Ensemble Deep Transfer Learning Research Articles

An Emerging Network for COVID-19 CT-Scan Classification using an ensemble deep transfer learning model

Over the past few years, the widespread outbreak of COVID-19 has caused the death of millions of people worldwide. Early diagnosis of the virus is essential to control its spread and provide timely treatment. Artificial intelligence methods are often used as powerful tools to reach a COVID-19 diagnosis via computed tomography (CT) samples. In this paper, artificial intelligence-based methods are introduced to diagnose COVID-19. At first, a network called CT6-CNN is designed, and then two ensemble deep transfer learning models are developed based on Xception, ResNet-101, DenseNet-169, and CT6-CNN to reach a COVID-19 diagnosis by CT samples. The publicly available SARS-CoV-2 CT dataset is utilized for our implementation, including 2481 CT scans. The dataset is separated into 2108, 248, and 125 images for training, validation, and testing, respectively. Based on experimental results, the CT6-CNN model achieved 94.66% accuracy, 94.67% precision, 94.67% sensitivity, and 94.65% F1-score rate. Moreover, the ensemble learning models reached 99.2% accuracy. Experimental results affirm the effectiveness of designed models, especially the ensemble deep learning models, to reach a diagnosis of COVID-19.

An Ensemble Deep Transfer Learning Model for Multi-dimensional Image Classification of Histological Prostate Biopsy Patterns

An Ensemble Deep Transfer Learning Model for Multi-dimensional Image Classification of Histological Prostate Biopsy Patterns

Automatic type Identification of Sub - Axial Vertebral Column Fractures using Deep learning Technique

Traumas like falls, sports injuries, or vehicle accidents are the main causes of Vertebral Column Fracture(VCFs) or spine fracture. The symptoms of VCF include back pain, swelling, numbness, and height decrease. VCF causes extreme pain, paralysis, difficulty in movement, etc. CT scans are inexpensive and effective in providing precise and quick VCF type detection. The determination of type VCF, however subject to inter-observer variability. To address this limitation this work introduces an automatic system for the detection of VCF type based on an ensemble of deep fine tuned models. This can assist the orthopaedicians in type identification of VCF which decreases the image interpretation time and increases the patient care time. For type identification, a total of two fine-tuned CNN architectures are used. Then, to further enhance the type identification performance, we developed an ensemble model of fine tuned VGG16 and ResNet50 deep learning models, which average the outputs of the models during final prediction. We used a dataset of 2820 CT images from eight different VCF types that were collected from Kasturba Medical college, Manipal Academy of Higher education, Manipal. The results shows that the ensemble model performs well compare to individual fine-tuned models with accuracy of 82%, precision of 0.84, recall of 0.82 and F1-score of 0.81 for VCF type identification from CT scans. This study shows that type identification of VCF in CT scans may be successfully accomplished using an ensemble deep transfer learning system with various fine tuned CNN architectures.

Battery health prognostic using efficient and robust aging trajectory matching with ensemble deep transfer learning

Accurate aging trajectory and lifetime prediction are key objectives for battery prognostic and health management. However, effective health prognostic is difficult to realize due to the different aging characteristics at different aging stages and incomplete aging data for practical applications. To embrace these challenges, we propose an intelligent battery health prognostic method using efficient and robust aging trajectory matching with ensemble deep transfer learning (EDTL). Firstly, dispensing with expertise in battery degradation, spectral clustering is offline performed for unsupervised degradation pattern recognition. Secondly, to ensure the accuracy of aging trajectory matching, lifetime indicator-based candidate cell selection fusing with similarity assessment using dynamic time warping provides multi-dimensional information in finding the optimally matched battery aging trajectory from the historical data. Finally, to robustly and accurately capture the long-term dependencies of battery aging, the bi-directional long short-term memory network with EDTL is employed. Experimental results demonstrate that the proposed method could achieve accurate and reliable health prognostic at different battery aging stages or in the presence of incomplete data with a maximum lifetime prediction error of 6.35%. Compared with traditional methods, our method could provide a more accurate battery health prognostic, which is of great significance for battery predictive maintenance.

Arithmetic Optimization with Ensemble Deep Transfer Learning Based燤elanoma Classification

Melanoma is a skin disease with high mortality rate while early diagnoses of the disease can increase the survival chances of patients. It is challenging to automatically diagnose melanoma from dermoscopic skin samples. Computer-Aided Diagnostic (CAD) tool saves time and effort in diagnosing melanoma compared to existing medical approaches. In this background, there is a need exists to design an automated classification model for melanoma that can utilize deep and rich feature datasets of an image for disease classification. The current study develops an Intelligent Arithmetic Optimization with Ensemble Deep Transfer Learning Based Melanoma Classification (IAOEDTT-MC) model. The proposed IAOEDTT-MC model focuses on identification and classification of melanoma from dermoscopic images. To accomplish this, IAOEDTT-MC model applies image preprocessing at the initial stage in which Gabor Filtering (GF) technique is utilized. In addition, U-Net segmentation approach is employed to segment the lesion regions in dermoscopic images. Besides, an ensemble of DL models including ResNet50 and ElasticNet models is applied in this study. Moreover, AO algorithm with Gated Recurrent Unit (GRU) method is utilized for identification and classification of melanoma. The proposed IAOEDTT-MC method was experimentally validated with the help of benchmark datasets and the proposed model attained maximum accuracy of 92.09% on ISIC 2017 dataset.

Joint modulation format recognition and optical performance monitoring for efficient fiber-optic communication links using ensemble deep transfer learning

We propose an ensemble deep transfer learning (EDTL) method, which is a more refined multilayer feature extraction achieved by aggregating the convolutional layers of pretrained convolutional neural network models for joint optical modulation format recognition (MFR) and optical performance monitoring (OPM) in fiber-optic communication links. Modulation formats, such as quadrature phase shift keying, 16 quadrature amplitude modulation (QAM), and 64 QAM, are monitored for the optical signal-to-noise ratio (OSNR) range of 20 to 30 dB by considering the dispersive effects of chromatic dispersion from 0 to 1200 ps / nm and polarization mode dispersion from 10 to 70 ps in the fiber-optic transmission path. First, the generated constellation diagrams affected by the impairments are used to optimize and evaluate the pretrained models based on classification targets. Then the proposed EDTL model is designed by aggregating the feature extractor parts of the pretrained models; it is implemented in three phases, and the results are comprehensively studied. Further, data augmentation and aggregation methods are introduced to enhance the performance of joint MFR and OPM. The results obtained prove that the proposed model provides faster convergence of MFR and better identification accuracy of OSNR toward optical signal diagnostics in optical networks for efficient optical link monitoring.

An Efficient Ensemble Model for Diagnosing Covid-19 and Pneumonia Using Chest X-Ray Images

Objectives : To propose an ensemble machine learning model for early identification of COVID-19 and pneumonia lung infections by analyzing the chest X-ray images. Methods: RGDSoft model is proposed for image classification which is a soft voting ensemble deep transfer learning strategy with pre-trained classifiers ResNet-18, GoogLeNet, and DenseNet-121. The model is tested on COVID-19 dataset having 1143 positive COVID-19, 1341 normal, and 1345 pneumonia images, and the Kermany dataset which has 5856 chest X-ray images divided into two groups: ”Pneumonia” and ”Normal”. Out of these image-set 80% of images are used for training and 20% for testing purposes. To demonstrate the efficiency of the proposed model, python is used for implementation. Performance results are evaluated and compared with the existing pre-trained models like GoogLeNet, ResNet18 and DensNet121. Findings: Efficiency of the proposed ensemble model is achieved with 98.1% accuracy level, 98.8% precision, 98.8% recall on kermany dataset whereas 94% accuracy, 96% precision and 96% recall on COVID-19 dataset which is optimum as compared with the most state-of-art models discussed in literature. Novelty: According to the findings of the comprehensive study, the proposed RGDSoft model not only outperforms most of the classifiers like GoogLeNet, ResNet18 and DenseNet121 in terms of combinations of accuracy, precision and recall but is so generic model which shows very good results on different datasets. Keywords: Machine Learning; Deep Learning; Covid19; Pneumonia; xray images; googlenet; resnet18; densenet121; ensemble

Image Classification For Plant Disease Prediction Using Ensemble Deep Transfer Learning

Image Classification For Plant Disease Prediction Using Ensemble Deep Transfer Learning

A reinforcement ensemble deep transfer learning network for rolling bearing fault diagnosis with Multi-source domains

Fault diagnosis with transfer learning has achieved great attention. However, existing methods mostly focused on single-source-single-target sceneries. In some cases, there may exist multiple source domains. Therefore, a reinforcement ensemble deep transfer learning network (REDTLN) is proposed for fault diagnosis with multi-source domains. Firstly, various new kernel maximum mean discrepancies (kMMDs) are used to construct multiple deep transfer learning networks (DTLNs) for single-source-single-target domain adaptation. The differences of kernel functions and source domains can help the DTLNs learn diverse transferable features. Secondly, a new unified metric is designed based on kMMD and diversity measures for unsupervised ensemble learning. Finally, using the unified metric as the reward, a reinforcement learning method is firstly explored to generate an effective combination rule for multi-domain-multi-model reinforcement ensemble. The proposed method is verified with experiment datasets, and the results empirically show its effectiveness and superiority compared with other methods.

SI‐EDTL: Swarm intelligence ensemble deep transfer learning for multiple vehicle detection in UAV images

AbstractThis article proposes a swarm intelligence ensemble deep transfer learning (named SI‐EDTL) for multiple vehicle detection in unmanned aerial vehicle (UAV) images. This method is based on Faster regional‐based convolutional neural networks (Faster R‐CNN), in which, a set of region proposals are extracted using region proposal network (RPN), and then, CNN is used to mine highly descriptive features of these windows to classify regions. We use three Faster R‐CNNs as feature extractors (InceptionV3, ResNet50, and GoogLeNet) that have already pre‐trained on ImageNet data, combined with five transfer classifiers (KNN, SVM, MLP, C4.5 Decision Tree, and Naïve Bayes). As a result, 15 different base learners are trained through deep transfer learning on a UAV dataset to classify the region proposals into multiple vehicles (car, van, truck, and bus). We combine these 15 base learners through a weighted averaging aggregation into four vehicle classes or no vehicle (background). Hyperparameters of the ensemble model are tuned using whale optimization algorithm, to achieve the best trade‐off between total accuracy, precision, and recall. The proposed SI‐EDTL model has been successfully developed using parallel processing in MATLAB R2020b. Experimental results on AU‐AIR dataset of UAV images demonstrate the superiority of the SI‐EDTL model against existing techniques.

COVED: A Hardware Accelerated Soft Computing Enabled Intelligent Value Chain Based Diagnostic Automation for nCOVID-19 Estimation and Identification

Purpose: COVID-19, a global pandemic, first appeared in the city of Wuhan, China, and has since spread differently across geographical borders, classes, and genders from various age groups, sometimes mutating its DNA strands in the process. The sheer magnitude of the pandemic's spread is putting a strain on hospitals and medical facilities. The need of the hour is to deploy IoT devices and robots to monitor patients' body vitals as well as their other pathological data to further control the spread. There has not been a more compelling need to use digital advances to remotely provide quality healthcare via computing devices and AI-powered medical aids. Method: This research developed a deployable Internet of Things (IoT) based infrastructure for the early and simple detection and isolation of suspected coronavirus patients, which was accomplished via the use of ensemble deep transfer learning. The proposed Internet of Things framework combines 4 different deep learning models: DenseNet201, VGG16, InceptionResNetV2, and ResNet152V2. Utilizing the deep ensemble model, the medical modalities are used to obtain chest high-resolution computed tomography (HRCT) images and diagnose the infection. Results: Over the HRCT image dataset, the developed deep ensemble model is collated to different state-of-the-art transfer learning (TL) models. The comparative investigation demonstrated that the suggested approach can aid radiologists inefficiently and swiftly diagnosing probable coronavirus patients. Conclusion: For the first time, our group has developed an AI-enabled Decision Support System to automate the entire process flow from estimation to detection of COVID-19 subjects as part of an Intelligent Value Chain algorithm. The screening is expected to eliminate the false negatives and asymptomatic ones out of the equation and hence the affected individuals could be identified in a total process time of 15 minutes to 1 hour. A Complete Deployable System with AI Influenced Prediction is described here for the first time. Not only did the authors suggest a Multiple Hypothesis based Decision Fusion Algorithm for forecasting the outcome, but they also did the predictive analytics. For simple confined isolation or hospitalization, this complete Predictive System was encased within an IoT ecosystem.

Predicting breast cancer response to neoadjuvant chemotherapy using ensemble deep transfer learning based on CT images.

To develop an ensemble a deep transfer learning model of CT images for predicting pathologic complete response (pCR) in breast cancer patients undergoing neoadjuvant chemotherapy (NAC). The data were obtained from the public dataset 'QIN-Breast' from The Cancer Imaging Archive (TCIA). CT images were gathered before and after the first cycle of NAC. CT images of 121 breast cancer patients were used to train and test the model. Among these patients, 58 achieved a pCR and 63 showed a non-pCR based pathology examination of surgical results after NAC. The dataset was split into training and testing subsets with a ratio of 7:3. In addition, the number of training samples in the dataset was increased from 656 to 1,968 by performing an image augmentation method. Two deep transfer learning models namely, DenseNet201 and ResNet152V2, and the ensemble model with a concatenation of two models, were trained and tested using CT images. The ensemble model obtained the highest accuracy of 100% on the testing dataset. Furthermore, we received the best performance of 100% in recall, precision and f1-score value for the ensemble model. This supports the fact that the ensemble model results in better-generalized model and leads to efficient framework. Although a 0.004 and 0.003 difference were seen between the AUC of two base models (DenseNet201 and ResNet152V2) and the proposed ensemble, this increase in the model quality is critical in medical research. T-SNE revealed that in the proposed ensemble, no points were clustered into the wrong class. These results expose the strong performance of the proposed ensemble. The study concluded that the ensemble model can increase the ability to predict breast cancer response to first-cycle NAC than two DenseNet201 and ResNet152V2 models.

Ensemble deep transfer learning model for Arabic (Indian) handwritten digit recognition

Ensemble deep transfer learning model for Arabic (Indian) handwritten digit recognition

Ensemble Deep Learning Using Faster R-CNN and Genetic Algorithm for Vehicle Detection in UAV Images

In this paper, an ensemble deep transfer learning (EDTL) based on Faster R-CNN is introduced for the vehicle detection in UAV images. We perform a weighted-averaging ensemble transfer learning comprising six base learners using a ResNet50 that have already pre-trained on ImageNet dataset. The weights of the six base learners as well as the final decision threshold are adaptively optimized via genetic algorithm, to maximize the total accuracy, precision, and recall. Simulation results on AU-AIR dataset demonstrate the superiority of the EDTL against the existing techniques, in terms of the total accuracy, and the trade-off between precision and recall.

Radiologist-Level Two Novel and Robust Automated Computer-Aided Prediction Models for Early Detection of COVID-19 Infection from Chest X-ray Images.

COVID-19 is an ongoing pandemic that is widely spreading daily and reaches a significant community spread. X-ray images, computed tomography (CT) images and test kits (RT-PCR) are three easily available options for predicting this infection. Compared to the screening of COVID-19 infection from X-ray and CT images, the test kits(RT-PCR) available to diagnose COVID-19 face problems such as high analytical time, high false negative outcomes, poor sensitivity and specificity. Radiological signatures that X-rays can detect have been found in COVID-19 positive patients. Radiologists may examine these signatures, but it's a time-consuming and error-prone process (riddled with intra-observer variability). Thus, the chest X-ray analysis process needs to be automated, for which AI-driven tools have proven to be the best choice to increase accuracy and speed up analysis time, especially in the case of medical image analysis. We shortlisted four datasets and 20 CNN-based models to test and validate the best ones using 16 detailed experiments with fivefold cross-validation. The two proposed models, ensemble deep transfer learning CNN model and hybrid LSTMCNN, perform the best. The accuracy of ensemble CNN was up to 99.78% (96.51% average-wise), F1-score up to 0.9977 (0.9682 average-wise) and AUC up to 0.9978 (0.9583 average-wise). The accuracy of LSTMCNN was up to 98.66% (96.46% average-wise), F1-score up to 0.9974 (0.9668 average-wise) and AUC up to 0.9856 (0.9645 average-wise). These two best pre-trained transfer learning-based detection models can contribute clinically by offering the patients prediction correctly and rapidly.

Artificial Intelligence and Medical Internet of Things Framework for Diagnosis of Coronavirus Suspected Cases.

The world has been facing the COVID-19 pandemic since December 2019. Timely and efficient diagnosis of COVID-19 suspected patients plays a significant role in medical treatment. The deep transfer learning-based automated COVID-19 diagnosis on chest X-ray is required to counter the COVID-19 outbreak. This work proposes a real-time Internet of Things (IoT) framework for early diagnosis of suspected COVID-19 patients by using ensemble deep transfer learning. The proposed framework offers real-time communication and diagnosis of COVID-19 suspected cases. The proposed IoT framework ensembles four deep learning models such as InceptionResNetV2, ResNet152V2, VGG16, and DenseNet201. The medical sensors are utilized to obtain the chest X-ray modalities and diagnose the infection by using the deep ensemble model stored on the cloud server. The proposed deep ensemble model is compared with six well-known transfer learning models over the chest X-ray dataset. Comparative analysis revealed that the proposed model can help radiologists to efficiently and timely diagnose the COVID-19 suspected patients.

Rapid COVID-19 diagnosis using ensemble deep transfer learning models from chest radiographic images.

The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) causes novel coronavirus disease (COVID-19) outbreak in more than 200 countries around the world. The early diagnosis of infected patients is needed to discontinue this outbreak. The diagnosis of coronavirus infection from radiography images is the fastest method. In this paper, two different ensemble deep transfer learning models have been designed for COVID-19 diagnosis utilizing the chest X-rays. Both models have utilized pre-trained models for better performance. They are able to differentiate COVID-19, viral pneumonia, and bacterial pneumonia. Both models have been developed to improve the generalization capability of the classifier for binary and multi-class problems. The proposed models have been tested on two well-known datasets. Experimental results reveal that the proposed framework outperforms the existing techniques in terms of sensitivity, specificity, and accuracy.

Ensemble deep transfer learning driven by multisensor signals for the fault diagnosis of bevel-gear cross-operation conditions

The existing intelligent fault diagnosis techniques of bevel gear focus on single-sensor signal analysis under the steady operation condition. In this study, a new method is proposed based on ensemble deep transfer learning and multisensor signals to enhance the fault diagnosis adaptability and reliability of bevel gear under various operation conditions. First, a novel stacked autoencoder (NSAE) is constructed using a denoising autoencoder, batch normalization, and the Swish activation function. Second, a series of source-domain NSAEs with multisensor vibration signals is pretrained. Third, the good model parameters provided by the source-domain NSAEs are transferred to initialize the corresponding target-domain NSAEs. Finally, a modified voting fusion strategy is designed to obtain a comprehensive result. The multisensor signals collected under the different operation conditions of bevel gear are used to verify the proposed method. The comparison results show that the proposed method can diagnose different faults in an accurate and stable manner using only one target-domain sample, thereby outperforming the existing methods.

Instance-based ensemble deep transfer learning network: A new intelligent degradation recognition method and its application on ball screw

Degradation recognition plays an important role in improving the safety of mechanical operation. For most of the existing recognition methods, using large amounts of labeled training data that obey the same probability distribution as testing data is an important pre-requisite for training effective recognition model. Unfortunately, it is difficult to collectmassive labeled condition data for some machines like ball screw. This makes it a huge challenge to build reliable recognition model since the labeled training data collected in target domain are insufficient. However, large amounts of labeled data collected in different but related domain (called source domain) are usually available, which can be treated as auxiliary training data to help build better recognition model in target domain. Inspired by the idea of transferring knowledge from source domain to target domain, a new intelligent method named instance-based ensemble deep transfer learning network (IEDT) is proposed in this paper to recognize the degradation under various operating conditions. IEDT mainly consists of three parts: First, source instances that fit better with the target domain are selected by filtering out these unrelated samples iteratively. The remaining source instances are employed to assist insufficient labeled target data to train multiple stacked auto-encoders (SAEs) with different activation functions. And then, the trained SAEs are transferred to target domain as feature extractors. The extracted features are fed into support vector machine (SVM) to construct SAE-SVM models, which are further trained by limited target training data and used for degradation recognition. Finally, ensemble strategy is proposed to calculate final results based on multiple predicted labels of individual SAE-SVMs. Run-to-failure test of ball screw is carried out to collect experimental data under different working conditions. The effectiveness of the proposed IEDT method is validated by four transfer degradation recognition experiments of ball screw. Results indicate that the proposed IEDT method is superior to comparison methods in degradation recognition when there is only a small amount of labeled condition data.