Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
PRMU, IBISML, IPSJ-CVIM |
2024-03-03 16:45 |
Hiroshima |
Hiroshima Univ. Higashi-Hiroshima campus (Primary: On-site, Secondary: Online) |
Visualization of diverse solutions with different number of topics in topic models Toshio Uchiyama, Tsukasa Hokimoto (HIU) IBISML2023-44 |
The Latent Dirichlet analysis is known as a topic model that is useful
for analyzing data such as documents. The hiera... [more] |
IBISML2023-44 pp.29-35 |
PRMU, IBISML, IPSJ-CVIM [detail] |
2023-03-03 16:40 |
Hokkaido |
Future University Hakodate (Primary: On-site, Secondary: Online) |
On the analysis of diverse solutions in topic models Toshio Uchiyama, Tsukasa Hokimoto (HIU) PRMU2022-124 IBISML2022-131 |
Probabilistic Latent Semantic Analysis and Latent Dirichlet analysis are known as topic models to analyze text data and ... [more] |
PRMU2022-124 IBISML2022-131 pp.355-362 |
PRMU |
2020-09-02 10:00 |
Online |
Online |
A method for clarifying differences between feature distributions of various solutions about topic model Toshio Uchiyama, Tsukasa Hokimoto (HIU) PRMU2020-8 |
Probabilistic Latent Semantic Analysis and Latent Dirichlet analysis are
known as topic models to analyze text data an... [more] |
PRMU2020-8 pp.1-6 |
PRMU |
2019-12-19 10:30 |
Oita |
|
A switching Markov model for evaluation of food functionality Tsukasa Hokimoto, Toshio Uchiyama (HIU) PRMU2019-46 |
For analytic purposes of the scientific processes on how food influence our health, the measurement data on medical or g... [more] |
PRMU2019-46 pp.1-6 |
PRMU |
2019-12-20 10:00 |
Oita |
|
Analysis method and results of solution diversity about topic model Toshio Uchiyama, Tsukasa Hokimoto (HIU) PRMU2019-54 |
Probabilistic Latent Semantic Analysis and Latent Dirichlet analysis are
known as topic models to analyze text data an... [more] |
PRMU2019-54 pp.49-54 |
PRMU, SP |
2018-06-28 16:30 |
Nagano |
|
Analysis of solution diversity about topic model Toshio Uchiyama (HIU) PRMU2018-26 SP2018-6 |
A Topic model is known as a useful statistical model for analyzing text
data and images. Many different parameters (s... [more] |
PRMU2018-26 SP2018-6 pp.25-30 |
PRMU, SP |
2017-06-22 17:00 |
Miyagi |
|
Investigation of solution diversity about probabilistic latent semantic analysis using normalized mutual information Toshio Uchiyama (Hokkaido Info. Univ.) PRMU2017-31 SP2017-7 |
Probabilistic Latent Semantic Analysis (PLSA) and Latent Dirichlet
analysis are known as topic models to analyze text ... [more] |
PRMU2017-31 SP2017-7 pp.33-38 |
PRMU, SP, WIT, ASJ-H |
2016-06-13 15:00 |
Tokyo |
|
Improvement of probabilistic latent semantic analysis using weighted information theoretic clustering Toshio Uchiyama (Hokkaido Info. Univ.) PRMU2016-43 SP2016-9 WIT2016-9 |
Probabilistic Latent Semantic Analysis and Latent Dirichlet analysis are
models to analyze images and documents. This ... [more] |
PRMU2016-43 SP2016-9 WIT2016-9 pp.47-52 |
PRMU, IBISML, IPSJ-CVIM [detail] |
2015-09-15 10:45 |
Ehime |
|
Improvement of nonnegative matrix factorization for probabilistic latent semantic analysis Toshio Uchiyama (HIU) PRMU2015-83 IBISML2015-43 |
Nonnegative Matrix Factorization (NMF) is equivalent to PLSA
(Probabilistic Latent Semantic Analysis), when it uses ge... [more] |
PRMU2015-83 IBISML2015-43 pp.117-122 |
PRMU, IBISML, IPSJ-CVIM [detail] |
2014-09-01 10:30 |
Ibaraki |
|
Nonnegative Matrix Factorization using competitive learning Toshio Uchiyama (Hokkaido Info. Univ.) PRMU2014-37 IBISML2014-18 |
Nonnegative Matrix Factorization (NMF) is a popular technique in data processing, and convergence-guranteed multiplicati... [more] |
PRMU2014-37 IBISML2014-18 pp.7-12 |
PRMU, IBISML, IPSJ-CVIM (Joint) [detail] |
2012-09-02 10:00 |
Tokyo |
|
Information theoretic clustering using competitive learning
-- Comparison of criterion functions and algorithms for document clustering -- Toshio Uchiyama (NTT) PRMU2012-33 IBISML2012-16 |
Information-theoretic clustering (ITC) finds clusters based on the similarity of the distributions of features. An ITC a... [more] |
PRMU2012-33 IBISML2012-16 pp.23-30 |
LOIS |
2012-03-09 15:40 |
Okinawa |
Meio Univ. |
Relevance Modeling of Linked Open Data and Users' Transaction Histories for Recommendation Robert Sumi, Yutaka Kabutoya, Tomoharu Iwata, Toshio Uchiyama, Ko Fujimura (NTT) LOIS2011-108 |
We propose using Linked Open Data (LOD) to inform a topic model for recommending both well-watched old movies and unwatc... [more] |
LOIS2011-108 pp.213-218 |
PRMU, DE |
2011-06-07 09:30 |
Kanagawa |
|
A Proposal of an Instant Question Search System Takeharu Eda, Toshio Uchiyama, Alice Chen, Katsuji Bessho, Ryoji Kataoka (NTT), Masatoshi Yoshikawa (Kyoto Univ.) DE2011-15 PRMU2011-46 |
[more] |
DE2011-15 PRMU2011-46 pp.85-89 |
PRMU, DE |
2011-06-07 10:00 |
Kanagawa |
|
Comparisons of document clustering algorithms and criterion functions Toshio Uchiyama, Takeharu Eda, Katsuji Bessho, Ko Fujimura (NTT) DE2011-16 PRMU2011-47 |
[more] |
DE2011-16 PRMU2011-47 pp.91-96 |
PRMU, DE |
2011-06-07 10:30 |
Kanagawa |
|
Analysis of Interests in a Topic using Query Logs Takayuki Adachi, Toshio Uchiyama, Ko Fujimura (NTT) DE2011-17 PRMU2011-48 |
This paper presents a method to extract users' interests about a topic from query logs, which reflect users' interests. ... [more] |
DE2011-17 PRMU2011-48 pp.97-102 |
PRMU, IE, MI |
2010-05-14 14:15 |
Aichi |
Chubu Univ. |
A novel method for minimum entropy clustering using competitive learning Toshio Uchiyama, Takeharu Eda, Katsuji Bessho, Tadasu Uchiyama, Katsuyoshi Tanabe (NTT) IE2010-39 PRMU2010-27 MI2010-27 |
We propose a novel method (algorithm), which uses competitive
learning, for clustering based on
minimizing average e... [more] |
IE2010-39 PRMU2010-27 MI2010-27 pp.139-144 |
PRMU, IE, MI |
2010-05-14 14:15 |
Aichi |
Chubu Univ. |
A Method for Generating Concept-base with Considering Co-occurrences between All Words Katsuji Bessho, Toshio Uchiyama, Tadasu Uchiyama (NTT) IE2010-41 PRMU2010-29 MI2010-29 |
When generating the concept vector as the meaning representation for the word, we propose a method that the co-occurrenc... [more] |
IE2010-41 PRMU2010-29 MI2010-29 pp.151-156 |
PRMU, IE, MI |
2010-05-14 14:45 |
Aichi |
Chubu Univ. |
DPC coding using concept base specialized in medical field Toshio Uchiyama (NTT), Kazuya Okamoto, Tadamasa Takemura (Kyoto Univ. Hospital), Takayuki Adachi (NTT), Naoto Kume, Tomohiro Kuroda (Kyoto Univ. Hospital), Tadasu Uchiyama (NTT), Hiroyuki Yoshihara (Kyoto Univ. Hospital) IE2010-42 PRMU2010-30 MI2010-30 |
The goal of our research is to achieve high classification accuracy for
DPC (Diagnosis Procedure Combination) coding f... [more] |
IE2010-42 PRMU2010-30 MI2010-30 pp.157-162 |
PRMU |
2009-03-13 17:00 |
Miyagi |
Tohoku Institute of Technology |
Word Association based on α-divergence and Application to Document Classification Katsuji Bessho, Toshio Uchiyama, Tadasu Uchiyama (NTT) PRMU2008-255 |
The co-occurrence vectors that are the co-occurrence frequencies between words and semantic attributes in a corpus refle... [more] |
PRMU2008-255 pp.105-110 |
LOIS |
2009-03-06 09:50 |
Okinawa |
Okinawa-seinen-kaikan |
Document Classification using Clustering of Training Data Katsuji Bessho, Toshio Uchiyama, Tadasu Uchiyama (NTT) OIS2008-85 |
In the document classification that uses concept vectors as semantic expressions of words, the positive example document... [more] |
OIS2008-85 pp.61-64 |