研究者詳細 - 平田　耕一

論文 - 平田　耕一

分割表示215 件中 21 - 40 件目／全件表示 >>

Predicting Geckler Classification from Gram Stained Smears Images for Sputum: Image Classification versus Object Detection 査読有り国際誌

Hitoshi Sugimoto, Ryotaro Funatsu, Kouichi Hirata

Proc. 15th International Conference on E-Service and Knowledge Management 122 - 127 2023年07月

Detecting Bacteria Causing Infectious Disease from Gram Stained Smears Images 査読有り国際誌

Ukyo Kashino, Syoma Terada, Kouichi Hirata

Proc. 15th International Conference on E-Service and Knowledge Management 13 - 18 2023年07月

Distance-Based Analysis of Positions in Amino Acid Sequences for Structural Proteins of SARS-CoV-2 Delta and Omicron Variants 査読有り国際誌

Ryota Nagashima, Uran Yamamoto, Kouichi Hirata

Proc. 15th International Conference on E-Service and Knowledge Management 39 - 44 2023年07月

イギリスで“science"が科学を意味するようになったのはいつなのか?

園井千音, 平田耕一

大分大学理工学部紀要 ( 大分大学理工学部 ) 1 22 - 30 2023年06月

担当区分：責任著者記述言語：日本語掲載種別：記事・総説・解説・論説等（大学・研究所紀要）

In this paper, we discuss when the word “science" mean science in the current sense in England. Then, by focusing on Journal of Science and the Arts published in 1817 and Edinburgh Journal of Science published in 1824, we point out that the word “science" meant science about 1817 in academic sense and it became the general sense about 1824 for the public.

DOI： 10.51073/17215

Subcaterpillar Isomorphism between Caterpillars: Subtree Isomorphism Restricted Text and Pattern Trees To Caterpillars 査読有り国際誌

Tomoya Miyazaki, Kouichi Hirata

Proc. 12th International Conference on Pattern Recognition Applications and Methods (ICPRAM2023) 89 - 94 2023年02月

Correlated Mutations of Positions among Structural Proteins in Delta and Omicron Variants for SARS-CoV-2 Amino Acid Sequences 査読有り国際誌

Yuishi Shimaya, Kouichi Hirata

Proc. 12th International Conference on Pattern Recognition Applications and Methods (ICPRAM2023) 344 - 349 2023年02月

微生物検査領域における人工知能導入の可能性招待有り査読有り

平田耕一

検査と技術 ( 医学書院 ) 51 ( 1 ) 48 - 50 2023年01月

Subcaterpillar Isomorphism: Subtree Isomorphism Restricted Pattern Trees to Caterpillars 査読有り国際誌

Tomoya Miyazaki, Kouichi Hirata

Proc. 17th Conference on Compute Science and Intelligence Systems (FedCSIS 2022) 351 - 356 2022年09月

担当区分：責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

Bulgaria Sofia 2022年09月04日 - 2022年09月07日

In this paper, we investigate a subcaterpillar isomorphism that is a problem, for a rooted labeled caterpillar P and a rooted labeled tree T, of determining whether or not there exists a subtree in T which is isomorphic to P. Then, we design two algorithms to solve the subcaterpillar isomorphism for a caterpillar P and a tree T in (i) O(p + tDhσ) time and O(Dh) space and in (ii) O(p + tDσ) time and O(D(h + H)) space, respectively. Here, p is the number of vertices in P, t is the number of vertices in T, h is the height of P, H is the height of T, σ is the number of alphabets for labels and D is the degree of T. Furthermore, we give experimental results of the two algorithms for artificial data and real data.

DOI： 10.15439/2022F113

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85141180597&origin=inward

Segmental Distance between Rooted Labeled Caterpillars 査読有り国際誌

Manami Hagihara, Tomoya Miyazaki, Kouichi Hirata

Proc. 14th International Conference on E-Service and Knowledge Management 107 - 112 2022年07月

担当区分：責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

Japan Kanazawa 2022年07月03日 - 2022年07月07日

A segmental distance for rooted labeled unordered trees is the edit distance such that the insertion and the deletion in the edit operations are allowed to either the root or the leaves. In this paper, we design the algorithm of computing the segmental distance for rooted labeled caterpillars in O(n+h2σ) time under the unit cost function, where n is the maximum number of vertices, h is the maximum height and σ is the number of labels, whereas the problem of computing the segmental distance for rooted labeled unordered trees is MAX SNP-hard.

DOI： 10.1109/IIAIAAI55812.2022.00030

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85139561095&origin=inward

Object Detection as Gram Positive Cocci in Gram Stained Smear Images 査読有り国際誌

Hitoshi Sugimoto, Kouichi Hirata

Proc. 14th International Conference on E-Service and Knowledge Management 134 - 137 2022年07月

担当区分：責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

Japan Kanazawa 2022年07月03日 - 2022年07月07日

In this paper, we detect Gram positive cossi in Gram stained smear images as object detection. As detectors, we adopt Faster R-CNN, RetinaNet and YOLOv5. Then, we give experimental results for detecting Gram positive cocci, and the detection by YOLOv5 is more successful than that by Faster R-CNN and RetinaNet.

DOI： 10.1109/IIAIAAI55812.2022.00035

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85139570315&origin=inward

Classifying Gram Positive Cocci and Gram Negative Bacilli in Gram Stained Smear Images 査読有り国際誌

Ibuki Kawano, Eri Kurumida, Syoma Terada, Kouichi Hirata

Proc. 14th International Conference on E-Service and Knowledge Management 55 - 60 2022年07月

担当区分：責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

Japan Kanazawa 2022年07月03日 - 2022年07月07日

In this paper, we classify Gram positive cocci and Gram negative bacilli in Gram stained smear images. We adopt pre-trained models of VGG16, VGG19, MobileNet and DenseNet by using ImageNet as learning models. Then, we give experimental results for classifying them, and the classification by MobileNet and DenseNet are more successful than that by VGG16 and VGG19.

DOI： 10.1109/IIAIAAI55812.2022.00021

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85139565934&origin=inward

Finding Correlated Mutations of Positions among Structural Proteins in SARS-CoV-2 Amino Acid Sequences 査読有り国際誌

Kan Yonashiro, Yuichi Shimaya, Kouichi Hirata

Proc. 14th International Conference on E-Service and Knowledge Management 61 - 64 2022年07月

担当区分：責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

Japan Kanazawa 2022年07月03日 - 2022年07月07日

In this paper, we find the correlated mutations of positions among structural proteins of spike, envelop, membrane and nucleocapsid proteins in amino acid sequences of SARS-CoV-2. Here, we adopt the algorithm designed by Shimada et al. (2012) of finding the correlated mutations formulated by joint entropy. In particular, we focus on whether or not the found correlated mutations contains spike protein substitutions in SARS-CoV-2 Delta variant.

DOI： 10.1109/IIAIAAI55812.2022.00022

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85139554865&origin=inward

Caterpillar Inclusion: Inclusion Problem for Rooted Labeled Caterpillars 査読有り国際誌

Tomoya Miyazaki, Manami Hagihara, Kouichi Hirata

Proc. 11th International Conference on Pattern Recognition Applications and Methods (ICPRAM2022) 280 - 287 2022年02月

Computing the Variations of Edit Distance for Rooted Labaled Caterpillars 査読有り国際誌

Manami Hagihara, Takuya Yoshino, Kouichi Hirata

Proc. 11th International Conference on Pattern Recognition Applications and Methods (ICPRAM2022) 272 - 279 2022年02月

Object Detection as Campylobacter Bacteria and Phagocytotic Activity of Leukocytes in Gram Stained Smears Images 査読有り国際誌

Kyohei Yoshihara, Kouichi Hirata

Proc. 11th International Conference on Pattern Recognition Applications and Methods (ICPRAM2022) 1 534 - 541 2022年02月

担当区分：責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

Online Online 2022年02月03日 - 2022年02月05日

In this paper, we apply object detection to Gram stained smear images, where objects are Campylobacter bacteria and phagocytotic activity of leukocytes. Then, we adopt three CNN-based object detectors of Faster R-CNN, RetinaNet and YOLOv5. The outline of the detection is first to annotate the regions of objects as Campylobacter bacteria and phagocytotic activity of leukocytes in training images, and then to detect the regions of objects in the remained test images by using the detectors. Finally, we give experimental results of detecting Campylobacter bacteria and phagocytotic activity of leukocytes in Gram stained smear images by using the detectors.

DOI： 10.5220/0010813800003122

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85139552318&origin=inward

Nearest-Neighbor Search from Large Datasets Using Narrow Sketches 査読有り国際誌

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

Proc. 11th International Conference on Pattern Recognition Applications and Methods (ICPRAM2022) 401 - 410 2022年02月

Detecting Camphylobacter Bacteria and Phagocytoic Activity of Leukocytes from Gram Stained Smears Images 査読有り国際誌

Kyohei Yoshihara, Kouichi Hirata

Proc. 12th International Conference on E-Service and Knowledge Management - 10 - 15 2021年07月

担当区分：責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

2021年07月11日 - 2021年07月16日

In this paper, we develop the method to detect Campylobacter bacteria and phagocytotic activity of leukocytes from Gram stained smears images. First, we improve VGG16 by adding batch normalization and by replacing flatten with global average pooling and construct the classifier by using transfer learning model based on the improved VGG16. Then, by comparing the detection by the VGG16 with that by the improved VGG16, for the classification of Camphylobacter bacteria, we give experimental results of classifying Campylobacter images with non-Campylobacter images. On the other hand, for the classification of phagocytotic activity of leukocytes, we give experimental results of classifying phagocytotic images with quasi- and non-phagocytotic images and of classifying phagocytotic images, quasi-phagocytotic images and non-phagocytotic images.

DOI： 10.1109/IIAI-AAI53430.2021.00002

Scopus

CiNii Research

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85133161784&origin=inward

Trim Distance between Positions in Necleotide Sequences for Structural Proteins of SARS-CoV-2 査読有り国際誌

Kan Yonashiro, Kouichi Hirata

Proc. 12th International Conference on E-Service and Knowledge Management - 35 - 40 2021年07月

担当区分：責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

2021年07月11日 - 2021年07月16日

A trim distance between two positions in the set of nucleotide sequences is a tree-based distance between the trimmed phylogenetic trees at two positions, each of which is obtained by applying the label-based closest-neighbor trimming method to the relabeled phylogenetic tree at the position that the index as a label of leaves is relabeled to the nucleotide occurring at the position. In this paper, as a tree-based distance, we adopt a label histogram distance and a depth histogram distance. Then, we introduce new trim distances that a label trim distance and a depth trim distance, respectively. Finally, by using the nucleotide sequences and the reconstructed phylogenetic tree from them provided from NCBI, we investigate the trim distances between the positions in the nucleotide sequences for structural proteins of spike, envelope, membrane and nucleocapsid proteins of SARS-CoV-2.

DOI： 10.1109/IIAI-AAI53430.2021.00006

Scopus

CiNii Research

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85133185828&origin=inward

Leaf-Preserving Distance between Rooted Labeled Caterpillars 査読有り国際誌

Manami Hagihara, Takuya Yoshino, Kouichi Hirata

Proc. 12th International Conference on E-Service and Knowledge Management 23 - 28 2021年07月

担当区分：責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

2021年07月11日 - 2021年07月16日

In this paper, we introduce a leaf-preserving distance between rooted labeled trees (trees, for short) as a distance that a leaf in a tree is corresponding to a leaf in another tree. Then, we show that the leaf-preserving distance is always smaller than or equal to the bottom-up distance and incomparable with the alignment distance, the isolated-subtree distance and the segmental distance, but the problem of computing the leaf-preserving distance between trees is MAX SNP-hard. On the other hand, for a rooted labeled caterpillar (caterpillar, for short) that is a tree transformed to a rooted path after removing all the leaves in it, we design an algorithm to compute the leaf-preserving distance between caterpillars in O(h2λ) time, where h is the maximum height and λ is the maximum number of leaves for given two caterpillars. Finally, we give experimental results for computing the leaf-preserving distance for caterpillars.

DOI： 10.1109/IIAI-AAI53430.2021.00004

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85133160471&origin=inward

Caterpillar Alignment Distace for Rooted Labeled Caterpillars: Distance Based on Alignments Requeired to Be Caterpillars 査読有り

Yoshiyuki Ukita, Takuya Yoshino, Kouichi Hirata

Recent Advances in Computational Optimization 920 111 - 134 2021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 labeled caterpillar (caterpillars, for short) is a rooted labeled tree transformed to a rooted path after removing all the leaves in it. In this paper, we discuss the alignment distance between two caterpillars, which is formulated as the minimum cost of possible alignments as supertrees of them. First, we point out that, whereas the alignment between two trees is always a tree, the alignment between two caterpillars is not always a caterpillar. Then, we formulate a caterpillar alignment distance such that the alignment is required to be a caterpillar. Also we formulate a caterpillar less-constrained mapping and show that the caterpillar alignment distance coincides with the minimum cost of possible caterpillar less-constrained mappings. Furthermore, we design the algorithm to compute the caterpillar alignment distance between two caterpillars in O(h2λ3) time under the general cost function and in O(h2λ) time under the unit cost function, where h is the maximum height and λ is the maximum number of leaves in caterpillars. Finally, we give experimental results of computing the caterpillar alignment distance.

DOI： 10.1007/978-3-030-58884-7_6

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85097616531&origin=inward

　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