挖掘多数据流的异步偶合模式是具有挑战性的工作.主要的研究工作包括:(1) 研究Haar小波滤波技术在挖掘流数据的异步偶合模式中的应用;(2) 引入小波系数序列来度量数据流的异步局域偶合度;证明了一系列定理,保证了度量方法的正确性;(3) 设计了环形滑动窗口和挖掘异步偶合模式的抗噪声增量算法,其时间复杂性小于O(n2);(4) 使用真实数据进行模拟实验,验证了算法的有效性.

Mining asynchronous coincidence pattern is a difficult task in multi-data streams. The main contributions of this work included: (1) The filter technique of Haar Wavelet is investigated and applied to mining asynchronous coincidence pattern in multi-streams; (2) The Wavelet coefficient series are applied to the measurement of asynchronous coincidence between data streams. A series of theorems are proved to ensure the validity of measuring asynchronous coincidence; (3) The anti-noise increment algorithms are designed on loop sliding windows to mine asynchronous coincidence pattern and implemented with complexity O(n2); (4) The extensive experiments on real data are given to validate algorithms.

Supported by the National Natural Science Foundation of China under Grant No.60473071 (国家自然科学基金); the National Research Foundation for the Doctoral Program of Higher Education of China under Grant No.20020610007 (国家教育部博士点基金)