IEEE Trans Neural Netw Learn Syst. 2017 Feb;28(2):464-469. doi: 10.1109/TNNLS.2016.2514841. Epub 2016 Jan 26.
This brief aims to reduce the data requirement for the identification of Boolean networks (BNs) by using the premined network topology information. First, a matching table is created and used for sifting the true from the false dependences among the nodes in the BNs. Then, a dynamic extension to matching table is developed to enable the dynamic locating of matching pairs to start as soon as possible. Next, based on the pseudocommutative property of the semitensor product, a position-transform mining is carried out to further improve data utilization. Combining the above, the topology of the BNs can be premined for the subsequent identification. Examples are given to illustrate the efficiency of reducing the data requirement. Some excellent features, such as the online and parallel processing ability, are also demonstrated.
本文旨在通过利用预先挖掘的网络拓扑信息，减少布尔网络（BN）识别所需的数据。首先，创建一个匹配表，并用于筛选 BNs 中节点之间的真实和虚假依赖关系。然后，开发了一种匹配表的动态扩展，以能够尽快开始动态定位匹配对。接下来，基于半张量积的准交换性质，进行位置变换挖掘，以进一步提高数据利用率。结合以上方法，可以预先挖掘 BNs 的拓扑结构，以便后续进行识别。给出了示例来说明减少数据需求的效率。还展示了一些优秀的特性，如在线和并行处理能力。
