scholarly journals Estimating Lower Extremity Running Gait Kinematics with a Single Accelerometer: A Deep Learning Approach

Sensors ◽  
2020 ◽  
Vol 20 (10) ◽  
pp. 2939
Author(s):  
Mohsen Gholami ◽  
Christopher Napier ◽  
Carlo Menon
Keyword(s):  
Deep Learning ◽  
Lower Extremity ◽  
Mean Squared Error ◽  
Sagittal Plane ◽  
Absolute Error ◽  
Angle Measurement ◽  
Learning Approach ◽  
Accelerometer Data ◽  
Lower Extremity Injuries ◽  
Optical Motion

Abnormal running kinematics are associated with an increased incidence of lower extremity injuries among runners. Accurate and unobtrusive running kinematic measurement plays an important role in the detection of gait abnormalities and the prevention of injuries among runners. Inertial-based methods have been proposed to address this need. However, previous methods require cumbersome sensor setup or participant-specific calibration. This study aims to validate a shoe-mounted accelerometer for sagittal plane lower extremity angle measurement during running based on a deep learning approach. A convolutional neural network (CNN) architecture was selected as the regression model to generalize in inter-participant scenarios and to minimize poorly estimated joints. Motion and accelerometer data were recorded from ten participants while running on a treadmill at five different speeds. The reference joint angles were measured by an optical motion capture system. The CNN model predictions deviated from the reference angles with a root mean squared error (RMSE) of less than 3.5° and 6.5° in intra- and inter-participant scenarios, respectively. Moreover, we provide an estimation of six important gait events with a mean absolute error of less than 2.5° and 6.5° in intra- and inter-participants scenarios, respectively. This study highlights an appealing minimal sensor setup approach for gait analysis purposes.

scholarly journals Deep Learning-Based Optimal Smart Shoes Sensor Selection for Energy Expenditure and Heart Rate Estimation

Sensors ◽  
2021 ◽  
Vol 21 (21) ◽  
pp. 7058
Author(s):  
Heesang Eom ◽  
Jongryun Roh ◽  
Yuli Sun Hariyani ◽  
Suwhan Baek ◽  
Sukho Lee ◽  
...  
Keyword(s):  
Heart Rate ◽  
Deep Learning ◽  
Energy Expenditure ◽  
Mean Squared Error ◽  
Pressure Sensors ◽  
Absolute Error ◽  
Coefficient Of Determination ◽  
Proposed Model ◽  
Point Pressure

Wearable technologies are known to improve our quality of life. Among the various wearable devices, shoes are non-intrusive, lightweight, and can be used for outdoor activities. In this study, we estimated the energy consumption and heart rate in an environment (i.e., running on a treadmill) using smart shoes equipped with triaxial acceleration, triaxial gyroscope, and four-point pressure sensors. The proposed model uses the latest deep learning architecture which does not require any separate preprocessing. Moreover, it is possible to select the optimal sensor using a channel-wise attention mechanism to weigh the sensors depending on their contributions to the estimation of energy expenditure (EE) and heart rate (HR). The performance of the proposed model was evaluated using the root mean squared error (RMSE), mean absolute error (MAE), and coefficient of determination (R2). Moreover, the RMSE was 1.05 ± 0.15, MAE 0.83 ± 0.12 and R2 0.922 ± 0.005 in EE estimation. On the other hand, and RMSE was 7.87 ± 1.12, MAE 6.21 ± 0.86, and R2 0.897 ± 0.017 in HR estimation. In both estimations, the most effective sensor was the z axis of the accelerometer and gyroscope sensors. Through these results, it is demonstrated that the proposed model could contribute to the improvement of the performance of both EE and HR estimations by effectively selecting the optimal sensors during the active movements of participants.

scholarly journals Cone Beam CT (CBCT) Based Synthetic CT Generation Using Deep Learning Methods for Dose Calculation of Nasopharyngeal Carcinoma Radiotherapy

2021 ◽  
Vol 20 ◽  
pp. 153303382110624
Author(s):  
Xudong Xue ◽  
Yi Ding ◽  
Jun Shi ◽  
Xiaoyu Hao ◽  
Xiangbin Li ◽  
...  
Keyword(s):  
Deep Learning ◽  
Mean Squared Error ◽  
Similarity Index ◽  
Dose Calculation ◽  
Absolute Error ◽  
Learning Methods ◽  
Index Analysis ◽  
Gamma Index ◽  
The Mean ◽  
Synthetic Ct

Objective: To generate synthetic CT (sCT) images with high quality from CBCT and planning CT (pCT) for dose calculation by using deep learning methods. Methods: 169 NPC patients with a total of 20926 slices of CBCT and pCT images were included. In this study the CycleGAN, Pix2pix and U-Net models were used to generate the sCT images. The Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), Peak Signal to Noise Ratio (PSNR), and Structural Similarity Index (SSIM) were used to quantify the accuracy of the proposed models in a testing cohort of 34 patients. Radiation dose were calculated on pCT and sCT following the same protocol. Dose distributions were evaluated for 4 patients by comparing the dose-volume-histogram (DVH) and 2D gamma index analysis. Results: The average MAE and RMSE values between sCT by three models and pCT reduced by 15.4 HU and 26.8 HU at least, while the mean PSNR and SSIM metrics between sCT by different models and pCT added by 10.6 and 0.05 at most, respectively. There were only slight differences for DVH of selected contours between different plans. The passing rates of 2D gamma index analysis under 3 mm/3% 3 mm/2%, 2 mm/3%and 2 mm/2% criteria were all higher than 95%. Conclusions: All the sCT had achieved better evaluation metrics than those of original CBCT, while the performance of CycleGAN model was proved to be best among three methods. The dosimetric agreement confirmed the HU accuracy and consistent anatomical structures of sCT by deep learning methods.

scholarly journals Cross-Racial Automatic Age Estimation from Facial Images using Deep Learning

2021 ◽  
Vol 9 (9) ◽  
pp. 1288-1294
Keyword(s):  
Deep Learning ◽  
Age Estimation ◽  
Mean Absolute Error ◽  
Absolute Error ◽  
Learning Approach ◽  
Racial Groups ◽  
Human Beings ◽  
The Mean ◽  
Facial Images ◽  
Facial Age

This paper presents a deep learning approach for age estimation of human beings using their facial images. The different racial groups based on skin colour have been incorporated in the annotations of the images in the dataset, while ensuring an adequate distribution of subjects across the racial groups so as to achieve an accurate Automatic Facial Age Estimation (AFAE). The principle of transfer learning is applied to the ResNet50 Convolutional Neural Network (CNN) initially pretrained for the task of object classification and finetuning it’s hyperparameters to propose an AFAE system that can be used to automate ages of humans across multiple racial groups. The mean absolute error of 4.25 years is obtained at the end of the research which proved the effectiveness and superiority of the proposed method.

scholarly journals EFFECTS OF SPORTS SPECIALIZATION ON LOWER EXTREMITY SAGITTAL PLANE LOADING IN ADOLESCENT MALES AND FEMALES

2020 ◽  
Vol 8 (4_suppl3) ◽  
pp. 2325967120S0028
Author(s):  
Shiho Goto ◽  
Joseph P. Hannon ◽  
Angellyn N. Grondin ◽  
James M. Bothwell ◽  
J. Craig Garrison
Keyword(s):  
Lower Extremity ◽  
Knee Flexion ◽  
Sagittal Plane ◽  
Adolescent Athletes ◽  
Lower Extremity Injuries ◽  
Male Adolescents ◽  
Increased Risk ◽  
Males And Females ◽  
Extremity Injuries ◽  
Dominant Side

Background: Sport specialization has been associated with increased risk of both acute and chronic lower extremity musculoskeletal injuries in adolescent athletes. Repetitive movement through sport specialization has been hypothesized to increase the stress through the lower extremity, leading to injury. However, the underlying mechanism is unclear. Purpose: The purpose of this study was to examine the differences in sagittal plane lower extremity loading between adolescent athletes who participate in a single sport (SS) verse those who participate multiple sports (MS). Methods: A cross sectional study design was used. A total 252 adolescent athletes participated in the study (Males: SS=26, Age=14.62±1.72, Ht=173.06±12.41 cm, Mass =62.47±14.72 Kg; MS=27, Age=13.52±1.72, Ht=171.61±11.20 cm, Mass =61.32±14.21 Kg Females: SS=127, Age=14.28±1.77, Ht=164.72±10.73 cm, Mass =58.29±11.17 Kg, MS=84, Age=13.62±1.41, Ht=163.22±7.67 cm, Mass =57.63±11.44 Kg). Participants were included if they were between the ages of 10 and 17, involved in high-risk sports for equal or greater than 50 hours per year, and reported no injuries in the 3 months prior to participation in the study. Joint moments of the hip, knee, and ankle were assessed at initial contact (IC) during a jump-landing (JL) task in both the dominant and non-dominant limbs. All values were normalized to the product of height and weight and averaged across three trials. Participants were grouped into SS or MS groups, then sub-grouped by gender. Separate independent t-tests were performed on each dependent variable for the dominant and non-dominant limbs in males and females to examine the differences between the groups (SS vs MS) (α = 0.05). Results: In the female cohort, the SS group demonstrated lesser knee flexion moments compared to the MS group on dominant side (SS=0.022 HtWt-1, MS=0.026 HtWt-1; p=0.012). The female SS group also demonstrated lesser hip extension moments (SS=0.031HtWt-1, MS=0.042 HtWt-1; p=0.022) and knee flexion moments on non-dominant side compared to that of the MS group (SS=0.023HtWt-1, MS=0.027 HtWt-1; p=0.013). There were no significant differences observed in any of the variables in male adolescents. Conclusion: Altered sagittal plane biomechanics were observed in female adolescents, but not in male adolescents during a JL task. The MS group had greater loading at the hip and knee joints than the SS group. Since MS has been suggested to increase the risk of lower extremity injuries, this biomechanical pattern at IC of a JL may be a profile for higher risk of lower extremity injuries. (394/400) [Table: see text]

scholarly journals Contribution of Lower Extremity Joints on Energy Absorption during Soft Landing

2021 ◽  
Vol 18 (10) ◽  
pp. 5130
Author(s):  
Akihiro Tamura ◽  
Kiyokazu Akasaka ◽  
Takahiro Otsudo
Keyword(s):  
Lower Extremity ◽  
Energy Absorption ◽  
Sagittal Plane ◽  
Three Dimensional ◽  
Mechanical Work ◽  
Knee Extensors ◽  
Soft Landing ◽  
Lower Extremity Injuries ◽  
Negative Effect ◽  
Extremity Injuries

Soft landing after jumping is associated with the prevention of lower extremity injuries during sports activities in terms of the energy absorption mechanisms. In this study, the contribution of lower extremity joints during soft landing was investigated. Subjects comprised 20 healthy females. Kinetics and kinematics data were obtained during drop vertical jumps using a three-dimensional motion analysis system. Negative mechanical work values in the lower extremity joints were calculated during landing. A multiple regression analysis was performed to determine which lower extremity joints contributed more in achieving soft landing. The means of mechanical work of the hip, knee, and ankle in the sagittal plane were −0.30 ± 0.17, −0.62 ± 0.31, and −1.03 ± 0.22 J/kg, respectively. Results showed that negative mechanical work in the hip and knee is effective in achieving soft landing. These findings indicate that energy absorption in the hip and knee joints might be an important factor in achieving soft landing, whereas that in the ankle has a negative effect. Therefore, when improving soft landing techniques, we should consider energy absorption in the hip and knee via eccentric activation of the hip and knee extensors during landing.

scholarly journals Performance Prediction for Higher Education Students Using Deep Learning

Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Shuping Li ◽  
Taotang Liu
Keyword(s):  
Neural Network ◽  
Higher Education ◽  
Deep Learning ◽  
Mean Squared Error ◽  
Absolute Error ◽  
Warning Signs ◽  
Education Students ◽  
Squared Error ◽  
Data Prediction ◽  
Training Mode

Predicting students’ performance is very important in matters related to higher education as well as with regard to deep learning and its relationship to educational data. Prediction of students’ performance provides support in selecting courses and designing appropriate future study plans for students. In addition to predicting the performance of students, it helps teachers and managers to monitor students in order to provide support to them and to integrate the training programs to obtain the best results. One of the benefits of student’s prediction is that it reduces the official warning signs as well as expelling students because of their inefficiency. Prediction provides support to the students themselves through their choice of courses and study plans appropriate to their abilities. The proposed method used deep neural network in prediction by extracting informative data as a feature with corresponding weights. Multiple updated hidden layers are used to design neural network automatically; number of nodes and hidden layers controlled by feed forwarding and backpropagation data are produced by previous cases. The training mode is used to train the system with labeled data from dataset and the testing mode is used for evaluating the system. Mean absolute error (MAE) and root mean squared error (RMSE) with accuracy used for evolution of the proposed method. The proposed system has proven its worth in terms of efficiency through the achieved results in MAE (0.593) and RMSE (0.785) to get the best prediction.

scholarly journals Prediction of COVID-19 Confirmed Cases after Vaccination: Based on Statistical and Deep Learning Models

2021 ◽  
Vol 3 (2) ◽  
pp. 153-165
Author(s):  
Meejoung Kim
Keyword(s):  
Deep Learning ◽  
Autocorrelation Function ◽  
Statistical Models ◽  
Short Term Memory ◽  
Mean Squared Error ◽  
Moving Average ◽  
Absolute Error ◽  
A Cell ◽  
Partial Autocorrelation Function ◽  
Autoregressive Conditional Heteroscedasticity

In this paper, we analyze and predict the number of daily confirmed cases of coronavirus (COVID-19) based on two statistical models and a deep learning (DL) model; the autoregressive integrated moving average (ARIMA), the generalized autoregressive conditional heteroscedasticity (GARCH), and the stacked long short-term memory deep neural network (LSTM DNN). We find the orders of the statistical models by the autocorrelation function and the partial autocorrelation function, and the hyperparameters of the DL model, such as the numbers of LSTM cells and blocks of a cell, by the exhaustive search. Ten datasets are used in the experiment; nine countries and the world datasets, from Dec. 31, 2019, to Feb. 22, 2021, provided by the WHO. We investigate the effects of data size and vaccination on performance. Numerical results show that performance depends on the used data's dates and vaccination. It also shows that the prediction by the LSTM DNN is better than those of the two statistical models. Based on the experimental results, the percentage improvements of LSTM DNN are up to 88.54% (86.63%) and 90.15% (87.74%) compared to ARIMA and GARCH, respectively, in mean absolute error (root mean squared error). While the performances of ARIMA and GARCH are varying according to the datasets. The obtained results may provide a criterion for the performance ranges and prediction accuracy of the COVID-19 daily confirmed cases.Doi: 10.28991/SciMedJ-2021-0302-7 Full Text: PDF

scholarly journals A Room Monitoring System Using Deep Learning and Perspective Correction Techniques

2020 ◽  
Vol 10 (13) ◽  
pp. 4423
Author(s):  
Huu-Huy Ngo ◽  
Feng-Cheng Lin ◽  
Yang-Ting Sehn ◽  
Mengru Tu ◽  
Chyi-Ren Dow
Keyword(s):  
Deep Learning ◽  
Monitoring System ◽  
Mean Squared Error ◽  
Absolute Error ◽  
Input Image ◽  
Detection Scheme ◽  
Person Detection ◽  
Monitoring Camera ◽  
Bounding Boxes ◽  
2D Images

Studies on room monitoring have only focused on objects in a singular and uniform posture or low-density groups. Considering the wide use of convolutional neural networks for object detection, especially person detection, we use deep learning and perspective correction techniques to propose a room monitoring system that can detect persons with different motion states, high-density groups, and small-sized persons owing to the distance from the camera. This system uses consecutive frames from the monitoring camera as input images. Two approaches are used: perspective correction and person detection. First, perspective correction is used to transform an input image into a 2D top-view image. This allows users to observe the system more easily with different views (2D and 3D views). Second, the proposed person detection scheme combines the Mask region-based convolutional neural network (R-CNN) scheme and the tile technique for person detection, especially for detecting small-sized persons. All results are stored in a cloud database. Moreover, new person coordinates in 2D images are generated from the final bounding boxes and heat maps are created according to the 2D images; these enable users to examine the system quickly in different views. Additionally, a system prototype is developed to demonstrate the feasibility of the proposed system. Experimental results prove that our proposed system outperforms existing schemes in terms of accuracy, mean absolute error (MAE), and root mean squared error (RMSE).

Sign in / Sign up

Export Citation Format

Share Document