Urban Sensing Based on Model-Driven Extensions to Crowd Replication

• Project/Area Number: 17K00117
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Information network
• Research Institution: Kyushu University
• Principal Investigator: Konomi Shin'ichi 九州大学, 基幹教育院, 教授 (70234804)
• Co-Investigator(Kenkyū-buntansha): 緒方 広明 京都大学, 学術情報メディアセンター, 教授 (30274260) ; 笹尾 知世 徳島大学, 人と地域共創センター, 助教 (60789733)
• Project Period (FY): 2017-04-01 – 2020-03-31
• Project Status: Completed (Fiscal Year 2019)
• Budget Amount: ¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000); Fiscal Year 2019: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000); Fiscal Year 2018: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000); Fiscal Year 2017: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
• Keywords: ユビキタスコンピューティング / 都市センシング / 行動複製 / モバイルセンシング / クラウドセンシング / アーバンコンピューティング / アクティブラーニング / アナリティクス

Outline of Final Research Achievements

The basic design and improvement of the model-driven behavior sampling tool was performed, and the performance was verified using the Crowd Replication Dataset acquired around the railway station. In addition, we proposed a data acquisition method based on active learning that enables labor-saving and highly accurate data acquisition, and verified its effectiveness using actual data. We also examined the user interface of the tool.

Academic Significance and Societal Importance of the Research Achievements

国際的に見ても独自性の高い取り組みである行動複製型データ収集に関して、理論・実践の両面で有意義な研究成果が得られた。本研究成果は、商圏・駅勢圏スケールの広い空間において網羅的に偏りの少ないミクロな行動データを取得する技術の発展に貢献するものであり、ひいてはデータに基づく新たな都市空間デザインの実践による空間の改善につながる可能性がある

Research Products

• [Int'l Joint Research] Open University Tanzania(タンザニア)
• [Journal Article] An Intelligent Platform for Offline Learners Based on Model-driven Crowdsensing over Intermittent Networks. (2020)
  • Author(s): Shin'ichi Konomi, Lulu Gao, Doreen Mushi
  • Journal Title: Proceedings of the 12th International Conference on Cross-Cultural Design Volume: To appear
  • Peer Reviewed / Int'l Joint Research
• [Journal Article] Crowd Replication: Sensing-Assisted Quantification of Human Behavior in Public Spaces (2019)
  • Author(s): Hemminki Samuli、Kuribayashi Keisuke、Konomi Shin'ichi、Nurmi Petteri、Tarkoma Sasu
  • Journal Title: ACM Transactions on Spatial Algorithms and Systems Volume: 5 Issue: 3 Pages: 1-34
  • DOI: 10.1145/3317666
  • Peer Reviewed / Int'l Joint Research
• [Journal Article] Crowd Replication: Sensing-Assisted Quantification of Human Behavior in Public Spaces. (2019)
  • Author(s): Samuli Hemminki, Keisuke Kuribayashi, Shin’ichi Konomi, Petteri Nurmi, Sasu Tarkoma
  • Journal Title: ACM Transactions on Spatial Algorithms and Systems Volume: 1 Pages: 1-1
  • Peer Reviewed / Int'l Joint Research
• [Journal Article] Designing a Mobile Behavior Sampling Tool for Spatial Analytics (2018)
  • Author(s): Shin'ichi Konomi and Tomoyo Sasao
  • Journal Title: Distributed, Ambient, and Pervasive Interactions - Sixth International Conference DAPI 2018, Held as Part of HCI International 2018, Las Vegas, Lecture Notes in Computer Science, Springer. Volume: 2018 Pages: 92-100
  • DOI: 10.1007/978-3-319-91131-1_7
  • ISBN: 9783319911304, 9783319911311
• [Presentation] Active Learning-based Crowd Replication (2020)
  • Author(s): Lulu Gao, Shin'ichi Konomi
  • Organizer: Proceedings of the 34th Annual Conference of the Japanese Society for Artificial Intelligence 2020
• [Book] Distributed, Ambient and Pervasive Interactions: Understanding Humans - Sixth International Conference, DAPI 2018, Held as Part of HCI International 2018 (2018)
  • Author(s): Norbert A. Streitz and Shin'ichi Konomi
  • Total Pages: 482
  • Publisher: Springer
  • ISBN: 9783319911243