研究者詳細 - 和田　親宗

論文 - 和田　親宗

分割表示392 件中 1 - 20 件目／全件表示 >>

内側に装着圧力を加える圧力負荷機能を有した開発装具が変形性膝関節症の立ち上がり動作に与える影響査読有り

山本裕晃,遠藤正英,馬場智大,橋本将志,和田親宗

理学療法科学 40 ( 3 ) 125 - 130 2025年06月

おむつ交換法の違いが腰部負荷へ与える影響

伏谷遼平, 和田親宗, 中野聡太

人間工学 ( 一般社団法人日本人間工学会 ) 61 ( Supplement ) 2F03-03 - 2F03-03 2025年05月

担当区分：責任著者記述言語：日本語掲載種別：研究論文（研究会，シンポジウム資料等）

介護者の腰痛は介護現場で重要な問題であり、中でもおむつ交換動作は腰部負荷が大きいとされる。そこで本研究では、IMUセンサによる動作データおよび手部負荷測定装置による手部負荷データをもとに筋骨格シミュレータにより、複数のおむつ交換時の姿勢や方法による腰部負荷を比較した。その結果、交換方法によって腰部負荷に明確な違いが見られ、負荷軽減法の示唆が得られた。

DOI： 10.5100/jje.61.2f03-03

CiNii Research

慣性センサ装着杖を用いた活動量推定手法の精度向上

佐々木優菜, 村上やよい, 藤本隆, 山邉郷介, 森藤達雄, 和田親宗

人間工学 ( 一般社団法人日本人間工学会 ) 61 ( Supplement ) 3F01-02 - 3F01-02 2025年05月

担当区分：最終著者記述言語：日本語掲載種別：研究論文（研究会，シンポジウム資料等）

我々は，杖に慣性センサを取り付けた杖型計測装置により，高齢者の活動量を推定しようと試みている．20名の高齢被験者を対象に，慣性センサデータから機械学習手法により活動量を推定し，市販の活動量計と比較したところ，推定精度の低い場合があった．その問題解決のために，ファインチューニングの導入や, 杖の使い方等で被験者を分類したところ，一部で推定精度の向上が見られた．このことから，杖の使用法等を考慮した上で，被験者数を増やし，さらなる精度向上を図っていく．

DOI： 10.5100/jje.61.3f01-02

CiNii Research

Lifting Posture Recognition for Occupational Health using Digital Image and Machine Learning 査読有り国際誌

Kodai Kitagawa, Arthur Ducoulombier, Mitsumasa Hida, Tadateru Kurosawa, Fuhui Guo, Chikamune Wada, Hiroaki Yamamoto

International Journal of Applied Biomedical Engineering 18 ( 1 ) 1 - 7 2025年05月

Improved YOLOv10 for Visually Impaired: Balancing Model Accuracy and Efficiency in the Case of Public Transportation 査読有り国際誌

Arifando R., Eto S., Tibyani T(Brawijaya university)., Wada C.

Informatics 12 ( 1 ) 2025年03月

担当区分：最終著者記述言語：英語掲載種別：研究論文（学術雑誌）

Advancements in automation and artificial intelligence have significantly impacted accessibility for individuals with visual impairments, particularly in the realm of bus public transportation. Effective bus detection and bus point-of-view (POV) classification are crucial for enhancing the independence of visually impaired individuals. This study introduces the Improved-YOLOv10, a novel model designed to tackle challenges in bus identification and pov classification by integrating Coordinate Attention (CA) and Adaptive Kernel Convolution (AKConv) into the YOLOv10 framework. The Improved YOLOv10 advances the YOLOv10 architecture through the incorporation of CA, which enhances long-range dependency modeling and spatial awareness, and AKConv, which dynamically adjusts convolutional kernels for superior feature extraction. These enhancements aim to improve both detection accuracy and efficiency, essential for real-time applications in assistive technologies. Evaluation results demonstrate that the Improved-YOLOv10 offers significant improvements in detection performance, including better Accuracy, Precision and Recall compared to YOLOv10. The model also exhibits reduced computational complexity and storage requirements, highlighting its efficiency. While the classification results show some trade-offs, with slightly decreased overall F1 score, the complexity of Giga Floating Point Operations (GFLOPs), Parameters, and Weight/MB in the Improved-YOLOv10 remains advantageous for classification tasks. The model’s architectural improvements contribute to its robustness and efficiency, making it a suitable choice for real-time applications and assistive technologies.

DOI： 10.3390/informatics12010007

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=105001174540&origin=inward

変形性膝関節症に対する膝装具が階段降段動作に与える影響－装着圧力に着目した開発装具による検証－査読有り

山本裕晃,遠藤正英,馬場智大,橋本将志,和田親宗

理学療法福岡 38 71 - 76 2025年03月

鍼刺激誘発による血中ヘモグロビン結合の一酸化窒素が及ぼす遠隔部末梢血管拡張査読有り

米田哲哉, 山川烈, 和田親宗

バイオメディカル・ファジィ・システム学会誌 ( バイオメディカル・ファジィ・システム学会 ) 26 ( 2 ) 53 - 58 2025年02月

担当区分：最終著者記述言語：日本語掲載種別：研究論文（学術雑誌）

鍼灸刺激により局所と遠隔部の血流が増加するメカニズムは、上脊髄反射が関与するとされてきた．しかし、筆者らの予備実験では、上脊髄反射の関与だけでは説明できない事象が観察された．血管拡張に一酸化窒素が関与することと，一酸化窒素は血中に拡散し，ヘモグロビンと結合することから，鍼刺激によって発生した一酸化窒素が血液で運ばれ、遠隔部で血管拡張を引き起こすという仮説を立てた．本研究では，ヒトを対象に指尖容積脈波計を用いて経皮酸素飽和度（SpO2）と心拍数（HR）を，また血流スコープを用いて血管径を測定することにより，一酸化窒素の存在とそれによ
る血管拡張現象の検証実験をおこなった．その結果，鍼刺激部位と測定部位との距離が近いほど，鍼刺激から血管拡張が生じるまでの時間が短かった．このことから，鍼刺激により発生した一酸化窒素が，血中に拡散し，ヘモグロビンと結合し，末梢血管に運搬され，遠隔部末梢血管拡張に寄与していることが推定できる．

DOI： 10.24466/jbfsa.26.2_53

CiNii Research

その他リンク： http://id.ndl.go.jp/bib/034049756

変形性膝関節症に対して開発した膝装具と既存装具の比較査読有り

山本裕晃, 遠藤正英, 馬場智大, 橋本将志, 和田親宗

理学療法科学 ( 理学療法科学学会 ) 40 ( 1 ) 42 - 46 2025年02月

担当区分：最終著者記述言語：日本語掲載種別：研究論文（学術雑誌）

〔目的〕装着圧力に着目して開発した膝装具と既存装具とを変形性膝関節症患者に装着し，装着圧力が高くなるか否かと，対象者による主観的な評価を比較した結果を検討した．〔対象と方法〕対象は変形性膝関節症患者20名（男性8名，女性12名）とした．まず，装着した際の装着圧力を既存装具と開発装具で比較した．計測後は，既存装具と開発装具で，装着難度，通気性，外観，重量感，装着感をVisual Analogue Scaleを用いて対象者の主観的な評価を比較した．〔結果〕装着圧力は，既存装具と開発装具に有意差が認められた．主観的な評価は有意差が認められなかった．〔結語〕開発装具は，装着圧力が既存装具より高く設定することが可能であったが，主観的な評価による差異は生じなかった．

DOI： 10.1589/rika.40.42

CiNii Research

その他リンク： https://www.jstage.jst.go.jp/article/rika/40/1/40_42/_pdf

Musculoskeletal simulation for patient transfer using hand load measurement device 査読有り国際誌

Ryo Uchimura, Ryohei Fushitani, Kodai Kitagawa, Chikamune Wada

International Journal of Research in Orthopaedics 11 ( 1 ) 1 - 5 2025年01月

体導音センサと畳み込みニューラルネットワークを用いたシャント音スペクトログラム画像からの自己血管内シャント機能評価推定査読有り

城屋敷健志, 和田親宗

医療機器学 ( 一般社団法人日本医療機器学会 ) 95 ( 1 ) 30 - 36 2025年01月

Performance Evaluation of YOLOv8 Models for Multi-Class Skin Lesion Detection from Dermoscopic Images 査読有り

Paramita C., Supriyanto C., Šolić P., Wada C., Dzaky A.A.

2025 International Conference on Smart Computing Iot and Machine Learning Siml 2025 2025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）

Skin cancer remains a significant global health issue, with over 1.5 million cases annually, including 330,000 melanomas. Ultraviolet (UV) radiation exposure is a primary risk factor, especially for fair-skinned populations. Early detection of skin cancer is critical to improving survival rates, particularly for melanoma, which poses a high mortality risk due to metastasis. This study explores the application of YOLOv8, a convolutional neural network model, for skin cancer detection using the HAM10000 dataset. The dataset underwent augmentation to address class imbalance and improve detection accuracy. Among the YOLOv8 variants, YOLOv8s demonstrated the highest performance with an mAP50 of 0.890, precision of 0.840, and recall of 0.857. For malignant lesion detection, YOLOv8m showed optimal sensitivity with a recall of 0.857. These findings underscore the potential of YOLOv8 in enhancing diagnostic accuracy for both benign and malignant skin cancer, contributing significantly to early detection efforts and deep learning applications in healthcare.

DOI： 10.1109/SIML65326.2025.11080819

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=105012729213&origin=inward

Evaluation of a system for measuring forces acting on the hand in assisting movements 国際誌

Ryo Uchimura, Ryohei Fushitani, Kodai Kitagawa, Chikamune Wada

12th International Symposium on Applied Engineering and Sciences (SAES2024) 172 2024年11月

Improved YOLOv8 for Assistive System for the Visually Impaired 国際誌

Ryo Uchimura, Ryohei Fushitani, Kodai Kitagawa, Chikamune Wada

12th International Symposium on Applied Engineering and Sciences (SAES2024) 24 2024年11月

Meal Guidance System for Visually Impaired People 査読有り国際誌

Hitunthakingpunt K., Wada C.

2024 Joint 13th International Conference on Soft Computing and Intelligent Systems and 25th International Symposium on Advanced Intelligent Systems, SCIS and ISIS 2024 2024年11月

担当区分：最終著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

Eating independently is a significant challenge for visually impaired individuals, and meal support devices can help them achieve this goal. Key information such as food types, plate positions, and the amount of remaining food is essential for creating an effective meal support system. This study proposes a method to detect and identify various food types, locate each plate on the dining table, and calculate the remaining food on each plate, expressed as a percentage. The research consists of three main steps. First, we modified the open-source UECFOOD100 dataset, selecting 63 classes of food with 11,140 images for food identification. The YOLO detection model was then trained to identify the food types, while a pre-trained YOLO model was used to detect and locate plates on the table. The bounding boxes generated by the detection model were used to determine the plate positions. Finally, an image processing technique calculated the remaining food on each plate, displaying the value as a percentage. The YOLO algorithm achieved precision, recall, mAP50, and mAP50-95 scores of 0.656, 0.537, 0.596, and 0.425, respectively. The system effectively determines the remaining food percentage on plates, aiding visually impaired individuals in meal management.

DOI： 10.1109/SCISISIS61014.2024.10759937

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85214671891&origin=inward

Fundamental Study on Muscle Activity in Running with SoftKnee Brace 査読有り国際誌

Kodai Kitagawa, Tomoya Murakami, Chikamune Wada, Hiroaki Yamamoto

18th International collaboration Symposium on Information, Production and Systems (ISIPS2024) P1(2pages) 2024年11月

Effect of Soft Knee Brace on Shank Movement in Running 査読有り国際誌

Kodai Kitagawa, Tomoya Murakami, Chikamune Wada, Hiroaki Yamamoto

Journal of Prosthetics Orthotics and Science Technology 3 ( 2 ) 42 - 47 2024年11月

Vertebral Force Prediction during Manual Lifting using Sagittal Plane Posture and Machine Learning 査読有り国際誌

Kitagawa K., Hida M., Wada C., Yamamoto H.

GCCE 2024 - 2024 IEEE 13th Global Conference on Consumer Electronics 952 - 953 2024年10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）

Vertebral force during manual lifting causes lower back pain (LBP) among workers in various occupational fields. Continuous monitoring of vertebral force is required for preventing LBP. Vertebral force can be measured directly by implant devices; however, these implant devices are difficult to install on general workers. Non-invasive technologies such as an optical motion capture system could estimate vertebral force, however, special measurement devices are necessary. The objective of this study is to propose non-invasive measurement method for vertebral force using ordinary digital camera. The proposed method predicts vertebral forces by machine learning and sagittal plane posture during manual lifting. The proposed method predicted vertebral forces for 48 trials manual lifting via leave-one-out-cross-validation. Training and testing of the proposed method used OrthoLoad database that included sagittal 2D images and vertebral force obtained from implant device. The results showed that the proposed method using model tree algorithm could predict vertebral force by greater than 0.7 correlation with actual values. These results indicate possibility that the proposed method can be used for vertebral force assessments using ordinary devices.

DOI： 10.1109/GCCE62371.2024.10760826

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85213360053&origin=inward

Evaluating YOLOv8 model With Out-of-distribution dataset and shape bias 査読有り国際誌

Eto S., Wada Y., Wada C.

GCCE 2024 - 2024 IEEE 13th Global Conference on Consumer Electronics 648 - 649 2024年10月

担当区分：最終著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

In recent years, numerous convolutional neural network (CNN) models have been proposed to achieve a high performance. Among them, YOLOv8 is a suitable model for edge devices with limited hardware resources because YOLOv8 is designed with consideration for deployment on edge devices such as consumer electronics. However, CNNs in edge devices must be robust against out-of-distribution data, and their robustness against out-of-distribution data has not been sufficiently verified. This study verifies the robustness of YOLOv8 for out-of-distribution data. We measured the out-of-distribution accuracy of lightweight models trained on ImageNet running in real time on the YOLOv8 backbone and edge devices. We also measured shape bias, the tendency to emphasize shape when categorizing, because it is known to be related to the robustness of out-of-distribution data. We trained YOLOv8 with ImageNet and evaluated it based on the out-of-distribution accuracy and shape bias. The experimental results show that the YOLOv8 backbone has a lower out-of-distribution accuracy than the other lightweight models. Moreover, the shape bias may facilitate the learning of feature representations that are useful for downstream tasks.

DOI： 10.1109/GCCE62371.2024.10760789

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85213404576&origin=inward

Feature Selection via Decision Tree in Foot Position Recognition during Patient Transfer using Smartphone Inertial Sensor 査読有り国際誌

Kodai Kitagawa, Ryo Takashima, Tadateru Kurosawa, Chikamune Wada

SICE Festival 2024 with Annual Conference (SICE2024) WeBT11.21 2024年08月

Effects of electrical stimulation of antagonist muscles on shoulder joint adduction force and grip strength 査読有り国際誌

Nakano Sota, Okada Hirotaka, Nakamura Kouichi, Kitagawa Kodai, Wada Chikamune

Journal of Physical Therapy Science ( 理学療法科学学会 ) 36 ( 7 ) 378 - 381 2024年07月

担当区分：最終著者記述言語：英語掲載種別：研究論文（学術雑誌）

[Purpose] This study aimed to determine whether applying electrical stimulation to the deltoid and extensor digitorum muscles could lead to a reduction in fixation force during shoulder joint adduction and grip strength. [Participants and Methods] Fifteen healthy adult males participated in this study. In the shoulder adduction force experiment, the middle fibers of the deltoid muscle of the dominant arm were electrically stimulated. In the grip strength experiment, the extensor digitorum muscle of the dominant arm was electrically stimulated. The forces exerted with and without the electrical stimulation were measured. [Results] The torque of the shoulder adduction force decreased significantly with electrical stimulation, while no significant change was observed in normalized grip strength with electrical stimulation. [Conclusion] The response of antagonist muscles to electrical stimulation varied according to location.

DOI： 10.1589/jpts.36.378

CiNii Research

その他リンク： https://www.jstage.jst.go.jp/article/jpts/36/7/36_2024-018/_pdf

　前のページ- 次のページ　

<和田 親宗>

論文 - 和田 親宗

<和田　親宗>

論文 - 和田　親宗