scholarly journals Comparison of a Deep Learning-Based Pose Estimation System to Marker-Based and Kinect Systems in Exergaming for Balance Training

Sensors ◽  
2020 ◽  
Vol 20 (23) ◽  
pp. 6940
Author(s):  
Elise Klæbo Vonstad ◽  
Xiaomeng Su ◽  
Beatrix Vereijken ◽  
Kerstin Bach ◽  
Jan Harald Nilsen
Keyword(s):  
Deep Learning ◽  
Pose Estimation ◽  
Gold Standard ◽  
Large Scale ◽  
Statistical Significance ◽  
Balance Training ◽  
Home Exercise ◽  
Rank Test ◽  
Camera System ◽  
Estimation System

Using standard digital cameras in combination with deep learning (DL) for pose estimation is promising for the in-home and independent use of exercise games (exergames). We need to investigate to what extent such DL-based systems can provide satisfying accuracy on exergame relevant measures. Our study assesses temporal variation (i.e., variability) in body segment lengths, while using a Deep Learning image processing tool (DeepLabCut, DLC) on two-dimensional (2D) video. This variability is then compared with a gold-standard, marker-based three-dimensional Motion Capturing system (3DMoCap, Qualisys AB), and a 3D RGB-depth camera system (Kinect V2, Microsoft Inc). Simultaneous data were collected from all three systems, while participants (N = 12) played a custom balance training exergame. The pose estimation DLC-model is pre-trained on a large-scale dataset (ImageNet) and optimized with context-specific pose annotated images. Wilcoxon’s signed-rank test was performed in order to assess the statistical significance of the differences in variability between systems. The results showed that the DLC method performs comparably to the Kinect and, in some segments, even to the 3DMoCap gold standard system with regard to variability. These results are promising for making exergames more accessible and easier to use, thereby increasing their availability for in-home exercise.

scholarly journals COVID-19 Detection Using Deep Learning Algorithm on Chest X-ray Images

Biology ◽  
2021 ◽  
Vol 10 (11) ◽  
pp. 1174
Author(s):  
Shamima Akter ◽  
F. M. Javed Mehedi Shamrat ◽  
Sovon Chakraborty ◽  
Asif Karim ◽  
Sami Azam
Keyword(s):  
Deep Learning ◽  
Learning Algorithm ◽  
Statistical Significance ◽  
Confusion Matrix ◽  
Original Data ◽  
Rank Test ◽  
X Rays ◽  
X Ray ◽  
Professional Exposure ◽  
Chest X Ray

COVID-19, regarded as the deadliest virus of the 21st century, has claimed the lives of millions of people around the globe in less than two years. Since the virus initially affects the lungs of patients, X-ray imaging of the chest is helpful for effective diagnosis. Any method for automatic, reliable, and accurate screening of COVID-19 infection would be beneficial for rapid detection and reducing medical or healthcare professional exposure to the virus. In the past, Convolutional Neural Networks (CNNs) proved to be quite successful in the classification of medical images. In this study, an automatic deep learning classification method for detecting COVID-19 from chest X-ray images is suggested using a CNN. A dataset consisting of 3616 COVID-19 chest X-ray images and 10,192 healthy chest X-ray images was used. The original data were then augmented to increase the data sample to 26,000 COVID-19 and 26,000 healthy X-ray images. The dataset was enhanced using histogram equalization, spectrum, grays, cyan and normalized with NCLAHE before being applied to CNN models. Initially using the dataset, the symptoms of COVID-19 were detected by employing eleven existing CNN models; VGG16, VGG19, MobileNetV2, InceptionV3, NFNet, ResNet50, ResNet101, DenseNet, EfficientNetB7, AlexNet, and GoogLeNet. From the models, MobileNetV2 was selected for further modification to obtain a higher accuracy of COVID-19 detection. Performance evaluation of the models was demonstrated using a confusion matrix. It was observed that the modified MobileNetV2 model proposed in the study gave the highest accuracy of 98% in classifying COVID-19 and healthy chest X-rays among all the implemented CNN models. The second-best performance was achieved from the pre-trained MobileNetV2 with an accuracy of 97%, followed by VGG19 and ResNet101 with 95% accuracy for both the models. The study compares the compilation time of the models. The proposed model required the least compilation time with 2 h, 50 min and 21 s. Finally, the Wilcoxon signed-rank test was performed to test the statistical significance. The results suggest that the proposed method can efficiently identify the symptoms of infection from chest X-ray images better than existing methods.

scholarly journals Human Movement Science in The Wild: Can Current Deep-Learning Based Pose Estimation Free Us from The Lab?

2021 ◽  
Author(s):  
Laurie Needham ◽  
Murray Evans ◽  
Darren P. Cosker ◽  
Logan Wade ◽  
Polly M. McGuigan ◽  
...  
Keyword(s):  
Deep Learning ◽  
Motion Capture ◽  
Pose Estimation ◽  
High Speed ◽  
Large Scale ◽  
Human Movement ◽  
Estimation Methods ◽  
Ground Truth Data ◽  
Estimation Algorithms ◽  
In The Wild

ABSTRACTHuman movement researchers are often restricted to laboratory environments and data capture techniques that are time and/or resource intensive. Markerless pose estimation algorithms show great potential to facilitate large scale movement studies ‘in the wild’, i.e., outside of the constraints imposed by marker-based motion capture. However, the accuracy of such algorithms has not yet been fully evaluated. We computed 3D joint centre locations using several deep-learning based pose estimation methods (OpenPose, AlphaPose, DeepLabCut) and compared to marker-based motion capture. Participants performed walking, running and jumping activities while marker-based motion capture data and multi-camera high speed images (200 Hz) were captured. The pose estimation algorithms were applied to 2D image data and 3D joint centre locations were reconstructed. Pose estimation derived joint centres demonstrated systematic differences at the hip and knee (~30 − 50 mm), most likely due to mislabeling of ground truth data in the training datasets. Where systematic differences were lower, e.g., the ankle, differences of 1 − 15 mm were observed depending on the activity. Markerless motion capture represents a highly promising emerging technology that could free movement scientists from laboratory environments. We provide recommendations relating to domain specific datasets and benchmarks, which will be vital to realising this goal.

Dietary Patterns: A New Therapeutic Approach for Depression?

2019 ◽  
Vol 20 (2) ◽  
pp. 123-129 ◽  
Author(s):  
Mariana Jesus ◽  
Tânia Silva ◽  
César Cagigal ◽  
Vera Martins ◽  
Carla Silva
Keyword(s):  
Depressive Symptoms ◽  
Dietary Patterns ◽  
Large Scale ◽  
Randomized Clinical Trials ◽  
Dietary Intervention ◽  
Common Mental Disorder ◽  
Controlled Trial ◽  
Statistical Significance ◽  
Inverse Association ◽  
The Impact

Introduction: The field of nutritional psychiatry is a fast-growing one. Although initially, it focused on the effects of vitamins and micronutrients in mental health, in the last decade, its focus also extended to the dietary patterns. The possibility of a dietary cost-effective intervention in the most common mental disorder, depression, cannot be overlooked due to its potential large-scale impact. Method: A classic review of the literature was conducted, and studies published between 2010 and 2018 focusing on the impact of dietary patterns in depression and depressive symptoms were included. Results: We found 10 studies that matched our criteria. Most studies showed an inverse association between healthy dietary patterns, rich in fruits, vegetables, lean meats, nuts and whole grains, and with low intake of processed and sugary foods, and depression and depressive symptoms throughout an array of age groups, although some authors reported statistical significance only in women. While most studies were of cross-sectional design, making it difficult to infer causality, a randomized controlled trial presented similar results. Discussion: he association between dietary patterns and depression is now well-established, although the exact etiological pathways are still unknown. Dietary intervention, with the implementation of healthier dietary patterns, closer to the traditional ones, can play an important role in the prevention and adjunctive therapy of depression and depressive symptoms. Conclusion: More large-scale randomized clinical trials need to be conducted, in order to confirm the association between high-quality dietary patterns and lower risk of depression and depressive symptoms.

Multi Disease-Prediction Framework Using Hybrid Deep Learning: An Optimal Prediction Model (Preprint)

2020 ◽  
Author(s):  
Anusha Ampavathi ◽  
Vijaya Saradhi T
Keyword(s):  
Feature Extraction ◽  
Big Data ◽  
Deep Learning ◽  
Weight Function ◽  
Optimization Algorithm ◽  
Large Scale ◽  
Heuristic Algorithms ◽  
Disease Prediction ◽  
Health Care Decisions ◽  
Proposed Model

UNSTRUCTURED Big data and its approaches are generally helpful for healthcare and biomedical sectors for predicting the disease. For trivial symptoms, the difficulty is to meet the doctors at any time in the hospital. Thus, big data provides essential data regarding the diseases on the basis of the patient’s symptoms. For several medical organizations, disease prediction is important for making the best feasible health care decisions. Conversely, the conventional medical care model offers input as structured that requires more accurate and consistent prediction. This paper is planned to develop the multi-disease prediction using the improvised deep learning concept. Here, the different datasets pertain to “Diabetes, Hepatitis, lung cancer, liver tumor, heart disease, Parkinson’s disease, and Alzheimer’s disease”, from the benchmark UCI repository is gathered for conducting the experiment. The proposed model involves three phases (a) Data normalization (b) Weighted normalized feature extraction, and (c) prediction. Initially, the dataset is normalized in order to make the attribute's range at a certain level. Further, weighted feature extraction is performed, in which a weight function is multiplied with each attribute value for making large scale deviation. Here, the weight function is optimized using the combination of two meta-heuristic algorithms termed as Jaya Algorithm-based Multi-Verse Optimization algorithm (JA-MVO). The optimally extracted features are subjected to the hybrid deep learning algorithms like “Deep Belief Network (DBN) and Recurrent Neural Network (RNN)”. As a modification to hybrid deep learning architecture, the weight of both DBN and RNN is optimized using the same hybrid optimization algorithm. Further, the comparative evaluation of the proposed prediction over the existing models certifies its effectiveness through various performance measures.

scholarly journals Deep Learning-Based Large-Scale Automatic Satellite Crosswalk Classification

2017 ◽  
Vol 14 (9) ◽  
pp. 1513-1517 ◽  
Author(s):  
Rodrigo F. Berriel ◽  
Andre Teixeira Lopes ◽  
Alberto F. de Souza ◽  
Thiago Oliveira-Santos
Keyword(s):  
Deep Learning ◽  
Large Scale

Deep Learning-Based Classification of Large-Scale Airborne LiDAR Point Cloud

2021 ◽  
pp. 1-15
Author(s):  
Mathieu Turgeon-Pelchat ◽  
Samuel Foucher ◽  
Yacine Bouroubi
Keyword(s):  
Deep Learning ◽  
Point Cloud ◽  
Large Scale ◽  
Airborne Lidar

scholarly journals Development and validation of a deep learning system to screen vision-threatening conditions in high myopia using optical coherence tomography images

2020 ◽  
pp. bjophthalmol-2020-317825
Author(s):  
Yonghao Li ◽  
Weibo Feng ◽  
Xiujuan Zhao ◽  
Bingqian Liu ◽  
Yan Zhang ◽  
...  
Keyword(s):  
Optical Coherence Tomography ◽  
Deep Learning ◽  
High Myopia ◽  
Large Scale ◽  
Learning System ◽  
Youden Index ◽  
Optical Coherence ◽  
Test Dataset ◽  
Independent Test ◽  
Independent Test Dataset

Background/aimsTo apply deep learning technology to develop an artificial intelligence (AI) system that can identify vision-threatening conditions in high myopia patients based on optical coherence tomography (OCT) macular images.MethodsIn this cross-sectional, prospective study, a total of 5505 qualified OCT macular images obtained from 1048 high myopia patients admitted to Zhongshan Ophthalmic Centre (ZOC) from 2012 to 2017 were selected for the development of the AI system. The independent test dataset included 412 images obtained from 91 high myopia patients recruited at ZOC from January 2019 to May 2019. We adopted the InceptionResnetV2 architecture to train four independent convolutional neural network (CNN) models to identify the following four vision-threatening conditions in high myopia: retinoschisis, macular hole, retinal detachment and pathological myopic choroidal neovascularisation. Focal Loss was used to address class imbalance, and optimal operating thresholds were determined according to the Youden Index.ResultsIn the independent test dataset, the areas under the receiver operating characteristic curves were high for all conditions (0.961 to 0.999). Our AI system achieved sensitivities equal to or even better than those of retina specialists as well as high specificities (greater than 90%). Moreover, our AI system provided a transparent and interpretable diagnosis with heatmaps.ConclusionsWe used OCT macular images for the development of CNN models to identify vision-threatening conditions in high myopia patients. Our models achieved reliable sensitivities and high specificities, comparable to those of retina specialists and may be applied for large-scale high myopia screening and patient follow-up.

Sign in / Sign up

Export Citation Format

Share Document