A simulation model often has parameters to be calibrated through evaluation against data obtained by experiments. The process could be prohibitively expensive if the execution of the model requires huge computational resources and/or the parameter search space is vast. For technology CAD (TCAD) topography simulation, used in semiconductor manufacturing, this is exactly the case. We present a method to replace the simulation with approximate computation based on Generative Adversarial Network. The method receives pairs of a simulation parameter set and a simulation result image as training examples and learns a model to mimic the simulation. Unlike most GANbased models, its learning is carried out in a supervised manner. We evaluate its performance by cross-validation and comparison with a human expert. Despite the small size of the available dataset, our method successfully generates an image close to the ground truth in 71% of the cases and qualitatively reproduces the educated guesses of the human expert on the behavior of the simulator.

Patent engineers are spending significant time analyzing patent claim structures to grasp the range of technology covered or to compare similar patents in the same patent family. Though patent claims are the most important section in a patent, it is hard for a human to examine them. In this paper, we propose an information-extraction-based technique to grasp the patent claim structure. We confirmed that our approach is promising through empirical evaluation of entity mention extraction and the relation extraction method. We also built a preliminary interface to visualize patent structures, compare patents, and search similar patents.

Nowadays, anybody can easily express their opinion publicly through Consumer Generated Media. Because of this, a phenomenon of flooding criticism on the Internet, called flaming, frequently occurs. Although there are strong demands for flaming management, namely, a service to reduce damage caused by a flaming after one occurs, it is very difficult to properly do so in practice. We are trying to keep the flaming from happening. Concretely, we propose methods to identify a potential tweet which will be a likely candidate of a flaming on Twitter, considering public opinion among twitter users. We divide flamings into three categories: criminal episodes, struggles between conflicting values and secret exposures. The first two represent the vast majority of flaming cases. As for the CEs, a Naive Bayes-based method has been promising to identify the cases. As for the SBCVs, we propose a dynamic P/N analysis based on daily polarity, which represents the strength of the polarity of public opinion on a given topic. An experiment using a past flaming case has shown that the method has successfully explained the case as one caused by a gap between the polarity of the tweet and that of public opinion.

Recently, the video hosting is one of the most popular services on the Web. The service user can search movies by title, tag, date, and so on. However, the user can hardly obtain information on a particular scene of a movie. Thus, it is very difficult to determine whether a movie contains interesting scenes or not. This research aims to provide information in order to help a user to choose a movie. Concretely, this paper proposes a method for labeling scenes in a movie using a video hosting service called "Nico Nico Douga". The proposed method extracts important scenes in a movie from "Nico Nico Douga" based on the statistics of social annotations attached to them. Also, using the characteristics of folksonomy the authors extract feature words for labeling. Moreover, in order to take advantage of the feature words, the authors estimate their semantic categories. We use the attached comments themselves to label the important scenes. In order to select the comments, the authors take into account the importance of the feature words with semantic categories in a scene. Finally, the authors carry out experiments to evaluate the proposed method and to discuss future works.

This paper proposes a method that classifies bloggers according to their interests. The method calculates three kinds of similarities. That is, the method calculates similarities between target objects discussed in the blogs by using social annotations. Here, products, works, and services are examples of the target objects. Next, the method calculates similarities between impressions related to the target objects based on blog articles posted by bloggers. Lastly, the method calculates similarities between the bloggers by combining the results of the method's first and second calculation steps, and classifies the bloggers based on the similarities. The paper applies the method to the Commutents data and the Yahoo! Japan Movie data, and verifies the effectiveness of the method.

This paper proposes a method that deals with missing values in the discovery of association rules. The method deals with items composed of attributes and attribute values. The method calculates two kinds of support. One is characteristic support and the other is possible support. The former is based on the number of examples that do not include missing values in attributes composing target items. The latter is based on the number of examples that do not include missing values in all attributes. The method extracts all item sets whose characteristic supports are larger than or equal to the predefined threshold. The paper evaluates the proposed method by comparing it with the previous method and verifies the effect of the proposed method.

This paper proposes a method that acquires a more appropriate classification model for label extraction. The model can extract specific labels from articles included in bulletin board sites. The labels represent the contents of the articles and are used to characterize the articles. The method selects two kinds of important examples not including a specific label by using expressions related to the label. The method inductively acquires the classification model from the selected examples and examples including the label. The paper applies the method to articles collected from three bulletin board sites and verifies its effect through comparative experiments

In this paper, we proposes a new approach called green behavior generation (GBG), which is designed to reduce the environmental burden without mental stress in daily life. A GBG system consists of sensing, modeling, and service elements. For sensing various kinds of data, a sensor home is constructed. The network system of the sensor home is based on advanced information and communication technology (ICT), such as networked home electric appliances and a ubiquitous sensor network, which are applied to collect energy consumption and context data simultaneously. An experimental example and the usefulness of the sensing environment are shown.

This paper proposes the sequential interestingness as a new evaluation criterion that evaluates a sequential pattern corresponding to the interests of analysts. The sequential pattern is composed of rows of item sets. The criterion satisfies the Apriori property. Also, this paper proposes three attribute constraints. These constraints can naturally evaluate relationships of attributes both in an item set and between continuous item sets. In addition, this paper proposes a mining method incorporating the criterion and the constraints. The method can efficiently discover all sequential patterns whose sequential interestingness is larger than or equal to a threshold and that satisfy the constraints. Lastly, this paper verifies the effectiveness of the proposed method by applying the method to medical examination data.