研究者詳細 - 井上　創造

論文 - 井上　創造

分割表示226 件中 41 - 60 件目／全件表示 >>

Exploring the Use of Accelerometer for Assisting Weight Lifting Exercise 査読有り国際誌

Nour Al Bogha, 井上創造, Brahim Benaissa

International Conference on Activity and Behavior Computing (ABC) 1 - 4 2020年08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）

Japan Kitakyushu

One of the most important aspects of professional athleticism and rehabilitation is muscle activation. Although sport tracking technologies are advancing
rapidly, existing technologies and devices for detecting muscle performance are still
out of common users’ hands, due to their complexity, invasive nature and high cost.
However, sensor equipped devices are getting widely available, which opens the
door to alternative solutions using software. In this work we explore the possibility
of using accelerometer data for muscle performance in a weightlifting exercise. By
investigating a predefined common weightlifting exercise, we exploited a correlation between the acceleration and the lifted weights using a simple RBF prediction
method, in a real experiment where data obtained from three participants. The obtained results show that the weight could be predicted in acceptable accuracy for
each individual, based on acceleration data.

その他リンク： https://abc-research.github.io/2020/

Towards New Performance Metrics for Multi-level Data for Activity Recognition 査読有り国際誌

Sayeda Shamma Alia, Paula Lago, 井上創造

International Conference on Activity and Behavior Computing (ABC) 1 - 8 2020年08月

A Method for Sensor-Based Activity Recognition in Missing Data Scenario 査読有り国際誌

Tahera Hossain, Md Atiqur Rahman Ahad, 井上創造

Sensors 20 ( 3811 ) 2 - 3 2020年07月

Wearable Sensor-Based Gait Analysis for Age and Gender Estimation 査読有り国際誌

Md Atiqur Rahman Ahad, Thanh Trung Ngo, Anindya Das Antar, Masud Ahmed, Tahera Hossain, Daigo Muramatsu, Yasushi Makihara, 井上創造, Yasushi Yagi

Sensors 20 ( 2424 ) 2 - 4 2020年04月

2050年の情報処理：7. 近未来を予測できる世界，Ability-awareな世界

井上創造

情報処理 61 ( 5 ) 453 - 455 2020年04月

担当区分：筆頭著者記述言語：日本語掲載種別：記事・総説・解説・論説等（学術雑誌）

本稿では，2050年の情報処理について，応用の観点から，以下の5点を展望した．それは，1.現在の機械学習技術の延長線上で，少し先の未来を予測する近未来予測技術が発展するだろうこと，2.原理研究だけではなく，手法に新規性がなくとも社会実装した結果得られた知見も重視すべきであること，3.伝統ある統計的仮説検定は30年後には廃れているであろうこと，4.身体的な人間拡張に加え，情報的な人間拡張のための，Ability-aware技術が確立しているであろうこと，5.現在の散在する情報プラットフォームが30年後にどれだけ継続されているかという懸念，である．

Kyutacar

その他リンク： http://id.nii.ac.jp/1001/00204305/

医療と介護のIoT

井上創造

総合リハビリテーション, 医学書院 48 ( 1 ) 35 - 41 2020年01月

Characterizing Word Embeddings for Zero-Shot Sensor-Based Human Activity Recognition 査読有り国際誌

松木萌, Paula Lago, 井上創造

MDPI Sensors 19 ( 22 ) 1 - 26 2019年11月

記述言語：英語掲載種別：研究論文（学術雑誌）

In this paper, we address Zero-shot learning for sensor activity recognition using word embeddings. The goal of Zero-shot learning is to estimate an unknown activity class (i.e., an activity that does not exist in a given training dataset) by learning to recognize components of activities expressed in semantic vectors. The existing zero-shot methods use mainly 2 kinds of representation as semantic vectors, attribute vector and embedding word vector. However, few zero-shot activity recognition methods based on embedding vector have been studied; especially for sensor-based activity recognition, no such studies exist, to the best of our knowledge. In this paper, we compare and thoroughly evaluate the Zero-shot method with different semantic vectors: (1) attribute vector, (2) embedding vector, and (3) expanded embedding vector and analyze their correlation to performance. Our results indicate that the performance of the three spaces is similar but the use of word embedding leads to a more efficient method, since this type of semantic vector can be generated automatically. Moreover, our suggested method achieved higher accuracy than attribute-vector methods, in cases when there exist similar information in both the given sensor data and in the semantic vector; the results of this study help select suitable classes and sensor data to build a training dataset.

DOI： 10.3390/s19225043

Kyutacar

その他リンク： https://doi.org/10.3390/s19225043

Human Activity Recognition using Earable Device 査読有り

Tahera Hossain, Md. Shafiqul Islam, Md Atiqur Rahman Ahad, 井上創造

ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp 2019) 5 2019年09月

Optimizing Activity Data Collection with Gamification Points Using Uncertainty Based Active Learning 査読有り

Nattaya Mairittha, Tittaya Marittha , 井上創造

International Workshop on Human Activity Sensing Corpus and Applications 7 pages 2019年09月

Nurse Care Activity Recognition Challenge: Summary and Results 査読有り

Paula Lago, Sayeda Shamma Alia, 武田紳吾, Tittaya Marittha , Nattaya Mairittha, Farina Faiz, 西村勇亮, 安達康平, 大北剛, Franois Charpillet , 井上創造

Ubicomp Workshop on Human Activity Sensing Corpus and Applications (HASCA) 6 pages 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）

London London

Although activity recognition has been studied for a long time now, research and applications have focused on physical activity recognition. Even if many application domains require the recognition of more complex activities, research on such activities has attracted less attention.
One reason for this gap is the lack of datasets to evaluate and compare different methods.
To promote research in such scenarios, we organized the \textit{Open Lab Nursing Activity Recognition Challenge} focusing on the recognition of complex activities related to the nursing domain. Nursing domain is one of the domains that can benefit enormously from activity recognition but has not been researched due to lack of datasets.
The competition used the CARECOM Nurse Care Activity Dataset, featuring 7 activities performed by 8 subjects in a controlled environment with accelerometer sensors, motion capture and indoor location sensor.
In this paper, we summarize the results of the competition.

Reduction of Marker-Body Matching Work in Activity Recognition Using Motion Capture 査読有り

武田紳吾, Paula Lago, 大北剛, 井上創造

International Workshop on Human Activity Sensing Corpus and Applications ７ pages 2019年09月

A Dialogue-Based Annotation for Activity Recognition 査読有り

Tittaya Marittha , Nattaya Mairittha, 井上創造

International Workshop on Human Activity Sensing Corpus and Applications 6 pages 2019年09月

スマートライフケア社会創造のための基盤づくり

柴田智広, 井上創造, 相馬功

システム制御情報学会誌 ( システム制御情報学会誌 ) 2019年09月

Evaluation of Transfer Learning for Human Activity Recognition among Different Datasets 査読有り

Md. Shafiqul Islam, 大北剛, 井上創造

International Conference on Pervasive Intelligence and Computing (2019) (IEEE PICom 2019) 2019年08月

On-Device Deep Learning Inference for Efficient Activity Data Collection 査読有り

Nattaya Mairittha, Tittaya Marittha , 井上創造

Sensors 19 ( 15 ) 2 - 0 2019年08月

記述言語：英語掲載種別：研究論文（学術雑誌）

Labeling activity data is a central part of the design and evaluation of human activity recognition systems. The performance of the systems greatly depends on the quantity and “quality” of annotations; therefore, it is inevitable to rely on users and to keep them motivated to provide activity labels. While mobile and embedded devices are increasingly using deep learning models to infer user context, we propose to exploit on-device deep learning inference using a long short-term memory (LSTM)-based method to alleviate the labeling effort and ground truth data collection in activity recognition systems using smartphone sensors. The novel idea behind this is that estimated activities are used as feedback for motivating users to collect accurate activity labels. To enable us to perform evaluations, we conduct the experiments with two conditional methods. We compare the proposed method showing estimated activities using on-device deep learning inference with the traditional method showing sentences without estimated activities through smartphone notifications. By evaluating with the dataset gathered, the results show our proposed method has improvements in both data quality (i.e., the performance of a classification model) and data quantity (i.e., the number of data collected) that reflect our method could improve activity data collection, which can enhance human activity recognition systems. We discuss the results, limitations, challenges, and implications for on-device deep learning inference that support activity data collection. Also, we publish the preliminary dataset collected to the research community for activity recognition.

Kyutacar

その他リンク： https://www.mdpi.com/1424-8220/19/15/3434

A Comparative Study on Missing Data Handling Using Machine Learning for Human Activity Recognition 査読有り

Tahera Hossain, 井上創造

International Conference on Activity and Behavior Computing 6 pages 2019年05月