Deep Learning Approach Research Articles

Reduction of Misclassifications in Wildfire Detection: A Weighted Ensemble Deep Learning Approach

Governments worldwide are increasingly prioritizing early wildfire detection to safeguard lives, property, and the environment. Although CNN-based models have demonstrated exceptional performance in various computer vision applications, the evolving nature of wildfire images poses significant challenges for a single CNN-based model in wildfire detection. In this study, we addressed this issue by integrating and weighting the differential learning capabilities of three individual transfer learning models: InceptionV3, ResNet50, and VGG16. Experimental results show that the ensemble deep learning models significantly outperformed all single classifiers across all performance metrics. Both the ensemble and weighted ensemble deep learning models achieved 99.7% accuracy, 99.5% precision, 100% recall, 99.8% F1-score, 0.5%false positive rate, 0.0% false negative rate and 0.3% error rate. Additionally, these models reduced the error rate by 98%, 91%, and 40% compared to the error rates of ResNet50, InceptionV3, and VGG16 respectively. A false negative rate of 0% indicates that our proposed ensemble deep learning models identified and predicted all the wildfire instances present in the test set correctly without a single misclassification. This positions our proposed ensemble deep learning models as superior choices for reducing misclassifications in wildfire detection.

A Deep Learning Approach for Automatic Music Genre Classification

A Deep Learning Approach for Automatic Music Genre Classification

Landslide susceptibility in Phuoc Son, Quang Nam: A deep learning approach

Landslide susceptibility in Phuoc Son, Quang Nam: A deep learning approach

Journey tracker: driver alerting system with a deep learning approach

Journey tracker: driver alerting system with a deep learning approach

Enhanced Lung Cancer Diagnosis and Staging With HRNeT: A Deep Learning Approach

Enhanced Lung Cancer Diagnosis and Staging With <scp>HRNeT</scp>: A Deep Learning Approach

Facial recognition and classification for customer information systems: a feature fusion deep learning approach with FFDMLC algorithm

Facial recognition and classification for customer information systems: a feature fusion deep learning approach with FFDMLC algorithm

Superpixel-ComBat modeling: A joint approach for harmonization and characterization of inter-scanner variability in T1-weighted images

Abstract T1-weighted imaging holds wide applications in clinical and research settings; however, the challenge of inter-scanner variability arises when combining data across scanners, which impedes multi-site research. To address this, post-acquisition harmonization methods such as statistical or deep learning approaches have been proposed to unify cross-scanner images. Nevertheless, how inter-scanner variability manifests in images and derived measures, and how to harmonize it in an interpretable manner, remains underexplored. To broaden our knowledge of inter-scanner variability and leverage it to develop a new harmonization strategy, we devised a pipeline to assess the interpretable inter-scanner variability in matched T1-weighted images across four 3T MRI scanners. The pipeline incorporates ComBat modeling with 3D superpixel parcellation algorithm (namely SP-ComBat), which estimates location and scale effects to quantify the shift and spread in relative signal distributions, respectively, concerning brain tissues in the image domain. The estimated parametric maps revealed significant contrast deviations compared to the joint signal distribution across scanners (p &amp;lt; 0.001), and the identified deviations in signal intensities may relate to differences in the inversion time acquisition parameter. To reduce the inter-scanner variability, we implemented a harmonization strategy involving proper image preprocessing and site effect removal by ComBat-derived parameters, achieving substantial improvement in image quality and significant reduction in variation of volumetric measures of brain tissues (p &amp;lt; 0.001). We also applied SP-ComBat to evaluate and characterize the performance of various image harmonization techniques, demonstrating a new way to assess image harmonization. In addition, we reported various metrics of T1-weighted images to quantify the impact of inter-scanner variation, including signal-to-noise ratio, contrast-to-noise ratio, signal inhomogeneity index, and structural similarity index. This study demonstrates a pipeline that extends the implementation of statistical ComBat method to the image domain in a practical manner for characterizing and harmonizing the inter-scanner variability in T1-weighted images, providing further insight for the studies focusing on the development of image harmonization methodologies and their applications.

Comparative analysis of ternary TiAlNb interatomic potentials: moment tensor vs. deep learning approaches

Intermetallic titanium aluminides, leveraging the ordered γ-TiAl phase, attract increasing attention in aerospace and automotive engineering due to their favorable mechanical properties at high temperatures. Of particular interest are γ-TiAl-based alloys with a Niobium (Nb) concentration of 5–10 at.%. It is a key question how to model such ternary alloys at the atomic scale with molecular dynamics (MD) simulations to better understand (and subsequently optimize) the alloys. Here, we present a comparative analysis of ternary TiAlNb interatomic potentials developed by the moment tensor potential (MTP) and deep potential molecular dynamics (DeePMD) methods specifically for the above mentioned critical Nb concentration range. We introduce a novel dataset (TiAlNb dataset) for potential training that establishes a benchmark for the assessment of TiAlNb potentials. The potentials were evaluated through rigorous error analysis and performance metrics, alongside calculations of material properties such as elastic constants, equilibrium volume, and lattice constant. Additionally, we explore finite temperature properties including specific heat and thermal expansion with both potentials. Mechanical behaviors, such as uniaxial tension and the calculation of generalized stacking fault energy, are analyzed to determine the impact of Nb alloying in TiAl-based alloys. Our results indicate that Nb alloying generally enhances the ductility of TiAl-based alloys at the expense of reduced strength, with the notable exception of simulations using DeePMD for the γ-TiAl phase, where this trend does not apply.

Deep learning predicted perceived age is a reliable approach for analysis of facial ageing: A proof of principle study.

Perceived age (PA) has been associated with mortality, genetic variants linked to ageing and several age-related morbidities. However, estimating PA in large datasets is laborious and costly to generate, limiting its practical applicability. To determine if estimating PA using deep learning-based algorithms results in the same associations with morbidities and genetic variants as human-estimated perceived age. Self-supervised learning (SSL) and deep feature transfer (DFT) deep learning (DL) approaches were trained and tested on human-estimated PAs and their corresponding frontal face images of middle-aged to elderly Dutch participants (n = 2679) from a population-based study in the Netherlands. We compared the DL-estimated PAs with morbidities previously associated with human-estimated PA as well as genetic variants in the gene MC1R; we additionally tested the PA associations with MC1R in a new validation cohort (n = 1158). The DL approaches predicted PA in this population with a mean absolute error of 2.84 years (DFT) and 2.39 years (SSL). In the training-test dataset, we found the same significant (p < 0.05) associations for DL PA with osteoporosis, ARHL, cognition, COPD and cataracts and MC1R, as with human PA. We also found a similar but less significant association for SSL and DFT PAs (0.69 and 0.71 years per allele, p = 0.008 and 0.011, respectively) with MC1R variants in the validation dataset as that found with human, SSL and DFT PAs in the training-test dataset (0.79, 0.78 and 0.71 years per allele respectively; all p < 0.0001). Deep learning methods can automatically estimate PA from facial images with enough accuracy to replicate known links between human-estimated perceived age and several age-related morbidities. Furthermore, DL predicted perceived age associated with MC1R gene variants in a validation cohort. Hence, such DL PA techniques may be used instead of human estimations in perceived age studies thereby reducing time and costs.

Energy efficient deep reinforcement learning approach to control the traffic flow in iot networks for smart city

Energy efficient deep reinforcement learning approach to control the traffic flow in iot networks for smart city

Improved deep learning prediction of antigen–antibody interactions

Identifying antibodies that neutralize specific antigens is crucial for developing effective immunotherapies, but this task remains challenging for many target antigens. The rise of deep learning-based computational approaches presents a promising avenue to address this challenge. Here, we assess the performance of a deep learning approach through two benchmark tests aimed at predicting antibodies for the receptor-binding domain of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) spike protein. Three different strategies for constructing input sequence alignments are employed for predicting structural models of antigen-antibody complexes. In our initial testing set, which comprises known experimental structures, these strategies collectively yield a significant top-ranked prediction for 61% of cases and a success rate of 47%. Notably, one strategy that utilizes the sequences of known antigen binders outperforms the other two, achieving a precision of 90% in a subsequent test set of ~1,000 antibodies, balanced between true and control antibodies for the antigen, albeit with a lower recall of 25%. Our results underscore the potential of integrating deep learning methods with single B cell sequencing techniques to enhance the prediction accuracy of antigen-antibody interactions.

High-sensitivity acceleration sensor detecting micro-mechanomyogram and deep learning approach for parkinson’s disease classification

High-sensitivity acceleration sensors have been independently developed by our research group to detect vibrations that are > 10 dB smaller than those detected by conventional commercial sensors. This study is the first to measure high-frequency micro-vibrations in muscle fibers, termed micro-mechanomyogram (MMG) in patients with Parkinson’s disease (PwPD) using a high-sensitivity acceleration sensor. We specifically measured the extensor pollicis brevis muscle at the base of the thumb in PwPD and healthy controls (HC) and detected not only low-frequency MMG (< 15 Hz) but also micro-MMG (≥ 15 Hz), which was preciously undetectable using commercial acceleration sensors. Analysis revealed remarkable differences in the frequency characteristics of micro-MMG between PwPD and HC. Specifically, during muscle power output, the low-frequency MMG energy was greater in PwPD than in HC, while the micro-MMG energy was smaller in PwPD compared to HC. These results suggest that micro-MMG detected by the high-sensitivity acceleration sensor provides crucial information for distinguishing between PwPD and HC. Moreover, a deep learning model trained on both low-frequency MMG and micro-MMG achieved a high accuracy (92.19%) in classifying PwPD and HC, demonstrating the potential for a diagnostic system for PwPD using micro-MMG.

Combined Deep Learning Approaches for Intrusion Detection Systems

Combined Deep Learning Approaches for Intrusion Detection Systems

A deep learning approach to case prioritisation of colorectal biopsies.

To create and validate a weakly supervised artificial intelligence (AI) model for detection of abnormal colorectal histology, including dysplasia and cancer, and prioritise biopsies according to clinical significance (severity of diagnosis). Triagnexia Colorectal, a weakly supervised deep learning model, was developed for the classification of colorectal samples from haematoxylin and eosin (H&E)-stained whole slide images. The model was trained on 24 983 digitised images and assessed by multiple pathologists in a simulated digital pathology environment. The AI application was implemented as part of a point and click graphical user interface to streamline decision-making. Pathologists assessed the accuracy of the AI tool, its value, ease of use and integration into the digital pathology workflow. Validation of the model was conducted on two cohorts: the first, on 100 single-slide cases, achieved micro-average model specificity of 0.984, micro-average model sensitivity of 0.949 and micro-average model F1 score of 0.949 across all classes. A secondary multi-institutional validation cohort, of 101 single-slide cases, achieved micro-average model specificity of 0.978, micro-average model sensitivity of 0.931 and micro-average model F1 score of 0.931 across all classes. Pathologists reflected their positive impressions on the overall accuracy of the AI in detecting colorectal pathology abnormalities. We have developed a high-performing colorectal biopsy AI triage model that can be integrated into a routine digital pathology workflow to assist pathologists in prioritising cases and identifying cases with dysplasia/cancer versus non-neoplastic biopsies.

Deep learning-powered visual place recognition for enhanced mobile multimedia communication in autonomous transport systems

The progress of autonomous transport systems (ATS) involves efficient multimedia communication for real-time data tradeoffs and environmental issues. Deep learning (DL) powered visual place recognition (VPR) was developed as an effective tool to improve mobile multimedia communication in ATS. VPR relates to the capability of a method or device to recognize and identify particular places or locations from the visual scene. This procedure involves inspecting visual data, like images or video frames, to control the unique features or features connected with diverse locations. By leveraging camera sensors, VPR allows vehicles to detect their surroundings, enabling context-aware communication and enhancing the entire system's performance. DL-empowered VPR offers a transformative manner to improve mobile multimedia communication in ATS. By identifying and understanding their situation, autonomous vehicles can communicate most effectively and operate reliably and safely, paving the way for a future characterized by seamless and intelligent transportation. This article develops a novel Deep Learning-Powered Visual Place Recognition for Enhanced Multimedia Communication in Autonomous Transport Systems (DLVPR-MCATS) methodology. The main aim of the DLVPR-MCATS methodology is to recognize visual places or not utilize optimal DL approaches. For this purpose, the DLVPR-MCATS approach utilizes a bilateral filtering (BF) based preprocessing model. For the feature fusion model, the DLVPR-MCATS approach follows three models: residual network (ResNet), EfficientNet, and MobileNetv2. Moreover, the hyperparameter tuning method uses the Harris Hawks Optimization (HHO) model. Finally, the bidirectional long short-term memory (BiLSTM) technique is implemented to recognize visual places. A wide range of simulations is executed to validate the solution of the DLVPR-MCATS method. The experimental validation of the DLVPR-MCATS method portrayed a superior performance over other models concerning various aspects.

A Hybrid Deep Learning Approach with Generative Adversarial Network for Credit Card Fraud Detection

Credit card fraud detection is a critical challenge in the financial industry, with substantial economic implications. Conventional machine learning (ML) techniques often fail to adapt to evolving fraud patterns and underperform with imbalanced datasets. This study proposes a hybrid deep learning framework that integrates Generative Adversarial Networks (GANs) with Recurrent Neural Networks (RNNs) to enhance fraud detection capabilities. The GAN component generates realistic synthetic fraudulent transactions, addressing data imbalance and enhancing the training set. The discriminator, implemented using various DL architectures, including Simple RNN, Long Short-Term Memory (LSTM) networks, and Gated Recurrent Units (GRUs), is trained to distinguish between real and synthetic transactions and further fine-tuned to classify transactions as fraudulent or legitimate. Experimental results demonstrate significant improvements over traditional methods, with the GAN-GRU model achieving a sensitivity of 0.992 and specificity of 1.000 on the European credit card dataset. This work highlights the potential of GANs combined with deep learning architectures to provide a more effective and adaptable solution for credit card fraud detection.

Optimization of solid oxide electrolysis cells using concentrated solar-thermal energy storage: A hybrid deep learning approach

The Solid Oxide Electrolysis Cell (SOEC) represents a cutting-edge solution for the conversion of CO2 and H2O into syngas, offering significant economic and environmental benefits. However, the process requires substantial high-temperature heat inputs, traditionally supplied by electricity. This study introduces a novel approach leveraging concentrated solar radiation as a renewable heat source for SOEC, addressing the challenge of its inherent fluctuations through the integration of Thermal Energy Storage (TES) systems. We propose a hybrid model that combines multi-physics simulation with a deep learning algorithm, enabling rapid optimization of the electrolysis process under real-time direct normal irradiance conditions. Our findings demonstrate that the inclusion of TES within the system architecture results in a remarkable 53 % reduction in temperature variation rate at the SOEC inlet, ensuring operational stability and efficiency. Furthermore, by fine-tuning capacity parameters, we have developed a control strategy that harmonizes efficiency with safety performance. The robustness of our system is underscored by its resilience to step changes, achieving a 75 % reduction in temperature fluctuations. This research contributes a pioneering method for the real-time optimization and control of SOEC systems, harnessing the power of TES to drive sustainable energy conversion with enhanced reliability and economic viability, facilitating precise and swift predictive capabilities even under dynamic operating conditions.

Respiratory Rate Estimation from Thermal Video Data Using Spatio-Temporal Deep Learning

Thermal videos provide a privacy-preserving yet information-rich data source for remote health monitoring, especially for respiration rate (RR) estimation. This paper introduces an end-to-end deep learning approach to RR measurement using thermal video data. A detection transformer (DeTr) first finds the subject’s facial region of interest in each thermal frame. A respiratory signal is estimated from a dynamically cropped thermal video using 3D convolutional neural networks and bi-directional long short-term memory stages. To account for the expected phase shift between the respiration measured using a respiratory effort belt vs. a facial video, a novel loss function based on negative maximum cross-correlation and absolute frequency peak difference was introduced. Thermal recordings from 22 subjects, with simultaneous gold standard respiratory effort measurements, were studied while sitting or standing, both with and without a face mask. The RR estimation results showed that our proposed method outperformed existing models, achieving an error of only 1.6 breaths per minute across the four conditions. The proposed method sets a new State-of-the-Art for RR estimation accuracy, while still permitting real-time RR estimation.

Deep Learning Method Applied to Autonomous Image Diagnosis for Prick Test

Background: The skin prick test (SPT) is used to diagnose sensitization to antigens. This study proposes a deep learning approach to infer wheal dimensions, aiming to reduce dependence on human interpretation. Methods: A dataset of SPT images (n = 5844) was used to infer a convolutional neural network for wheal segmentation (ML model). Three methods for inferring wheal dimensions were evaluated: the ML model; the standard protocol (MA1); and approximation of the area as an ellipse using diameters measured by an allergist (MA2). The results were compared with assisted image segmentation (AIS), the most accurate method. Bland–Altman analysis, distribution analyses, and correlation tests were applied to compare the methods. This study also compared the percentage deviation among these methods in determining the area of wheals with regular geometric shapes (n = 150) and with irregular shapes (n = 150). Results: The Bland–Altman analysis showed that the difference between methods was not correlated with the absolute area. The ML model achieved a segmentation accuracy of 85.88% and a strong correlation with the AIS method (ρ = 0.88), outperforming all other methods. Additionally, MA1 showed significant error (13.44 ± 13.95%) for pseudopods. Conclusions: The ML protocol can potentially automate the reading of SPT, offering greater accuracy than the standard protocol.

Role of inter- and extra-lesion tissue, transfer learning, and fine-tuning in the robust classification of breast lesions

Accurate and unbiased classification of breast lesions is pivotal for early diagnosis and treatment, and a deep learning approach can effectively represent and utilize the digital content of images for more precise medical image analysis. Breast ultrasound imaging is useful for detecting and distinguishing benign masses from malignant masses. Based on the different ways in which benign and malignant tumors affect neighboring tissues, i.e., the pattern of growth and border irregularities, the penetration degree of the adjacent tissue, and tissue-level changes, we investigated the relationship between breast cancer imaging features and the roles of inter- and extra-lesional tissues and their impact on refining the performance of deep learning classification. The novelty of the proposed approach lies in considering the features extracted from the tissue inside the tumor (by performing an erosion operation) and from the lesion and surrounding tissue (by performing a dilation operation) for classification. This study uses these new features and three pre-trained deep neuronal networks to address the challenge of breast lesion classification in ultrasound images. To improve the classification accuracy and interpretability of the model, the proposed model leverages transfer learning to accelerate the training process. Three modern pre-trained CNN architectures (MobileNetV2, VGG16, and EfficientNetB7) are used for transfer learning and fine-tuning for optimization. There are concerns related to the neuronal networks producing erroneous outputs in the presence of noisy images, variations in input data, or adversarial attacks; thus, the proposed system uses the BUS-BRA database (two classes/benign and malignant) for training and testing and the unseen BUSI database (two classes/benign and malignant) for testing. Extensive experiments have recorded accuracy and AUC as performance parameters. The results indicate that the proposed system outperforms the existing breast cancer detection algorithms reported in the literature. AUC values of 1.00 are calculated for VGG16 and EfficientNet-B7 in the dilation cases. The proposed approach will facilitate this challenging and time-consuming classification task.