Monday, 2017/08/21

  • 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
  • tagcloud11-new
  • iv_slider
    How to drive safely & defensively?
    Learning from experts.
    Check out our project
  • webslide_urbdyn-1
    Urban Dynamics
    Location data from smartphones
    help us understand demographics of cities.
    Check out our project
  • fullyConnectedCRFs-dataset
    You're not alone.
    Collective Activity Recognition
    with Fully Connected CRFs
    Check out our project
  • top_image_steered_crowdsensning
    Steered CrowdSensing
    You're more valuable than you think.
    Help people with your palm.
    Check out our project
  • wearable
    Pedometers see through the deep inside of your community.
    Working-Relationship Detection
    from Fitbit Sensor Data
    Check out our project

Introduction

Welcome to Shimosaka Research Group.

This laboratory pursues innovative machine intelligence in ubiquitous and pervasive computing.

Research topics include deployments of wearable or ambient sensors for pervasive sensing, intelligent data analytics for modeling human behavior, and lifelog (quantify-self-technology).

The lab. is led by Masamichi Shimosaka who collaborate with graduate students in Dept of Computer Science in ISE/TITECH.

Towards succeeds on next level applications in ubiquitous computing, we collaborate with companies and governmental organizations as well as national scientific foundation in Japan.

Masamichi Shimosaka has moved to CS/ISE/TITECH from IMI/IST/UTokyo since July 2015. The group has restarted as lab. at TITECH!

Tweet

Our Projects

Irregularity prediction based on transit app logs

Irregularity prediction based on transit app logs

2017/02/04 |
Working-Relationship Detection from Fitbit Sensor Data

Working-Relationship Detection from Fitbit Sensor Data

2015/10/05 |
Urban dynamics analysis with large-scale Location data from smartphones

Urban dynamics analysis with large-scale Location data from smartphones

2015/10/05 |
Modeling risk anticipation and defensive driving on residential roads using inverse reinforcement learning

Modeling risk anticipation and defensive driving on residential roads using inverse reinforcement learning

2015/08/17 |
Consistent collective activity recognition with fully connected CRFs

Consistent collective activity recognition with fully connected CRFs

2014/09/01 |
Steered Crowdsensing

Steered Crowdsensing

2014/08/06 |
An easy-to-install system for daily walking ability assessment with a distance sensor array

An easy-to-install system for daily walking ability assessment with a distance sensor array

2013/04/01 |
Hand Shape Classification with a Wearable Wrist Contour Sensor

Hand Shape Classification with a Wearable Wrist Contour Sensor

2013/04/01 |
Health score prediction with high-level activity features

Health score prediction with high-level activity features

2013/04/01 |
Frustratingly Simplified Deployment in Wi-Fi Localization via Route Annotation.

Frustratingly Simplified Deployment in Wi-Fi Localization via Route Annotation.

2012/04/01 |
Indoor activity recognition with discriminative deformable part models

Indoor activity recognition with discriminative deformable part models

2012/04/01 |
Modeling and Predicting Going-out Behavior via Dirichlet process mixture

Modeling and Predicting Going-out Behavior via Dirichlet process mixture

2012/04/01 |
Counting People in Crowded Environment

Counting People in Crowded Environment

2011/04/01 |
Driver behavior modeling from multiple drivers’ data

Driver behavior modeling from multiple drivers’ data

2011/04/01 |
Behavior Prediction from Trajectories in a House by Estimating Transition Model Using Stay Points

Behavior Prediction from Trajectories in a House by Estimating Transition Model Using Stay Points

2011/04/01 |
Driver behavior modeling based on Bayesian collaborative learning

Driver behavior modeling based on Bayesian collaborative learning

2010/04/01 |
The Optimization of Sensor Arrangement and Feature Selection in Activity Recognition

The Optimization of Sensor Arrangement and Feature Selection in Activity Recognition

2010/04/01 |

Social Networks

  • twitter
  • rss

Recent News

  • Irregularity prediction based on transit app logs 2017/02/04
  • Presenting our paper on fast inverse reinforcement learning at AAAI 2017 2017/02/02
  • Presenting our paper on Bayesian simultaneous clustering and topic modeling at ECML-PKDD2016 2016/09/08
  • Presenting our paper on irregurality prediction using transit app logs at UbiComp2016 (Sep. 12 ~ Sep. 16) @Heidelberg, Germany 2016/09/06
  • Presenting our paper on RSSI-based indoor localizasion at UbiComp2016 (September, 2016 @Heidelberg) 2016/09/06
  • New Members of April 2016 2016/04/25
  • Our paper on Wireless indoor localization with sensor placement optimization has been published in Advanced Robotics 2016/03/30
  • Working-Relationship Detection from Fitbit Sensor Data 2015/10/05
  • Urban dynamics analysis with large-scale Location data from smartphones 2015/10/05
  • Presenting our paper on Forecasting Urban Dynamics with Mobility Logs at UbiComp2015 (September, 2015 @Osaka) 2015/10/05
Tweet

Search

Copyright 2015 · Shimosaka Research Group at TITECH