Three perspectives of data mining

This paper reviews three recent books on data mining written from three different perspectives, i.e., databases, machine learning, and statistics. Although the exploration in this paper is suggestive instead of conclusive, it reveals that besides some common properties, different perspectives lay strong emphases on different aspects of data mining. The emphasis of the database perspective is on efficiency because this perspective strongly concerns the whole discovery process and huge data volume. The emphasis of the machine learning perspective is on effectiveness because this perspective is heavily attracted by substantive heuristics working well in data analysis although they may not always be useful. As for the statistics perspective, its emphasis is on validity because this perspective cares much for mathematical soundness behind mining methods.     

Forming the optimal union of multiple databases

Many organizations, best illustrated by libraries, have access to hundreds of databases possessing varying degrees of complimentary and overlapping records. While users may receive positive marginal benefits from data duplications, all databases and their services cannot be supported because of resource limitations. This paper attempts to conceptualize the problem of database collection in an environment of multiple databases, with differential content and performance characteristics, diverse users, and limited resources. It defines the database collection problem as a constrained zero-one integer programming problem and solves for the optimal combination or union of databases. Several extensions are shown, where special conditions are imposed on the relationships between databases and/or their availability.     

信息管理系统在规模化种鸡场的应用

在深入调查规模化畜禽养殖场的经营管理现状的基础上,系统分析了规模化畜禽养殖场生产条件下畜禽养殖企业的新特点和新要求,运用PowerBuild9．0设计软件,设计了能满足现代规模化畜禽养殖场生产经营管理需要的信息管理模块。该系统在规模化种鸡场生产管理中实施应用,取得良好效果。     

基于无线物联网数据库的环境监测系统的实现

基于ARM9s3c2440处理器和嵌入式Linux系统平台,利用嵌入式数据库SQLite设计了环境监测系统。通过无线网络访问数据库里的温湿度数据,并利用JavaScript脚本绘制出温湿度随时间变化的曲线。该方案运行可靠、管理方便。     

A remark on the complexity of consistent conjunctive query answering under primary key violations

A natural way for capturing uncertainty in the relational data model is by allowing relations that violate their primary key. A repair of such relation is obtained by selecting a maximal number of tuples without ever selecting two tuples that agree on their primary key. Given a Boolean query q, CERTAINTY(q) is the problem that takes as input a relational database and asks whether q evaluates to true on every repair of that database. In recent years, CERTAINTY(q) has been studied primarily for conjunctive queries. Conditions have been determined under which CERTAINTY(q) is coNP-complete, first-order expressible, or not first-order expressible. A remaining open question was whether there exist conjunctive queries q without self-join such that CERTAINTY(q) is in PTIME but not first-order expressible. We answer this question affirmatively.     

Dynamic Web Service discovery architecture based on a novel peer based overlay network

Service Oriented Computing and its most famous implementation technology Web Services (WS) are becoming an important enabler of networked business models. Discovery mechanisms are a critical factor to the overall utility of Web Services. So far, discovery mechanisms based on the UDDI standard rely on many centralized and area-specific directories, which poses information stress problems such as performance bottlenecks and fault tolerance. In this context, decentralized approaches based on Peer to Peer overlay networks have been proposed by many researchers as a solution. In this paper, we propose a new structured P2P overlay network infrastructure designed for Web Services Discovery. We present theoretical analysis backed up by experimental results, showing that the proposed solution outperforms popular decentralized infrastructures for web discovery, Chord (and some of its successors), BATON (and it’s successor) and Skip-Graphs.     

Scalable satisfiability checking and test data generation from modeling diagrams

We explore the automatic generation of test data that respect constraints expressed in the Object-Role Modeling (ORM) language. ORM is a popular conceptual modeling language, primarily targeting database applications, with significant uses in practice. The general problem of even checking whether an ORM diagram is satisfiable is quite hard: restricted forms are easily NP-hard and the problem is undecidable for some expressive formulations of ORM. Brute-force mapping to input for constraint and SAT solvers does not scale: state-of-the-art solvers fail to find data to satisfy uniqueness and mandatory constraints in realistic time even for small examples. We instead define a restricted subset of ORM that allows efficient reasoning yet contains most constraints overwhelmingly used in practice. We show that the problem of deciding whether these constraints are consistent (i.e., whether we can generate appropriate test data) is solvable in polynomial time, and we produce a highly efficient (interactive speed) checker. Additionally, we analyze over 160 ORM diagrams that capture data models from industrial practice and demonstrate that our subset of ORM is expressive enough to handle their vast majority.