Deep Transfer Learning based Fusion Model for Environmental Remote Sensing Image Classification Model

Tuberculosis (TB) remains a leading infectious disease worldwide, and early, reliable screening using chest X-rays (CXRs) is essential in low-resource settings. The scarcity of labeled TB-positive CXR images limits the effectiveness of deep learning models. This study investigates whether Conditional Generative Adversarial Networks (CGANs) can generate realistic TB-positive CXR images to balance training data and improve the classification performance of fine-tuned deep transfer learning (DTL) models. We trained a CGAN (LSGAN formulation) to synthesize class-conditional grayscale CXR images at 128x128 resolution and used the generated images to augment the Shenzhen TB dataset. Three pre-trained DTL architectures (DenseNet121, VGG16, and MobileNetV3Small) were fine-tuned on both original and CGAN-augmented datasets. Experiments used stratified 70/10/20 train/validation/test splits and a fixed random seed (random_state=42) to ensure reproducibility. Model performance was evaluated using accuracy, precision, recall (sensitivity), F1-score, confusion matrices, and ROC/AUC curves. The experiments were executed on an NVIDIA Tesla P100 GPU (16GB) in a Kaggle runtime environment; total CGAN+classifier processing reported a wall-clock runtime of 39 minutes 30 seconds for the baseline experimental run. CGAN augmentation produced consistent improvements across models: DenseNet121 improved from 93.0% to 94.6% test accuracy, VGG16 improved from 96.3% to 96.8%, and MobileNetV3Small improved from 93.0% to 93.5%. Class-conditional GAN augmentation can modestly but usefully improve DTL classifier performance in TB detection when labeled data are scarce, though further cross-dataset validation is required before clinical deployment.

Electricity load forecasting is a crucial undertaking within all the deregulated markets globally. Among the research challenges on a global scale, the investigation of deep transfer learning (DTL) in the field of electricity load forecasting represents a fundamental effort that can inform artificial intelligence applications in general. In this paper, a comprehensive study is reported regarding day-ahead electricity load forecasting. For this purpose, three sequence-to-sequence (Seq2seq) deep learning (DL) models are used, namely the multilayer perceptron (MLP), the convolutional neural network (CNN) and the ensemble learning model (ELM), which consists of the weighted combination of the outputs of MLP and CNN models. Also, the study focuses on the development of different forecasting strategies based on DTL, emphasizing the way the datasets are trained and fine-tuned for higher forecasting accuracy. In order to implement the forecasting strategies using deep learning models, load datasets from three Greek islands, Rhodes, Lesvos, and Chios, are used. The main purpose is to apply DTL for day-ahead predictions (1–24 h) for each month of the year for the Chios dataset after training and fine-tuning the models using the datasets of the three islands in various combinations. Four DTL strategies are illustrated. In the first strategy (DTL Case 1), each of the three DL models is trained using only the Lesvos dataset, while fine-tuning is performed on the dataset of Chios island, in order to create day-ahead predictions for the Chios load. In the second strategy (DTL Case 2), data from both Lesvos and Rhodes concurrently are used for the DL model training period, and fine-tuning is performed on the data from Chios. The third DTL strategy (DTL Case 3) involves the training of the DL models using the Lesvos dataset, and the testing period is performed directly on the Chios dataset without fine-tuning. The fourth strategy is a multi-task deep learning (MTDL) approach, which has been extensively studied in recent years. In MTDL, the three DL models are trained simultaneously on all three datasets and the final predictions are made on the unknown part of the dataset of Chios. The results obtained demonstrate that DTL can be applied with high efficiency for day-ahead load forecasting. Specifically, DTL Case 1 and 2 outperformed MTDL in terms of load prediction accuracy. Regarding the DL models, all three exhibit very high prediction accuracy, especially in the two cases with fine-tuning. The ELM excels compared to the single models. More specifically, for conducting day-ahead predictions, it is concluded that the MLP model presents the best monthly forecasts with MAPE values of 6.24% and 6.01% for the first two cases, the CNN model presents the best monthly forecasts with MAPE values of 5.57% and 5.60%, respectively, and the ELM model achieves the best monthly forecasts with MAPE values of 5.29% and 5.31%, respectively, indicating the very high accuracy it can achieve.

Sustainability has become a key factor on our planet. If this concept is applied correctly, our planet will be greener and more eco-friendly. Nowadays, waste classification and management practices have become more evident than ever. It plays a crucial role in the sustainability ecosystem. Computer algorithms and deep learning can help in this sustainability challenge. In this paper, An Optimized Neutrosophic Deep Learning (ONDL) model was proposed to classify waste objects. Two datasets were tested in this research {Dataset for Waste Management 1 (DSWM1), and Dataset for Waste Management 2 (DSWM2)}. DSWM1 consists of two classes (Organic or Recycled) objects. The DSWM2 consists of three classes (Organic, Recycled, or Non-Recyclable) objects. Both datasets exist publicly on the internet. The ONDL model architecture is constructed based on Alexnet as a Deep Transfer Learning (DTL) model and the conversion of images to True (T) neutrosophic domain and Grey Wolf Optimization (GWO) for the image features selection. The selection process of the building components of the ONDL model is comprehensive as different DTL models (Alexnet, Googlenet, and Resnet18) are tested, and three neutrosophic domains (T, I, and F) domain are included. The ONDL model proved its efficiency against all the tested models, moreover, it achieves competitive results with related works in terms of testing accuracy and performance metrics. In DSWM1, the ONDL model achieved 0.9189, 0.9177, 0.9176, and 0.9177 in Testing Accuracy (TA), Precision (P), Recall (R), and F1 score. In DSWM2, it achieved 0.8532, 0.7728, 0.7944, and 0.7835 in TA, P, R, and F1 Score consequently.

Multimodal deep transfer learning to predict retinal vein occlusion macular edema recurrence after anti-VEGF therapy

Precise underwater classification of small aquaculture species is essential for sustainable fisheries management, biodiversity monitoring, and automated marine ecosystem analysis. But it is still a challenging task owing to underwater image distortions from poor visibility, lighting changes, occlusions, and the high computational complexity of traditional deep learning models. To address these issues, we propose a Lightweight Variational Quantum Enhanced Deep Transfer Learning framework. This hybrid deep transfer learning model integrates pretrained classical convolutional neural networks with variational quantum circuits to improve feature representation and classification efficiency. The framework is designed to reduce computational complexity while enhancing accuracy by leveraging quantum feature extraction techniques. Experimental evaluations on curated small aquafarming species dataset demonstrate that the proposed approach achieves high classification accuracy (up to 99.25%) with significantly fewer parameters and floating-point operations, indicating its potential for resource-constrained applications. Ablation studies further validate the impact of quantum layers on model performance. These results suggest that quantum deep transfer learning models can offer a promising direction for robust and efficient underwater species classification.

PurposeTo differentiate complicated appendicitis (CA) from uncomplicated appendicitis (UA) in children, we developed and validated an artificial intelligence (AI) model using a multimodal approach integrating ultrasound images and clinical data.MethodsA retrospective analysis was performed on 372 pathologically confirmed pediatric appendicitis cases (230 male, 142 female) from three centers, all with preoperative abdominal ultrasound. Deep learning (DL) features and radiomic features were extracted from appendiceal ultrasound images using deep transfer learning (DTL) and conventional radiomic methods, respectively. We selected 12 radiomic features, 9 DL features, and 3 clinical features—namely, white blood cell count (WBC), neutrophil count (NEU), and C-reactive protein (CRP)—for building the machine learning classification model. Based on these features, four distinct models were constructed: the Rad model (radiomic features only), the DL model (DL features only), the DTL model (combined radiomic and DL features), and the Combine model (integrating all three feature types: radiomic, DL, and clinical features). Model performance was evaluated using receiver operating characteristic (ROC) curves, decision curve analysis (DCA), and the DeLong test. Finally, the combined model was compared to the performance of clinicians with varying levels of experience.ResultsThe combined model demonstrated consistently favorable performance across all cohorts (AUC: 0.940, 0.895, 0.866, and 0.783 for training and validation sets, respectively). The model's accuracy (0.862) and positive predictive value (0.896) were comparable to senior surgeons (0.741, 0.970) and superior to junior surgeons (0.672, 0.865) in the internal validation cohort. DCA confirmed the clinical utility of the combined model over conventional strategies.ConclusionOur ultrasound-based AI model provides reliable differentiation between CA and UA in children, offering potential value as a diagnostic support tool for clinical decision making.

Coronavirus disease-19 (COVID-19) has rapidly spread all over the world. It is found that the low sensitivity of reverse transcription-polymerase chain reaction (RT-PCR) examinations during the early stage of COVID-19 disease. Thus, efficient models are desirable for early-stage testing of COVID-19 infected patients. Chest X-ray (CXR) images of COVID-19 infected patients have shown some bilateral changes. In this paper, deep transfer learning and a deep forest-based model are proposed to diagnose COVID-19 infection from CXR images. Initially, features of X-ray images are extracted using the well-known deep transfer learning model (i.e., ResNet101), which does not require tuning many parameters compared to the deep convolutional neural network (CNN). After that, the deep forest model is utilised to predict COVID-19 infected patients. The deep forest is based upon ensemble learning and requires a small number of hyper-parameters. Additionally, the proposed model is trained on a multi-class dataset that contains four different classes as COVID-19 (+), pneumonia, tuberculosis, and healthy patients. The comparisons are drawn among the proposed deep transfer learning and deep forest-based models, the competitive models. The obtained results show that the proposed model effectively diagnoses COVID-19 infection with an accuracy of 99.4%.

Face recognition is widely used as identity authentication method in the Internet of Things (IoTs). However, compared with static camera, the background of IoT devices may change. Additionally, the facial expression or posture may change as well. Although face recognition has been researched for several decades, it is still a challenging task to design a robust face recognition system in IoT environment. This paper designs a special face recognition system by introducing deep transfer learning to adapt difference scenes in IoT environment. The face recognition system consists of two parts: terminal smart devices and cloud center. The terminal smart device consists of a camera to capture face picture, a wireless network part to communicate with cloud center, and a screen to show recognition result. The cloud center receives the face picture from terminal smart device and returns the face recognition result by using an offline deep transfer learning model. Compared with previous models, deep transfer learning model can better adapt different scenes. The experiments shows that the proposed face recognition system achieves more promising results than two source‐only models and two shallow transfer learning models.

Background: The accurate classification between malignant and benign breast lesions detected on mammograms is a crucial but difficult challenge for reducing false-positive recall rates and improving the efficacy of breast cancer screening. Objective: This study aims to optimize a new deep transfer learning model by implementing a novel attention mechanism in order to improve the accuracy of breast lesion classification. Methods: ResNet50 is selected as the base model to develop a new deep transfer learning model. To enhance the accuracy of breast lesion classification, we propose adding a convolutional block attention module (CBAM) to the standard ResNet50 model and optimizing a new model for this task. We assembled a large dataset with 4280 mammograms depicting suspicious soft-tissue mass-type lesions. A region of interest (ROI) is extracted from each image based on lesion center. Among them, 2480 and 1800 ROIs depict verified benign and malignant lesions, respectively. The image dataset is randomly split into two subsets with a ratio of 9:1 five times to train and test two ResNet50 models with and without using CBAM. Results: Using the area under ROC curve (AUC) as an evaluation index, the new CBAM-based ResNet50 model yields AUC = 0.866 ± 0.015, which is significantly higher than that obtained by the standard ResNet50 model (AUC = 0.772 ± 0.008) (p < 0.01). Conclusion: This study demonstrates that although deep transfer learning technology attracted broad research interest in medical-imaging informatic fields, adding a new attention mechanism to optimize deep transfer learning models for specific application tasks can play an important role in further improving model performances.

This study aimed to present an analysis of deep transfer learning models to support the early diagnosis of Covid-19 disease using X-ray images. For this purpose, the deep transfer learning models VGG-16, VGG-19, Inception V3 and Xception, which were successful in the ImageNet competition, were used to detect Covid-19 disease. Also, 280 chest x-ray images were used for the training data, and 140 chest x-ray images were used for the test data. As a result of the statistical analysis, the most successful model was Inception V3 (%92), the next successful model was Xception (%91), and the VGG-16 and VGG-19 models gave the same result (%88). The proposed deep learning model offers significant advantages in diagnosing covid-19 disease issues such as test costs, test accuracy rate, staff workload, and waiting time for test results.

Coronavirus, also known as COVID-19, has spread to several countries around the world. It was announced as a pandemic disease by The World Health Organization (WHO) in 2020 for its devastating impact on humans. With the advancements in computer science algorithms, the detection of this type of virus in the early stages is urgently needed for the fast recovery of patients. In this paper, a study of neutrosophic set significance on deep transfer learning models will be presented. The study will be conducted over a limited COVID-19 x-ray. The study relies on neutrosophic set and theory to convert the medical images from the grayscale spatial domain to the neutrosophic domain. The neutrosophic domain consists of three types of images, and they are the True (T) images, the Indeterminacy (I) images, and the Falsity (F) images. The dataset used in this research has been collected from different sources. The dataset is classified into four classes {COVID-19, normal, pneumonia bacterial, and pneumonia virus}. This study aims to review the effect of neutrosophic sets on deep transfer learning models. The selected deep learning models in this study are Alexnet, Googlenet, and Restnet18. Those models are selected as they have a small number of layers on their architectures. To test the performance of the conversion to the neutrosophic domain, more than 36 trials have been conducted and recorded. A combination of training and testing strategies by splitting the dataset into (90–10%, 80–20%, 70–30) is included in the experiments. Four domains of images are tested, and they are, the original domain, the True (T) domain, the Indeterminacy (I) domain, and the Falsity (F) domain. The four domains with the different training and testing strategies were tested using the selected deep transfer models. According to the experimental results, the Indeterminacy (I) neutrosophic domain achieves the highest accuracy possible with 87.1% in the testing accuracy and performance metrics such as Precision, Recall, and F1 Score. The study concludes that using the neutrosophic set with deep learning models may be an encouraging transition to achieve better testing accuracy, especially with limited COVID-19 datasets.

Brain Tumor is a deadly diagnosis that, if not detected early on, can cause significant damage to a patient’s brain, disrupting the body’s functions and even leading to death. However, the conventional method of detecting brain tumors is conducting MRI scans which a medical expert then consults for diagnosis. While time-consuming, this method also leaves room for human error, especially in cases where the tumor is in its early stages. Thus, the diagnosis of brain tumors must be made accurately in the least time possible. This paper aims to prevent premature mortality, provide health in resource-constrained settings, and seek patients’ healthy lives, which can be done through timely and accurate diagnosis of brain tumors. In this paper, three different deep transfer learning models are used after adding fine-tuned layers to detect brain tumors in a dataset of 251 Magnetic Resonance Imaging (MRI) scans. The transfer learning models used are VGG16, InceptionV3, and ResNet50, with fine-tuned Dropout, Flatten, and Dense added layers. The highest accuracy was achieved with the VGG16 model, which had an accuracy of 91.58%. Thus, deep learning models are proven effective in detecting brain tumors without the unwanted expense of time and resources.

We aimed at comparing intratumoral and peritumoral deep learning, radiomics, and fusion models in predicting KRAS mutations in rectal cancer using endorectal ultrasound imaging. This study included 304 patients with rectal cancer from Fujian Medical University Union Hospital. The patients were randomly divided into a training group (213 patients) and a test group (91 patients) at a 7:3 ratio. Radiomics and deep learning models were established using primary tumor and peritumoral images. In the optimally performing regions-of-interest, two fusion strategies, a feature-based and a decision-based model, were employed to build the fusion models. The Shapley additive explanation (SHAP) method was used to evaluate the significance of features in the optimal radiomics, deep learning, and fusion models. The performance of each model was assessed using the area under the receiver operating characteristic curve (AUC) and decision curve analysis (DCA). In the test cohort, both the radiomics and deep learning models exhibited optimal performance with a 10-pixel patch extension, yielding AUC values of 0.824 and 0.856, respectively. The feature-based DLRexpand10_FB model attained the highest AUC (0.896) across all study sets. In addition, the DLRexpand10_FB model demonstrated excellent sensitivity, specificity, and DCA. SHAP analysis underscored the deep learning feature (DL_1) as the most significant factor in the hybrid model. The feature-based fusion model DLRexpand10_FB can be employed to predict KRAS gene mutations based on pretreatment endorectal ultrasound images of rectal cancer. The integration of peritumoral regions enhanced the predictive performance of both the radiomics and deep learning models.

Health state estimation of cutting tools is a key component for maintaining the reliability and stability of the manufacturing process. Although deep learning (DL) based tool wear indirect monitoring methods have been presented, most of them require a substantial amount of data to avoid high misclassification rates. To this end, this article proposes a novel estimation approach based on data-enhanced deep transfer learning (TL) methodology, which integrates multivariate data enhancements, deep convolution network, and generative adversarial learning for state assessment of the tool wear under small sample size. The proposed method includes three innovative points: 1) a multi-step data enhancement method is employed to augment the wavelet scalogram data as model input; 2) a novel training process is adopted to obtain optimal hyperparameters of TL-AlexNet and TL-VGGNet-16 model; 3) a deep transfer learning model for the enhanced data is presented to adaptively estimate the health state of the cutting tools. The proposed approach only requires a small quantity of data to achieve satisfactory estimation performance compared with other DL methods through experimental validation, and the average prediction accuracy for each stage is greater than 95%, which demonstrates the effectiveness and superiority of the presented model.

Hepatocyte proteome destabilization and novel targets for PFASs unveiled through combined thermal proteome profiling and deep transfer learning.