IEICE Transactions on Information and Systems
Online ISSN : 1745-1361
Print ISSN : 0916-8532
Volume E94.D , Issue 3
Showing 1-40 articles out of 40 articles from the selected issue
Special Section on Knowledge Discovery, Data Mining and Creativity Support System
  • Thanaruk THEERAMUNKONG
    2011 Volume E94.D Issue 3 Pages 403
    Published: March 01, 2011
    Released: March 01, 2011
    JOURNALS FREE ACCESS
    Download PDF (62K)
  • Nichnan KITTIPHATTANABAWON, Thanaruk THEERAMUNKONG, Ekawit NANTAJEEWAR ...
    Type: PAPER
    2011 Volume E94.D Issue 3 Pages 404-415
    Published: March 01, 2011
    Released: March 01, 2011
    JOURNALS FREE ACCESS
    Recently, to track and relate news documents from several sources, association rule mining has been applied due to its performance and scalability. This paper presents an empirical investigation on how term representation basis, term weighting, and association measure affects the quality of relations discovered among news documents. Twenty four combinations initiated by two term representation bases, four term weightings, and three association measures are explored with their results compared to human judgment of three-level relations: completely related, somehow related, and unrelated relations. The performance evaluation is conducted by comparing the top-k results of each combination to those of the others using so-called rank-order mismatch (ROM). The experimental results indicate that a combination of bigram (BG), term frequency with inverse document frequency (TFIDF) and confidence (CONF), as well as a combination of BG, TFIDF and conviction (CONV), achieves the best performance to find the related documents by placing them in upper ranks with 0.41% ROM on top-50 mined relations. However, a combination of unigram (UG), TFIDF and lift (LIFT) performs the best by locating irrelevant relations in lower ranks (top-1100) with 9.63% ROM. A detailed analysis on the number of the three-level relations with regard to their rankings is also performed in order to examine the characteristic of the resultant relations. Finally, a discussion and an error analysis are given.
    Download PDF (1075K)
  • Dang Hung TRAN, Tu Bao HO, Tho Hoan PHAM, Kenji SATOU
    Type: PAPER
    2011 Volume E94.D Issue 3 Pages 416-422
    Published: March 01, 2011
    Released: March 01, 2011
    JOURNALS FREE ACCESS
    One kind of functional noncoding RNAs, microRNAs (miRNAs), form a class of endogenous RNAs that can have important regulatory roles in animals and plants by targeting transcripts for cleavage or translation repression. Researches on both experimental and computational approaches have shown that miRNAs indeed involve in the human cancer development and progression. However, the miRNAs that contribute more information to the distinction between the normal and tumor samples (tissues) are still undetermined. Recently, the high-throughput microarray technology was used as a powerful technique to measure the expression level of miRNAs in cells. Analyzing this expression data can allow us to determine the functional roles of miRNAs in the living cells. In this paper, we present a computational method to (1) predicting the tumor tissues using high-throughput miRNA expression profiles; (2) finding the informative miRNAs that show strong distinction of expression level in tumor tissues. To this end, we perform a support vector machine (SVM) based method to deeply examine one recent miRNA expression dataset. The experimental results show that SVM-based method outperforms other supervised learning methods such as decision trees, Bayesian networks, and backpropagation neural networks. Furthermore, by using the miRNA-target information and Gene Ontology annotations, we showed that the informative miRNAs have strong evidences related to some types of human cancer including breast, lung, and colon cancer.
    Download PDF (351K)
  • Viet Cuong NGUYEN, Le Minh NGUYEN, Akira SHIMAZU
    Type: PAPER
    2011 Volume E94.D Issue 3 Pages 423-431
    Published: March 01, 2011
    Released: March 01, 2011
    JOURNALS FREE ACCESS
    In the text summarization field, a table-of-contents is a type of indicative summary that is especially suited for locating information in a long document, or a set of documents. It is also a useful summary for a reader to quickly get an overview of the entire contents. The current models for generating a table-of-contents produced relatively low quality output with many meaningless titles, or titles that have no overlapping meaning with the corresponding contents. This problem may be due to the lack of semantic information and topic information in those models. In this research, we propose to integrate supportive knowledge into the learning models to improve the quality of titles in a generated table-of-contents. The supportive knowledge is derived from a hierarchical clustering of words, which is built from a large collection of raw text, and a topic model, which is directly estimated from the training data. The relatively good results of the experiments showed that the semantic and topic information supplied by supportive knowledge have good effects on title generation, and therefore, they help to improve the quality of the generated table-of-contents.
    Download PDF (574K)
  • Marut BURANARACH, Nopphadol CHALORTHAM, Ye Myat THEIN, Thepchai SUPNIT ...
    Type: PAPER
    2011 Volume E94.D Issue 3 Pages 432-439
    Published: March 01, 2011
    Released: March 01, 2011
    JOURNALS FREE ACCESS
    Improving quality of healthcare for people with chronic conditions requires informed and knowledgeable healthcare providers and patients. Decision support and clinical information system are two of the main components to support improving chronic care. In this paper, we describe an ontology-based information and knowledge management framework that is important for chronic disease care management. Ontology-based knowledge acquisition and modeling based on knowledge engineering approach provides an effective mechanism in capturing expert opinion in form of clinical practice guidelines. The framework focuses on building of healthcare ontology and clinical reminder system that link clinical guideline knowledge with patient registries to support evidenced-based healthcare. We describe implementation and approaches in integrating clinical reminder services to existing healthcare provider environment by focusing on augmenting decision making and improving quality of patient care services.
    Download PDF (753K)
  • Prachya BOONKWAN, Thepchai SUPNITHI
    Type: PAPER
    2011 Volume E94.D Issue 3 Pages 440-447
    Published: March 01, 2011
    Released: March 01, 2011
    JOURNALS FREE ACCESS
    This paper presents a syntax-based framework for gap resolution in analytic languages. CCG, reputable for dealing with deletion under coordination, is extended with a memory mechanism similar to the slot-and-filler mechanism, resulting in a wider coverage of syntactic gaps patterns. Though our grammar formalism is more expressive than the canonical CCG, its generative power is bounded by Partially Linear Indexed Grammar. Despite the spurious ambiguity originated from the memory mechanism, we also show that its probabilistic parsing is feasible by using the dual decomposition algorithm.
    Download PDF (647K)
  • Nopphadol CHALORTHAM, Phuriwat LEESAWAT, Taneth RUANGRAJITPAKORN, Thep ...
    Type: PAPER
    2011 Volume E94.D Issue 3 Pages 448-455
    Published: March 01, 2011
    Released: March 01, 2011
    JOURNALS FREE ACCESS
    This paper presents a framework of supporting system for a drug formulation. We designed ontology to represent the related knowledge for reusable and sharing purposes. The designed ontology is applied with operation rules to suggest an appropriate generic drug production based on information of original drug. The system also provides a validation module to preliminarily approve a pharmaceutical equivalence of the suggested result. Preliminary testing with four random samples shows potential to reformulate a generic product by returning a satisfactory and acceptable of the system suggestions for all samples.
    Download PDF (1631K)
  • Motoki MIURA, Taro SUGIHARA, Susumu KUNIFUJI
    Type: PAPER
    2011 Volume E94.D Issue 3 Pages 456-464
    Published: March 01, 2011
    Released: March 01, 2011
    JOURNALS FREE ACCESS
    Practitioners of the Jiro Kawakita (KJ) method, a method for organizing ideas, typically use paper labels and four-colored ball-point pens to record their ideas during the creative thinking process. A similar approach is used in group KJ method sessions; however, the effectiveness of capturing and sharing the diagrams and information is limited because of the large amount of paper required. Considering the merits of the conventional paper-pen approach and the demand for quick sharing of diagrams after a session, we designed and implemented a system to digitize group KJ sessions — not just the diagrams but also the details of the creative process. We used digital pens during the session to capture the position and orientation of labels as well as their content. We confirmed the efficiency of our system by applying it to several GKJ sessions.
    Download PDF (1694K)
  • Peerasak INTARAPAIBOON, Ekawit NANTAJEEWARAWAT, Thanaruk THEERAMUNKONG
    Type: PAPER
    2011 Volume E94.D Issue 3 Pages 465-478
    Published: March 01, 2011
    Released: March 01, 2011
    JOURNALS FREE ACCESS
    Due to the limitations of language-processing tools for the Thai language, pattern-based information extraction from Thai documents requires supplementary techniques. Based on sliding-window rule application and extraction filtering, we present a framework for extracting semantic information from medical-symptom phrases with unknown boundaries in Thai unstructured-text information entries. A supervised rule learning algorithm is employed for automatic construction of information extraction rules from hand-tagged training symptom phrases. Two filtering components are introduced: one uses a classification model to predict rule application across a symptom-phrase boundary based on instantiation features of rule internal wildcards, the other uses weighted classification confidence to resolve conflicts arising from overlapping extractions. In our experimental study, we focus our attention on two basic types of symptom phrasal descriptions: one is concerned with abnormal characteristics of some observable entities and the other with human-body locations at which primitive symptoms appear. The experimental results show that the filtering components improve precision while preserving recall satisfactorily.
    Download PDF (3994K)
  • Peerasak INTARAPAIBOON, Ekawit NANTAJEEWARAWAT, Thanaruk THEERAMUNKONG
    Type: PAPER
    2011 Volume E94.D Issue 3 Pages 479-486
    Published: March 01, 2011
    Released: March 01, 2011
    JOURNALS FREE ACCESS
    Based on sliding-window rule application and extraction filtering, we present a framework for extracting multi-slot frames describing chemical reactions from Thai free text with unknown target-phrase boundaries. A supervised rule learning algorithm is employed for automatic construction of pattern-based extraction rules from hand-tagged training phrases. A filtering method is devised for removal of incorrect extraction results based on features observed from text portions appearing between adjacent slot fillers in source documents. Extracted reaction frames are represented as concept expressions in description logics and are used as metadata for document indexing. A document knowledge base supporting semantics-based information retrieval is constructed by integrating document metadata with domain-specific ontologies.
    Download PDF (675K)
Special Section on Data Engineering
  • Jun MIYAZAKI
    2011 Volume E94.D Issue 3 Pages 487-488
    Published: March 01, 2011
    Released: March 01, 2011
    JOURNALS FREE ACCESS
    Download PDF (57K)
  • Mohammed AL-KATEB, Sasi Sekhar KUNTA, Byung Suk LEE
    Type: PAPER
    2011 Volume E94.D Issue 3 Pages 489-503
    Published: March 01, 2011
    Released: March 01, 2011
    JOURNALS FREE ACCESS
    This paper focuses on the coalescing operator applied to the processing of continuous queries with temporal functions and predicates over windowed data streams. Coalescing is a key operation enabling the evaluation of interval predicates and functions on temporal tuples. Applying this operation for temporal query processing on windowed streams brings the challenge of coalescing tuples in a window extent each time the window slides over the data stream. This coalescing becomes even more involving when some tuples arrive out of order. This paper distinguishes between eager coalescing and lazy coalescing, the two known coalescing schemes. The former coalesces tuples during window extent update and the latter does it during window extent scan. With these two schemes, the paper first presents algorithms for updating a window extent for both tuple-based and time-based windows. Then, the problem of optimally selecting between eager and lazy coalescing for concurrent queries is formulated as a 0-1 integer programming problem. Through extensive performance study, the two schemes are compared and the optimal selection is demonstrated.
    Download PDF (489K)
  • Hisashi KURASAWA, Daiji FUKAGAWA, Atsuhiro TAKASU, Jun ADACHI
    Type: PAPER
    2011 Volume E94.D Issue 3 Pages 504-514
    Published: March 01, 2011
    Released: March 01, 2011
    JOURNALS FREE ACCESS
    This paper proposes a new method to reduce the cost of nearest neighbor searches in metric spaces. Many similarity search indexes recursively divide a region into subregions by using pivots, and construct a tree-structured index. Most of recently developed indexes focus on pruning objects and do not pay much attention to the tree balancing. As a result, indexes having imbalanced tree-structure may be constructed and the search cost is degraded. We propose a similarity search index called the Partitioning Capacity (PC) Tree. It selects the optimal pivot in terms of the PC that quantifies the balance of the regions partitioned by a pivot as well as the estimated effectiveness of the search pruning by the pivot. As a result, PCTree reduces the search cost for various data distributions. We experimentally compared PCTree with four indexes using synthetic data and five real datasets. The experimental results shows that the PCTree successfully reduces the search cost.
    Download PDF (1715K)
  • Jeong-Dong KIM, Jiseong SON, Doo-Kwon BAIK
    Type: PAPER
    2011 Volume E94.D Issue 3 Pages 515-524
    Published: March 01, 2011
    Released: March 01, 2011
    JOURNALS FREE ACCESS
    Metadata registry (MDR) is based on the international standard ISO/IEC 11179. The committee of ISO/IEC JTC 1/SC 32, which had standardized the MDR, has started to improvise the MDR, and the improvised version is named extended MDR (XMDR). However, the XMDR does not fully support the ontology concept, and no method is available for mapping ontology registrations onto registries. To overcome the limitations of the outdated XMDR, this paper proposes an extended XMDR (XMDR+) framework. The XMDR+ framework provides a method for mapping of ontology registrations between the metadata registry and ontologies. To improve the functions of the XMDR, we have proposed herein a framework that is capable of defining a model that manages the relations not only among ontological concepts but also among instances, and guarantees the management and storage of their relationships for supporting valid relations of the ontologies.
    Download PDF (1996K)
  • Dengping WEI, Ting WANG, Ji WANG
    Type: PAPER
    2011 Volume E94.D Issue 3 Pages 525-534
    Published: March 01, 2011
    Released: March 01, 2011
    JOURNALS FREE ACCESS
    With the aim to improve the effectiveness of SAWSDL service discovery, this paper proposes a novel discovery method for SAWSDL services, which is based on the matchmaking of so-called fine-grained data semantics that is defined via sets of atomic elements with built-in data types. The fine-grained data semantics can be obtained by a transformation algorithm that decomposes parameters at message level into a set of atomic elements, considering the characteristics of SAWSDL service structure and semantic annotations. Then, a matchmaking algorithm is proposed for the matching of fine-grained data semantics, which avoids the complex and expensive structural matching at the message level. The fine-grained data semantics is transparent to the specific data structure of message-level parameters, therefore, it can help to match successfully similar Web services with different data structures of parameters. Moreover, a comprehensive measure is proposed by considering together several important components of SAWSDL service descriptions at the same time. Finally, this method is evaluated on SAWSDL service discovery test collection SAWSDL-TC2 and compared with other SAWSDL matchmakers. The experimental results show that our method can improve the effectiveness of SAWSDL service discovery with low average query response time. The results imply that fine-grained parameters fit to represent the data semantics of SAWSDL services, especially when data structures of parameters are not important for semantics.
    Download PDF (326K)
  • Dian-Song WU, Tyne LIANG
    Type: PAPER
    2011 Volume E94.D Issue 3 Pages 535-541
    Published: March 01, 2011
    Released: March 01, 2011
    JOURNALS FREE ACCESS
    In this paper, effective Chinese definite anaphora resolution is addressed by using feature weight learning and Web-based knowledge acquisition. The presented salience measurement is based on entropy-based weighting on selecting antecedent candidates. The knowledge acquisition model is aimed to extract more semantic features, such as gender, number, and semantic compatibility by employing multiple resources and Web mining. The resolution is justified with a real corpus and compared with a classification-based model. Experimental results show that our approach yields 72.5% success rate on 426 anaphoric instances. In comparison with a general classification-based approach, the performance is improved by 4.7%.
    Download PDF (3627K)
  • Kaipeng LIU, Binxing FANG, Weizhe ZHANG
    Type: PAPER
    2011 Volume E94.D Issue 3 Pages 542-551
    Published: March 01, 2011
    Released: March 01, 2011
    JOURNALS FREE ACCESS
    With the emergence of Web 2.0, social tagging systems become highly popular in recent years and thus form the so-called folksonomies. Personalized tag recommendation in social tagging systems is to provide a user with a ranked list of tags for a specific resource that best serves the user's needs. Many existing tag recommendation approaches assume that users are independent and identically distributed. This assumption ignores the social relations between users, which are increasingly popular nowadays. In this paper, we investigate the role of social relations in the task of tag recommendation and propose a personalized collaborative filtering algorithm. In addition to the social annotations made by collaborative users, we inject the social relations between users and the content similarities between resources into a graph representation of folksonomies. To fully explore the structure of this graph, instead of computing similarities between objects using feature vectors, we exploit the method of random-walk computation of similarities, which furthermore enable us to model a user's tag preferences with the similarities between the user and all the tags. We combine both the collaborative information and the tag preferences to recommend personalized tags to users. We conduct experiments on a dataset collected from a real-world system. The results of comparative experiments show that the proposed algorithm outperforms state-of-the-art tag recommendation algorithms in terms of prediction quality measured by precision, recall and NDCG.
    Download PDF (768K)
  • Hideki KAWAI, Adam JATOWT, Katsumi TANAKA, Kazuo KUNIEDA, Keiji YAMADA
    Type: PAPER
    2011 Volume E94.D Issue 3 Pages 552-563
    Published: March 01, 2011
    Released: March 01, 2011
    JOURNALS FREE ACCESS
    This paper introduces a future and past search engine, ChronoSeeker, which can help users to develop long-term strategies for their organizations. To provide on-demand searches, we tackled two technical issues: (1) organizing efficient event searches and (2) filtering out noises from search results. Our system employed query expansion with typical expressions related to event information such as year expressions, temporal modifiers, and context terms for efficient event searches. We utilized a machine-learning technique of filtering noise to classify candidates into information or non-event information, using heuristic features and lexical patterns derived from a text-mining approach. Our experiment revealed that filtering achieved an 85% F-measure, and that query expansion could collect dozens more events than those without expansion.
    Download PDF (1313K)
  • Adam JATOWT, Yukiko KAWAI, Katsumi TANAKA
    Type: PAPER
    2011 Volume E94.D Issue 3 Pages 564-577
    Published: March 01, 2011
    Released: March 01, 2011
    JOURNALS FREE ACCESS
    Due to the increased preservation efforts, large amounts of past Web data have been stored in Web archives and other archival repositories. Utilizing this data can offer certain benefits to users, for example, it can facilitate page understanding. In this paper, we propose a system for interactive exploration of page histories. We demonstrate an application called Page History Explorer (PHE) for summarizing and visualizing histories of Web pages. PHE portrays the overview of page evolution, characterizes its typical content over time and lets users observe page histories from different viewpoints. In addition, it enables flexible comparison of histories of different pages.
    Download PDF (1980K)
  • Tatsuya OGAWA, Qiang MA, Masatoshi YOSHIKAWA
    Type: PAPER
    2011 Volume E94.D Issue 3 Pages 578-586
    Published: March 01, 2011
    Released: March 01, 2011
    JOURNALS FREE ACCESS
    In this paper, we propose a novel stakeholder mining mechanism for analyzing bias in news articles by comparing descriptions of stakeholders. Our mechanism is based on the presumption that interests often induce bias of news agencies. As we use the term, a “stakeholder” is a participant in an event described in a news article who should have some relationships with other participants in the article. Our approach attempts to elucidate bias of articles from three aspects: stakeholders, interests of stakeholders, and the descriptive polarity of each stakeholder. Mining of stakeholders and their interests is achieved by analysis of sentence structure and the use of RelationshipWordNet, a lexical resource that we developed. For analyzing polarities of stakeholder descriptions, we propose an opinion mining method based on the lexical resource SentiWordNet. As a result of analysis, we construct a relations graph of stakeholders to group stakeholders sharing mutual interests and to represent the interests of stakeholders. We also describe an application system we developed for news comparison based on the mining mechanism. This paper presents some experimental results to validate the proposed methods.
    Download PDF (838K)
  • Min LUO, Akitsugu WATANABE, Haruo YOKOTA
    Type: PAPER
    2011 Volume E94.D Issue 3 Pages 587-601
    Published: March 01, 2011
    Released: March 01, 2011
    JOURNALS FREE ACCESS
    Scalability and availability are the key features of parallel database systems. To realize scalability, many dynamic load-balancing methods with data placement and parallel index structures on shared-nothing parallel infrastructure have been proposed. Data migration with range-partitioned placement using a parallel Btree is one solution. The combination of range partitioning and chained declustered replicas provides high availability (HA) while preserving scalability. However, independent treatment of the primary and backup data in each node requires long failover times. We propose a novel method for the compound treatment of chained declustered replicas using a parallel Btree, termed the Fat-Btree. In the proposed method, a single Fat-Btree provides access paths to both the primary and backup data of all processor elements (PEs), which greatly reduces failover time. Moreover, these access paths overlap between two neighboring PEs, which enables dynamic load balancing without physical data migration by dynamically redirecting the access paths. In addition, this compound treatment improves memory space utilization to enable index processing with good scalability. Experiments using PostgreSQL on a 160-node PC cluster demonstrate the effectiveness of the high scalability and availability of our proposed method.
    Download PDF (2878K)
  • Yongkun WANG, Kazuo GODA, Miyuki NAKANO, Masaru KITSUREGAWA
    Type: PAPER
    2011 Volume E94.D Issue 3 Pages 602-611
    Published: March 01, 2011
    Released: March 01, 2011
    JOURNALS FREE ACCESS
    Flash SSDs are being incorporated in many enterprise storage platforms recently and expected to play a notable role for IO-intensive applications. However, the IO characteristics of flash SSDs are very different from those of hard disks. Since existent storage subsystems are designed on the basis of characteristics of hard disks, the IO performance of flash SSDs may not be obtained as expected. This paper provides an evaluation of flash SSDs in transaction processing systems with TPC-C benchmark. We present performance results with various configurations and describe our observations of the IO behaviors at different levels along the IO path, which helps to understand the performance of flash-based transaction processing systems and provides certain references to build flash-based systems for IO-intensive applications.
    Download PDF (1364K)
Regular Section
  • Rodion MOISEEV, Shinpei HAYASHI, Motoshi SAEKI
    Type: PAPER
    Subject area: Software System
    2011 Volume E94.D Issue 3 Pages 612-621
    Published: March 01, 2011
    Released: March 01, 2011
    JOURNALS FREE ACCESS
    Object Constraint Language (OCL) is frequently applied in software development for stipulating formal constraints on software models. Its platform-independent characteristic allows for wide usage during the design phase. However, application in platform-specific processes, such as coding, is less obvious because it requires usage of bespoke tools for that platform. In this paper we propose an approach to generate assertion code for OCL constraints for multiple platform specific languages, using a unified framework based on structural similarities of programming languages. We have succeeded in automating the process of assertion code generation for four different languages using our tool. To show effectiveness of our approach in terms of development effort, an experiment was carried out and summarised.
    Download PDF (771K)
  • Ki-Hoon LEE, Young-Ho PARK
    Type: PAPER
    Subject area: Data Engineering, Web Information Systems
    2011 Volume E94.D Issue 3 Pages 622-631
    Published: March 01, 2011
    Released: March 01, 2011
    JOURNALS FREE ACCESS
    XQuery has become the standard for querying XML. Just like SQL, XQuery allows nested expressions. To optimize XQuery processing, a lot of research has been done on normalization, i.e., transforming nested expressions to equivalent unnested ones. Previous normalization rules are classified into two categories—source-level and algebra-level—depending on whether a construct is specified in the XQuery syntax or as equivalent algebraic expressions. From an implementation point of view, the former is preferable to the latter since it can be implemented in a variety of XQuery engines with different algebras. However, existing source-level rules have several problems: They do not handle quantified expressions, incur duplicated query results, and use many temporary files. In this paper, we propose new source-level normalization rules that solve these problems. Through analysis and experiments, we show that our normalization rules can reduce query execution time from hours to a few seconds and can be adapted to a variety of XQuery engines.
    Download PDF (2906K)
  • Huakang LI, Jie HUANG, Qunfei ZHAO
    Type: PAPER
    Subject area: Artificial Intelligence, Data Mining
    2011 Volume E94.D Issue 3 Pages 632-638
    Published: March 01, 2011
    Released: March 01, 2011
    JOURNALS FREE ACCESS
    In this paper, we propose a method for robot self-position identification by active sound localization. This method can be used for autonomous security robots working in room environments. A system using an AIBO robot equipped with two microphones and a wireless network is constructed and used for position identification experiments. Differences in arrival time to the robot's microphones are used as localization cues. To overcome the ambiguity of front-back confusion, a three-head-position measurement method is proposed. The position of robot can be identified by the intersection of circles restricted using the azimuth differences among different sound beacon pairs. By localizing three or four loudspeakers as sound beacons positioned at known locations, the robot can identify its position with an average error of 7cm in a 2.5×3.0m2 working space in the horizontal plane. We propose adjusting the arrival time differences (ATDs) to reduce the errors caused when the sound beacons are high mounted. A robot navigation experiment was conducted to demonstrate the effectiveness of the proposed position-identification system.
    Download PDF (591K)
  • Ken KANEIWA, Riichiro MIZOGUCHI
    Type: PAPER
    Subject area: Artificial Intelligence, Data Mining
    2011 Volume E94.D Issue 3 Pages 639-647
    Published: March 01, 2011
    Released: March 01, 2011
    JOURNALS FREE ACCESS
    This paper proposes a new semantics that characterizes the time and/or situation dependencies of properties, together with the ontological notion of existential rigidity. For this purpose, we present order-sorted tempo-situational logic (OSTSL) with rigid/anti-rigid sorts and an existential predicate. In this logic, rigid/anti-rigid sorted terms enable the expressions for sortal properties, and temporal and situational operators suitably represent the ontological axioms of existential rigidity and time and/or situation dependencies. A specific semantics of OSTSL adheres to the temporal and situational behaviors of properties based on existential rigidity. As a result, the semantics guarantees that the ontological axioms of properties expressed by sorted tempo-situational formulas are logically valid.
    Download PDF (233K)
  • Atsunori OGAWA, Satoshi TAKAHASHI, Atsushi NAKAMURA
    Type: PAPER
    Subject area: Speech and Hearing
    2011 Volume E94.D Issue 3 Pages 648-658
    Published: March 01, 2011
    Released: March 01, 2011
    JOURNALS FREE ACCESS
    This paper proposes an efficient combination of state likelihood recycling and batch state likelihood calculation for accelerating acoustic likelihood calculation in an HMM-based speech recognizer. Recycling and batch calculation are each based on different technical approaches, i.e. the former is a purely algorithmic technique while the latter fully exploits computer architecture. To accelerate the recognition process further by combining them efficiently, we introduce conditional fast processing and acoustic backing-off. Conditional fast processing is based on two criteria. The first potential activity criterion is used to control not only the recycling of state likelihoods at the current frame but also the precalculation of state likelihoods for several succeeding frames. The second reliability criterion and acoustic backing-off are used to control the choice of recycled or batch calculated state likelihoods when they are contradictory in the combination and to prevent word accuracies from degrading. Large vocabulary spontaneous speech recognition experiments using four different CPU machines under two environmental conditions showed that, compared with the baseline recognizer, recycling and batch calculation, our combined acceleration technique further reduced both of the acoustic likelihood calculation time and the total recognition time. We also performed detailed analyses to reveal each technique's acceleration and environmental dependency mechanisms by classifying types of state likelihoods and counting each of them. The analysis results comfirmed the effectiveness of the combined acceleration technique.
    Download PDF (824K)
  • Longbiao WANG, Norihide KITAOKA, Seiichi NAKAGAWA
    Type: PAPER
    Subject area: Speech and Hearing
    2011 Volume E94.D Issue 3 Pages 659-667
    Published: March 01, 2011
    Released: March 01, 2011
    JOURNALS FREE ACCESS
    We propose a blind dereverberation method based on spectral subtraction using a multi-channel least mean squares (MCLMS) algorithm for distant-talking speech recognition. In a distant-talking environment, the channel impulse response is longer than the short-term spectral analysis window. By treating the late reverberation as additive noise, a noise reduction technique based on spectral subtraction was proposed to estimate the power spectrum of the clean speech using power spectra of the distorted speech and the unknown impulse responses. To estimate the power spectra of the impulse responses, a variable step-size unconstrained MCLMS (VSS-UMCLMS) algorithm for identifying the impulse responses in a time domain is extended to a frequency domain. To reduce the effect of the estimation error of the channel impulse response, we normalize the early reverberation by cepstral mean normalization (CMN) instead of spectral subtraction using the estimated impulse response. Furthermore, our proposed method is combined with conventional delay-and-sum beamforming. We conducted recognition experiments on a distorted speech signal simulated by convolving multi-channel impulse responses with clean speech. The proposed method achieved a relative error reduction rate of 22.4% in relation to conventional CMN. By combining the proposed method with beamforming, a relative error reduction rate of 24.5% in relation to the conventional CMN with beamforming was achieved using only an isolated word (with duration of about 0.6s) to estimate the spectrum of the impulse response.
    Download PDF (322K)
  • Kei HASHIMOTO, Heiga ZEN, Yoshihiko NANKAKU, Akinobu LEE, Keiichi TOKU ...
    Type: PAPER
    Subject area: Speech and Hearing
    2011 Volume E94.D Issue 3 Pages 668-678
    Published: March 01, 2011
    Released: March 01, 2011
    JOURNALS FREE ACCESS
    This paper proposes Bayesian context clustering using cross validation for hidden Markov model (HMM) based speech recognition. The Bayesian approach is a statistical technique for estimating reliable predictive distributions by treating model parameters as random variables. The variational Bayesian method, which is widely used as an efficient approximation of the Bayesian approach, has been applied to HMM-based speech recognition, and it shows good performance. Moreover, the Bayesian approach can select an appropriate model structure while taking account of the amount of training data. Since prior distributions which represent prior information about model parameters affect estimation of the posterior distributions and selection of model structure (e.g., decision tree based context clustering), the determination of prior distributions is an important problem. However, it has not been thoroughly investigated in speech recognition, and the determination technique of prior distributions has not performed well. The proposed method can determine reliable prior distributions without any tuning parameters and select an appropriate model structure while taking account of the amount of training data. Continuous phoneme recognition experiments show that the proposed method achieved a higher performance than the conventional methods.
    Download PDF (455K)
  • Yan DENG, Wei-Qiang ZHANG, Yan-Min QIAN, Jia LIU
    Type: PAPER
    Subject area: Speech and Hearing
    2011 Volume E94.D Issue 3 Pages 679-689
    Published: March 01, 2011
    Released: March 01, 2011
    JOURNALS FREE ACCESS
    One typical phonotactic system for language recognition is parallel phone recognition followed by vector space modeling (PPRVSM). In this system, various phone recognizers are applied in parallel and fused at the score level. Each phone recognizer is trained for a known language, which is assumed to extract complementary information for effective fusion. But this method is limited by the large amount of training samples for which word or phone level transcription is required. Also, score fusion is not the optimal method as fusion at the feature or model level will retain more information than at the score level. This paper presents a new strategy to build and fuse parallel phone recognizers (PPR). This is achieved by training multiple acoustic diversified phone recognizers and fusing at the feature level. The phone recognizers are trained on the same speech data but using different acoustic features and model training techniques. For the acoustic features, Mel-frequency cepstral coefficients (MFCC) and perceptual linear prediction (PLP) are both employed. In addition, a new time-frequency cepstrum (TFC) feature is proposed to extract complementary acoustic information. For the model training, we examine the use of the maximum likelihood and feature minimum phone error methods to train complementary acoustic models. In this study, we fuse phonotactic features of the acoustic diversified phone recognizers using a simple linear fusion method to build the PPRVSM system. A novel logistic regression optimized weighting (LROW) approach is introduced for fusion factor optimization. The experimental results show that fusion at the feature level is more effective than at the score level. And the proposed system is competitive with the traditional PPRVSM. Finally, the two systems are combined for further improvement. The best performing system reported in this paper achieves an equal error rate (EER) of 1.24%, 4.98% and 14.96% on the NIST 2007 LRE 30-second, 10-second and 3-second evaluation databases, respectively, for the closed-set test condition.
    Download PDF (599K)
  • Michael PAUL, Andrew FINCH, Eiichiro SUMITA
    Type: PAPER
    Subject area: Natural Language Processing
    2011 Volume E94.D Issue 3 Pages 690-697
    Published: March 01, 2011
    Released: March 01, 2011
    JOURNALS FREE ACCESS
    This paper proposes an unsupervised word segmentation algorithm that identifies word boundaries in continuous source language text in order to improve the translation quality of statistical machine translation (SMT) approaches. The method can be applied to any language pair in which the source language is unsegmented and the target language segmentation is known. In the first step, an iterative bootstrap method is applied to learn multiple segmentation schemes that are consistent with the phrasal segmentations of an SMT system trained on the resegmented bitext. In the second step, multiple segmentation schemes are integrated into a single SMT system by characterizing the source language side and merging identical translation pairs of differently segmented SMT models. Experimental results translating five Asian languages into English revealed that the proposed method of integrating multiple segmentation schemes outperforms SMT models trained on any of the learned word segmentations and performs comparably to available monolingually built segmentation tools.
    Download PDF (443K)
  • Yuanzhi CHENG, Quan JIN, Hisashi TANAKA, Changyong GUO, Xiaohua DING, ...
    Type: PAPER
    Subject area: Biological Engineering
    2011 Volume E94.D Issue 3 Pages 698-706
    Published: March 01, 2011
    Released: March 01, 2011
    JOURNALS FREE ACCESS
    We describe a technique for the registration of three dimensional (3D) knee femur surface points from MR image data sets; it is a technique that can track local cartilage thickness changes over time. In the first coarse registration step, we use the direction vectors of the volume given by the cloud of points of the MR image to correct for different knee joint positions and orientations in the MR scanner. In the second fine registration step, we propose a global search algorithm that simultaneously determines the optimal transformation parameters and point correspondences through searching a six dimensional space of Euclidean motion vectors (translation and rotation). The present algorithm is grounded on a mathematical theory - Lipschitz optimization. Compared with the other three registration approaches (ICP, EM-ICP, and genetic algorithms), the proposed method achieved the highest registration accuracy on both animal and clinical data.
    Download PDF (778K)
  • Tetsuo MORIYA, Itaru KATAOKA
    Type: LETTER
    Subject area: Fundamentals of Information Systems
    2011 Volume E94.D Issue 3 Pages 707-709
    Published: March 01, 2011
    Released: March 01, 2011
    JOURNALS FREE ACCESS
    Let Q be the set of all primitive words over a finite alphabet having at least two letters. In this paper, we study the language D(1) of all non-overlapping (d-primitive) words, which is a proper subset of Q. We show that D(1) is a context-sensitive langauage but not a deterministic context-free language. Further it is shown that [D(1)]n is not regular for n ≥ 1.
    Download PDF (69K)
  • Jianxin LIAO, Jingyu WANG, Tonghong LI, Xiaomin ZHU
    Type: LETTER
    Subject area: Information Network
    2011 Volume E94.D Issue 3 Pages 710-713
    Published: March 01, 2011
    Released: March 01, 2011
    JOURNALS FREE ACCESS
    We propose a novel probing scheme capable of discovering shared bottlenecks among multiple paths between two multihomed hosts simultaneously, without any specific help from the network routers, and a subsequent grouping approach for partitioning these paths into groups. Simulation results show that the probing and grouping have an excellent performance under different network conditions.
    Download PDF (494K)
  • Jihwan SONG, Deokmin HAAM, Yoon-Joon LEE, Myoung-Ho KIM
    Type: LETTER
    Subject area: Artificial Intelligence, Data Mining
    2011 Volume E94.D Issue 3 Pages 714-717
    Published: March 01, 2011
    Released: March 01, 2011
    JOURNALS FREE ACCESS
    In this paper, we introduce a new sequential pattern, the Interactive User Sequence Pattern (IUSP). This pattern is useful for grouping highly interrelated users in one-way communications such as e-mail, SMS, etc., especially when the communications include many spam users. Also, we propose an efficient algorithm for discovering IUSPs from massive one-way communication logs containing only the following information: senders, receivers, and dates and times. Even though there is a difficulty in that our new sequential pattern violates the Apriori property, the proposed algorithm shows excellent processing performance and low storage cost in experiments on a real dataset.
    Download PDF (852K)
  • Yu QIU, Kiichi URAHAMA
    Type: LETTER
    Subject area: Image Processing and Video Processing
    2011 Volume E94.D Issue 3 Pages 718-720
    Published: March 01, 2011
    Released: March 01, 2011
    JOURNALS FREE ACCESS
    We present a simple technique for enhancing multi-modal images. The unsharp masking (UM) is at first nonlinearized to prevent halos around large edges. This edge-preserving UM is then extended to cross-sharpening of multi-modal images where a component image is sharpened with the aid of more clear edges in another component image.
    Download PDF (328K)
  • Do QUAN, Yo-Sung HO
    Type: LETTER
    Subject area: Image Processing and Video Processing
    2011 Volume E94.D Issue 3 Pages 721-724
    Published: March 01, 2011
    Released: March 01, 2011
    JOURNALS FREE ACCESS
    In JPEG2000, the Cohen-Daubechies-Feauveau (CDF) 9/7-tap wavelet filter was implemented by using the conventional lifting scheme. However, the filter coefficients remain complex, and the conventional lifting scheme disregards image edges in the coding process. In order to solve these issues, we propose a lifting scheme in two steps. In the first step, we select the appropriate filter coefficients; in the second step, we employ a median operator to regard image edges. Experimental results show that the peak signal-to-noise ratio (PSNR) value of the proposed lifting scheme is significantly improved, by up to 0.75dB on average, compared to that of the conventional lifting scheme in the CDF 9/7-tap wavelet filter of JPEG2000.
    Download PDF (552K)
  • Hanhoon PARK, Hideki MITSUMINE, Mahito FUJII
    Type: LETTER
    Subject area: Image Recognition, Computer Vision
    2011 Volume E94.D Issue 3 Pages 725-728
    Published: March 01, 2011
    Released: March 01, 2011
    JOURNALS FREE ACCESS
    Speeded up robust features (SURF) can detect scale- and rotation-invariant features at high speed by relying on integral images for image convolutions. However, since the number of image convolutions greatly increases in proportion to the image size, another method for reducing the time for detecting features is required. In this letter, we propose a method, called ordinal convolution, of reducing the number of image convolutions for fast feature detection in SURF and compare it with a previous method based on sparse sampling.
    Download PDF (253K)
  • Yuan HU, Jingqi YAN, Wei LI, Pengfei SHI
    Type: LETTER
    Subject area: Image Recognition, Computer Vision
    2011 Volume E94.D Issue 3 Pages 729-733
    Published: March 01, 2011
    Released: March 01, 2011
    JOURNALS FREE ACCESS
    A robust method is presented for 3D face landmarking with facial pose and expression variations. This method is based on Multi-level Partition of Unity (MPU) Implicits without relying on texture, pose, orientation and expression information. The MPU Implicits reconstruct 3D face surface in a hierarchical way. From lower to higher reconstruction levels, the local shapes can be reconstructed gradually according to their significance. For 3D faces, three landmarks, nose, left eyehole and right eyehole, can be detected uniquely with the analysis of curvature features at lower levels. Experimental results on GavabDB database show that this method is invariant to pose, holes, noise and expression. The overall performance of 98.59% is achieved under pose and expression variations.
    Download PDF (593K)
  • Masaki MURATA, Hiroki TANJI, Kazuhide YAMAMOTO, Stijn DE SAEGER, Yasun ...
    Type: LETTER
    Subject area: Natural Language Processing
    2011 Volume E94.D Issue 3 Pages 734-737
    Published: March 01, 2011
    Released: March 01, 2011
    JOURNALS FREE ACCESS
    In this study, we extracted articles describing problems, articles describing their solutions, and articles describing their causes from a Japanese Q&A style Web forum using a supervised machine learning with 0.70, 0.86, and 0.56 F values, respectively. We confirmed that these values are significantly better than their baselines. This extraction will be useful to construct an application that can search for problems provided by users and display causes and potential solutions.
    Download PDF (67K)
feedback
Top