久保山 哲二

グラフ構造を持つデータが増加しており、グラフ構造データから特徴的構造を得るための機械学習手法が盛んに研究されている。本研究では、TTSPグラフの正事例集合をクラスタリングする手法を用いて、正事例と負事例のTTSPグラフデータから、特徴的な複合的ワイルドカード付きTTSPグラフパターンを獲得する進化的学習手法について報告する。

木構造データからの機械学習が注目されている． 本研究では，正事例のラベル情報を利用する進化的学習を用いて，正事例と負事例の木構造データを分類するワイルドカードを持つ頂点ラベル付きタグ木パターンを獲得する手法を提案する．

グラフ構造データからの機械学習が注目されており，多くの化合物は外平面的グラフの構造を持つことが知られている． 本研究では，正事例のラベル情報を利用する二段階構造の進化的学習を用いて，正事例と負事例の外平面的グラフを分類する複合的なワイルドカード付きブロック保存型外平面的グラフパターンを獲得する手法を提案する．

グラフ構造データからの機械学習やデータマイニングが注目されている．本稿では，外平面的グラフに対するグラフ分類問題に取り組むため，正事例と負事例の外平面的グラフから，遺伝的プログラミングを用いて特徴的なワイルドカード付きブロック保存型外平面的グラフパターンを獲得する進化的手法を提案する．

We consider representing tree structured features of structured data which are represented by rooted trees with ordered children. As representations of tree structured features, we use ordered tree patterns, called ordered wildcard tree patterns, which have structures of rooted ordered trees, structured variables and wildcards for edge labels. A structured variable can be replaced with an arbitrary rooted ordered tree. First we show that it is hard to compute two types of optimum frequent ordered wildcard tree patterns. Then we present an algorithm for enumerating all maximally frequent ordered wildcard tree patterns. Finally we consider extended ordered wildcard tree patterns, called ordered tag tree patterns, which have structured variables, wildcards, tags and keywords, and present an algorithm for enumerating all maximally frequent ordered tag tree patterns.We consider representing tree structured features of structured data which are represented by rooted trees with ordered children. As representations of tree structured features, we use ordered tree patterns, called ordered wildcard tree patterns, which have structures of rooted ordered trees, structured variables and wildcards for edge labels. A structured variable can be replaced with an arbitrary rooted ordered tree. First we show that it is hard to compute two types of optimum frequent ordered wildcard tree patterns. Then we present an algorithm for enumerating all maximally frequent ordered wildcard tree patterns. Finally we consider extended ordered wildcard tree patterns, called ordered tag tree patterns, which have structured variables, wildcards, tags and keywords, and present an algorithm for enumerating all maximally frequent ordered tag tree patterns.

学習院大学のキャンパス内における無線 LAN の利用動向を分析した結果について報告する.

CWC (Combination of Weakest Components), a successful consistency-based feature selection algorithm, is known to outperform not only other consistency-based algorithms but many non-consistency-based filter algorithms in terms of time-efficiency and predictive accuracy. In this paper, we propose two methods to develop a new consistency-based feature selection algorithm based on CWC: One is to improve the predictive accuracy of CWC, and the other is to support the requirement of multiple outputs. With respect to the predictive accuracy, we found through intensive experiments that the order of investigating features to determine whether to eliminate the feature (CWC is a backward elimination algorithm) can affect the performance of CWC to a large extent, and identified the best order of the three orders that we investigated. On the other hand, when considering the way how we perform feature selection in the real world, we see that the role of feature selection is to provide candidates for the feature set that could explain the target problem the best, and we should examine their actual relevance separately in a manner specific to the problem. In this sense, it is desirable that a feature selection algorithm outputs multiple feature sets, but CWC can output only a single feature set per a dataset. Our idea to solve this problem is to run CWC multiple times taking advantage of its excellent time-efficiency, and we propose an algorithm for iterative execution of CWC using the outputs of the previous executions as feedback.