Saturday, 2025/05/24

  • CS/AI
  • C
  • TITECH
  • Switch Language
    • ja日本語 (Japanese)
    • enEnglish

Shimosaka Research Group

pursuing MIUBIQ (machine intelligence in UbiComp Research)

  • Home
    • Members
    • Location
  • News
  • Projects
  • Publications
  • Awards
  • Archives
    • Codes
    • Datasets
Navigation
News Presenting our paper on fine-grained urban dynamics prediction with hierarchical Bayes on PAKDD 2021

Presenting our paper on fine-grained urban dynamics prediction with hierarchical Bayes on PAKDD 2021

2021/05/11 | NewsPresentations | 1594 views |

The 25th Pacific Asia Conference on Knowledge Discovery and Data Mining (PAKDD-2021) is May 11-14, 2021 at online conference.

The following oral presentation will be delivered.

In recent years, the use of smartphone Global Positioning System (GPS) logs has accelerated the analysis of urban dynamics. Predicting the population of a city is important for understanding the land use patterns of specific areas of interest. The current state-of-the-art predictive model is a variant of bilinear Poisson regression models. It is independently optimized for each point of interest (POI) using the GPS logs captured at that single POI. Thus, it is prone to instability during fine-scale POI analysis. Inspired by the success of topic modeling, in this study, we propose a novel approach based on the hierarchical Dirichlet process mixture regression to capture the relationship between POIs and upgrade the prediction performance. Specifically, the proposed model enables mixture regression for each POI, while the parameters of each regression are shared across the POIs owing to the hierarchical Bayesian property. The empirical study using 32 M GPS logs from mobile phones in Tokyo shows that our model for large-scale finer-mesh analysis outperforms the state-of-the-art models. We also show that our proposed model realizes important applications, such as visualizing the relationship between cities or abnormal population increase during an event.

-presentation information-
Research Session 12 (May 14, 2021, 10:15 – 12:30 Indian Standard Time (IST) (UTC + 05:30))

Yuta Hayakawa*, Kota Tsubouchi**, Masamichi Shimosaka*:
Simultaneous multiple POI population patternanalysis system with HDP mixture regression
(*Tokyo Institute of Technology, **Yahoo Japan Corporation)

  • tweet

Comments are disabled for this post

Social Networks

  • twitter
  • rss

Recent News

  • Presenting our paper on Exploiting Periodic UWB CIRs for Robust Activity Recognition with Attention-aware Multi-level Wavelet at PerCom2025 2025/02/15
  • Presenting our paper on revealing Universities’ Atmosphere from Visitor Interests has been presented at IEEE BigData 2024 2024/12/16
  • Our paper on adaptive incremental-decremental BLE placement optimization for accurate indoor positioning has been presented at IPIN2024. 2024/10/23
  • Presenting two papers at SIGSPATIAL 2024 2024/10/23
  • Forecasting Crowded Events using Public Announcements with Large Language Models 2024/10/15
  • Forecasting Lifespan of Crowded Events Inspired by Acoustic Synthesis Technique 2024/07/04
  • Our paper on forecasting lifespan of crowded events has been published in IEEE Access 2024/07/04
  • Presenting our paper on Stable IRL from failed demonstrations at IV2024 2024/05/30
  • Presenting our demo on the application “CityScouter” at UbiComp 2023 2023/10/11
  • Presenting our paper on efficient Bluetooth beacon deployment for campus-scale crowd density monitoring application at UbiComp2023 2023/10/05

Search

Copyright 2015 · Shimosaka Research Group at TITECH