Search

The paper introduces a rough set model to analyze an information system in which some conditions and decision data are missing. Many studies have focused on missing condition data, but very few have accounted for missing decision data. Common approaches tend to remove objects with missing decision data because such objects are apparently considered worthless from the perspective of decision-making. However, we indicate that this removal may lead to information loss. Our method retains such objects with missing decision data. We observe that a scenario involving missing decision data is somewhat similar to the situation of semi-supervised learning, because some objects are characterized by complete decision data whereas others are not. This leads us to the idea of estimating potential candidates for the missing data using the available data. These potential candidates are determined by two quantitative indicators: local decision probability and universal decision probability. These potential candidates allow us to define set approximations and the definition of reduct. We also compare the reducts and rules induced from two information systems: one removes objects with missing decision data and the other retains such objects. We highlight that the knowledge induced from the former can be induced from the latter using our approach. Thus, our method offers a more generalized approach to handle missing decision data and prevents information loss.

Spontaneous communication is an integral part of any workplace as well as everyday life. In workplaces that use computer or similar devices, most of the spontaneous conversations happen over email or chat. Frequent use of chat application or email disrupts a recipient’s workflow and leads to constant interruptions causing task fragmentation. In this paper, we present a receiver oriented Interruption-Information Management (IIM) chat which incorporates automated agents to prevent receivers from getting a plethora of messages. This framework manages both interruption and forthcoming information in the chat interface. It is a novel approach in the area of interruption management. It not only considers interruption management, but also manages the information based on the users’ behavior and preferences. It is a cooperative approach where both the message sender and the receiver work together to deliver messages during the receiver’s most favorable times. The receiver contributes to manage interruption whereas the sender contributes to manage information, together forming an interruption-information management mechanism to decide the least interruptible time for message delivery.

Naive Bayes Classifier is an effective and easy method in general, and is used popularly in document classification. It's also a particularly useful classifier for large dataset. Naive Bayes assigns instances to a class label through maximizing the posterior probability assuming that the instance features are independent of each other. Using this model, many-to-one assumption was proposed to deal with the case where a class may be constituted of many different components. An issue of this approach is how to construct these components on each class. In this paper, we propose a simple heuristic solution of applying a hierarchical tree for assigning components to classes. Through evaluation experiments, we find that the proposed approach shows better performance than the conventional one when the training data size is large enough. Some other issues in practicing many-to-one assumption are also discussed.

Protein name identification in text is an important and challenging fundamental precursor in biomedical information processing. For example, accurate identification of protein names affects the finding of protein-protein interactions from biomedical literature. In this paper, we present an efficient protein name identification technique based on a rich set of features: orthographic, morphological as well as Proteinhood features which are introduced newly in this study. The method was evaluated on GENIA corpus with the use of different machine learning algorithms. The highest values for precision 92.1%, recall 86.5% and F-measure 89.2% were achieved on Random Forest, while reducing the training and testing time significantly. We studied and showed the impact of the Proteinhood feature in protein identification as well as the effect of tuning the parameters of the machine learning algorithm.

Protein named entity identification is one of the most essential and fundamental predecessor for extracting information about protein-protein interactions from biomedical literature. In this paper, we explore the use of abstracts of biomedical literature in MEDLINE for protein name identification and present the results of the conducted experiments. We present a robust and e ective approach to classify biomedical named entities into protein and non-protein classes, based on a rich set of features: orthographic, keyword, morphological and newly introduced Protein-Score features. Our procedure shows significant performance in the experiments on GENIA corpus using Random Forest, achieving the highest values of precision 92.7%, recall 91.7%, and F-measure 92.2% for protein identification, while reducing the training and testing time significantly.

Notification delivered at an inappropriate time is usually considered an interruption. To ensure appropriate timing, we considered treating the self-initiated intermission as a period for interrupting users without causing distractions. This intermission is the time to report oneself as being available for an interaction or being ready for an interruption. This gives users the privilege of choosing a suitable time to handle interruptions without hampering any currently active task. Users’ interruptibility is compared at the time of self-initiated intermission with two alternative types of interruption presentation: application switching and regular intervals. An empirical study showed that the self-initiated intermission is the best approach for interrupting users because their interruptibility is high at this time. We also found that users report on their intermission approximately up to four times during an hour long time span.

This paper proposes interactive decoration design support system introducing interactive evolutionary computation. Evaluation problem existing human can be evaluated synthesizing multi objectives. The proposed system made it importance dividing the human evaluation into two part, which is including regular level of design quality and user's subjective evaluation by affective or Kansei image, and assumed to acquire good results by executing in serial order in a certain evaluation phase. From the experimental results, effectiveness of proposed methodology involving evolution by using fitness evaluation of decoration designs for quality and evolution by user evaluation are confirmed.

Original rough set theory deals with precise and complete data, even though real applications frequently contain imperfect information. Missing values are typical imperfect data studied in rough set research. Many ideas have been proposed in the literature to solve the issue of imperfect data, but hardly a single solution is sufficient for multiple types of imperfect data containing imprecision and uncertainty. The paper models some basic relations between objects with respect to an imperfect attribute value using the Dempster-Shafer theory of evidence, and defines uncertain relations between objects with multiple imperfect attribute values by combining basic relations defined in a single attribute. It also proposes new rough set models based on these basic relations and discusses the properties of these models.

The original rough set theory deals with precise and complete data, while real applications frequently contain imperfect information. A typical imperfect data studied in rough set research is the missing values. Though there are many ideas proposed to solve the issue in the literature, the paper adopts a probabilistic approach, because it can incorporate other types of imperfect data including imprecise and uncertain values in a single approach. The paper first discusses probabilities of attribute values assuming different type of attributes in real applications, and proposes a generalized method of probability of matching. This probability is then used to define valued tolerance/similarity relations and to develop new rough set models based on the valued tolerance/similarity relations. An algorithm for deriving decision rules based on the rough set models is also studied and proposed.

This paper discusses and proposes a rough set model for an incomplete information system, which defines an extended tolerance relation using frequency of attribute values in such a system. It first discusses some rough set extensions in incomplete information systems. Next, “probability of matching” is defined from data in information systems and then measures the degree of tolerance. Consequently, a rough set model is developed using a tolerance relation defined with a threshold. The paper discusses the mathematical properties of the newly developed rough set model and also introduces a method to derive reducts and the core.

Spontaneous communication is an integral part of any workplace as well as everyday life. Most of the spontaneous communications happen over email or chat applications in workplaces that use computer technologies. Frequent use of chat application or email hampers the recipient's workflow and leads to constant interruptions causing task fragmentation. In this paper, we present a receiver oriented interruption-information management framework using automated agents to prevent receivers from a plethora of messages. This framework manages both the interruption and upcoming information in the chat interface. This study is a novel approach in the area of interruption management, which not only considers interruption management but also processes information based on users' behavior and preferences. This framework is a cooperative approach where both the message sender and the receiver work together to deliver messages during favorable times. The receiver contributes to manage interruption whereas the sender helps to manage information, together forming an interruption-information management mechanism for deciding the least interruptible time for message delivery. The study shows that users become comparatively more productivity and complete more task with the relatively short amount of time while using the interruption-information management chat interface than conventional chat.

Rough set approach has been applied successfully to many studies of product design analysis and design support systems. Essence of the approach is regarded as acquisitions of design knowledge from a decision table, where design attributes of existing products and consumers' impressions build from their outer appearance are contained. This approach helps us design products with the target impression in a systematic way. However, impressions of products designed in the way might be generated in the same cognitive process as ones of existing products. In the sense, impressions of those products might not have any novelty. The paper proposes a systematic approach to design products that have novelty as well as the target impression. It defines a design distance in the attributes space using conceptual hierarchies of attributes values, and explores the space to find designs that satisfy both novelty and the target impression. The approach was applied to glasses design and shown to be effective for design that seeks novelty.

Document clustering is a textmining technique for unsupervised document organization. It helps the users browse and navigate large sets of documents. Ho et al. proposed a Tolerance Rough Set Model (TRSM) [1] for improving the vector space model that represents documents by vectors of terms and applied it to document clustering. In this paper we analyze their model to propose a new model for efficient clustering of documents. We introduce Similarity Rough Set Model (SRSM) as another model for presenting documents in document clustering. The model is evaluated by experiments on test collections. The experiment results show that the SRSM document clusteringmethod outperforms the one with TRSM and the results of SRSM are less affected by the value of parameter than TRSM.

The paper discusses the use of parallel computation to obtain rough set approximations from large-scale information systems where missing data exist in both condition and decision attributes. To date, many studies have focused on missing condition data, but very few have accounted for missing decision data, especially in enlarging datasets. One of the approaches for dealing with missing data in condition attributes is named twofold rough approximations. The paper aims to extend the approach to deal with missing data in the decision attribute. In addition, computing twofold rough approximations is very intensive, thus the approach is not suitable when input datasets are large. We propose parallel algorithms to compute twofold rough approximations in large-scale datasets. Our method is based on MapReduce, a distributed programming model for processing large-scale data. We introduce the original sequential algorithm first and then the parallel version is introduced. Comparison between the two approaches through experiments shows that our proposed parallel algorithms are suitable for and perform efficiently on large-scale datasets that have missing data in condition and decision attributes.

本稿では，最近提案された証拠理論における条件則の一般化について論じ，不確実な信念を条件とする新たな一般化条件則を提案する．また，既存の証拠推論が本論文で提案する一般化条件則によって解釈可能であることを示す．最近キマラらによって提案された条件則は，以下の３つの要件を満足する．a）条件付基本確率の焦点要素は条件となる集合の部分集合に限られる，b）空集合でない任意の条件に対して条件付基本確率は定義される，c）条件が全体集合である条件付基本確率は条件なしの基本確率に等しい．これらの３つの要件すべてを満足する既存の条件則は存在しないが，証拠理論が人間の主観における不確実性を表現するとすれば，これらの要件は自然で妥当な要件と考えられる．また，条件に信頼度を導入することで，a）の要件を緩和する一般化条件則も提案されている．本論文では，まず，キマラらの一般化条件則をさらに一般化する．本稿で提案する一般化条件則は，条件として基本確率の形で与えられる信念を用いる．同様な条件則は Ichihashi らや Dubois らによっても提案されているが，これらの一般化条件則はベイズ規則およびジェフリー規則の一般化であるため上記の要件 b）を満たさない．本稿で提案する条件則は a）の要件を緩和したのみで， b）と c）の要件を共に満たす．さらに，本論文では既存の証拠推論と一般化条件則の関係について論じる．証拠推論はベイズ推論の拡張として解釈することができるが，新たに，本稿では Smets らの移転可能信念モデル（Transferable Belief Model）における証拠の結合として解釈できること，および本稿で提案する一般化条件則によって解釈可能であることを示す．

The human interface design for household appliances is becoming far more difficult than that in the past, because they have so many functions that the users could not remember all of their operations as well as the size is so compact that enough buttons, switches, and/or displays could not be placed on the control panel. The paper proposes a novel idea of human interface named Push like talking for such appliances, which could be a new design paradigm for the human interface of future electronic/information appliances. The PLT is applied to a human interface of a multi-functional telephone. Then, the evaluation shows the possibility that the PLT paradigm would provide a manualless human interface for appliances in the future.

We investigate the combinatorial effect of evolutionary multi-objective optimization (EMO) with interactive evolutionary computation (IEC). The purposes and combination ways of several presented EMO and IEC researches are different. We evaluated seven combination ways of four EMO objectives given by fitness functions and one IEC objective given by a pseudo-IEC user outputting stable evaluation regardless repeated experiments in our previous experiments. In this paper, we extend experimental conditions to 39 and evaluate them: 3 pseudo-users X 13 combination ways of 4 + 1 objectives. We also consider features of this system.