Upgrade to Pro — share decks privately, control downloads, hide ads and more …

情報の世界 2022年度 第12回「個人のデータ」 #情報の世界 / Data of Individual 2022

情報の世界 2022年度 第12回「個人のデータ」 #情報の世界 / Data of Individual 2022

2022年7月7日(木)に開催された北海道情報大学の講義「情報の世界」の第12回「個人のデータ 〜 ウェアラブルデバイス、行動認識、画像処理、プライバシー、パーソナルデータ etc.」の講義資料

yumulab

July 07, 2022
Tweet

More Decks by yumulab

Other Decks in Technology

Transcript

  1. 2022.07.07 ๺ւಓ৘ใେֶ ৘ใϝσΟΞֶ෦ ৘ใϝσΟΞֶՊ ౬ଜ ཌྷ !"#$%& ()*+,-$./012345167891:+/.;%1<%=>-$%&'?@AB CDEFEGH'I'CDEFEJKL DEFEMKCNOPQORONKSBKABQT

    ৘ใͷੈք ୈ12ճ
  2. !"#$ • Twitter΁ͷײ૝ɾ࣭໰ͷ౤ߘ׻ܴ (͜ͷतۀͷࢲͷճͷΈ) • ϋογϡλά #৘ใͷੈք • HIU-WiFi͔ΒTwitterͭͳ͕Βͳ͍ͷͰ(͝ΊΜͶ🥺)ɺɹ εϚϗ͔Β౤ߘ͍ͯͩ͘͠͞

    • ޶όϨͨ͘͠ͳ͍ਓ͸तۀ༻ΞΧ΢ϯτ࡞ΔͱΑ͍͔΋ • εϥΠυͷࡱӨɾεΫγϣ΋౤ߘOKͰ͢🙆 • খςετͷεΫγϣ౤ߘ͸NG🙅 2
  3. %&'() • ࠓ೔ͷߨٛςʔϚ͸ʮݸਓͷσʔλʯ • ʮݸਓʯͱ͍͍ͭͭɺ͍ΖΜͳ࿩͕͋Γ·͢ • ͨͿΜ৘ใաଟͰ͢ • ͋ͱͰPOLITE3ͷϦϯΫूΛৼΓฦ͍ͬͯͩ͘͞ •

    ͥͻʮࣗ෼͕ͲͷΑ͏ʹؔΘΕΔ͔ʯΛҙࣝ͠ͳ͕Β ฉ͍͍ͯͩ͘͞ 3 👀 σϞ͋Γ ಈը͋Γ
  4. %&'() 4 લ൒ (40෼) ΢ΣΞϥϒϧσόΠεɺߦಈೝࣝɺը૾ॲཧ ޙ൒ (25෼) ϓϥΠόγʔɺύʔιφϧσʔλ খςετ (20෼)

    BreakɿTeachable Machineɹ(5෼)
  5. *+,-+./0-1234'567'89: 5 • ஍ਤ্ͷσʔλΛΧοίΑ͘ՄࢹԽͰ͖ΔWebγεςϜ(Uber) 👀 kepler.gl https://kepler.gl/

  6. ;<=>?@5ABC 6 ϝΨω (JINS MEME) JINS MEME https://jinsmeme.com/ Apple Watch

    Series 3 https://www.apple.com/jp/shop/buy-watch/apple-watch-series-3 Apple Watch
  7. DE1FGHI1J 7 Xiaomi MiεϚʔτόϯυ6-ੈքҰͷϙʔλϒϧ | Xiaomi Japa n https://www.mi.com/jp/product/mi-smart-band-6/ ¥4,870

  8. KLMN1DODO 8 JINS MEME https://jinsmeme.com/ ¥19,800 + ¥500/݄(1೥໨ແྉ)

  9. KLMN1DODO 9 👀

  10. PQRH+.1S1KLMN1DODO 10 Vtuner | JINS MEME https://jinsmeme.com/vtuner/ 👀

  11. TUVW • େྔͷσʔλΛػց(ίϯϐϡʔλ)͕ಡΈࠐΜͰ ֶश͠ɺͦͷֶशͨ݁͠Ռ(Ϟσϧ)Λ࢖ͬͯॲཧ Λߦ͏ • Ͱ͖Δ͜ͱ • ෼ྨɺ༧ଌɺҟৗݕ஌ɺੜ੒ 11

  12. 2XY:Z[\] • ༷ʑͳσʔλΛ༻͍ͯਓؒͷߦಈΛೝࣝ͢Δ • ϔϧεέΞɺεϙʔπͳͲʹ׆༻ 12 ڑ཭ηϯα ಈըɾը૾ ߦಈೝࣝ RUNNING

    WALKING SITTING STANDING JUMPING σʔλ εϚʔτϑΥϯ ʢՃ଎౓ɾ܏͖ɾ஍࣓ؾ౳ʣ ΢ΣΞϥϒϧσόΠε ʢՃ଎౓ɾ຺೾౳ʣ
  13. ^_`abc$deZ[\] • Bayat et al., A Study on Human Activity

    Recognition Using Accelerometer Data from Smartphones (2014) • εϚʔτϑΥϯͷՃ଎౓ηϯ αͰߦಈೝࣝ • 2005೥ࠒ(εϚʔτϑΥϯ͕ ग़Δલʂ)͔Β͔͞Μʹ΍Β Ε͍ͯΔݚڀ 13
  14. fghiabc$deZ[\] • Laput et al., Synthetic Sensors: Towards General-Purpose Sensing

    (2017) • Ոఉ಺ͰͷߦಈΛΧϝϥΛ࢖ΘͣʹϚΠΫɺ੺֎ઢηϯαɺՃ଎౓ηϯαɺ࣓ྗܭͳͲΛ౥ࡌͨ͠ηϯαͰਪఆ 14 Synthetic Sensors: Towards General-Purpose Sensing https://youtu.be/aqbKrrru2co
  15. jklmno7pbq$deZ[rs • ߴྛΒ, ਍அπʔϧΛ༻͍ͨεϚʔτλοϓͷফඅిྗ৘ใʹΑΔਓͷߦಈਪఆਫ਼౓ ͷ࣮ূධՁ (2018) • εϚʔτλοϓͰऔಘͨ͠ফඅిྗྔ͔Βʮىচʯʮ֎ग़ʯʮؼ୐ʯʮब৸ʯΛਪఆ 15

  16. tBuvtw6x6'yz{|}~•]€ • ૔ڮΒ, τΠϨοτϖʔύͷճసʹجͮ͘τΠϨ࢖༻ऀࣝผख๏ (2017) • τΠϨοτϖʔύʔͷਊʹ֯଎౓ηϯαΛઃஔ͠ɺ5ͭͷಛ௃ྔ(࢖༻ྔɺ ࣌ؒɺ଎౓ͷ࠷େ஋ɺ଎౓ͷฏۉ஋ɺ଎౓ͷ෼ࢄ)͔Β࢖༻ऀΛਪఆ 16

  17. C•6‚1S1ƒ„ 17 ʲSSK໺ٿެࣜʳεΠϯάΛ஌Δɻ͔ͩΒଧܸ͕มΘΔɻόοςΟϯάʹIoTֵ໋ʂόοτεΠϯάηϯαʔʮSWINGɹCOACHʯ https://youtu.be/QL7Eo35LJZ8

  18. C•6‚1S1cv…6 18 Technical Shot https://technical-shot.com/ The Best Wearable Soccer Tracker

    App | PlayerMake r https://www.playermaker.com/
  19. C•6‚1S1cv…6†>q‡6 19 SPT JAPANʛެࣜαΠτ https://www.sportsperformancetracking.jp/ GPSͰ ҐஔΛ௥੻

  20. C•6‚1S1>bobq 20 EVORIDE ORPHE - γϡʔζ͕ɺίʔνʹͳΔɻʛΞγοΫεެࣜ https://www.asics.com/jp/ja-jp/mk/running/evorideorphe

  21. ˆ‰Š‹5ABCŒ•.++ 21 ͸͡Ίͯͷํ΁ | DFree - ഉᔔ༧ଌσόΠε/Toilet Timing Predicting Device

    https://dfree.biz/personal/beginners.html
  22. Z[\]Ž567Ž•>BA•6 • ػցֶशʹΑΓ͞·͟·ͳߦಈೝ͕ࣝՄೳʹ • ࿙Εͯ΋໰୊ͳ͍ͱࢥͬͨσʔλ͔Βɺ༧ظ͠ͳ͍৘ใ(ߦಈཤྺͳͲ) ͕࿙ΕΔՄೳੑ΋͋Δ • σʔλͷѻ͍͸ɺ͜Ε·ͰҎ্ʹϓϥΠόγʔʹ഑ྀ͢Δඞཁ͕͋Δ 22

  23. TUVWŽ‘’“” • ػցֶशͱը૾ॲཧ෼໺͸૬ޓʹີ઀ʹൃల • Α͘࢖ΘΕΔศརͳπʔϧΛ3ͭ঺հ • YOLO • MediaPipe •

    Teachable Machine 23
  24. •–—–˜™š›œ=@•pžŸ 24 YOLO Open Images in New York https://youtu.be/69Ii3HjUiTM

  25. D+IEG E,+ • Google͕ఏڙ͢ ΔΦʔϓϯιʔε πʔϧ • Pythonɺ JavaScriptͳͲ͍ Ζ͍ΖͳݴޠͰϥ

    ΠϒϥϦ͕͋Δ 25 👀 Home - mediapipe https://google.github.io/mediapipe/
  26. D+IEG E,+1¡GHI¢'£¤¥ 26 ๭Ξχϝͷѱ໾͕࢖͏ʮͱ͓͖ͬͯͷख඼ʯͬΆ͍ېढ͕࢖͑Δʢؾ͕͢Δ͔΋͠Εͳ͍ʣWebΞϓϦ V3 ͷࢼ࡞ʢʁʣ https://youtu.be/wyOzbHk_tVE

  27. D+IEG E,+1 ¦¢+'£¤¥ 27 ্൒਎Ͱԋ૗ | ProtoPedia https://protopedia.net/prototype/2840 👀

  28. §+G¨©Gª-+1DG¨©EH+ • Google͕ఏڙ͢ΔػցֶशϞσϧੜ੒πʔϧɺWeb্ͰࢼͤΔ 28 👀 Teachable Machine https://teachablemachine.withgoogle.com/

  29. UM?KV • Teachable MachineͰ ʮάʔʯʮνϣΩʯʮύʔʯ Λೝࣝͯ͠Έ·͠ΐ͏ • Teachable MachineͷWeb αΠτ͔Βʮ࢖ͬͯΈΔʯɹɹɹɹɹɹ

    ˠʮը૾ϓϩδΣΫτʯɹ ˠʮඪ४ͷը૾Ϟσϧʯ • ࡞ۀ࣌ؒ5෼ • ٳܜ΋͜ͷؒʹ͍ͯͩ͘͠͞
  30. =«q>'¬- 30 ৗઃలࣔʰΞφάϥͷ͏ͨɹʙফ͑ͨത࢜ͱ࢒͞Εͨ૷ஔʙʱ https://youtu.be/75jA7F8AXC4

  31. =«q>'¬- 31 ৗઃలࣔʮΞφάϥͷ͏ͨ―ফ͑ͨത࢜ͱ࢒͞Εͨ૷ஔʯ https://youtu.be/j1zLBXUoG3I

  32. ®vt¯6°…±> • Πϯλʔωοτӽ͠ʹө૾ΛݟΔ͜ͱ͕Ͱ͖ΔΧϝϥ • ๷൜Χϝϥɺࣗ୐ϖοτ؂ࢹ etc. • ੬ऑͳύεϫʔυ΍όοΫυΞʹΑΔෆਖ਼ΞΫηεͷϦεΫ΋ 32 தࠃ੡ωοτϫʔΫΧϝϥʹ؅ཧऀݖݶΛୣऔͰ͖ΔόοΫυΞͷଘࡏ͕ใࠂ͞ΕΔ

    - GIGAZINE https://gigazine.net/news/20200207-xiongmai-backdoor/
  33. N¡–Œ²M • Πϯλʔωοτ઀ଓػثͷݕࡧαΠτ 33

  34. EH¢+¨G³ • ύεϫʔυઃఆ͍ͯ͠ͳ͍ωοτϫʔΫΧϝϥͷө૾ΛूΊͨWebαΠτ΋͋Δ 34 ๷൜Χϝϥө૾Λͷ͖ͧݟͰ͖ͯ͠·͏ʮinsecamʯϨϏϡʔɺ೔ຊͷ๷൜Χϝϥ΋1000୆Ҏ্ϦΞϧλΠϜͰ౪ΈݟՄೳ - GIGAZINE https://gigazine.net/news/20200718-insecam/

  35. M–§L´O • Πϯλʔωοτ઀ଓػثͷ੬ऑੑௐࠪ • ૯຿লɺࠃཱݚڀ։ൃ๏ਓ৘ใ௨৴ݚڀػߏ͕࣮ࢪ 35 NOTICEʛαΠόʔ߈ܸʹѱ༻͞ΕΔ͓ͦΕͷ͋ΔIoTػثͷௐࠪɺ஫ҙשىΛߦ͏ϓϩδΣΫτ https://notice.go.jp/

  36. …±>µ¶'•>BA•6·¸ 36 JRେࡕӺϏϧͷʮإࣝผʯ࣮ূ࣮ݧɺϓϥΠόγʔ৵֐ͷݒ೦͔ΒԆظ | ೔ܦΫϩεςοΫʢxTECHʣ https://xtech.nikkei.com/it/article/NEWS/20140311/542723/ ຊ࣮ূ࣮ݧ͸ݪଇͱͯ͠ɺຽ๏ٴͼಠཱߦ੓๏ਓ౳ݸਓ৘ใอޢ๏ʹ͸ҧ൓͠ͳ͍ͱͷ݁࿦Λಘͨ ػߏ๏ʹج͖ͮઃཱ͞Εͨެతஂମͱͯ͠ͷઆ໌੹೚ΛՌ͍ͨͯ͠ͳ͍ɺͱͷ൷൑Λ໔Εͳ͍Ͱ͋Ζ͏ ө૾ηϯαʔ࢖༻େن໛࣮ূ࣮ݧݕ౼ҕһձ ௐࠪใࠂॻΑΓ

  37. ¹Xº»Žx6¼«@567 37 ύʔιφϧσʔλɿݸਓʹؔ͢Δ৘ใ ݸਓ৘ใɿݸਓΛࣝผͰ͖Δ৘ใ ࢯ໊ ੜ೥݄೔ ॅॴ ݸਓͷଐੑ৘ใ Ҡಈɾߦಈɾߪങཤྺ ΢ΣΞϥϒϧػث͔Βऩूͨ͠৘ใ

  38. x6¼«@567'¥˜nAB@½Y¾¿ • ܞଳి࿩ར༻ऀͷҐஔ৘ใΛ౷ܭతʹར༻ (ߪೖՄ) 38 ʲެࣜʳϞόΠϧۭؒ౷ܭ | Ґஔ৘ใͳͲͷϏοάσʔλΛར༻ͨ͠ਓޱ౷ܭ৘ใ https://mobaku.jp/ 👀

  39. º»ÀZ 39 ৘ใۜߦͱ͸ | ৘ใۜߦαʔϏεDprimeɿࡾඛ̛̪̟৴ୗۜߦ https://www.tr.mufg.jp/dprime/service/about/

  40. º»ÀZ • ৘ใΛ༬͚Δ(౉͢)ͷ͸ෆ҆ʁ • ೔ຊͰ࠷ॳʹͰ͖ͨۜߦ͸1873(໌࣏6)೥ͷୈҰ ࠃཱۜߦ • ೔ຊͰ࠷ॳʹͰ͖ͨ௨՟͸ 7ੈلޙ൒ͷ෋ຊમ 40

  41. Á¿à 41 NEC ൿີܭࢉ | NEC https://jpn.nec.com/secure-computation/index.html

  42. •>BA•6†aÄÅpÆÇŽÈÉ • ๏཯ͷઢҾ͖͸֬ݻͨΔ΋ͷͰ͸ͳ͍ • ղऍʹ෯͕͋Δ(ͳͷͰࡋ൑ͰܾΊΔ) • ࣌୅എܠͷӨڹΛड͚ͯҐஔ͚͕ͮมΘΔ • Coinhiveࣄ݅ •

    ޿ࠂΛࡌͤΔ୅ΘΓʹ҉߸௨՟ϚΠχϯάΛߦ͏ɺWebαΠ τͷ৽͍͠ऩӹγεςϜCoinhive͕ҧ๏ͱ͞Εݕڍ • 1৹ɿແࡑɹɹ2৹ɿ༗ࡑɹɹ࠷ߴࡋɿແࡑ 42
  43. ÊŽ# • ৽͍͠΋ͷ ← ෆ҆ ← ࢓૊Έ͕Θ͔Βͳ͍ • ύʔιφϧσʔλ •

    AI • ϒϩοΫνΣʔϯ • etc. • ࢓૊ΈΛษڧͯ͠ෆ҆Λ෷১͠Α͏ 43
  44. ËÌÌ#º» 44 @shiropen2 AIͷҨిࢠ

  45. ËÍ{$ • খςετʹऔΓ૊ΜͰ͍ͩ͘͞ • 2ճडݧͰ͖·͢ • క੾ɿ࣍ճߨٛ։࢝࣌(07/14 16:15)·Ͱ • ײ૝ॻ͍͍ͯͩ͘͞

    (೚ҙɺ੒੷ʹؔ܎ͳ͠) 45