No abstract

Storm is the most popular realtime stream processing platform, which can be used to deal with online machine learning. Similar to how Hadoop provides a set of general primitives for doing batch processing, Storm provides a set of general primitives for doing realtime computation. SAMOA includes distributed algorithms for the most common machine learning tasks like Mahout for Hadoop. SAMOA is both a platform and a library. In this paper, Forest cover types, a large benchmaking dataset available at the UCI KDD Archive is used as the data stream source. Vertical Hoeffding Tree, a parallelizing streaming decision tree induction for distributed enviroment, which is incorporated in SAMOA API is applied on Storm platform. This study compared stream prcessing technique for predicting forest cover types from cartographic variables with traditional classic machine learning algorithms applied on this dataset. The test then train method used in this system is totally different from the traditional train then test. The results of the stream processing technique indicated that it’s output is aymptotically nearly identical to that of a conventional learner, but the model derived from this system is totally scalable, real-time, capable of dealing with evolving streams and insensitive to stream ordering.

SUMMARYWith the high speed innovation of information technology, many production scheduling systems have been developed. However, a lot of customization according to individual production environment is required, and then a large investment for development and maintenance is indispensable. Therefore now the direction to construct scheduling systems should be changed. The final objective of this research aims at developing a system which is built by it extracting the scheduling technique automatically through the daily production scheduling work, so that an investment will be reduced. This extraction mechanism should be applied for various production processes for interoperability. Using the master information extracted by the system, production scheduling operators can be supported to accelerate the production scheduling work easily and accurately without any restriction of scheduling operations. By installing this extraction mechanism, it is easy to introduce a scheduling system without a lot of expense for customization. In this paper, first a model for expressing a scheduling problem is proposed. Then the guideline to extract the scheduling information and use the extracted information is shown and some applied functions are also proposed based on it.