Deep Learning Models Research Articles

ZooCNN: A Zero-Order Optimized Convolutional Neural Network for Pneumonia Classification Using Chest Radiographs

Pneumonia, a leading cause of mortality in children under five, is usually diagnosed through chest X-ray (CXR) images due to its efficiency and cost-effectiveness. However, the shortage of radiologists in the Least Developed Countries (LDCs) emphasizes the need for automated pneumonia diagnostic systems. This article presents a Deep Learning model, Zero-Order Optimized Convolutional Neural Network (ZooCNN), a Zero-Order Optimization (Zoo)-based CNN model for classifying CXR images into three classes, Normal Lungs (NL), Bacterial Pneumonia (BP), and Viral Pneumonia (VP); this model utilizes the Adaptive Synthetic Sampling (ADASYN) approach to ensure class balance in the Kaggle CXR Images (Pneumonia) dataset. Conventional CNN models, though promising, face challenges such as overfitting and have high computational costs. The use of ZooPlatform (ZooPT), a hyperparameter finetuning strategy, on a baseline CNN model finetunes the hyperparameters and provides a modified architecture, ZooCNN, with a 72% reduction in weights. The model was trained, tested, and validated on the Kaggle CXR Images (Pneumonia) dataset. The ZooCNN achieved an accuracy of 97.27%, a sensitivity of 97.00%, a specificity of 98.60%, and an F1 score of 97.03%. The results were compared with contemporary models to highlight the efficacy of the ZooCNN in pneumonia classification (PC), offering a potential tool to aid physicians in clinical settings.

Smart Defect Detection in Aero-Engines: Evaluating Transfer Learning with VGG19 and Data-Efficient Image Transformer Models

This study explores the impact of transfer learning on enhancing deep learning models for detecting defects in aero-engine components. We focused on metrics such as accuracy, precision, recall, and loss to compare the performance of models VGG19 and DeiT (data-efficient image transformer). RandomSearchCV was used for hyperparameter optimization, and we selectively froze some layers during training to help better tailor the models to our dataset. We conclude that the difference in performance across all metrics can be attributed to the adoption of the transformer-based architecture by the DeiT model as it does this well in capturing complex patterns in data. This research demonstrates that transformer models hold promise for improving the accuracy and efficiency of defect detection within the aerospace industry, which will, in turn, contribute to cleaner and more sustainable aviation activities.

Class-Patch Similarity Weighted Embedding for Few-Shot Infrared Image Classification

Infrared imaging plays a vital role in critical surveillance, military reconnaissance, and industrial inspection applications due to its advantages such as strong concealment and the ability to operate around the clock. However, the combination of low infrared image resolution and complex background scenarios poses significant challenges for traditional deep learning models in accurately extracting the most discriminative features for classification. These models are often disrupted by irrelevant features, especially when data for new classes is scarce. Current few-shot learning approaches heavily rely on comparing image patches, but the scarcity of data can significantly degrade the performance of recognition algorithms. To address these challenges, we propose the Class Patch Similarity Weighted Embedding (CPSWE) framework for few-shot infrared target classification. The CPSWE framework employs a ViT architecture for feature extraction. By introducing class embeddings and calculating similarity-based weights for each patch, CPSWE reweights the patch features to enhance their relevance to the target class. This approach improves the discriminability of class-related features, leading to better generalization in few-shot settings. Furthermore, we introduce an infrared dataset specifically designed for few-shot learning, combining multiple open-source datasets to support research in this area. Extensive experiments on the few-shot learning benchmark dataset miniImageNet and the infrared dataset miniIRNet show that CPSWE outperforms existing few-shot learning methods, achieving significant improvements in classification accuracy on infrared image datasets with limited labeled samples.

FundusNet: A Deep-Learning Approach for Fast Diagnosis of Neurodegenerative and Eye Diseases Using Fundus Images

Early-stage detection of neurodegenerative diseases is crucial for effective clinical treatment. However, current diagnostic methods are expensive and time-consuming. In this study, we present FundusNet, a deep-learning model trained on fundus images, for rapid and cost-effective diagnosis of neurodegenerative diseases. FundusNet achieved superior performance in age prediction (MAE 2.55 year), gender classification (AUC 0.98), and neurodegenerative disease diagnosis—Parkinson’s disease AUC 0.75 ± 0.03, multiple sclerosis AUC 0.77 ± 0.02. Grad-CAM was used to identify which part of the image contributes to diagnosis. Imaging biomarker interpretation demonstrated that FundusNet effectively identifies clinical retina structures associated with diseases. Additionally, the model’s high accuracy in predicting genetic risk suggests that its performance could be further enhanced with larger training datasets.

Deep Learning and Automatic Detection of Pleomorphic Esophageal Lesions—A Necessary Step for Minimally Invasive Panendoscopy

Background: Capsule endoscopy (CE) improved the digestive tract assessment; yet, its reading burden is substantial. Deep-learning (DL) algorithms were developed for the detection of enteric and gastric lesions. Nonetheless, their application in the esophagus lacks evidence. The study aim was to develop a DL model for esophageal pleomorphic lesion (PL) detection. Methods: A bicentric retrospective study was conducted using 598 CE exams. Three different CE devices provided 7982 esophageal frames, including 2942 PL lesions. The data were divided into the training/validation and test groups, in a patient-split design. Three runs were conducted, each with unique patient sets. The sensitivity, specificity, accuracy, positive and negative predictive value (PPV and NPV), area under the conventional receiver operating characteristic curve (AUC-ROC), and precision–recall curve (AUC-PR) were calculated per run. The model’s diagnostic performance was assessed using the median and range values. Results: The median sensitivity, specificity, PPV, and NPV were 75.8% (63.6–82.1%), 95.8% (93.7–97.9%), 71.9% (50.0–90.1%), and 96.4% (94.2–97.6%), respectively. The median accuracy was 93.5% (91.8–93.8%). The median AUC-ROC and AUC-PR were 0.82 and 0.93. Conclusions: This study focused on the automatic detection of pleomorphic esophageal lesions, potentially enhancing the diagnostic yield of this type of lesion, compared to conventional methods. Specific esophageal DL algorithms may provide a significant contribution and bridge the gap for the implementation of minimally invasive CE-enhanced panendoscopy.

Artificial Intelligence for Cervical Spine Fracture Detection: A Systematic Review of Diagnostic Performance and Clinical Potential.

Systematic review. Artificial intelligence (AI) and deep learning (DL) models have recently emerged as tools to improve fracture detection, mainly through imaging modalities such as computed tomography (CT) and radiographs. This systematic review evaluates the diagnostic performance of AI and DL models in detecting cervical spine fractures and assesses their potential role in clinical practice. A systematic search of PubMed/Medline, Embase, Scopus, and Web of Science was conducted for studies published between January 2000 and July 2024. Studies that evaluated AI models for cervical spine fracture detection were included. Diagnostic performance metrics were extracted and included sensitivity, specificity, accuracy, and area under the curve. The PROBAST tool assessed bias, and PRISMA criteria were used for study selection and reporting. Eleven studies published between 2021 and 2024 were included in the review. AI models demonstrated variable performance, with sensitivity ranging from 54.9% to 100% and specificity from 72% to 98.6%. Models applied to CT imaging generally outperformed those applied to radiographs, with convolutional neural networks (CNN) and advanced architectures such as MobileNetV2 and Vision Transformer (ViT) achieving the highest accuracy. However, most studies lacked external validation, raising concerns about the generalizability of their findings. AI and DL models show significant potential in improving fracture detection, particularly in CT imaging. While these models offer high diagnostic accuracy, further validation and refinement are necessary before they can be widely integrated into clinical practice. AI should complement, rather than replace, human expertise in diagnostic workflows.

A method for enhancing the accuracy of industrial bearing surface defect detection

ABSTRACT Deep learning models often encounter challenges when detecting surface defects on industrial bearings, including inaccurate feature extraction caused by random shapes and multi-scale defects, as well as high leakage rates of small objects in complex multi-object scenes. To address these challenges, a YOLOv8n-based method (YOLOv8-IWDD) is proposed for detecting bearing surface defects. Firstly, the ImplicitHead detection head is introduced, which utilises implicit addition and multiplication to highlight key features. This enhancement improves feature extraction, resulting in improved detection accuracy for small objects, especially in complex multi-object scenarios, and effectively reduces missed detections. Secondly, the Inner-WIoU loss function optimises bounding box localisation, enabling the model to better handle randomly shaped defects, accelerate convergence, and enhance localisation accuracy. In addition, dynamic label assignment and dynamic sampling strategies are proposed to achieve flexible adjustment of sample assignment and sampling method, which further improves the detection accuracy and robustness. These strategies enhance the model’s robustness in handling multi-scale and complex shape defects. The experimental results show that YOLOv8-IWDD improves mAP0.5 by 2.9%, mAP0.5:0.95 by 9.4%, precision by 2.2%, and recall by 6.5% compared with the YOLOv8n model. The method achieves promising results in detecting surface defects on industrial bearings.

A Smart Camera With Integrated Deep Learning Processing for Disease Detection in Open Field Crops of Grape, Apple, and Carrot

ABSTRACTDowny mildew (Plasmopara), apple scab (Venturia inaequalis), and Alternaria leaf blight are endemic diseases that affect crops worldwide. The diseases can cause severe losses in grapes, apples and carrots when not detected and treated in an early stage. The European Union Horizon 2020 OPTIMA project aimed to improve disease detection in the open field with an automated detection system as part of an integrated pest management (IPM) system. In this research, we investigated the automated detection of downy mildew in grape, apple scab in apple and Alternaria leaf blight in carrot, using a deep convolutional neural network (CNN) on RGB color images. Detections from the CNN served as input to a Decision Support System (DSS), to precisely locate and quantify the disease, so that appropriate and timely application of plant protection products could be recommended. The focus of our study was on a smart camera implementation with integrated deep‐learning processing in real‐field conditions. The question was whether the deep learning model, when trained on images of disease symptoms recorded in conditioned circumstances, can also perform on images of disease symptoms recorded in field conditions. This type of evaluation is called open‐set evaluation, and so far it has received little attention in plant disease detection research. Therefore, the goal of our research was to evaluate the performance of a deep learning model in an open‐set evaluation scenario in commercial vineyards, orchards, and open fields. The model's performance in the open‐set scenario was compared to its performance in the closed‐set scenario, which involved evaluating the trained model on images similar to those used for model training. Our results showed that the model's performance in the closed‐set scenario with F1 scores of 66.3% (downy mildew), 45.1% (apple scab), and 42.1% (Alternaria) was notably better than in the open‐set scenario, with F1 scores of 34.8% (downy mildew), 5.5% (apple scab) and 4.2% (Alternaria). Uniform Manifold Approximation and Projection (UMAP) analysis proved the significant difference between the open‐set and closed‐set data sets. Our result should encourage other researchers to carry out similar open‐set evaluations to get realistic impressions of their model's performance under field conditions. A subset of our image data set has been made publicly available at https://doi.org/10.5281/zenodo.6778647.

Human Identification System using Images

The present study focuses on the challenges of human long-range recognition with deep learning, and AlexNet performance is considered, being one of the most recognized convolutional neural networks. A specially curated dataset was used to mimic the real world in a more practical and realistic scenario, which involves subjects varying in distances and angles while creating low-resolution issues with variability in lighting and distractions from the environment. The system starts by passing the input dataset through a local Laplacian filter that is utilized to enhance the quality of images before feeding it into a pre-trained AlexNet model. The results reveal that AlexNet reaches a recognition accuracy of 65% and shows that image properties such as sharpness and contrast significantly affect performance, as measured by the mean and standard deviation. The study underlines requirements of high-quality images for applications in long-range human recognition and sheds insight into the ways enhancements in images could improve performance in deep learning models. Results support further evolution of more potent human recognition systems, particularly in application domains such as surveillance and security in which the accurate identification of a target from a long distance is highly critical. Key Words: Long-range recognition, Human recognition, Deep learning, Image processing

Semaphore Recognition Using Deep Learning

This study explored the application of deep learning models for signal flag recognition, comparing YOLO11 with basic CNN, ResNet18, and DenseNet121. Experimental results demonstrated that YOLO11 outperformed the other models, achieving superior performance across all common evaluation metrics. The confusion matrix further confirmed that YOLO11 exhibited the highest classification accuracy among the tested models. Moreover, by integrating MediaPipe’s human posture data with image data to create multimodal inputs for training, it was observed that the posture data significantly enhanced the model’s performance. Leveraging MediaPipe’s posture data for annotation generation and model training enabled YOLO11 to achieve an impressive 99% accuracy on the test set. This study highlights the effectiveness of YOLO11 for flag signal recognition tasks. Furthermore, it demonstrates that when handling tasks involving human posture, MediaPipe not only enhances model performance through posture feature data but also facilitates data processing and contributes to validating prediction results in subsequent stages.

Dynamic Spatial–Temporal Graph Neural Network for Cooling Capacity Prediction in HVDC Systems

Predicting the cooling capacity of converter valves is crucial for maintaining the stability and efficiency of high-voltage direct current (HVDC) systems. This task involves handling complex, multi-dimensional time-series data with strong inter-variable dependencies and temporal dynamics. Traditional machine learning methods, while effective in static scenarios, struggle to capture these dependencies, and existing deep learning models often lack the ability to jointly model spatial and temporal relationships. To address these challenges, we propose a novel framework that integrates Graph Neural Networks (GNNs) with temporal dynamics. The GNN component captures spatial dependencies by representing the data as a graph, where nodes correspond to system variables, and edges encode their relationships. Temporal dependencies are modeled using temporal convolutional layers and recurrent neural networks (RNNs), enabling the framework to learn both short-term variations and long-term trends. Additionally, a graph attention mechanism dynamically adjusts the importance of variable relationships, improving prediction accuracy and interoperability. The proposed method demonstrates superior performance over traditional machine learning and deep learning baselines on real-world cooling system data. These results validate the effectiveness of the framework for industrial applications such as cooling system monitoring and predictive maintenance.

Using Hybrid Deep Learning Models to Predict Dust Storm Pathways with Enhanced Accuracy

As a potential consequence of climate change, the intensity and frequency of dust storms are increasing. A dust storm arises when strong winds blow loose dust from a dry surface, transporting soil particles from one place to another. The environmental and human health impacts of dust storms are substantial. Accordingly, studying the monitoring of this phenomenon and predicting its pathways for early decision making and warning are vital. This study employs deep learning methods to predict dust storm pathways. Specifically, hybrid CNN-LSTM and ConvLSTM models have been proposed for the 24 h-ahead prediction of dust storms in the region under study. The Modern-Era Retrospective Analysis for Research and Applications version 2 (MERRA-2) product that includes the dust particles and the meteorological information, such as surface wind speed and direction, relative humidity, surface air temperature, and skin temperature, is used to train the proposed models. These contextual features are selected utilizing the random forest feature importance method. The results indicate an improvement in the performance of both models by considering the contextual information. Moreover, a 0.2 increase in the Kappa coefficient criterion across all forecast hours indicates the CNN-LSTM model outperforms the ConvLSTM model when contextual information is considered.

Intelligent skin disease prediction system using transfer learning and explainable artificial intelligence

Skin diseases impact millions of people around the world and pose a severe risk to public health. These diseases have a wide range of effects on the skin’s structure, functionality, and appearance. Identifying and predicting skin diseases are laborious processes that require a complete physical examination, a review of the patient’s medical history, and proper laboratory diagnostic testing. Additionally, it necessitates a significant number of histological and clinical characteristics for examination and subsequent treatment. As a disease’s complexity and quantity of features grow, identifying and predicting it becomes more challenging. This research proposes a deep learning (DL) model utilizing transfer learning (TL) to quickly identify skin diseases like chickenpox, measles, and monkeypox. A pre-trained VGG16 is used for transfer learning. The VGG16 can identify and predict diseases more quickly by learning symptom patterns. Images of the skin from the four classes of chickenpox, measles, monkeypox, and normal are included in the dataset. The dataset is separated into training and testing. The experimental results performed on the dataset demonstrate that the VGG16 model can identify and predict skin diseases with 93.29% testing accuracy. However, the VGG16 model does not explain why and how the system operates because deep learning models are black boxes. Deep learning models’ opacity stands in the way of their widespread application in the healthcare sector. In order to make this a valuable system for the health sector, this article employs layer-wise relevance propagation (LRP) to determine the relevance scores of each input. The identified symptoms provide valuable insights that could support timely diagnosis and treatment decisions for skin diseases.

UniAMP: enhancing AMP prediction using deep neural networks with inferred information of peptides

Antimicrobial peptides (AMPs) have been widely recognized as a promising solution to combat antimicrobial resistance of microorganisms due to the increasing abuse of antibiotics in medicine and agriculture around the globe. In this study, we propose UniAMP, a systematic prediction framework for discovering AMPs. We observe that feature vectors used in various existing studies constructed from peptide information, such as sequence, composition, and structure, can be augmented and even replaced by information inferred by deep learning models. Specifically, we use a feature vector with 2924 values inferred by two deep learning models, UniRep and ProtT5, to demonstrate that such inferred information of peptides suffice for the task, with the help of our proposed deep neural network model composed of fully connected layers and transformer encoders for predicting the antibacterial activity of peptides. Evaluation results demonstrate superior performance of our proposed model on both balanced benchmark datasets and imbalanced test datasets compared with existing studies. Subsequently, we analyze the relations among peptide sequences, manually extracted features, and automatically inferred information by deep learning models, leading to observations that the inferred information is more comprehensive and non-redundant for the task of predicting AMPs. Moreover, this approach alleviates the impact of the scarcity of positive data and demonstrates great potential in future research and applications.

A benchmark of deep learning approaches to predict lung cancer risk using national lung screening trial cohort

Deep learning (DL) methods have demonstrated remarkable effectiveness in assisting with lung cancer risk prediction tasks using computed tomography (CT) scans. However, the lack of comprehensive comparison and validation of state-of-the-art (SOTA) models in practical settings limits their clinical application. This study aims to review and analyze current SOTA deep learning models for lung cancer risk prediction (malignant-benign classification). To evaluate our model’s general performance, we selected 253 out of 467 patients from a subset of the National Lung Screening Trial (NLST) who had CT scans without contrast, which are the most commonly used, and divided them into training and test cohorts. The CT scans were preprocessed into 2D-image and 3D-volume formats according to their nodule annotations. We evaluated ten 3D and eleven 2D SOTA deep learning models, which were pretrained on large-scale general-purpose datasets (Kinetics and ImageNet) and radiological datasets (3DSeg-8, nnUnet and RadImageNet), for their lung cancer risk prediction performance. Our results showed that 3D-based deep learning models generally perform better than 2D models. On the test cohort, the best-performing 3D model achieved an AUROC of 0.86, while the best 2D model reached 0.79. The lowest AUROCs for the 3D and 2D models were 0.70 and 0.62, respectively. Furthermore, pretraining on large-scale radiological image datasets did not show the expected performance advantage over pretraining on general-purpose datasets. Both 2D and 3D deep learning models can handle lung cancer risk prediction tasks effectively, although 3D models generally have superior performance than their 2D competitors. Our findings highlight the importance of carefully selecting pretrained datasets and model architectures for lung cancer risk prediction. Overall, these results have important implications for the development and clinical integration of DL-based tools in lung cancer screening.

Optimized Deep Learning Model for Predicting Liver Metastasis in Colorectal Cancer Patients

Colorectal cancer is a leading type of cancer worldwide and a major contributor to cancer fatalities, and liver metastasis is the most likely distant metastasis in colorectal cancer patients. Classifying and predicting whether liver metastasis occurs in colorectal cancer patients can help doctors timely determine the progress of the disease and form a more reasonable treatment plan, which results in a better prognosis for patients. In this paper, using the Surveillance, Epidemiology, and End Results database, selecting both symmetric and asymmetric features, we extracted the disease-related data of 40,870 patients who were pathologically diagnosed with colorectal cancer from 2010 to 2015 and classified and modeled whether the patients developed liver metastasis to show the symmetry of this study. A total of six deep learning models were utilized, and hyperparameter optimization was performed on the models using the Crested Porcupine Optimizer. The best-performing model was selected and model interpretation was performed to explore the features that affect whether patients develop liver metastasis. Among the six deep learning models selected, the FT-Transformer model, which was hyperparameter optimized by the Crested Porcupine Optimizer, performed the best, with an accuracy of 0.945, with a 95% confidence interval (CI) of [0.942, 0.952], and an AUC of 0.949, with a 95% CI of [0.942, 0.957]. This study can help doctors make medical decisions, detect patients with liver metastases of colorectal cancer earlier, monitor the indicators that have a significant impact on the occurrence of liver metastasis in patients, and use timely surgical treatment, radiotherapy, chemotherapy, and other corresponding therapeutic interventions to improve the survival rate of patients.

Development of a model for measuring sagittal plane parameters in 10–18-year old adolescents with idiopathic scoliosis based on RTMpose deep learning technology

PurposeThe study aimed to develop a deep learning model for rapid, automated measurement of full-spine X-rays in adolescents with Adolescent Idiopathic Scoliosis (AIS). A significant challenge in this field is the time-consuming nature of manual measurements and the inter-individual variability in these measurements. To address these challenges, we utilized RTMpose deep learning technology to automate the process.MethodsWe conducted a retrospective multicenter diagnostic study using 560 full-spine sagittal plane X-ray images from five hospitals in Inner Mongolia. The model was trained and validated using 500 images, with an additional 60 images for independent external validation. We evaluated the consistency of keypoint annotations among different physicians, the accuracy of model-predicted keypoints, and the accuracy of model measurement results compared to manual measurements.ResultsThe consistency percentages of keypoint annotations among different physicians and the model were 90–97% within the 4-mm range. The model's prediction accuracies for key points were 91–100% within the 4-mm range compared to the reference standards. The model's predictions for 15 anatomical parameters showed high consistency with experienced physicians, with intraclass correlation coefficients ranging from 0.892 to 0.991. The mean absolute error for SVA was 1.16 mm, and for other parameters, it ranged from 0.22° to 3.32°. A significant challenge we faced was the variability in data formats and specifications across different hospitals, which we addressed through data augmentation techniques. The model took an average of 9.27 s to automatically measure the 15 anatomical parameters per X-ray image.ConclusionThe deep learning model based on RTMpose can effectively enhance clinical efficiency by automatically measuring the sagittal plane parameters of the spine in X-rays of patients with AIS. The model's performance was found to be highly consistent with manual measurements by experienced physicians, offering a valuable tool for clinical diagnostics.

Application of Developing Artificial Intelligence (AI) Techniques to Model Pan Evaporation Trends in Slovak River Sub-Basins

The modeling of pan evaporation (Ep) trends in Slovak river sub-basins was conducted using advanced artificial intelligence (AI) techniques algorithms to accurately calculate evaporation rates based on daily climate data from 2010 to 2023 across eight sub-basins in the Slovak Republic. The AI modeling results reveal that the Bodrog, Hornád, Ipeľ, Morava, Slaná, and Váh river basins are experiencing increases in evaporation, while the Dunaj and Hron rivers show declining trends. This divergence may indicate varying ecological factors influencing the evaporation dynamics of each river. A comprehensive set of 28 machine learning (ML) and deep learning (DL) models was employed, including ML techniques such as linear regression, tree-based, support vector machines (both with and without kernels), ensemble, and Gaussian process methods; as well as DL approaches like neural networks (narrow, medium, wide, bilayered, and trilayered). Among these, stepwise linear regression provided the most optimal fit. The minimum redundancy maximum relevance (mRMR) method was utilized for feature selection to balance relevance and redundancy effectively. The results suggest that emphasizing relative humidity (RH) and minimum temperature (tmin) significantly enhances accuracy, highlighting the critical roles of these factors in modeling pan evaporation trends. The results offer precise evaporation analyses to improve water management and lessen scarcity.

Explainable Self-Supervised Dynamic Neuroimaging Using Time Reversal

Objective: Functional magnetic resonance imaging data pose significant challenges due to their inherently noisy and complex nature, making traditional statistical models less effective in capturing predictive features. While deep learning models offer superior performance through their non-linear capabilities, they often lack transparency, reducing trust in their predictions. This study introduces the Time Reversal (TR) pretraining method to address these challenges. TR aims to learn temporal dependencies in data, leveraging large datasets for pretraining and applying this knowledge to improve schizophrenia classification on smaller datasets. Methods: We pretrained an LSTM-based model with attention using the TR approach, focusing on learning the direction of time in fMRI data, achieving over 98 % accuracy on HCP and UK Biobank datasets. For downstream schizophrenia classification, TR-pretrained weights were transferred to models evaluated on FBIRN, COBRE, and B-SNIP datasets. Saliency maps were generated using Integrated Gradients (IG) to provide post hoc explanations for pretraining, while Earth Mover’s Distance (EMD) quantified the temporal dynamics of salient features in the downstream tasks. Results: TR pretraining significantly improved schizophrenia classification performance across all datasets: median AUC scores increased from 0.7958 to 0.8359 (FBIRN), 0.6825 to 0.7778 (COBRE), and 0.6341 to 0.7224 (B-SNIP). The saliency maps revealed more concentrated and biologically meaningful salient features along the time axis, aligning with the episodic nature of schizophrenia. TR consistently outperformed baseline pretraining methods, including OCP and PCL, in terms of AUC, balanced accuracy, and robustness. Conclusions: This study demonstrates the dual benefits of the TR method: enhanced predictive performance and improved interpretability. By aligning model predictions with meaningful temporal patterns in brain activity, TR bridges the gap between deep learning and clinical relevance. These findings emphasize the potential of explainable AI tools for aiding clinicians in diagnostics and treatment planning, especially in conditions characterized by disrupted temporal dynamics.

Harnessing advanced hybrid deep learning model for real-time detection and prevention of man-in-the-middle cyber attacks

The growing number of connected devices in smart home environments has amplified security risks, particularly from Man-in-the-Middle (MitM) attacks. These attacks allow cybercriminals to intercept and manipulate communication streams between devices, often remaining undetected. Traditional rule-based methods struggle to cope with the complexity of these attacks, creating a need for more advanced, adaptive intrusion detection systems. This research introduces the AEXB Model, a hybrid deep learning approach that combines the feature extraction capabilities of an AutoEncoder with the classification power of XGBoost. By combining these complementary methods, the model enhances detection accuracy and significantly reduces false positives. The AEXB Model’s methodology encompasses robust preprocessing steps, including data cleaning, scaling, and dimensionality reduction, followed by comprehensive feature engineering and selection techniques, such as Recursive Feature Elimination (RFE) and correlation analysis. By applying this approach to the Intrusion Detection in Smart Home (IDSH) dataset, the model achieves an impressive 97.24% accuracy, demonstrating its effectiveness in identifying anomalous network behavior indicative of MitM attacks. Additionally, the model’s real-time detection capabilities allow for rapid responses to threats, thus providing continuous protection in dynamic smart home environments.