Editorial—Music Information Retrieval

Increasing availability of music data via Internet evokes demand for efficient search through music files. Users' interests include melody tracking, harmonic structure analysis, timbre identification, and so on. We visualize, in an illustrative example, why content based search is needed for music data and what difficulties must be overcame to build an intelligent music information retrieval system.     

Textual Data Mining to Support Science and Technology Management

This paper surveys applications of data mining techniques to large text collections, and illustrates how those techniques can be used to support the management of science and technology research. Specific issues that arise repeatedly in the conduct of research management are described, and a textual data mining architecture that extends a classic paradigm for knowledge discovery in databases is introduced. That architecture integrates information retrieval from text collections, information extraction to obtain data from individual texts, data warehousing for the extracted data, data mining to discover useful patterns in the data, and visualization of the resulting patterns. At the core of this architecture is a broad view of data mining—the process of discovering patterns in large collections of data—and that step is described in some detail. The final section of the paper illustrates how these ideas can be applied in practice, drawing upon examples from the recently completed first phase of the textual data mining program at the Office of Naval Research. The paper concludes by identifying some research directions that offer significant potential for improving the utility of textual data mining for research management applications.     

Using Rough Sets with Heuristics for Feature Selection

Practical machine learning algorithms are known to degrade in performance (prediction accuracy) when faced with many features (sometimes attribute is used instead of feature) that are not necessary for rule discovery. To cope with this problem, many methods for selecting a subset of features have been proposed. Among such methods, the filter approach that selects a feature subset using a preprocessing step, and the wrapper approach that selects an optimal feature subset from the space of possible subsets of features using the induction algorithm itself as a part of the evaluation function, are two typical ones. Although the filter approach is a faster one, it has some blindness and the performance of induction is not considered. On the other hand, the optimal feature subsets can be obtained by using the wrapper approach, but it is not easy to use because of the complexity of time and space. In this paper, we propose an algorithm which is using rough set theory with greedy heuristics for feature selection. Selecting features is similar to the filter approach, but the evaluation criterion is related to the performance of induction. That is, we select the features that do not damage the performance of induction.     

音乐检索特征库构建方法

合理的音乐特征库构建方法对于实现准确音乐检索具有重要意义.以基于内容音乐检索框架为基础,将音乐特征库的构建分为采用基音提取方法建库、采用乐谱信息建库和采用MIDI分析方法建库3种方式,并提出一种基音提取及后处理方法和MIDI分析方法实现音乐特征库的构建.实验结果表明,这两种建库方法是正确有效的,可以准确、快速地实现音乐特征库的构建.     

Opportunity explorer: Navigating large databases using knowledge discovery templates

TheNielsen Opportunity Explorer ^tmproduct can be used by sales and trade marketing personnel within consumer packaged goods manufacturers to understand how their products are performing in the market place and find opportunities to sell more product, more profitably to the retailers. Opportunity Explorer uses data collected at the point-of-sale terminals, and by auditors of A. C. Nielsen. Opportunity Explorer uses a knowledge-base of market research expertise to analyze large databases and generate interactive reports using knowledge discovery templates, converting a large space of data into concise, inter-linkedinformation frames. Each information frame addresses specific business issues, and leads the user to seek related information by means of dynamically created hyperlinks.     

Fisher算法在语音声学模型分析中的研究与应用

语音识别中,通常把发音过程看作短时平衡的随机过程,为同时兼顾到平隐性和短时性,马尔可失链成为语音建模的有效工具。本文在声学模型研究中,首次引进了多元统计分析的理论,用Fisher算法对语音模型的状态中心分类进行了研究,提出了一种新的基于Fisher算法的状态中心估计方法,并同时指出了在汉语语音识别中,HMM状态数宜取在6－8之间。     

极小极大规则学习及在决策树规则简化中的应用

文中在粗糙集理论中的约简概念的启发下提出极小规则和极大规则的概念及极小极大规则学习。     

分布式大数据函数依赖发现

在关系数据库中,函数依赖发现是一种十分重要的数据库分析技术,在知识发现、数据库语义分析、数据质量评估以及数据库设计等领域有着广泛的应用.现有的函数依赖发现算法主要针对集中式数据,通常仅适用于数据规模比较小的情况.在大数据背景下,分布式环境函数依赖发现更富有挑战性.提出了一种分布式环境下大数据的函数依赖发现算法,其基本思想是首先在各个节点利用本地数据并行进行函数依赖发现,基于以上发现的结果对函数依赖候选集进行剪枝,然后进一步利用函数依赖的左部(left hand side, LHS)的特征,对函数依赖候选集进行分组,针对每一组候选函数依赖并行执行分布式环境发现算法,最终得到所有函数依赖.对不同分组情况下所能检测的候选函数依赖数量进行了分析,在算法的执行过程中,综合考虑了数据迁移量和负载均衡的问题.在真实的大数据集上的实验表明,提出的检测算法在检测效率方面与已有方法相比有明显的提升.     

基于不完备信息系统的Rough Set决策规则提取方法

对象信息的不完备性是从实例中归纳学习的最大障碍。针对不完备的信息，研究了基于不完备信息系统的粗糙集决策规则提取方法，利用分层递减约简算法，通过实例有效地分析和处理了含有缺省数据和不精确数据的信息系统，扩展了粗糙集的应用领域。     

多媒体数据库中基于内容的音频分类综述

根据不同的应用背景和分类对象,分别概述了多媒体数据库中基于内容的音频分类的一些关键技术,如特征提取和分类器设计,并分析了各种基于内容的音频分类方法的优缺点,讨论了存在的问题,指出了未来的研究方向。     

Redundant Hash Addressing of Feature Sequences Using the Self-Organizing Map

Kohonen's Self-Organizing Map (SOM) is combined with the Redundant Hash Addressing (RHA) principle. The SOM encodes the input feature vector sequence into the sequence of best-matching unit (BMU) indices and the RHA principle is then used to associate the BMU index sequence with the dictionary items. This provides a fast alternative for dynamic programming (DP) based methods for comparing and matching temporal sequences. Experiments include music retrieval and speech recognition. The separation of the classes can be improved by error-corrective learning. Comparisons to DP-based methods are presented.     

智能化搜索引擎技术的研究进展

阐述了传统信息获取的几种模型，分析比较它们之间的优劣，归纳总结了信息获取模型的层次框架．对智能化信息获取技术的研究进展和概况进行综述，并给出了若干值得研究的问题及相应的关键技术．     

A survey on the use of pattern recognition methods for abstraction, indexing and retrieval of images and video

The need for content-based access to image and video information from media archives has captured the attention of researchers in recent years. Research efforts have led to the development of methods that provide access to image and video data. These methods have their roots in pattern recognition. The methods are used to determine the similarity in the visual information content extracted from low level features. These features are then clustered for generation of database indices. This paper presents a comprehensive survey on the use of these pattern recognition methods which enable image and video retrieval by content.     

基于内容的音频与音乐分析综述

机器听觉包括三大研究领域:语音信号处理与识别、一般音频信号分析、基于内容的音乐信号分析.其中,语音信号处理与识别早已成为一个传统的研究热点.随着信息科学与技术的迅速发展,基于内容的音频与音乐信号分析也逐渐成为一个新的研究热点,近几年来取得了大量研究成果.文章将对1990年以后该领域上所取得的研究成果进行综述,包括基于内容的音频或音乐信号自动分类、分割、检索以及音乐作品自动分析等内容.     

基于小波的心音信号分析及其特征提取

心音信号是人体最重要的生理信号之一,它包含了人体心脏和血管中丰富的原始信息.心脏杂音和心音改变的出现,往往是心脏病的最早特征.由于心音信号是一种典型的非平稳信号,所以传统的频域分析已经不能满足研究的需要.文章将时域、时频和功率谱能量等特性分析相结合,研究心音信号的分析方法,提取各种特征以区分不同的心音.理论分析和仿真实...     

LEARNING IN RELATIONAL DATABASES: A ROUGH SET APPROACH

Knowledge discovery in databases, or dala mining, is an important direction in the development of data and knowledge-based systems. Because of the huge amount of data stored in large numbers of existing databases, and because the amount of data generated in electronic forms is growing rapidly, it is necessary to develop efficient methods to extract knowledge from databases. An attribute-oriented rough set approach has been developed for knowledge discovery in databases. The method integrates machine-learning paradigm, especially learning-from-examples techniques, with rough set techniques. An attribute-oriented concept tree ascension technique is first applied in generalization, which substantially reduces the computational complexity of database learning processes. Then the cause-effect relationship among the attributes in the database is analyzed using rough set techniques, and the unimportant or irrelevant attributes are eliminated. Thus concise and strong rules with little or no redundant information can be learned efficiently. Our study shows that attribute-oriented induction combined with rough set theory provide an efficient and effective mechanism for knowledge discovery in database systems.     

Ontological Approach for Information Discovery in Internet Databases

The Internet has solved the age-old problem of network connectivity and thus enabling the potential access to, and data sharing among large numbers of databases. However, enabling users to discover useful information requires an adequate metadata infrastructure that must scale with the diversity and dynamism of both users' interests and Internet accessible databases. In this paper, we present a model that partitions the information space into a distributed, highly specialized domain ontologies. We also introduce inter-ontology relationships to cater for user-based interests across ontologies defined over Internet databases. We also describe an architecture that implements these two fundamental constructs over Internet databases. The aim of the proposed model and architecture is to eventually facilitate data discovery and sharing for Internet databases.