研究者詳細 - 大北　剛

論文 - 大北　剛

分割表示85 件中 21 - 40 件目／全件表示 >>

Three-year Review of the 2018-2020 SHL Challenge on Transportation and Locomotion Mode Recognition from Mobile Sensors 査読有り国際誌

Lin Wang, Hristijan Gjoreski, Mathias Ciliberto, Paula Lago, Kazuya Murao, Tsuyoshi Okita and Daniel Roggen

Frontiers 3 2021年09月

記述言語：英語掲載種別：研究論文（学術雑誌）

The Sussex-Huawei Locomotion-Transportation (SHL) Recognition Challenges aim to advance and capture the state-of-the-art in locomotion and transportation mode recognition from smartphone motion (inertial) sensors. The goal of this series of machine learning and data science challenges was to recognize eight locomotion and transportation activities (Still, Walk, Run, Bus, Car, Train, Subway). The three challenges focused on time-independent (SHL 2018), position-independent (SHL 2019) and user-independent (SHL 2020) evaluations, respectively. Overall, we received 48 submissions (out of 93 teams who registered interest) involving 201 scientists over the three years. The survey captures the state-of-the-art through a meta-analysis of the contributions to the three challenges, including approaches, recognition performance, computational requirements, software tools and frameworks used. It was shown that state-of-the-art methods can distinguish with relative ease most modes of transportation, although the differentiating between subtly distinct activities, such as rail transport (Train and Subway) and road transport (Bus and Car) still remains challenging. We summarize insightful methods from participants that could be employed to address practical challenges of transportation mode recognition, for instance, to tackle over-fitting, to employ robust representations, to exploit data augmentation, and to exploit smart post-processing techniques to improve performance. Finally, we present baseline results to compare the three challenges with a unified recognition pipeline and decision window length.

DOI： 10.3389/fcomp.2021.713719

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85115915802&origin=inward

Summary of the Third Nurse Care Activity Recognition Challenge-Can We Do from the Field Data? 査読有り

Alia S.S., Adachi K., Hossain T., Le N.T., Kaneko H., Lago P., Okita T., Inoue S.

UbiComp/ISWC 2021 - Adjunct Proceedings of the 2021 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2021 ACM International Symposium on Wearable Computers 428 - 433 2021年09月

非接触性の人と物体における相互作用検出方法の提案

豊坂祐樹, 大北剛

DICOMOシンポジウム 2021年06月

脳血腫の分類: セグメンテーションと分類のジョイント学習

平野北斗, 大北剛

arxiv 2021年03月

Improvement of Human Action Recognition Using 3D Pose Estimation 査読有り

Adachi K., Lago P., Okita T., Inoue S.

Smart Innovation, Systems and Technologies 204 21 - 37 2021年01月

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

While Human Action Recognition (HAR) using motion capture can perform well with high accuracy, it requires a high computational cost for recording and post-processing. To avoid this, we build a HAR system using 3D pose estimation from the single-camera video instead of motion capture. One drawback in this approach is that the performance is considerably dependent on the camera position. This paper investigates how we can use the pose estimate constantly without the effect of camera position even when the camera position in the test data is changed. We augment the data by rotating around the 3D pose estimate to improve the accuracy when using different camera positions in the test data and in the training data. The strategy of augmenting training data shows improvements up to 55.7% in accuracy, compared with the case of 2D pose with no augmentation.

DOI： 10.1007/978-981-15-8944-7_2

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85107353674&origin=inward

会議報告：NeurIPS 2020（The 34th Conference on Neural Information Processing Systems）査読有り

高瀬翔, 坂本陸, 大北剛

人工知能 ( 一般社団法人人工知能学会 ) 36 ( 4 ) 527 - 531 2021年01月

Summary of the sussex-huawei locomotion-transportation recognition challenge 2020 査読有り

Wang L., Gjoreski H., Ciliberto M., Lago P., Murao K., Okita T., Roggen D.

UbiComp/ISWC 2020 Adjunct - Proceedings of the 2020 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2020 ACM International Symposium on Wearable Computers 351 - 358 2020年09月

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

In this paper we summarize the contributions of participants to the third Sussex-Huawei Locomotion-Transportation (SHL) Recognition Challenge organized at the HASCA Workshop of UbiComp/ISWC 2020. The goal of this machine learning/data science challenge is to recognize eight locomotion and transportation activities (Still, Walk, Run, Bike, Bus, Car, Train, Subway) from the inertial sensor data of a smartphone in a user-independent manner with an unknown target phone position. The training data of a "train"user is available from smartphones placed at four body positions (Hand, Torso, Bag and Hips). The testing data originates from "test"users with a smartphone placed at one, but unknown, body position. We introduce the dataset used in the challenge and the protocol of the competition. We present a meta-analysis of the contributions from 15 submissions, their approaches, the software tools used, computational cost and the achieved results. Overall, one submission achieved F1 scores above 80%, three with F1 scores between 70% and 80%, seven between 50% and 70%, and four below 50%, with a latency of maximum of 5 seconds.

DOI： 10.1145/3410530.3414341

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85091885062&origin=inward

8th international workshop on human activity sensing corpus and applications (HASCA) 査読有り

Murao K., Enokibori Y., Gjoreski H., Lago P., Okita T., Siirtola P., Hiroi K., Scholl P.M., Ciliberto M.

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

The recognition of complex and subtle human behaviors from wearable sensors will enable next-generation human-oriented computing in scenarios of high societal value (e.g., dementia care). This will require large-scale human activity corpus and much improved methods to recognize activities and the context in which they occur. This workshop deals with the challenges of designing reproducible experimental setups, running large-scale dataset collection campaigns, designing activity and context recognition methods that are robust and adaptive, and evaluating systems in the real world. We wish to reflect on future methods, such as lifelong learning approaches that allow open-ended activity recognition. This year HASCA will welcome papers from participants to the Third Sussex-Huawei Locomotion and Transportation Recognition Challenge and Second Nursing Activity Recognition Challenge in special sessions.

DOI： 10.1145/3410530.3414612

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85091833400&origin=inward

Perception of interaction between hand and object 査読有り

Toyosaka Y., Okita T.

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

Action knowledge graphs can play a central role in smart cities, smart homes, robot planning, and so on. This is since both of the subject and the object of the actions can add more meaningful information for the higher-level application than the action alone as a predicate. We built a system that generates the action knowledge graphs from video using deep learning. Especially, we propose an algorithm which perceives the interaction between hand and object by measuring the proximity between them with considering the direction of fingers. We showed that this approach achieves the performance of 83% in accuracy using the Stair Lab data.

DOI： 10.1145/3410530.3414363

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85091839586&origin=inward

Summary of the 2nd nurse care activity recognition challenge using lab and field data 査読有り

Alia S.S., Lago P., Adachi K., Hossain T., Goto H., Okita T., Inoue S.

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

2nd Nurse Care Activity Recognition Challenge using Lab and Field Data is organized as a part of HASCA workshop and is continuation of Nurse Care Activity Recognition Challenge [7]. We give the description of the dataset and summarize the approaches used by the teams in this Challenge. In this challenge, data collected in both lab and real-world setting is provided to the challenge participants with an aim to bridge the gap between lab and practical field to reduce the workload of the nurses. The challenge was started on May 1, 2020 and continued until July 9, 2020. Accuracy is used as performance metric to evaluate the submissions. The winning team used k-NN classifier and achieved about 22.35% accuracy.

DOI： 10.1145/3410530.3414611

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85091886199&origin=inward

Translation Between Waves, wave2wave 国際誌

Tsuyoshi Okita, Hirotaka Hachiya, Sozo Inoue, Naonori Ueda

arxiv 2020年07月

手と物体の相互作用の認識とその知識グラフの生成

豊坂祐樹, 大北剛

DICOMOシンポジウム 361 - 367 2020年06月

U-netを用いた異常検知による肺炎の検知

長村徹, 徳永旭将, 大北剛

DICOMOシンポジウムプロシーディングス 526 - 533 2020年06月

SHAP値や重要度を用いたモデル解釈性: 包除積分ネットワークとXGBoostの比較

板橋将之, 本田あおい, 大北剛

火の国シンポジウムプロシーディングス 2020年03月

アマゾン商品レビューの感情分析と評価スコアの相関性の検証

高山なつき, Mario Koppen, 大北剛

火の国シンポジウムプロシーディングス 2020年03月

会議報告：The 33rd Conference on Neural Information Processing Systems（NeurIPS 2019）査読有り

大北剛

人工知能 ( 一般社団法人人工知能学会 ) 35 ( 3 ) 465 - 466 2020年01月

ビデオからの3次元姿勢推定と機械学習を用いた行動認識の試み

安達康平,大北剛,井上創造

ソフト九州プロシーディングス 2019年11月

不変リスク最小化の考察

大北剛

ソフト九州プロシーディングス 2019年11月

混合正規分布のデータセットにおけるAntlion clusteringと既存のクラスタリング手法との比較

豊坂祐樹,福田亮治,大北剛,宮野英次

ソフト九州プロシーディングス 2019年11月

Summary of the Sussex-Huawei locomotion-transportation recognition challenge 2019 査読有り

Wang L., Gjoreski H., Ciliberto M., Lago P., Murao K., Okita T., Roggen D.

UbiComp/ISWC 2019- - Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers 849 - 856 2019年09月

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

In this paper we summarize the contributions of participants to the Sussex-Huawei Transportation-Locomotion (SHL) Recognition Challenge organized at the HASCA Workshop of UbiComp 2019. The goal of this machine learning/data science challenge is to recognize eight locomotion and transportation activities (Still, Walk, Run, Bike, Bus, Car, Train, Subway) from the inertial sensor data of a smartphone in a placement independent manner. The training data is collected with smartphones placed at three body positions (Torso, Bag and Hips), while the testing data is collected with a smartphone placed at another body position (Hand). We introduce the dataset used in the challenge and the protocol for the competition. We present a meta-analysis of the contributions from 14 submissions, their approaches, the software tools used, computational cost and the achieved results. Overall, three submissions achieved F1 scores between 70% and 80%, five with F1 scores between 60% and 70%, five between between 50% and 60%, and one below 50%, with a latency of a maximum of 5 seconds.

DOI： 10.1145/3341162.3344872

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85072892002&origin=inward

　前のページ - 次のページ　

<大北 剛>

論文 - 大北 剛

<大北　剛>

論文 - 大北　剛