood search (LNS) as a diversification strategy is proposed and applied to the capacitated vehicle routing problem. The AVNS consists of two stages: a learning phase and a multi-level VNS with guided local search. The adaptive aspect is integrated in the local search where a set of highly successful local searches is selected based on the intelligent selection mechanism. In addition, the hybridisation of LNS with the AVNS enables the solution to escape from the local minimum effectively. To make the algorithm more competitive in terms of the computing time, a simple and flexible data structure and a neighbourhood reduction scheme are embedded. Finally, we adapt a new local search move and an effective removal strategy for the LNS. The proposed AVNS was tested on the benchmark data sets from the literature and produced very competitive results.     

一种基于动态小生境的自组织学习算法

提出了一种基于动态小生境的自组织学习算法(dynamic niche-based self-organizing learning algorithm,简称DNSLA),实现了基于0-1编码的动态学习机制.种群中的个体由被动适应转为主动学习,即通过系统的自组织学习而实现与环境的友好交互,因而具有更强健的动态环境适应能力,能够及时、准确地侦测到环境的变化并跟踪极值点在搜索空间内的运动轨迹,具有良好的可移植性和很强的泛化能力.一系列动态测试问题的对比仿真实验结果表明,该算法即使在剧烈动荡的环境中也能很好地与环境进行稳定而友好的交互学习,表现出了很强的鲁棒性,其动态搜索能力和极值点跟踪能力远优于同类搜索方法.     

Tool use in computer-based learning environments: towards a research framework

Computer-based learning environments often confront learners with a number of tools, i.e. non-embedded support devices. Such environments assume learners to be good judges of their own learning needs. However, research indicates that students do not always make adequate choices for their learning process. This especially becomes an issue with the use of open learning environments, which are assumed to foster the acquisition of complex problem solving skills. Such open learning environments offer students tools to support their learning. Consequently, it is needed to understand factors that influence tool use and acquire insight in learning effects of tool use. Both issues are addressed in this contribution.A review of the existing literature has been undertaken by performing a search on the Web of Science and the PsycInfo database. Results indicate that there is some evidence for learner, tool and task characteristics to influence tool use. No clear indication was found for a learning effect of tool use. The conclusion proposes a research framework for the systematic study of tools.     

EDUCA: A web 2.0 authoring tool for developing adaptive and intelligent tutoring systems using a Kohonen network

This paper presents a Web 2.0 Learning Environment, for a systematic creation of adaptive and intelligent tutoring systems. Authoring contents is made by a community of users including teachers and students. The tutoring systems adapt the contents according to the best learning style using self-organizing maps (SOMs). The SOM was trained for classifying Felder–Silverman learning styles. The most important advantage of these unsupervised neural networks is that they do not require an external teacher for presenting a training set. The approach was implemented under an authoring tool that allows the production of personalized learning material to be used under collaborative and mobile learning environments. The tutoring systems together with the neural network can also be exported to mobile devices. We present different results to the approach working under the authoring tool.     

Adaptive item‐based learning environments based on the item response theory: possibilities and challenges

The popularity of intelligent tutoring systems (ITSs) is increasing rapidly. In order to make learning environments more efficient, researchers have been exploring the possibility of an automatic adaptation of the learning environment to the learner or the context. One of the possible adaptation techniques is adaptive item sequencing by matching the difficulty of the items to the learner's knowledge level. This is already accomplished to a certain extent in adaptive testing environments, where the test is tailored to the person's ability level by means of the item response theory (IRT). Even though IRT has been a prevalent computerized adaptive test (CAT) approach for decades and applying IRT in item‐based ITSs could lead to similar advantages as in CAT (e.g. higher motivation and more efficient learning), research on the application of IRT in such learning environments is highly restricted or absent. The purpose of this paper was to explore the feasibility of applying IRT in adaptive item‐based ITSs. Therefore, we discussed the two main challenges associated with IRT application in such learning environments: the challenge of the data set and the challenge of the algorithm. We concluded that applying IRT seems to be a viable solution for adaptive item selection in item‐based ITSs provided that some modifications are implemented. Further research should shed more light on the adequacy of the proposed solutions.     

Web环境下基于移动多Agent技术的CBIR系统

采用移动多Agent技术,提出了一种灵活的基于内容的Web图像检索系统模型。系统将传统的Web图像检索功能封装于不同的Agent中。各Agent自主运行并相互协调,共同完成分布式Web图像检索。由于图像搜索策略封装于移动Agent中,可在数据源本地实现快速的图像匹配,减少了网络信息交换;网络管理Agent消除了异构网络带来的通信障碍。实验表明该图像检索系统具有良好的自治性、伸缩性和适应性以及灵活的在线扩展能力。     

A modal learning adaptive function neural network applied to handwritten digit recognition

A novel combination of the adaptive function neural network (ADFUNN) and on-line snap-drift learning is presented in this paper and applied to optical and pen-based recognition of handwritten digits [E. Alpaydin, F. Alimoglu for Optical Recognition of Handwritten Digits and E. Alpaydin, C. Kaynak for Pen-Based Recognition of Handwritten Digits http://www.ics.uci.edu/~mlearn/databases/optdigits/http://www.ics.uci.edu/~mlearn/databases/pendigits/]. Snap-drift [S.W. Lee, D. Palmer-Brown, C.M. Roadknight, Performance-guided neural network for rapidly self-organising active network management (Invited Paper), Journal of Neurocomputing, 61C, 2004, pp. 5-20] employs the complementary concepts of common (intersection) feature learning (called snap) and LVQ (drift towards the input patterns) learning, and is a fast, unsupervised method suitable for on-line learning and non-stationary environments where new patterns are continually introduced. ADFUNN [M. Kang, D. Palmer-Brown, An adaptive function neural network (ADFUNN) for phrase recognition, in: The International Joint Conference on Neural Networks (IJCNN05), Montréal, Canada, 2005, D. Palmer-Brown, M. Kang, ADFUNN: An adaptive function neural network, in: The 7th International Conference on Adaptive and Natural Computing Algorithms (ICANNGA05), Coimbra, Portugal, 2005] is based on a linear piecewise neuron activation function that is modified by a novel gradient descent supervised learning algorithm. It has recently been applied to the Iris dataset, and a natural language phrase recognition problem, exhibiting impressive generalisation classification ability with no hidden neurons. The unsupervised single layer snap-drift is effective in extracting distinct features from the complex cursive-letter datasets, and the supervised single layer ADFUNN is capable of solving linearly inseparable problems rapidly. In combination within one network (SADFUNN), these two methods are more powerful and yet simpler than MLPs, at least on this problem domain. We experiment on SADFUNN with two handwritten digits datasets problems from the UCI Machine Learning repository. The problems are learned rapidly and higher generalisation results are achieved than with a MLP.     

Ontology-based semantic search on the Web and its combination with the power of inductive reasoning

Semantic Web search is currently one of the hottest research topics in both Web search and the Semantic Web. In previous work, we have presented a novel approach to Semantic Web search, which allows for evaluating ontology-based complex queries that involve reasoning over the Web relative to an underlying background ontology. We have developed the formal model behind this approach, and provided a technique for processing Semantic Web search queries, which consists of an offline ontological inference step and an online reduction to standard Web search. In this paper, we continue this line of research. We further enhance the above approach by the use of inductive rather than deductive reasoning in the offline inference step. This increases the robustness of Semantic Web search, as it adds the important ability to handle inconsistencies, noise, and incompleteness, which are all very likely to occur in distributed and heterogeneous environments such as the Web. The inductive variant also allows to infer new (not logically deducible) knowledge (from training individuals). We report on a prototype implementation of (both the deductive and) the inductive variant of our approach in desktop search, and we provide extensive new experimental results, especially on the running time and the precision and the recall of our new?approach.     

Exploiting Query Repetition and Regularity in an Adaptive Community-Based Web Search Engine

Search engines continue to struggle with the challenges presented by Web search: vague queries, impatient users and an enormous and rapidly expanding collection of unmoderated, heterogeneous documents all make for an extremely hostile search environment. In this paper we argue that conventional approaches to Web search -- those that adopt a traditional, document-centric, information retrieval perspective -- are limited by their refusal to consider the past search behaviour of users during future search sessions. In particular, we argue that in many circumstances the search behaviour of users is repetitive and regular; the same sort of queries tend to recur and the same type of results are often selected. We describe how this observation can lead to a novel approach to a more adaptive form of search, one that leverages past search behaviours as a means to re-rank future search results in a way that recognises the implicit preferences of communities of searchers. We describe and evaluate the I-SPY search engine, which implements this approach to collaborative, community-based search. We show that it offers potential improvements in search performance, especially in certain situations where communities of searchers share similar information needs and use similar queries to express these needs. We also show that I-SPY benefits from important advantages when it comes to user privacy. In short, we argue that I-SPY strikes a useful balance between search personalization and user privacy, by offering a unique form of anonymous personalization, and in doing so may very well provide privacy-conscious Web users with an acceptable approach to personalized search.