0% Complete
صفحه اصلی
/
سی و سومین کنفرانس بین المللی مهندسی برق
Real-Time Prediction of Lower Limb AngularTrajectories Using an Optimized LSTM Model withMarkerless Motion Capture
نویسندگان :
Amirhossein Jafari
1
Hamed Jalaly Bidgoly
2
1- دانشگاه صنعتی اصفهان
2- دانشگاه صنعتی اصفهان
کلمات کلیدی :
Gait analysis،Joint angle prediction،Markerless motion capture،Long Short-Term Memory (LSTM)،Assistive devices
چکیده :
Lower limb dysfunction affects millions of people worldwide and often requires the use of assistive devices to restore mobility. While passive devices provide support, they lack the adaptability of active devices, which utilize actuated joints for more natural locomotion. The active devices rely on control architectures that predict angular gait trajectories, ensuring precise synchronization with human motion. This study proposes a Long Short-Term Memory (LSTM)-based model to predict the angular trajectories of the ankle, knee, and thigh during walking. The model was trained using data from a markerless motion capture system, eliminating the need for wearable sensors and simplifying the data acquisition process. Optimization techniques such as pruning and quantization were applied to enhance real-time performance in resource-constrained assistive devices. Additionally, we developed an algorithm to address inaccuracies in the pose estimator’s joint angle predictions caused by challenging capturing conditions. This algorithm improves data reliability through outlier detection and correction. The experimental results demonstrate that the optimized model accurately predicts gait trajectories across varying walking speeds, showcasing its potential for integrating active assistive devices to improve mobility and adaptability.Lower limb dysfunction affects millions of people worldwide and often requires the use of assistive devices to restore mobility. While passive devices provide support, they lack the adaptability of active devices, which utilize actuated joints for more natural locomotion. The active devices rely on control architectures that predict angular gait trajectories, ensuring precise synchronization with human motion. This study proposes a Long Short-Term Memory (LSTM)-based model to predict the angular trajectories of the ankle, knee, and thigh during walking. The model was trained using data from a markerless motion capture system, eliminating the need for wearable sensors and simplifying the data acquisition process. Optimization techniques such as pruning and quantization were applied to enhance real-time performance in resource-constrained assistive devices. Additionally, we developed an algorithm to address inaccuracies in the pose estimator’s joint angle predictions caused by challenging capturing conditions. This algorithm improves data reliability through outlier detection and correction. The experimental results demonstrate that the optimized model accurately predicts gait trajectories across varying walking speeds, showcasing its potential for integrating active assistive devices to improve mobility and adaptability.
لیست مقالات
لیست مقالات بایگانی شده
Low-Leakage 6T SRAM Cell for In-Memory Computing with High Stability
Deniz Najafi - Behzad Ebrahimi
Floquet model of spatiotemporally modulated graphene-based structures
Mahsa Valizadeh - Leila Yousefi - MirFaez Miri
مدلسازی ترانسفورماتورهای کم تلفات در شرایط عملکرد غیرعادی و بررسی تأثیر آن ها بر تلفات فنی شبکه قدرت
محمدرضا موسوی خادمی - غلامرضا زارع پلکوئی - مرتضی موسوی خادمی
بازشناسی مقاوم زمانی – مکانی انسان در یک سیستم نظارتی بر اساس شبکه GAN
آزاده سادات موسوی - شهریار برادران شکوهی
بررسی و شبیه سازی اضافه ولتاژهای صاعقه در نیروگاه خورشیدی برق خراسان و ارائه سیستم حفاظتی مناسب
هادی علی آبادی - بهزاد کرمانی
بهبود عملکرد یک ( LOC ) Lab – On –Chipپیشرفته مبتنی بر فناوری MEMSبه کمک تقویت میدان الکتریکی ساختار
شیوا عظیمی نام - فهیمه مروی - کیان جعفری
بهینه سازی تزویج فیبر نوری باریک شده و موجبر نوری بر بستر پلیمر
مهتاب حسینعلی زاده - مونا ثریا - غلام محمد پارسا نسب - شکراله کریمیان
Vision Transformer and Parallel Convolutional Neural Network for Speech Emotion Recognition
Saber Hashemi - Mohammad Asgari
پیش بینی قیمت انرژی الکتریکی در بازار روز بعد با استفاده از شبکه عصبی مصنوعی تعمیم یافته و با در نظر گرفتن محدودیت سوخت رسانی
حسین صابر - سعید محسنی - رضا پورآقابابا - مصطفی یحیی آبادی
Classifying Human Spatial Navigation Anxiety Using Electrooculography Signals and Machine Learning Techniques
Saeed Mousavi - Sara Ashrafi - Mehdi Delrobaei
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 40.4.2