Deep Transfer Learning Approach Research Articles

A deep transfer learning approach for cross-subject recognition of mental tasks based on functional near-infrared spectroscopy

In the field of brain-computer interfaces (BCIs) based on functional near-infrared spectroscopy (fNIRS), traditional subject-specific decoding methods suffer from the limitations of long calibration time and low cross-subject generalizability, which restricts the promotion and application of BCI systems in daily life and clinic. To address the above dilemma, this study proposes a novel deep transfer learning approach that combines the revised inception-residual network (rIRN) model and the model-based transfer learning (TL) strategy, referred to as TL-rIRN. This study performed cross-subject recognition experiments on mental arithmetic (MA) and mental singing (MS) tasks to validate the effectiveness and superiority of the TL-rIRN approach. The results show that the TL-rIRN significantly shortens the calibration time, reduces the training time of the target model and the consumption of computational resources, and dramatically enhances the cross-subject decoding performance compared to subject-specific decoding methods and other deep transfer learning methods. To sum up, this study provides a basis for the selection of cross-subject, cross-task, and real-time decoding algorithms for fNIRS-BCI systems, which has potential applications in constructing a convenient and universal BCI system.

XECG-Beats: an explainable deep transfer learning approach for ECG-based heartbeat classification

Early detection of abnormal heartbeats is of great importance for cardiologists for early diagnosis of cardiac diseases. This will help patients to receive in time diagnosis and prevention. Conventionally, physicians provide cardiac diagnoses by visual examination of electrocardiograms (ECGs). However, this can be a very time consuming and demanding task and, in some cases, may lead to overlooking and wrong diagnosis of life-threatening heart diseases. Therefore, an intelligent model can help to automatically analyze these huge amount of ECGs captured by different devices in clinical practice. A deep transfer learning approach is used to utilize the capability of different trained deep neural networks and to test them on new unseen datasets without the need to fully re-train the model. Two deep neural networks, namely, Visual Geometry Group (VGG) and Residual Network (ResNet) are utilized for classification of ECGs heartbeats. The models are evaluated using two unseen ECG datasets (i.e., SVDB and INCARTDB) by only optimizing their last classification layers. The overall area under curve for receiver operating characteristic (AUCROC) of two VGG and ResNet models are 0.961 and 0.966 on the SVDB dataset, respectively, and both models achieve 0.981 on the INCARTDB. This paper proposes an accurate and explainable model to classify ECG heartbeats into five categories recommended by the ANSI/AAMI standard. The proposed method paves the way to use pre-trained deep neural networks in real-time monitoring of heart patients using ECG data and to help clinicians understand the decision made by the models on each case using an explainable approach.

A Deep Transfer Learning Approach for Sleep Stage Classification and Sleep Apnea Detection Using Wrist-Worn Consumer Sleep Technologies.

Obstructive sleep apnea (OSA) is a common, underdiagnosed sleep-related breathing disorder with serious health implications Objective - We propose a deep transfer learning approach for sleep stage classification and sleep apnea (SA) detection using wrist-worn consumer sleep technologies (CST). Methods - Our model is based on a deep convolutional neural network (DNN) utilizing accelerometers and photo-plethysmography signals from nocturnal recordings. The DNN was trained and tested on internal datasets that include raw data from clinical and wrist-worn devices; external validation was performed on a hold-out test dataset containing raw data from a wrist-worn CST. Results - Training on clinical data improves performance significantly, and feature enrichment through a sleep stage stream gives only minor improvements. Raw data input outperforms feature-based input in CST datasets. The system generalizes well but performs slightly worse on wearable device data compared to clinical data. However, it excels in detecting events during REM sleep and is associated with arousal and oxygen desaturation. We found; cases that were significantly underestimated were characterized by fewer of such event associations. Conclusion - This study showcases the potential of using CSTs as alternate screening solution for undiagnosed cases of OSA. Significance - This work is significant for its development of a deep transfer learning approach using wrist-worn consumer sleep technologies, offering comprehensive validation for data utilization, and learning techniques, ultimately improving sleep apnea detection across diverse devices.

Predicting the Prognosis of HIFU Ablation of Uterine Fibroids Using a Deep Learning-Based 3D Super-Resolution DWI Radiomics Model: A Multicenter Study

Rationale and ObjectivesTo assess the feasibility and efficacy of a deep learning based three-dimensional (3D) super-resolution diffusion-weighted imaging (DWI) radiomics model in predicting the prognosis of high-intensity focused ultrasound (HIFU) ablation of uterine fibroids. MethodsThis retrospective study included 360 patients with uterine fibroids who received HIFU treatment, including Center A (training set: N=240; internal testing set: N=60) and Center B (external testing set: N=60) and were classified as having a favorable or unfavorable prognosis based on the postoperative non-perfusion volume ratio. A deep transfer learning approach was used to construct super-resolution DWI (SR-DWI) based on conventional high-resolution DWI (HR-DWI), and 1198 radiomics features were extracted from manually segmented regions of interest in both image types. Following data preprocessing and feature selection, radiomics models were constructed for HR-DWI and SR-DWI using Support Vector Machine (SVM), Random Forest (RF), and Light Gradient Boosting Machine (LightGBM) algorithms, with performance evaluated using area under the curve (AUC) and decision curves. ResultAll DWI radiomics models demonstrated superior AUC in predicting HIFU ablated uterine fibroids prognosis compared to expert radiologists (AUC: 0.706, 95% CI: 0.647-0.748). When utilizing different machine learning algorithms, the HR-DWI model achieved AUC values of 0.805 (95% CI: 0.679-0.931) with SVM, 0.797 (95% CI: 0.672-0.921) with RF, and 0.770 (95% CI: 0.631-0.908) with LightGBM. Meanwhile, the SR-DWI model outperformed the HR-DWI model (P<0.05) across all algorithms, with AUC values of 0.868 (95% CI: 0.775-0.960) with SVM, 0.824 (95% CI: 0.715-0.934) with RF, and 0.821 (95% CI: 0.709-0.933) with LightGBM. And decision curve analysis further confirmed the good clinical value of the models. ConclusionDeep learning based 3D SR-DWI radiomics model demonstrated favorable feasibility and effectiveness in predicting the prognosis of HIFU ablated uterine fibroids, which was superior to HR-DWI model and assessment by expert radiologists.

Using autoencoders and deep transfer learning to determine the stellar parameters of 286 CARMENES M dwarfs

Context. Deep learning (DL) techniques are a promising approach among the set of methods used in the ever-challenging determination of stellar parameters in M dwarfs. In this context, transfer learning could play an important role in mitigating uncertainties in the results due to the synthetic gap (i.e. difference in feature distributions between observed and synthetic data). Aims. We propose a feature-based deep transfer learning (DTL) approach based on autoencoders to determine stellar parameters from high-resolution spectra. Using this methodology, we provide new estimations for the effective temperature, surface gravity, metallicity, and projected rotational velocity for 286 M dwarfs observed by the CARMENES survey. Methods. Using autoencoder architectures, we projected synthetic PHOENIX-ACES spectra and observed CARMENES spectra onto a new feature space of lower dimensionality in which the differences between the two domains are reduced. We used this low-dimensional new feature space as input for a convolutional neural network to obtain the stellar parameter determinations. Results. We performed an extensive analysis of our estimated stellar parameters, ranging from 3050 to 4300 K, 4.7 to 5.1 dex, and −0.53 to 0.25 dex for Teff, log 𝑔, and [Fe/H], respectively. Our results are broadly consistent with those of recent studies using CARMENES data, with a systematic deviation in our Teff scale towards hotter values for estimations above 3750 K. Furthermore, our methodology mitigates the deviations in metallicity found in previous DL techniques due to the synthetic gap. Conclusions. We consolidated a DTL-based methodology to determine stellar parameters in M dwarfs from synthetic spectra, with no need for high-quality measurements involved in the knowledge transfer. These results suggest the great potential of DTL to mitigate the differences in feature distributions between the observations and the PHOENIX-ACES spectra.

Optimizing clinico-genomic disease prediction across ancestries: a machine learning strategy with Pareto improvement

BackgroundAccurate prediction of an individual’s predisposition to diseases is vital for preventive medicine and early intervention. Various statistical and machine learning models have been developed for disease prediction using clinico-genomic data. However, the accuracy of clinico-genomic prediction of diseases may vary significantly across ancestry groups due to their unequal representation in clinical genomic datasets.MethodsWe introduced a deep transfer learning approach to improve the performance of clinico-genomic prediction models for data-disadvantaged ancestry groups. We conducted machine learning experiments on multi-ancestral genomic datasets of lung cancer, prostate cancer, and Alzheimer’s disease, as well as on synthetic datasets with built-in data inequality and distribution shifts across ancestry groups.ResultsDeep transfer learning significantly improved disease prediction accuracy for data-disadvantaged populations in our multi-ancestral machine learning experiments. In contrast, transfer learning based on linear frameworks did not achieve comparable improvements for these data-disadvantaged populations.ConclusionsThis study shows that deep transfer learning can enhance fairness in multi-ancestral machine learning by improving prediction accuracy for data-disadvantaged populations without compromising prediction accuracy for other populations, thus providing a Pareto improvement towards equitable clinico-genomic prediction of diseases.

Enhanced Segmentation of Ischemic Stroke Lesion in MRI Images Using a Geometrically Customised Deep Convolution Model (GCDCM)

Ischemic stroke lesion often known as a stroke, is a significant health issue that requires accurate analysis and classification of brain magnetic resonance imaging (MRI) data. In this study, we propose a novel deep transfer learning approach, called geometrically customized deep convolution model, for the purpose of MRI analysis and classification of brain stroke. Neurostroke segmentation is a serious medical image processing challenge. Segmented regions aid disease identification and treatment. Anywhere can form thrombi. Segmentation facilitates automatic detection because they can be any size or shape. Popular image analysis tool MRI diagnoses well. This diagnostic method shows brain stroke architecture. MRI must replace manual detection. Online datasets recommended cerebral stroke detection and segmentation. Deep learning model MRI scans and detectron 2 with masked CNN Nets segment thrombus. This net architecture recognises dataset stroke boundaries. Classifying strokes with vgg16, resnet50, inceptionv3, and resnet5 transfer learning is possible. Mask the image, then binary predict by eliminating the skull, extracting features, and iterating to find stroke. The model and thrombus mask are predicted if the binary prediction matches the human forecast. Otherwise, data processing resumes. Binary prediction uses the segmentation region and pixels overlap between the ground truth and predicted segmentation to calculate parameters. Compared to reality, the categorization of medical images with weak signals seems tough, especially with a short "train" dataset. Mixing deep learning architectures avoids these drawbacks and extracts signals to accurately classify classes. Deep neural networks best recognise, find, and divide computer vision objects for clinical image analysis. Preprocessing MRI scans, skull stripping with deep CNN architecture combinational net, and brain stroke segmentation are our main tasks. Modern medical image processing is hard. Flexible and uneven borders make brain strokes hard to identify and segment. The transfer learning-based super pixel approach segments brainstrokes. Because we predict every visual pixel, dense prediction occurs. Early discovery of thrombus improves treatment and survival. These procedures have considerably improved our quality indexes.

A Novel Optimized Colonic adenocarcinoma Detection using Deep Transfer Learning Approach with XceptionTS Model

Colonic adenocarcinoma is a major contributor to global mortality, highlighting the crucial need for efficient detection and classification techniques. This research presents a new method called XceptionTS for classifying and detecting colon cancer using colonoscopy pictures. The XceptionTS method utilizes deep transfer learning techniques by leveraging the Xception model architecture. Nonlinear Mean Filtering (NMF) is used as a noise reduction method in image processing to improve the quality of colonoscopy pictures. We combine the MobileNetV2 and ResNet-50 models for healthcare image segmentation and feature extraction, respectively. The XceptionTS classifier efficiently gives accurate class labels to medical photos by combining Tabu Search Optimization with the strong Xception architecture. The assessment of the effectiveness of XceptionTS model is done using a dataset of 1560 colonoscopy images. An extensive comparison study is undertaken by analyzing the efficacy of our suggested approach with existing research. The XceptionTS system outperforms previous methodologies in colon cancer classification and detection tasks, showing higher accuracy and robustness according to experimental results. Our findings indicate that the XceptionTS technique shows potential as an advanced tool to increase the effectiveness of Colonic adenocarcinoma diagnosis, which could lead to better patient outcomes and healthcare management.

A Novel QCT-Based Deep Transfer Learning Approach for Predicting Stiffness Tensor of Trabecular Bone Cubes

ObjectivesThis study was performed to prove the concept that transfer learning techniques, assisted with a generative model, could be used to alleviate the ‘big data’ requirement for training high-fidelity deep learning (DL) models in prediction of stiffness tensor of trabecular bone cubes. Material and methodsTransfer learning approaches of domain adaptation were used, in which a source domain included 1,641 digital trabecular bone cubes synthesized from a generative model, and a target domain included 868 real trabecular bone cubes from human cadaver femurs. Simulated quantitative computed tomography (QCT) images of both the synthesized and real bone cubes were used as input, whereas the stiffness tensor of these cubes determined using finite element simulations were used as output. Three transfer learning algorithms, including instance-based (TrAdaBoostR2 and WANN) and parameter-based (RNN) methods, were used. Two case studies, one with varying sizes of training dataset and the other with a gender-biased training dataset, were performed to evaluate these deep transfer learning models in comparison with a base deep learning (DL) model trained using the dataset from the target domain. ResultsThe results indicated that these deep transfer learning models were robust both to sample size and to the gender-biased training dataset, whereas the base DL model was very sensitive to such changes. Among the three transfer learning algorithms, the prediction accuracy of the RNN-based deep transfer learning model was the best (0.92-0.96%) and comparable to that of the base DL model trained using the dataset from the target domain. ConclusionThis study proved the proposed concept and confirmed that high fidelity QCT-based deep learning models could be obtained for prediction of stiffness tensor of trabecular bone cubes.

Creating Proactive Cyber Threat Intelligence with Hacker Exploit Labels: A Deep Transfer Learning Approach

The rapid proliferation of complex information systems has been met by an ever-increasing quantity of exploits that can cause irreparable cyber breaches. To mitigate these cyber threats, academia and industry have placed a significant focus on proactively identifying and labeling exploits developed by the international hacker community. However, prevailing approaches for labeling exploits in hacker forums do not leverage metadata from exploit darknet markets or public exploit repositories to enhance labeling performance. In this study, we adopted the computational design science paradigm to develop a novel information technology artifact, the deep transfer learning exploit labeler (DTL-EL). DTL-EL incorporates a pre-initialization design, multi-layer deep transfer learning (DTL), and a self-attention mechanism to automatically label exploits in hacker forums. We rigorously evaluated the proposed DTL-EL against state-of-the-art non-DTL benchmark methods based in classical machine learning and deep learning. Results suggest that the proposed DTL-EL significantly outperforms benchmark methods based on accuracy, precision, recall, and F1-score. Our proposed DTL-EL framework provides important practical implications for key stakeholders such as cybersecurity managers, analysts, and educators.

Deep Transfer Learning Approach for Student Attendance System During the COVID-19 Pandemic

Deep Transfer Learning Approach for Student Attendance System During the COVID-19 Pandemic

Transfer learning model for cash-instrument prediction adopting a Transformer derivative

Investors aiming for high market returns must accurately predict the prices of various cash instruments. However, making accurate predictions is challenging due to the complex cyclic and trending characteristic of markets, characterized by high volatility and unpredictable fluctuations. Furthermore, many studies overlook how interactions between different markets affect price movements. To address these problems, this research introduces a deep transfer-learning approach derived from the Transformer model, named the rotary-positional encoding autocorrelation Transformer (RAT). Unlike traditional methods, the RAT employs autocorrelation instead of self-attention to more effectively capture periodic features, while rotary-positional encoding preserves both the absolute and relative positioning within sequences to enhance trend understanding. Through transfer learning, the RAT model extracts deep features from a source domain and applies them to a target domain, demonstrating superior performance over LSTM, CNN-LSTM, gated recurrent units (GRUs), and Transformer models in multi-day predictions across 12 cash-instrument datasets. It achieved a substantial increase in accuracy, with a 35.83% reduction in mean squared error (MSE), a 23.95% reduction in mean absolute error (MAE), and a 32.63% increase in the coefficient of determination (R2). This study validates the RAT model’s effectiveness in predicting financial instrument prices.

Empowering EEG motor imagery classification with deep transfer learning approach

AbstractThe brain‐computer interface (BCI) enables individuals with impairments to interact with the real world without relying on the neuromuscular pathway. BCI leverages artificial intelligence (AI) models for control. It can capture brain activity patterns associated with mental processes and convert them into commands for actuators. One promising application of BCI is in rehabilitation centres. When compared to traditional methods integrated with machine learning (ML) approaches that were initially explored in the past decade, there is a relatively limited number of studies utilizing deep learning (DL) approaches in BCI applications. A novel approach has been developed for the automatic recognition of motor imagery (MI) tasks. This article introduces the improved sparrow search algorithm with deep transfer learning‐based EEG motor imagery classification (ISSADTL‐EEGMIC) algorithm for BCIs. The presented ISSADTL‐EEGMIC algorithm primarily focuses on the automated classification of motor imagery tasks. To achieve this, the ISSADTL‐EEGMIC method first preprocesses EEG signals using the wavelet packet decomposition (WPD) technique. Additionally, it employs the neural architecture search network (NASNet) technique for feature extraction. Moreover, the ISSADTL‐EEGMIC model performs the classification process using the stacked sparse autoencoder (SSAE) model. Furthermore, hyperparameter optimization of the SSAE model is performed using the ISSA technique, which helps achieve maximum classification performance. The results from the simulation of the ISSADTL‐EEGMIC algorithm have been examined using two benchmark datasets. The experimental findings suggest that it outperforms recent approaches in terms of performance.

A TinyML solution for an IoT-based communication device for hearing impaired

Research on automatic translation of sign language to verbal languages has been progressively explored in recent years to assist speech and hearing-impaired people in communicating with non-signers. In this paper, a tiny machine learning (TinyML) solution is proposed for sign language recognition using a low-cost, wearable, internet-of things (IoT) device. A lightweight deep neural network is deployed on the edge device to interpret isolated signs from the Indian sign language using the time-series data collected from the motion sensors of the device. The scarcity of labeled training data is addressed by employing the deep transfer learning approach. Here, the knowledge gained from the data collected using the motion sensors of a different device is used to initialize the model parameters. The performance of the model is assessed in terms of classification accuracy and prediction time for different sampling rates and transferring schemes. The model achieves an average accuracy of 87.18% when all the parameters are retrained with just 4 observations of each sign recorded from the motion sensors of the proposed IoT device. The recognized sign is transmitted to a cloud platform in real-time. A mobile application, SignTalk, is also developed, which wirelessly receives the predicted signs from the cloud and displays it as text. Additionally, text-to-speech conversion is also provided on SignTalk to vocalize the predicted sign for better communication.

A deep transfer learning approach to construct the allowable load space of notched composite laminates

Allowable load is one of the core parameters for the design and service of composite structures (CSs). However, due to the large design parameters, cumbersome design procedure and complicated simulation model of CSs, considerable amounts of experiments and simulations are needed to determine the allowable load of CSs, which is costly and inefficient, hindering the wide application of CSs in industry. In this work, we present a general deep transfer learning approach to construct the allowable load space (ALS) of notched laminates by considering various design parameters such as geometries, materials, stacking angles, ply numbers, laminate types and load types. Initially, an ensemble deep neural network (Ensemble) is trained, which can predict the allowable loads of notched laminate with known design parameters well. Here the Ensemble guided by ensemble learning is trained to reduce the errors generated by manually setting. Then, the pre-trained Ensemble is transferred to new design parameters by fine-tuning it with scarce new samples. Finally, the ALS of notch laminates is constructed by integrating the pre-trained and fine-tuned models, covering both known and diverse new design parameters. Our approach can easily be extended to other CSs.

Intelligent Caching Based on Popular Content in Vehicular Networks: A Deep Transfer Learning Approach

Intelligent Caching Based on Popular Content in Vehicular Networks: A Deep Transfer Learning Approach

Robust Remote Sensing Image Classification utilizing Multiverse Optimization Model with Deep Transfer Learning Approach

The classifying process of Remote Sensing Image (RSI) has been crucial in diverse applications, involving land cover mapping, environmental monitoring, disaster assessment, and urban planning. Conventionally, image classification in Remote Sensing (RS) relies on Machine Learning (ML) and handcrafted feature extraction approaches. But, lately, Deep Learning (DL) has become an effective and powerful method for RSI classification. DL algorithms, especially Convolutional Neural Network (CNN), have shown great performance in different Computer Vision (CV) tasks, involving image classification. This study proposes a Robust RSI Classification using Multiverse Optimization Algorithm with Deep Transfer Learning (RRSIC-MVO) model. The RRSIC-MVO technique exploits the DL with hyper-parameter selection mechanism to classify the RSI. In the presented RRSIC-MVO technique, the noise occurrence can be handled by joint bilateral filter (JBF). Following, MobileNetv3 model is applied for feature extractor and its hyper-parameters can be elected by the use of FA. Finally, soft-margin support vector machine (SM-SVM) model is applied for classification purposes. A series of investigations are accomplished on RS dataset for assessing the RRSIC-MVO model. The outputs demonstrate the effectiveness of RRSIC-MVO technique, outperforming traditional machine learning methods.

A Deep Transfer Learning Approach for Addressing Yaw Pose Variation to Improve Face Recognition Performance

A Deep Transfer Learning Approach for Addressing Yaw Pose Variation to Improve Face Recognition Performance

Empowering diagnosis: an astonishing deep transfer learning approach with fine tuning for precise lung disease classification from CXR images

A fast and precise diagnosis is crucial for the treatment and management of lung diseases, which are a major global cause of morbidity and mortality. Medical diagnosis and treatment planning depend heavily on the classification of lung diseases. The correct diagnosis and classification of many lung disease types is crucial for effective management and treatment. Radiologists with training evaluate medical images subjectively in order to classify lung diseases using traditional approaches. This paper proposed an effective technique for classifying lung diseases from CXR images. For the accurate classification of lung disorders, three distinct fine-tuned models are proposed. The effectiveness of the suggested fine-tuned models was evaluated using a newly developed CXR image dataset. According to the experimental findings, the proposed fine-tuned models outperformed the existing lung disease categorization models the accuracy is 98%. The suggested approach can effectively be used for lung disease classification.

Prediction of Hypoglycemia From Continuous Glucose Monitoring in Insulin-Treated Patients With Type 2 Diabetes Using Transfer Learning on Type 1 Diabetes Data: A Deep Transfer Learning Approach.

Hypoglycemia is common in insulin-treated type 2 diabetes (T2D) patients, which can lead to decreased quality of life or premature death. Deep learning models offer promise of accurate predictions, but data scarcity poses a challenge. This study aims to develop a deep learning model utilizing transfer learning to predict hypoglycemia. Continuous glucose monitoring (CGM) data from 226 patients with type 1 diabetes (T1D) and 180 patients with T2D were utilized. Data were structured into one-hour samples and labeled as hypoglycemia or not depending on whether three consecutive CGM values were below 3.9 [mmol/L] (70 mg/dL) one hour after the sample. A convolutional neural network (CNN) was pre-trained with the T1D data set and subsequently fitted using a T2D data set, all while being optimized toward maximizing the area under the receiver operating characteristics curve (AUC) value, and it was externally validated on a separate T2D data set. The developed model was externally validated with 334 711 one-hour CGM samples, of which 15 695 (4.69%) were labeled as hypoglycemic. The model achieved an AUC of 0.941 and a positive predictive value of 40.49% at a specificity of 95% and a sensitivity of 69.16%. The transfer learned CNN model showed promising performance in predicting hypoglycemic episodes and with slightly better results than a non-transfer learned CNN model.