Upgrade to Pro — share decks privately, control downloads, hide ads and more …
Sign up for free

Shoe Recognition Model with Floor Pressure Sens...

Avatar for yumulab yumulab
November 06, 2024
Research
82
0

Shoe Recognition Model with Floor Pressure Sensors (Slide)

2024年11月3日(日)〜7日(木)に開催されたSENSORCOMM2024の発表資料(スライド)

Avatar for yumulab

yumulab

November 06, 2024

More Decks by yumulab

See All by yumulab
オープンキャンパス模擬講義 Webカメラを使ったインタラクティブWebアプリの開発 / oc2026
Avatar for yumulab yumulab
0
62
非試合日の野球場を楽しむためのARホームランボールキャッチ体験システムの開発 / EC79-miyazaki
Avatar for yumulab yumulab
0
440
MR流体を用いたセルフセンシング可能な触覚デバイスの提案 / haptics36-kamimura
Avatar for yumulab yumulab
0
140
歌詞駆動パーティクルライブ制作支援ツールの提案 / wiss2025-kamimura
Avatar for yumulab yumulab
0
18
人の移動を通信媒介とする電子ペーパーサイネージのための圧電素子を用いた近接駆動方式の提案 / wiss2025-akiba
Avatar for yumulab yumulab
0
19
ASMR耳かき動画のための音と触覚の同時提示システムの提案 / wiss2025-shimizu
Avatar for yumulab yumulab
0
15
地産地消型センシングに向けた植物の葉への電子回路形成の検討 / wiss2025-yumura
Avatar for yumulab yumulab
0
16
Bluetooth Low Energyの海に潜る / Dive to Bluetooth Low Energy
Avatar for yumulab yumulab
0
160
湯村研究室の紹介2025 / yumulab2025
Avatar for yumulab yumulab
0
380

Other Decks in Research

See All in Research
Anthropic が提案する LLM の内部状態を自然言語で説明可能にした Natural Language Autoencoders / Natural Language Autoencoders Produce Unsupervised Explanations of LLM Activations
Avatar for Shunsuke KITADA shunk031
0
280
第64回CV・PRML勉強会　論文紹介：Linguistic Priors for Visual Decoupling: Towards Symmetric Vision-Brain Alignment
Avatar for Soki Katayama sokikatayama
0
210
JICA QUEST 共創×革新プログラム Impact Report（海ノ向こうコーヒー）
Avatar for 坂ノ途中 ontheslope
0
650
量子サマースクール2026「量子計算機アーキテクチャ分野の概観」
Avatar for Yosuke Ueno youten622
1
910
SAM3を用いたコマ・吹き出しの 領域検出と分割構造からの読み順推定
Avatar for kzmssk kzmssk
0
140
[IR Reading 2026春 論文紹介] LLM-based Listwise Reranking under the Effect of Positional Bias (ECIR 2026) /IR-Reading-2026-Spring
Avatar for Kohei Shinden koheishinden
PRO
0
430
視覚若手の会LENSって何？？
Avatar for 小島瑞貴 mickey_0226
0
270
最先端NLP勉強会2026 論文紹介：Reasoning with Sampling: Your Base Model is Smarter Than You Think (ICLR 2026 paper)
Avatar for Kogoro kogoro
4
640
ros2-perf-multihost: 分散システムにおける客観的なアーキテクチャ評価フレームワーク
Avatar for takasehideki takasehideki
0
270
[最先端NLP勉強会2026] Agentic Rubrics as Contextual Verifiers for SWE Agents
Avatar for Ryo Fujii rfujii
1
360
多様なデータを許容し学習し続ける模倣学習 / Advanced Imitation Learning for VLA
Avatar for PRIN Lab prinlab
0
330
MIRU2026 チュートリアル講演2：三次元データ処理の動向
Avatar for Naoya Chiba nnchiba
6
4.9k

Featured

See All Featured
実際に使うSQLの書き方 徹底解説 / pgcon21j-tutorial
Avatar for soudai sone soudai
PRO
203
76k
Taking LLMs out of the black box: A practical guide to human-in-the-loop distillation
Avatar for Ines Montani inesmontani
PRO
3
2.4k
The Organizational Zoo: Understanding Human Behavior Agility Through Metaphoric Constructive Conversations (based on the works of Arthur Shelley, Ph.D)
Avatar for Dr. Kim W Petersen kimpetersen
PRO
0
460
[Rails World 2023 - Day 1 Closing Keynote] - The Magic of Rails
Avatar for Eileen M. Uchitelle eileencodes
38
3k
B2B Lead Gen: Tactics, Traps & Triumph
Avatar for Sophie Logan marketingsoph
0
250
Product Roadmaps are Hard
Avatar for C. Todd Lombardo iamctodd
55
13k
The Director’s Chair: Orchestrating AI for Truly Effective Learning
Avatar for Mike Taylor tmiket
1
300
The AI Revolution Will Not Be Monopolized: How open-source beats economies of scale, even for LLMs
Avatar for Ines Montani inesmontani
PRO
3
3.7k
Building the Perfect Custom Keyboard
Avatar for Naoto Takai takai
2
880
Future Trends and Review - Lecture 12 - Web Technologies (1019888BNR)
Avatar for Beat Signer signer
PRO
0
3.8k
Building an army of robots
Avatar for Kyle Neath kneath
307
46k
Building AI with AI
Avatar for Ines Montani inesmontani
PRO
1
1.2k

Transcript

  1. Shoe Recognition Model with Floor Pressure Sensors Sora Kamimura *1

    Tetsuo Yutani *2 Atsuko Shibuya *2 Tsubasa Yumura *1 *1 Hokkaido Information University *2 FirstFourNotes, LLC <%FNP>

  2. Table of contents  #BDLHSPVOE1VSQPTF  1SFTTVSFTFOTPS  .PEFM 

    %BUBTFUT  3FTVMU%JTDVTTJPO  $PODMVTJPO

  3. #BDLHSPVOE1VSQPTF 5SB ffi D fl PXBOBMZTJT #ZDBNFSB 4VSWFJMMBODFDBNFSBTDBOCFEJWFSUFE $BONBOBHFBMBSHFBSFBCZPOFDBNFSB *OWBTJPOPGQSJWBDZ

    #MJOETQPUTDBVTFECZPCTUBDMFT ɾ*NQSPWFEXPSLF ffi DJFODZ ɾ"WPJESJTL DPMMJTJPOT GBMMT FUDʜ  #Z fl PPSQSFTTVSFTFOTPS /PQSJWBDZJTTVF /PCMJOETQPUT

  4. #BDLHSPVOE1VSQPTF 5SB ff i D fl PXBOBMZTJTCBTFE fl PPSQSFTTVSFTFOTPS SFRVJSFTJEFOUJ

    fi DBUJPOPGQFPQMF )VNBOJEFOUJ fi DBUJPOVTFT XFJHIU TUSJEFMFOHUI TQFFE TIPFUZQF FUD *OUIJTTUVEZ XFEFWFMPQUIF TIPFSFDPHOJUJPONPEFMXJUI fl PPSQSFTTVSFTFOTPST

  5. 1SFTTVSFTFOTPS .BUFSJBMT ɾ7FMPTUBU QSFTTVSFTFOTJUJWFDPOEVDUJWFTIFFU ɾ$PQQFSGPJMUBQF ɾ"SEVJOP 4USVDUVSF ɾ$PQQFSGPJMUBQFTBSFNNXJEFBOE ɹTQBDFENNBQBSU ɾUBQFTCPUIWFSUJDBMMZBOEIPSJ[POUBMMZ

    ɾNFBTVSFNFOUQPJOUT ɾ.FBTVSFUIFWPMUBHFBUFBDIQPJOUFWFSZNT

  6. .PEFM ɾ5IF*OQVUMBZFSSFDFJWFTSBXEBUB ɾ5IFIJEEFOMBZFSJTUISFFGVMMZDPOOFDUFEMBZFS ɾ5IFPVUQVUMBZFSXJMMPVUQVUUIFTIPFJEFOUJ fi DBUJPOFTUBCMJTINFOU ɹ TOFBLFS SPPNTIPF BOETBOEBM

    /FVSBMOFUXPSLNPEFM

  7. %BUBTFUT )PXUPDPMMFDU  $BMJCSBUJPOUIFTFOTPS  1VUPOTIPF  8BJUBGFXTFDPOET TPST 

     .FBTVSFNFOUT  .FBTVSFNFOUTUJNFT JOFBDITIPF %BUB5ZQF ɾ&BDITFOTPS ʙ PS.FSHFE ɾ)PXMPOHXBJUGPSNFBTVSF TPST  ɾ/PSNBMPS3PUBUFEEFHSFFTGPS ɹEBUBBVHNFOUBUJPO

  8. 3FTVMU ɾ5IF'NFBTVSFJOTJT ɹIJHIFSUIBOT ˠ7JCSBUJPOTBOEPUIFSOPJTFTJT ɹMFTTCZXBJUJOH ɾ*OTFDPOET UIF'NFBTVSFPG ɹNFSHFEEBUBJTIJHIFSUIBO ɹFBDITFOTPSEBUB ˠ5IFTFOTPSIBTBTFOTJUJWJUZCJBT

    ɹ"OE NPEFMDBOUMFBSOJUCZ ɹFBDITFOTPSEBUB ɹ#VUMFBSOJOHCFDBNFQPTTJCMFCZ ɹNFSHFEEBUB 'NFBTVSF F = 2 × precision × recall precision + recall

  9. $PODMVTJPO ɾ*OUIJTTUVEZ XFEFWFMPQFEUIFOFVSBMOFUXPSLNPEFMUPSFDPHOJ[F ɹTIPFUZQFTXJUI fl PPSQSFTTVSFTFOTPSXJUIB7FMPTUBU ɾ6TJOHBSPUBUFEEBUBTFUQSPWFEUPCFUIFNPTUF ff FDUJWFBQQSPBDIGPS ɹSFBMXPSMEBQQMJDBUJPOT

    ɾ5IFSFBSFMBSHFEJ ff FSFODFCFUXFFOUIFFYQFSJNFOUBMFOWJSPONFOU ɹBOEUIFBTTVNFESFBMFOWJSPONFOU ɾ5IFSFBSFQSPCMFNTTVDIBTSFBDUJPOSBUFBOEBMMPXBCMFQSFTTVSF ɾ8FXJMMDPOUJOVFUPEFWFMPQCPUIIBSEXBSFBOETPGUXBSFUPTPMWF ɹUIFTFQSPCMFNT