Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
PRMU, IBISML, IPSJ-CVIM |
2024-03-03 15:00 |
Hiroshima |
Hiroshima Univ. Higashi-Hiroshima campus (Primary: On-site, Secondary: Online) |
Learning VQ-VAE for Image Dimensionality Reduction with Spatial Frequency Loss Naoyuki Ichimura (AIST) PRMU2023-60 |
Vector Quantized-Variational AutoEncoders (VQ-VAEs) are a type of deep neural networks designed to learn an approximate ... [more] |
PRMU2023-60 pp.53-58 |
NC, MBE, NLP, MICT (Joint) [detail] |
2024-01-25 16:50 |
Tokushima |
Naruto University of Education |
Analysis of Synchrophasor Data in a Distribution Grid Using Koopman Mode Decomposition toward Dimensionality Reduction Tadahiro Yano, Yoshihiko Susuki (Kyoto Univ.) NLP2023-118 MICT2023-73 MBE2023-64 |
In this report, we study a method to reduce the dimension on highly-resolved time series data of voltage phasors measure... [more] |
NLP2023-118 MICT2023-73 MBE2023-64 pp.162-165 |
IMQ |
2023-12-22 14:00 |
Toyama |
University of Toyama |
[Invited Lecture]
Machine learning application for 2D/3D data analysis in material science Kentaro Kutsukake (RIKEN) IMQ2023-9 |
In materials science, data is becoming increasingly complex, high-dimension, large-scale, and numerous, consequently, hi... [more] |
IMQ2023-9 pp.1-3 |
PRMU, IPSJ-CVIM, IPSJ-DCC, IPSJ-CGVI |
2023-11-17 14:40 |
Tottori |
(Primary: On-site, Secondary: Online) |
Parameter determination method for Isomap based on topological geometry Miura Suyama, Hitoshi Sakano (Shimane Univ) PRMU2023-34 |
In this study, we propose a method to determine the neighborhood parameters of Isomap, a nonlinear dimensionality reduct... [more] |
PRMU2023-34 pp.103-106 |
DE |
2023-06-16 08:50 |
Tokyo |
Musashino University (Primary: On-site, Secondary: Online) |
Analysis of Impact of Interest Rate Hikes on U.S. Industry Market Capitalization
-- Time Series Data Analysis by Amplitude-based Clustering -- Saki Takabatake, Yukari Shirota (Gakushuin Univ.) DE2023-1 |
The U.S. Federal Reserve Board (FRB) has been raising the Federal Funds Rate (FF Rate), since March 2022 for price stabi... [more] |
DE2023-1 pp.1-6 |
CCS, NLP |
2023-06-09 13:55 |
Tokyo |
Tokyo City Univ. |
Analysis of Vocal and Ventricular Folds Data Using Machine Learning Takumi Inoue, Kota Shiozawa, Isao Tokuda (Rits Univ) NLP2023-24 CCS2023-12 |
Vocal fold vibration is a nonlinear phenomenon in the real world. In humans, vocal folds can produce complex sounds by i... [more] |
NLP2023-24 CCS2023-12 pp.49-52 |
NLP, MSS |
2023-03-15 14:20 |
Nagasaki |
(Primary: On-site, Secondary: Online) |
Pareto-based dimensionality reduction of parameters for simple piecewise linear circuits Ryunosuke Numata, Toshimichi Saito (HU) MSS2022-72 NLP2022-117 |
This paper studies dimensionality reduction of parameters in switching power converters. In order to characterize the c... [more] |
MSS2022-72 NLP2022-117 pp.53-57 |
HWS, VLD |
2023-03-02 14:15 |
Okinawa |
(Primary: On-site, Secondary: Online) |
[Memorial Lecture]
DependableHD: A Hyperdimensional Learning Framework for Edge-oriented Voltage-scaled Circuits [Memorial lecture] Dehua Liang (Osaka Univ.), Hiromitsu Awano (Kyoto Univ.), Noriyuki Miura, Jun Shiomi (Osaka Univ.) VLD2022-93 HWS2022-64 |
Voltage scaling is a promising approach for energy efficiency but also brings challenges to guaranteeing stable circuit ... [more] |
VLD2022-93 HWS2022-64 p.111 |
NLP |
2022-11-24 10:20 |
Shiga |
(Primary: On-site, Secondary: Online) |
Reconstructing of Vocal Fold Vibration Video by Echo State Network and Dimensionality Reduction Tomu Noguchi, Kota Shiozawa, Isao Tokuda (Ritsumeikan Univ.) NLP2022-56 |
Video data provides an effective means for capturing the dynamics of experimental object. The dimensionality that actual... [more] |
NLP2022-56 pp.1-4 |
SIP |
2022-08-26 10:48 |
Okinawa |
Nobumoto Ohama Memorial Hall (Ishigaki Island) (Primary: On-site, Secondary: Online) |
Instantaneous linear dimensionality reduction for array signal processing Natsuki Ueno, Nobutaka Ono (TMU) SIP2022-65 |
Linear dimensionality reduction of time-series signals observed by a sensor array is often useful in balancing the accur... [more] |
SIP2022-65 pp.81-85 |
VLD, HWS [detail] |
2022-03-07 13:40 |
Online |
Online |
[Memorial Lecture]
DistriHD: A Memory Efficient Distributed Binary Hyperdimensional Computing Architecture for Image Classification Dehua Liang, Jun Shiomi, Noriyuki Miura (Osaka Univ.), Hiromitsu Awano (Kyoto Univ.) VLD2021-84 HWS2021-61 |
Hyper-Dimensional (HD) computing is a brain-inspired learning approach for efficient and fast learning on today’s embedd... [more] |
VLD2021-84 HWS2021-61 p.44 |
NLP, MICT, MBE, NC (Joint) [detail] |
2022-01-23 10:55 |
Online |
Online |
Reward-oriented Environment Inference on Reinforcement Learning Kazuki Takahashi (Kogakuin Univ.), Tomoki Fukai (OIST), Yutaka Sakai (Tamagawa Univ.), Takashi Takekawa (Kogakuin Univ.) NC2021-42 |
Experiments on humans using the bandit problem have shown that dimensionality reduction of complex observations to a sta... [more] |
NC2021-42 pp.49-54 |
IT |
2021-07-09 14:30 |
Online |
Online |
Construction of Dimension Reduction Matrix for Signal Recovery of Multivariate Gaussian Vectors Kento Yokoyama, Tadashi Wadayama, Satoshi Takabe (NIT) IT2021-26 |
In compressed sensing, we discuss the problem of estimating the sparse original signal $¥bm{x} ¥in ¥mathbb{R}^n$ from th... [more] |
IT2021-26 pp.63-68 |
NS, RCS (Joint) |
2020-12-18 13:50 |
Online |
Online |
[Invited Lecture]
A Study on Higher-Order Large MIMO Detection via Concatenated Beam- and Antenna- Domain Layered BP Takumi Takahashi (Osaka Univ.), Shinsuke Ibi (Doshisha Univ.), Seiichi Sampei (Osaka Univ.) NS2020-102 RCS2020-149 |
In large multi-user multi-input multi-output systems, the computational cost and circuit scale on the base station (BS) ... [more] |
NS2020-102 RCS2020-149 pp.79-84 |
HCGSYMPO (2nd) |
2020-12-15 - 2020-12-17 |
Online |
Online |
A Consideration on Detecting Anormal Respondents in Large Questionnaire Response Data Hiroyuki Takahashi, Wataru Kameyama, Mutsumi Suganuma (Waseda Univ.) |
In a questionnaire with a variety of questions for consumers to answer, there may be a small number of specific answers ... [more] |
|
MBE, NC, NLP, CAS (Joint) [detail] |
2020-10-29 10:50 |
Online |
Online |
Classification of binary data based on binary neural networks Kento Saka, Tomoyuki Togawa, Toshimichi Saito (HU) NC2020-8 |
This paper presents a novel application of binary neural networks to clustering of data sets.
The network characterized... [more] |
NC2020-8 pp.1-4 |
SIS, ITE-BCT |
2020-10-01 13:00 |
Online |
Online |
Evaluation of linear dimensionality reduction methods considering visual information protection for privacy-preserving machine learning Masaki Kitayama, Nobutaka Ono, Hitoshi Kiya (Tokyo Metro. Univ.) SIS2020-13 |
In this paper, linear dimensionality reduction methods are evaluated in terms of difficulty in estimating the visual inf... [more] |
SIS2020-13 pp.17-22 |
CQ |
2020-07-16 16:25 |
Online |
Online |
[Tutorial Invited Lecture]
Fast calculation methods for electro-holography considering application and communication Takashi Nishitsuji (TMU) CQ2020-27 |
The enormous computational complexity is one of the significant issue for the practical use of an electro-hologrpahy, wh... [more] |
CQ2020-27 pp.27-32 |
HIP, HCS, HI-SIGCOASTER [detail] |
2020-05-14 14:40 |
Online |
Online |
On Effective Dimensions, Riemann Metric Tensor Estimation and Dimension Reduction of Facial Expression Space Masashi Shinto, Jinhui Chao (Chuo Univ.) HCS2020-2 HIP2020-2 |
In this paper we first present definitions of effective dimensions for Riemann manifolds and psychophysical spaces. Then... [more] |
HCS2020-2 HIP2020-2 pp.7-12 |
SP, EA, SIP |
2020-03-02 10:35 |
Okinawa |
Okinawa Industry Support Center (Cancelled but technical report was issued) |
Dimension reduction without multiplication in machine learning Nobutaka Ono (TMU) EA2019-104 SIP2019-106 SP2019-53 |
In this study, we propose a dimension reduction method for machine learning by only selecting elements without multiplic... [more] |
EA2019-104 SIP2019-106 SP2019-53 pp.21-26 |