In this paper, we analyzed the 400 millions of Tweet data which posted around the Great East Japan Earthquake to find how the twitter used and how Twitter was influenced by the disaster. We modeled the time series data of retweet by Log Normal Mixture Model. By using Log Normal Mixture Model, we estimate the diffusion ability of each user. We simulated the information diffusion to validate the estimate method. From the result of the simulation, we clarify that the correlation between true diffusion ability and estamated diffusion ability is higher than the correlation between true diffusion ability and degree of each agent. By using proposed method, we can estimate influencer from information diffusion with higher accuracy than using degree.

Local SNS supports not only activities of the local society but is expected as a network infrastructure to support activities responding to disasters. This study examined the roles for and the potentiality of the Local SNS, which was specialized for local characteristics, to play at the time of disaster, clarifying the manner of actual use of the Local SNS during the Great East Japan Earthquake through analysis of the log data that were available at the time of the disaster. It was made clear that, during the Great East Japan Earthquake, the Local SNS was effectively functioning as the place for collecting the necessary information for the disaster areas and for support activities.

様々な環境で動作するエージェントを評価するためには，問題となる環境とエージェントの振舞いの間にある関係を明らかにする必要がある．これまでに我々は，地図上の道路ネットワークの構造と建物配置に注目し，問題となる環境（地図）を定量化する方法を提案し，この手法を用いて異なる環境で振舞うエージェントの行動を評価する可能性について検討した．本研究では，これまでの研究成果をもとに，地図上の道路ネットワークの構造と建物配置の情報をより表現できる手法を提案するために地図を画像として捉え，構造的な特徴を抽出する方法を考察する．考察にあたり様々な地図及びエージェントを用いて，その関係性を分析した結果は，従来よりもはっきりと地図とエージェントの振る舞いの間における関係性を示した．

Sugar content is a key factor of the delicacy which consumers demand of farm product such as fruit and tomato. Improvement of the sugar content is important because it influence a price and quality in the market. However, measurement about the influence of the growth process and the environmental condition of farms on sugar content is not fully performed. In order to improve the quality of farm product, we attempt to develop the sugar content monitor which measures the sugar content of object vegetables or fruit continuously at the farm by remote control.

In the markets of fresh foods like vegetables and fish, a Dutch auction is used for clearing a market by virtue of its promptness and simplicity, which are important in trading perishable goods. However, in single-sided auctions, such as a Dutch auction, sellers cannot participate in price-making process. A standard two-sided auction market collects bids from traders and matches buyers' higher bids and sellers' lower bids to find the most efficient allocation, assuming that values of unsold items remain unchanged. Nevertheless, in the fresh foods market, sellers suffer loss when they fail to sell their product because it perishes after the lapse of its time limit. To develop a suitable mechanism for trading fresh foods, we investigate the design of a dynamic two-sided auction market, where bids arrive dynamically with their time limits. Our market mechanism aims at improving traders' profitability by reducing trade failures in the face of uncertainty of incoming/leaving bids. For the purpose, we have developed a heuristic matching rule of the market to prioritize traders' bids based on their time-criticality. Based on the research results, we are now constructing fishery trading systems to improve revenues of fishermen in the areas affected by the Great East Japan Earthquakes.

サービスの現場では売上データや会員データ，発注データなど多種多様なデータが大量に蓄積されている．これらの大規模データは顧客理解のために有用であり，著者らもデータマイニングなどの技術を応用した顧客モデル構築技術などを開発してきた．しかしながら，購買など観測可能な顧客行動からだけでは"行動の理由” を理解することは難しい．そこで，アンケートを用いた顧客ライフスタイル分類にも取り組んでいる．本報では，小売業（流通量販店）の顧客約4 千名に対して行ったアンケートから顧客のライフスタイルを分類し，その上で行動データからライフスタイルを推定・付与した結果ついて述べる．