اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدContinuous Prediction of Lower-Limb Kinematics From Multi-Modal Biomedical Signals
74
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
The fast-growing techniques of measuring and fusing multi-modal biomedical signals enable advanced motor intent decoding schemes of lowerlimb exoskeletons, meeting the increasing demand for rehabilitative or assistive applications of take-home healthcare. Challenges of exoskeletons motor intent decoding schemes remain in making a continuous prediction to compensate for the hysteretic response caused by mechanical transmission. In this paper, we solve this problem by proposing an ahead of time continuous prediction of lower limb kinematics, with the prediction of knee angles during level walking as a case study. Firstly, an end-to-end kinematics prediction network(KinPreNet), consisting of a feature extractor and an angle predictor, is proposed and experimentally compared with features and methods traditionally used in ahead-of-time prediction of gait phases. Secondly, inspired by the electromechanical delay(EMD), we further explore our algorithms capability of compensating response delay of mechanical transmission by validating the performance of the different sections of prediction time. And we experimentally reveal the time boundary of compensating the hysteretic response. Thirdly, a comparison of employing EMG signals or not is performed to reveal the EMG and kinematic signals collaborated contributions to the continuous prediction. During the experiments, EMG signals of nine muscles and knee angles calculated from inertial measurement unit (IMU) signals are recorded from ten healthy subjects. To the best of our knowledge, this is the first study of continuously predicting lower-limb kinematics in an ahead-of-time manner based on the electromechanical delay (EMD).
قيم البحث
اقرأ أيضاً
Freezing-of-gait a mysterious symptom of Parkinsons disease and defined as a sudden loss of ability to move forward. Common treatments of freezing episodes are currently of moderate efficacy and can likely be improved through a reliable freezing eval
uation. Basic-science studies about the characterization of freezing episodes and a 24/7 evidence-support freezing detection system can contribute to the reliability of the evaluation in daily life. In this study, we analyzed multi-modal features from brain, eye, heart, motion, and gait activity from 15 participants with idiopathic Parkinsons disease and 551 freezing episodes induced by turning in place. Statistical analysis was first applied on 248 of the 551 to determine which multi-modal features were associated with freezing episodes. Features significantly associated with freezing episodes were ranked and used for the freezing detection. We found that eye-stabilization speed during turning and lower-body trembling measure significantly associated with freezing episodes and used for freezing detection. Using a leave-one-subject-out cross-validation, we obtained a sensitivity of 97%+/-3%, a specificity of 96%+/-7%, a precision of 73%+/-21%, a Matthews correlation coefficient of 0.82+/-0.15, and an area under the Precision-Recall curve of 0.94+/-0.05. According to the Precision-Recall curves, the proposed freezing detection method using the multi-modal features performed better than using single-modal features.
Goal: This paper presents an algorithm for accurately estimating pelvis, thigh, and shank kinematics during walking using only three wearable inertial sensors. Methods: The algorithm makes novel use of a constrained Kalman filter (CKF). The algorithm
iterates through the prediction (kinematic equation), measurement (pelvis position pseudo-measurements, zero velocity update, flat-floor assumption, and covariance limiter), and constraint update (formulation of hinged knee joints and ball-and-socket hip joints). Results: Evaluation of the algorithm using an optical motion capture-based sensor-to-segment calibration on nine participants ($7$ men and $2$ women, weight $63.0 pm 6.8$ kg, height $1.70 pm 0.06$ m, age $24.6 pm 3.9$ years old), with no known gait or lower body biomechanical abnormalities, who walked within a $4 times 4$ m$^2$ capture area shows that it can track motion relative to the mid-pelvis origin with mean position and orientation (no bias) root-mean-square error (RMSE) of $5.21 pm 1.3$ cm and $16.1 pm 3.2^circ$, respectively. The sagittal knee and hip joint angle RMSEs (no bias) were $10.0 pm 2.9^circ$ and $9.9 pm 3.2^circ$, respectively, while the corresponding correlation coefficient (CC) values were $0.87 pm 0.08$ and $0.74 pm 0.12$. Conclusion: The CKF-based algorithm was able to track the 3D pose of the pelvis, thigh, and shanks using only three inertial sensors worn on the pelvis and shanks. Significance: Due to the Kalman-filter-based algorithms low computation cost and the relative convenience of using only three wearable sensors, gait parameters can be computed in real-time and remotely for long-term gait monitoring. Furthermore, the system can be used to inform real-time gait assistive devices.
Precise trajectory prediction of surrounding vehicles is critical for decision-making of autonomous vehicles and learning-based approaches are well recognized for the robustness. However, state-of-the-art learning-based methods ignore 1) the feasibil
ity of the vehicles multi-modal state information for prediction and 2) the mutual exclusive relationship between the global traffic scene receptive fields and the local position resolution when modeling vehicles interactions, which may influence prediction accuracy. Therefore, we propose a vehicle-descriptor based LSTM model with the dilated convolutional social pooling (VD+DCS-LSTM) to cope with the above issues. First, each vehicles multi-modal state information is employed as our models input and a new vehicle descriptor encoded by stacked sparse auto-encoders is proposed to reflect the deep interactive relationships between various states, achieving the optimal feature extraction and effective use of multi-modal inputs. Secondly, the LSTM encoder is used to encode the historical sequences composed of the vehicle descriptor and a novel dilated convolutional social pooling is proposed to improve modeling vehicles spatial interactions. Thirdly, the LSTM decoder is used to predict the probability distribution of future trajectories based on maneuvers. The validity of the overall model was verified over the NGSIM US-101 and I-80 datasets and our method outperforms the latest benchmark.
This paper presents an algorithm that makes novel use of distance measurements alongside a constrained Kalman filter to accurately estimate pelvis, thigh, and shank kinematics for both legs during walking and other body movements using only three wea
rable inertial measurement units (IMUs). The distance measurement formulation also assumes hinge knee joint and constant body segment length, helping produce estimates that are near or in the constraint space for better estimator stability. Simulated experiments shown that inter-IMU distance measurement is indeed a promising new source of information to improve the pose estimation of inertial motion capture systems under a reduced sensor count configuration. Furthermore, experiments show that performance improved dramatically for dynamic movements even at high noise levels (e.g., $sigma_{dist} = 0.2$ m), and that acceptable performance for normal walking was achieved at $sigma_{dist} = 0.1$ m. Nevertheless, further validation is recommended using actual distance measurement sensors.
Pedestrian behavior prediction is one of the major challenges for intelligent driving systems in urban environments. Pedestrians often exhibit a wide range of behaviors and adequate interpretations of those depend on various sources of information su
ch as pedestrian appearance, states of other road users, the environment layout, etc. To address this problem, we propose a novel multi-modal prediction algorithm that incorporates different sources of information captured from the environment to predict future crossing actions of pedestrians. The proposed model benefits from a hybrid learning architecture consisting of feedforward and recurrent networks for analyzing visual features of the environment and dynamics of the scene. Using the existing 2D pedestrian behavior benchmarks and a newly annotated 3D driving dataset, we show that our proposed model achieves state-of-the-art performance in pedestrian crossing prediction.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
