研究者詳細 - 平田　耕一

論文 - 平田　耕一

分割表示215 件中 41 - 60 件目／全件表示 >>

グラム染色画像からのキャンピロバクターと白血球貪食の推定

吉原教平, 橋本和貴, 平田耕一

第114回人工知能学会基本問題研究会, 人工知能学会研究会資料 SIG-FPAI-C002 7 - 11 2020年11月

Pivot Selection for Narrow Sketches by Optimization Algorithms 査読有り国際誌

Naoya Higuchi, Yasunobu Imamura, Vladimir Mic, Takeshi Shinohara, Kouichi Hirata, Tetsuji Kuboyama

Proc. 13th Interenational Conference on Similarity Search and Application (SISAP2020), Lecture Notes in Computer Science ( Springer-Verlag ) 12440 33 - 46 2020年09月

記述言語：英語掲載種別：研究論文（学術雑誌）

Online Online 2020年09月30日 - 2020年10月02日

Sketches are compact bit strings that are considered as products of an LSH for high-dimensional data. We use them in filtering for narrowing down solution candidates in similarity search. We propose a pivot selection method for narrow sketches with a length such as 16-bits by optimization algorithms with the accuracy of filtering itself as the objective function.

DOI： 10.1007/978-3-030-60936-8_3

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85093832416&origin=inward

狭い16ビットのスケッチを用いた高速最近傍検索査読有り

樋口直哉, 今村安伸, 久保山哲二, 平田耕一, 篠原武

情報処理学科論文誌数理モデル化と応用 ( 情報処理学会 ) 13 ( 1 ) 13 - 22 2020年03月

Detection System of Gram Types for Bacteria from Gram Stained Smears Images 査読有り国際誌

Ryosuke Iida, Kazuki Hashimoto, Kouichi Hirata, Kimiko Matsuoka, Shigeki Yokoyama

Proc. 9th International Conference on Pattern Recognition Applications and Methods (ICPRAM2020) 477 - 484 2020年02月

Heavy Caterpillar Distances for Rooted Labeled Unordered Trees 査読有り国際誌

Nozomi Abe, Takuya Yoshino, Kouichi Hirata

Proc. 9th International Conference on Pattern Recognition Applications and Methods (ICPRAM2020) 198 - 204 2020年02月

Detecting Geckler Classification from Gram Stained Smears Images for Sputum 査読有り国際誌

Kazuki Hashimoto, Ryosuke Iida, Kouichi Hirata, Kimiko Matsuoka, Shigeki Yokoyama

Proc. 9th International Conference on Pattern Recognition Applications and Methods (ICPRAM2020) 469 - 476 2020年02月

Path Histogram Distance and Complete Subtree Histogram Distance for Rooted Labeled Caterpillars 査読有り国際誌

Taiga Kawaguchi, Takuya Yoshino, Kouichi Hirata

Journal of Information and Telecommunication 4 ( 2 ) 199 - 212 2020年01月

担当区分：責任著者記述言語：英語掲載種別：研究論文（学術雑誌）

A rooted labelled caterpillar (a caterpillar, for short) is a rooted labelled unordered tree transformed to a path after removing all the leaves in it. In this paper, we discuss two histogram distance between caterpillars. One is a path histogram distance as an L1-distance between the histograms of paths from the root to every leaf and another is a complete subtree histogram distance as an L1-distance between the histograms of complete subtrees for every node. While the latter is always a metric for general trees, the former is not a metric. In this paper, we show that, for caterpillars, the path histogram distance is always a metric, simply linear-time computable and incomparable with the edit distance. Furthermore, we give experimental results for caterpillars in real data of comparing the path histogram distance and the complete subtree histogram distance with the isolated-subtree distance as the most general tractable variation of the edit distance.

DOI： 10.1080/24751839.2020.1718443

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85104838825&origin=inward

Annealing by Increasing Resampling 査読有り国際誌

Naoya Higuchi, Yasunobu Imamura, Takeshi Shinohara, Kouichi Hirata, Tetsuji Kuboyama

Lecture Notes in Computer Science 11996 71 - 92 2020年01月

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

Annealing by Increasing Resampling (AIR, for short) is a stochastic hill-climbing optimization algorithm that evaluates the objective function for resamplings with increasing size. At the beginning stages, AIR makes state transitions like a random walk, because it uses small resamplings for which evaluation has large error at high probability. At the ending stages, AIR behaves like a local search because it uses large resamplings very close to the entire sample. Thus AIR works similarly as the conventional Simulated Annealing (SA, for short). As a rationale for AIR approximating SA, we show that both AIR and SA can be regarded as a hill-climbing algorithm according to objective function evaluation with stochastic fluctuations. The fluctuation in AIR is explained by the probit, while in SA by the logit. We show experimentally that the logit can be replaced with the probit in MCMC, which is a basis of SA. We also show experimental comparison of SA and AIR for two optimization problems, sparse pivot selection for dimension reduction, and annealing-based clustering. Strictly speaking, AIR must use resampling independently performed at each transition trial. However, it has been demonstrated by experiments that reuse of resampling within a certain number of times can speed up optimization without losing the quality of optimization. In particular, the larger the samples used for evaluation, the more remarkable the superiority of AIR is in terms of speed with respect to SA.

DOI： 10.1007/978-3-030-40014-9_4

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85079553108&origin=inward

Fast Filtering for Nearest Neighbor Search by Sketch Enumeration without Using Matching 査読有り国際誌

Naoya Higuchi, Yasunobu Imamura, Tetsuji Kuboyama, Kouichi Hirata, Takeshi Shinohara

Proc. 32nd Australian Joint Conference on Advances in Artificial Intelligence, Lecture Notes in Artificial Intelligence 11919 240 - 252 2019年12月

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

オーストラリアアデレード 2019年12月02日 - 2019年12月05日

A sketch is a lossy compression of high-dimensional data into compact bit strings such as locality sensitive hash. In general, k nearest neighbor search using sketch consists of the following two stages. The first stage narrows down the top K candidates, for some K ≥ k,, using a priority measure of sketch as a filter. The second stage selects the k nearest objects from K candidates. In this paper, we discuss the search algorithms using fast filtering by sketch enumeration without using matching. Surprisingly, the search performance is rather improved by the proposed method when narrow sketches with smaller number of bits such as 16-bits than the conventional ones are used. Furthermore, we compare the search efficiency by sketches of various widths for several databases, which have different numbers of objects and dimensionalities. Then, we can observe that wider sketches are appropriate for larger databases, while narrower sketches are appropriate for higher dimension.

DOI： 10.1007/978-3-030-35288-2_20

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85076560904&origin=inward

Alignment for Rooted Labeled Caterpillars 査読有り

Yoshiyuki Ukita, Takuya Yoshino, Kouichi Hirata

Preprints of Position Papers of the 2019 Federated Conference on Computer Science and Information Systems 12 - 25 2019年09月

Iterative Consistency-Based Feature Selection and Its Application to Nucleotide Sequences of Influenza A Viruses 査読有り

Sho Shimamura, Kouichi Hirata

Information Engineering Express 5 ( 1 ) 86 - 96 2019年05月

Introducing Fluctuation into Increasing Order of Symmetric Uncertainty for Consistency-Based Feature Selection 査読有り

Sho Shimamura, Kouichi Hirata

Proc. 15th Annual Conference on Theory and Applications of Models of Computation, Lecture Notes in Computer Science 11436 550 - 565 2019年04月

The Reselection of Adjacent Sets by Consistency-Based Feature Selection Algorithm 査読有り

Sho Shimamura, Kouichi Hirata

Proc. 2nd International Conference on Information Science and System 4 pages 2019年03月

グラム染色画像からの菌分類推定システムの開発

橋本和貴, 飯田亮介, 平田耕一

第109回人工知能学会基本問題研究会, 人工知能学会研究会資料 SIG-FPAI-B803 99 - 104 2019年03月

Annealing by Increasing Resampling in the Unified View of Simulated Annealing 査読有り

Yasunobu Imamura, Naoya Higuchi, Takeshi Shinohara, Kouichi Hirata, Tetsuji Kuboyama

Proc. 8th International Conference on Pattern Recognition Applications and Methods 173 - 180 2019年02月

Vertical and Horizontal Distances to Approximate Edit Distance for Rooted Labeled Caterpillars 査読有り

Kohei Muraka, Takuya Yoshino, Kouichi Hirata

Proc. 8th International Conference on Pattern Recognition Applications and Methods 590 - 597 2019年02月

Bipartite Edge Correlation Clustering: Finding an Edge Biclique Partition from a Bipartite Graph with Minimum Disagreement 査読有り

Mikio Mizukami, Tetsuji Kuboyama, Kouichi Hirata

Proc. 8th International Conference on Pattern Recognition Applications and Methods 699 - 706 2019年02月

Fast Nearest Neighbor Search with Narrow 16-Bit Sketch 査読有り

Naoya Higuchi, Yasunobu Imamura, Tetsuji Kuboyama, Kouichi Hirata, Takeshi Shinohara

Proc. 8th International Conference on Pattern Recognition Applications and Methods 540 - 547 2019年02月

Earth Mover's Distance Between Rooted Labeled Unordered Trees Formulated from Complete Subtrees 査読有り

Taiga Kawaguchi, Takuya Yoshino, Kouichi Hirata

ICPRAM2018: Proc. International Conference on Pattern Recognition Applications and Methods, Lecture Notes in Artificial Intelligence 11351 65 - 88 2019年01月

LCA Histogram Distance for Rooted Labeled Caterpillars 査読有り

Takuya Yoshino, Kohei Muraka, Kouichi Hirata

Proc. 10th International Conference on Knowledge Discovery and Information Retrieval (KDIR 2018) 2018年09月

　前のページ - 次のページ　

<平田 耕一>

論文 - 平田 耕一

<平田　耕一>

論文 - 平田　耕一