scholarly journals Methods for Improving Deep Learning-Based Cardiac Auscultation Accuracy: Data Augmentation and Data Generalization

2021 ◽  
Vol 11 (10) ◽  
pp. 4544
Author(s):  
Yoojin Jeong ◽  
Juhee Kim ◽  
Daeyeol Kim ◽  
Jinsoo Kim ◽  
Kwangkee Lee
Keyword(s):  
Deep Learning ◽  
Data Augmentation ◽  
Cost Effective ◽  
Study Data ◽  
Quality Data ◽  
Cardiac Auscultation ◽  
Noninvasive Technique ◽  
Performance Improvements ◽  
Sensitivity Specificity ◽  
Data Generalization

Cardiac auscultation is a cost-effective and noninvasive technique for cardiovascular disease detection. Recently, various studies have been underway for cardiac auscultation using deep learning, not doctors. When training a deep learning network, it is important to secure large amount of high-quality data. However, medical data are difficult to obtain, and in most cases the number of abnormal classes is insufficient. In this study, data augmentation is used to supplement the insufficient amount of data, and data generalization to generate data suitable for convolutional neural networks (CNN) is proposed. We demonstrate performance improvements by inputting them into the CNN. Our method achieves an overall performance of 96%, 81%, and 90% for sensitivity, specificity, and F1-score, respectively. Diagnostic accuracy was improved by 18% compared to when it was not used. Particularly, it showed excellent detection success rate for abnormal heart sounds. The proposed method is expected to be applied to an automatic diagnosis system to detect heart abnormalities and help prevent heart disease through early detection.

scholarly journals Artificial intelligence–based detection of aortic stenosis from chest radiographs

2021 ◽  
Author(s):  
Daiju Ueda ◽  
Akira Yamamoto ◽  
Shoichi Ehara ◽  
Shinichi Iwata ◽  
Koji Abo ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Aortic Stenosis ◽  
Predictive Value ◽  
Cost Effective ◽  
Chest Radiographs ◽  
Validation Dataset ◽  
Learning Models ◽  
Test Dataset ◽  
Sensitivity Specificity

Abstract Aims We aimed to develop models to detect aortic stenosis (AS) from chest radiographs—one of the most basic imaging tests—with artificial intelligence. Methods and Results We used 10433 retrospectively collected digital chest radiographs from 5638 patients to train, validate, and test three deep learning models. Chest radiographs were collected from patients who had also undergone echocardiography at a single institution between July 2016 and May 2019. These were labelled from the corresponding echocardiography assessments as AS-positive or AS-negative. The radiographs were separated on a patient basis into training (8327 images from 4512 patients, mean age 65 ± [SD] 15 years), validation (1041 images from 563 patients, mean age 65 ± 14 years), and test (1065 images from 563 patients, mean age 65 ± 14 years) datasets. The soft voting-based ensemble of the three developed models had the best overall performance for predicting AS with an AUC, sensitivity, specificity, accuracy, positive predictive value, and negative predictive value of 0.83 (95% CI 0.77–0.88), 0.78 (0.67–0.86), 0.71 (0.68–0.73), 0.71 (0.68–0.74), 0.18 (0.14–0.23), and 0.97 (0.96–0.98), respectively, in the validation dataset and 0.83 (0.78–0.88), 0.83 (0.74–0.90), 0.69 (0.66–0.72), 0.71 (0.68–0.73), 0.23 (0.19–0.28), and 0.97 (0.96–0.98), respectively, in the test dataset. Conclusion Deep learning models using chest radiographs have the potential to differentiate between radiographs of patients with and without AS. Lay summary We created AI models using deep learning to identify aortic stenosis from chest radiographs. Three AI models were developed and evaluated with 10433 retrospectively collected radiographs and labelled from echocardiography reports. The ensemble AI model could detect aortic stenosis in a test dataset with an AUC of 0.83 (95% CI 0.78–0.88). Since chest radiography is a cost effective and widely available imaging test, our model can provide an additive resource for the detection of aortic stenosis.

scholarly journals Accelerometer-Based Human Fall Detection Using Convolutional Neural Networks

Sensors ◽  
2019 ◽  
Vol 19 (7) ◽  
pp. 1644 ◽  
Author(s):  
Guto Santos ◽  
Patricia Endo ◽  
Kayo Monteiro ◽  
Elisson Rocha ◽  
Ivanovitch Silva ◽  
...  
Keyword(s):  
Deep Learning ◽  
Data Augmentation ◽  
Fog Computing ◽  
Open Data ◽  
Fall Detection ◽  
Public Health Issue ◽  
Global Public Health ◽  
Severe Injuries ◽  
Using Data ◽  
Sensitivity Specificity

Human falls are a global public health issue resulting in over 37.3 million severe injuries and 646,000 deaths yearly. Falls result in direct financial cost to health systems and indirectly to society productivity. Unsurprisingly, human fall detection and prevention are a major focus of health research. In this article, we consider deep learning for fall detection in an IoT and fog computing environment. We propose a Convolutional Neural Network composed of three convolutional layers, two maxpool, and three fully-connected layers as our deep learning model. We evaluate its performance using three open data sets and against extant research. Our approach for resolving dimensionality and modelling simplicity issues is outlined. Accuracy, precision, sensitivity, specificity, and the Matthews Correlation Coefficient are used to evaluate performance. The best results are achieved when using data augmentation during the training process. The paper concludes with a discussion of challenges and future directions for research in this domain.

scholarly journals Deep Learning with Open Data for Desert Road Mapping

2020 ◽  
Vol 12 (14) ◽  
pp. 2274
Author(s):  
Christopher Stewart ◽  
Michele Lazzarini ◽  
Adrian Luna ◽  
Sergio Albani
Keyword(s):  
Deep Learning ◽  
Large Scale ◽  
Data Augmentation ◽  
Low Cost ◽  
Open Data ◽  
Cost Effective ◽  
Training Data ◽  
Desert Sand ◽  
Model Training ◽  
Shifting Sand

The availability of free and open data from Earth observation programmes such as Copernicus, and from collaborative projects such as Open Street Map (OSM), enables low cost artificial intelligence (AI) based monitoring applications. This creates opportunities, particularly in developing countries with scarce economic resources, for large–scale monitoring in remote regions. A significant portion of Earth’s surface comprises desert dune fields, where shifting sand affects infrastructure and hinders movement. A robust, cost–effective and scalable methodology is proposed for road detection and monitoring in regions covered by desert sand. The technique uses Copernicus Sentinel–1 synthetic aperture radar (SAR) satellite data as an input to a deep learning model based on the U–Net architecture for image segmentation. OSM data is used for model training. The method comprises two steps: The first involves processing time series of Sentinel–1 SAR interferometric wide swath (IW) acquisitions in the same geometry to produce multitemporal backscatter and coherence averages. These are divided into patches and matched with masks of OSM roads to form the training data, the quantity of which is increased through data augmentation. The second step includes the U–Net deep learning workflow. The methodology has been applied to three different dune fields in Africa and Asia. A performance evaluation through the calculation of the Jaccard similarity coefficient was carried out for each area, and ranges from 84% to 89% for the best available input. The rank distance, calculated from the completeness and correctness percentages, was also calculated and ranged from 75% to 80%. Over all areas there are more missed detections than false positives. In some cases, this was due to mixed infrastructure in the same resolution cell of the input SAR data. Drift sand and dune migration covering infrastructure is a concern in many desert regions, and broken segments in the resulting road detections are sometimes due to sand burial. The results also show that, in most cases, the Sentinel–1 vertical transmit–vertical receive (VV) backscatter averages alone constitute the best input to the U–Net model. The detection and monitoring of roads in desert areas are key concerns, particularly given a growing population increasingly on the move.

scholarly journals Automated Diagnosis of Chest X-Ray for Early Detection of COVID-19 Disease

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Ebrahim Mohammed Senan ◽  
Ali Alzahrani ◽  
Mohammed Y. Alzahrani ◽  
Nizar Alsharif ◽  
Theyazn H. H. Aldhyani
Keyword(s):  
Deep Learning ◽  
Data Augmentation ◽  
Area Under The Curve ◽  
World Health ◽  
X Ray ◽  
Medical Sector ◽  
The World ◽  
Health Organization ◽  
Many Sources ◽  
Sensitivity Specificity

In March 2020, the World Health Organization announced the COVID-19 pandemic, its dangers, and its rapid spread throughout the world. In March 2021, the second wave of the pandemic began with a new strain of COVID-19, which was more dangerous for some countries, including India, recording 400,000 new cases daily and more than 4,000 deaths per day. This pandemic has overloaded the medical sector, especially radiology. Deep-learning techniques have been used to reduce the burden on hospitals and assist physicians for accurate diagnoses. In our study, two models of deep learning, ResNet-50 and AlexNet, were introduced to diagnose X-ray datasets collected from many sources. Each network diagnosed a multiclass (four classes) and a two-class dataset. The images were processed to remove noise, and a data augmentation technique was applied to the minority classes to create a balance between the classes. The features extracted by convolutional neural network (CNN) models were combined with traditional Gray-level Cooccurrence Matrix (GLCM) and Local Binary Pattern (LBP) algorithms in a 1-D vector of each image, which produced more representative features for each disease. Network parameters were tuned for optimum performance. The ResNet-50 network reached accuracy, sensitivity, specificity, and Area Under the Curve (AUC) of 95%, 94.5%, 98%, and 97.10%, respectively, with the multiclasses (COVID-19, viral pneumonia, lung opacity, and normal), while it reached accuracy, sensitivity, specificity, and AUC of 99%, 98%, 98%, and 97.51%, respectively, with the binary classes (COVID-19 and normal).

scholarly journals Automated Diagnosis of COVID-19 Using Deep Learning and Data Augmentation on Chest CT

2020 ◽  
Author(s):  
Runwen Hu ◽  
Guanqi Ruan ◽  
Shijun Xiang ◽  
Minghui Huang ◽  
Qiaoyi Liang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Receiver Operating Characteristic ◽  
Operating Characteristic ◽  
Data Augmentation ◽  
Chest Ct ◽  
Training Set ◽  
Sensitivity Specificity ◽  
Noisy Labels ◽  
Testing Set

AbstractBackgroundCoronavirus disease 2019 (COVID-19) has surprised the world since the beginning of 2020, and the rapid growth of COVID-19 is beyond the capability of doctors and hospitals that could deal in many areas. The chest computed tomography (CT) could be served as an effective tool in detection of COVID-19. It is valuable to develop automatic detection of COVID-19.Materials and MethodsThe collected dataset consisted of 1042 chest CT images (including 521 COVID-19, 397 healthy, 76 bacterial pneumonia and 48 SARS) obtained by exhaustively searching available data on the Internet. Then, these data are divided into three sets, referred to training set, validation set and testing set. Sixteen data augmentation operations are designed to enrich the training set in deep learning training phase. Multiple experiments were conducted to analyze the performance of the model in the detection of COVID-19 both in case of no noisy labels and noisy labels. The performance was assessed by the area under the receiver operating characteristic (AUC), sensitivity, specificity and accuracy.ResultsThe data augmentation operations on the training set are effective for improvement of the model performance. The area under the receiver operating characteristic curve is 0.9689 with (95% CI: 0.9308, 1) in case of no noisy labels for the classification of COVID-19 from heathy subject, while the per-exam sensitivity, specificity and accuracy for detecting COVID-19 in the independent testing set are 90.52%, 91.58% and 91.21%, respectively. In the classification of COVID-19 from other hybrid cases, the average AUC of the proposed model is 0.9222 with (95%CI: 0.8418, 1) if there are no noisy labels. The model is also robust when part of the training samples is marked incorrectly. The average AUC is 92.23% in the case of noisy labels of 10% in the training set.ConclusionA deep learning model with insufficient samples can be developed by using data augmentation in assisting medical workers in making quick and correct diagnosis of COVID-19.

Levenshtein Augmentation Improves Performance of SMILES Based Deep-Learning Synthesis Prediction

2020 ◽  
Author(s):  
Dean Sumner ◽  
Jiazhen He ◽  
Amol Thakkar ◽  
Ola Engkvist ◽  
Esben Jannik Bjerrum
Keyword(s):  
Neural Networks ◽  
Pattern Recognition ◽  
Deep Learning ◽  
Recurrent Neural Networks ◽  
Data Augmentation ◽  
State Of The Art ◽  
Sequence Similarity ◽  
Learning Models ◽  
Underlying Network

<p>SMILES randomization, a form of data augmentation, has previously been shown to increase the performance of deep learning models compared to non-augmented baselines. Here, we propose a novel data augmentation method we call “Levenshtein augmentation” which considers local SMILES sub-sequence similarity between reactants and their respective products when creating training pairs. The performance of Levenshtein augmentation was tested using two state of the art models - transformer and sequence-to-sequence based recurrent neural networks with attention. Levenshtein augmentation demonstrated an increase performance over non-augmented, and conventionally SMILES randomization augmented data when used for training of baseline models. Furthermore, Levenshtein augmentation seemingly results in what we define as <i>attentional gain </i>– an enhancement in the pattern recognition capabilities of the underlying network to molecular motifs.</p>

A Deep Learning based Arabic Script Recognition System: Benchmark on KHAT

2020 ◽  
Vol 17 (3) ◽  
pp. 299-305 ◽  
Author(s):  
Riaz Ahmad ◽  
Saeeda Naz ◽  
Muhammad Afzal ◽  
Sheikh Rashid ◽  
Marcus Liwicki ◽  
...  
Keyword(s):  
Deep Learning ◽  
Character Recognition ◽  
Data Augmentation ◽  
Short Term Memory ◽  
Recognition System ◽  
Learning Approach ◽  
Arabic Text ◽  
Data Set ◽  
Processing Step ◽  
Handwritten Arabic

This paper presents a deep learning benchmark on a complex dataset known as KFUPM Handwritten Arabic TexT (KHATT). The KHATT data-set consists of complex patterns of handwritten Arabic text-lines. This paper contributes mainly in three aspects i.e., (1) pre-processing, (2) deep learning based approach, and (3) data-augmentation. The pre-processing step includes pruning of white extra spaces plus de-skewing the skewed text-lines. We deploy a deep learning approach based on Multi-Dimensional Long Short-Term Memory (MDLSTM) networks and Connectionist Temporal Classification (CTC). The MDLSTM has the advantage of scanning the Arabic text-lines in all directions (horizontal and vertical) to cover dots, diacritics, strokes and fine inflammation. The data-augmentation with a deep learning approach proves to achieve better and promising improvement in results by gaining 80.02% Character Recognition (CR) over 75.08% as baseline.

Use of Resource-Efficient Plants to Reduce Nitrogen, Phosphorus, and Pesticide Runoff in Residential and Commercial Landscapes

1993 ◽  
Vol 28 (3-5) ◽  
pp. 205-213 ◽  
Author(s):  
Billy Hipp ◽  
Susan Alexander ◽  
Tim Knowles
Keyword(s):  
Comparative Study ◽  
Pollution Prevention ◽  
Cost Effective ◽  
Quality Data ◽  
Water Quality Data ◽  
Discharge System ◽  
Landscape Plant ◽  
Pollutant Concentrations ◽  
Pesticide Runoff ◽  
Nitrogen Phosphorus

Runoff from typical urban and suburban landscapes may contain significant levels of nitrogen, phosphorus, and a broad spectrum of various pesticides (mainly herbicides and insecticides) due to excessive application rates of these chemicals and high irrigation requirements of most commonly used landscape plant species. Preliminary water quality data (runoff) from a comparative study of 20 microwatersheds using 4 different levels of maintenance, show reductions in these types of pollutants in runoff for microwatersheds planted to resource efficient plants. Utilization of plants indigenous to an ecoregion (and other resource efficient plants) in landscape design and management allows considerable reduction in inputs from fertilizer, water, and pesticides. This results in lower pollutant concentrations in runoff and is estimated to result in lower total pollutant loadings from such systems. Installation of native or resource efficient plants in new developments (commercial and residential) and replacement of existing landscapes with these plants as older plants die or neighborhoods are updated could provide cities and suburban areas with a cost-effective, low-maintenance, and aesthetically-pleasing pollution control technology. Data from the comparative study should provide municipalities charged with meeting the new requirements of the National Pollutant Elimination Discharge System with a way to compare the pollution prevention effectiveness of resource-efficient landscapes with more traditional structural urban runoff controls.

scholarly journals Application of Deep Learning in Integrated Pest Management: A Real-Time System for Detection and Diagnosis of Oilseed Rape Pests

2019 ◽  
Vol 2019 ◽  
pp. 1-14 ◽  
Author(s):  
Yong He ◽  
Hong Zeng ◽  
Yangyang Fan ◽  
Shuaisheng Ji ◽  
Jianjian Wu
Keyword(s):  
Deep Learning ◽  
Integrated Pest Management ◽  
Pest Management ◽  
Real Time ◽  
Oilseed Rape ◽  
Data Augmentation ◽  
Low Cost ◽  
Response Speed ◽  
Original Model ◽  
Real Time System

In this paper, we proposed an approach to detect oilseed rape pests based on deep learning, which improves the mean average precision (mAP) to 77.14%; the result increased by 9.7% with the original model. We adopt this model to mobile platform to let every farmer able to use this program, which will diagnose pests in real time and provide suggestions on pest controlling. We designed an oilseed rape pest imaging database with 12 typical oilseed rape pests and compared the performance of five models, SSD w/Inception is chosen as the optimal model. Moreover, for the purpose of the high mAP, we have used data augmentation (DA) and added a dropout layer. The experiments are performed on the Android application we developed, and the result shows that our approach surpasses the original model obviously and is helpful for integrated pest management. This application has improved environmental adaptability, response speed, and accuracy by contrast with the past works and has the advantage of low cost and simple operation, which are suitable for the pest monitoring mission of drones and Internet of Things (IoT).

Sign in / Sign up

Export Citation Format

Share Document