Encoder-decoder Network Research Articles

Secure Dual Network for Reversible Facial Image Anonymization Through the Latent Space Manipulation

We develop a method to automatically and stably anonymize and de-anonymize face images with encoder-decoder networks and provide a robust and secure solution for identity protection. Our fundamental framework is an NN-based encoder-decoder pair with a dual inferencing mechanism. We denote it as the Secure Dual Network (SDN), which can simultaneously achieve multi-attribute face de-identification and re-identification without any pre-trained/auxiliary model. In more detail, the SDN can take responsibility for successfully anonymizing the face images while generating surrogate faces, satisfying the user-defined specific conditions. Meanwhile, SDN can also execute the de-anonymization procedure and visually indistinguishably reconstruct the original ones if re-identification is required. Designing and implementing the loss functions based on information theory (IT) is one of the essential parts of our work. With the aid of the well-known IT-related quantity, Mutual Information, we successfully explained the physical meaning of our trained models. Extensive experiments justify that with pre-defined multi-attribute identity features, SDN generates user-preferred and diverse appearance anonymized faces for successfully defending against attacks from hackers and, therefore, achieves the goal of privacy protection. Moreover, it can reconstruct the original image nearly perfectly if re-identification is necessary.

Decoding multi-limb movements from two-photon calcium imaging of neuronal activity using deep learning

Objective.Brain-machine interfaces (BMIs) aim to restore sensorimotor function to individuals suffering from neural injury and disease. A critical step in implementing a BMI is to decode movement intention from recorded neural activity patterns in sensorimotor areas. Optical imaging, including two-photon (2p) calcium imaging, is an attractive approach for recording large-scale neural activity with high spatial resolution using a minimally-invasive technique. However, relating slow two-photon calcium imaging data to fast behaviors is challenging due to the relatively low optical imaging sampling rates. Nevertheless, neural activity recorded with 2p calcium imaging has been used to decode information about stereotyped single-limb movements and to control BMIs. Here, we expand upon prior work by applying deep learning to decode multi-limb movements of running mice from 2p calcium imaging data.Approach.We developed a recurrent encoder-decoder network (LSTM-encdec) in which the output is longer than the input.Main results.LSTM-encdec could accurately decode information about all four limbs (contralateral and ipsilateral front and hind limbs) from calcium imaging data recorded in a single cortical hemisphere.Significance.Our approach provides interpretability measures to validate decoding accuracy and expands the utility of BMIs by establishing the groundwork for control of multiple limbs. Our work contributes to the advancement of neural decoding techniques and the development of next-generation optical BMIs.

Polarimetric synthetic aperture radar image classification for accurate landcover mapping with advanced encoder–decoder networks using multi-dimensional probabilistic voting ensemble

Polarimetric synthetic aperture radar image classification for accurate landcover mapping with advanced encoder–decoder networks using multi-dimensional probabilistic voting ensemble

REDalign: accurate RNA structural alignment using residual encoder-decoder network

BackgroundRNA secondary structural alignment serves as a foundational procedure in identifying conserved structural motifs among RNA sequences, crucially advancing our understanding of novel RNAs via comparative genomic analysis. While various computational strategies for RNA structural alignment exist, they often come with high computational complexity. Specifically, when addressing a set of RNAs with unknown structures, the task of simultaneously predicting their consensus secondary structure and determining the optimal sequence alignment requires an overwhelming computational effort of O(L6)\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$O(L^6)$$\\end{document} for each RNA pair. Such an extremely high computational complexity makes these methods impractical for large-scale analysis despite their accurate alignment capabilities.ResultsIn this paper, we introduce REDalign, an innovative approach based on deep learning for RNA secondary structural alignment. By utilizing a residual encoder-decoder network, REDalign can efficiently capture consensus structures and optimize structural alignments. In this learning model, the encoder network leverages a hierarchical pyramid to assimilate high-level structural features. Concurrently, the decoder network, enhanced with residual skip connections, integrates multi-level encoded features to learn detailed feature hierarchies with fewer parameter sets. REDalign significantly reduces computational complexity compared to Sankoff-style algorithms and effectively handles non-nested structures, including pseudoknots, which are challenging for traditional alignment methods. Extensive evaluations demonstrate that REDalign provides superior accuracy and substantial computational efficiency.ConclusionREDalign presents a significant advancement in RNA secondary structural alignment, balancing high alignment accuracy with lower computational demands. Its ability to handle complex RNA structures, including pseudoknots, makes it an effective tool for large-scale RNA analysis, with potential implications for accelerating discoveries in RNA research and comparative genomics.

Dynamic modeling of post-combustion carbon capture process based on multi-gate mixture-of-experts incorporating dual-stage attention-based encoder-decoder network

Solvent-based post-combustion carbon capture (PCC) technology is a promising, near-term solution for decarbonizing power generation and industrial facilities. Model-based process simulation is crucial for the optimal design and operation of the PCC process. Recently, data-driven models have gained attention due to their adaptability, efficient computation and high accuracy. However, the nonlinearity, strong couplings and multi-time scale features of the PCC process pose significant challenges for model identification. To this end, this paper proposes a multi-gate mixture-of-experts incorporating dual-stage attention-based encoder-decoder (MMoE-DAED) network for dynamic modeling of the PCC process under wide operating conditions. An encoder-decoder composed of long short-term memory (LSTM) network is employed to extract features from the time-dependent input data and learn the complex dynamic interactions caused by the inertial and delay properties of the process. Dual-stage attention mechanism is incorporated into the encoder and decoder respectively to select the most relevant input features and their correlations within the time series data. To enhance multi-output prediction accuracy, multi-gate mixture-of-experts (MMoE) framework that considers correlations of multitask learning is implemented. Simulation results using operating data from a PCC experimental setup indicate that the proposed modeling approach accurately predicts the steady-state values and dynamic trends of the CO2 capture rate and stripper bottom temperature over a wide operating range. The RMSE, MAPE and R2 indices for the CO2 capture rate are 2.1592, 0.0295, 0.9641, respectively, and for the stripper bottom temperature are 0.1491, 0.0003, 0.9833, respectively. Validations on a PCC simulator further verify the accuracy and efficiency of the MMoE-DAED model, which enables an 80.87% reduction in computation time compared to the simulator. This paper points to a new direction for the data-driven dynamic modeling of complex energy conversion processes.

Real-Time IMU-Based Kinematics in the Presence of Wireless Data Drop.

Wireless inertial motion capture holds promise for real-time human-machine interfaces and home-based rehabilitation applications. However, wireless data drop can cause significant estimation errors deteriorating performance or even making the system unusable. It is currently unclear how to estimate non-periodic kinematics with wearable inertial measurement units (IMUs) in the presence of wireless data drop (packet loss). We thus propose a novel inference encoder-decoder network model for real-time kinematics during dynamic movement. Twenty-four healthy subjects performed yoga, golf, swimming, dance, and badminton movement activities while wearing IMUs and 10-90% of each IMU's data were randomly removed to determine the effects of data drop on estimation accuracy with and without the proposed model. Results demonstrated a reduction in RMSE of 45.2% to 51.5% in the upper limb kinematic estimation of the proposed model compared to the No Prediction strategy, and a reduction of 19.1% to 31.3% of the proposed model compared with an baseline LSTM model. In addition, the proposed model has significantly less error (p<0.05) than the No Prediction strategy and the baseline LSTM model for 10%, 20%, 30%, 40%, 50%, 60%, 70%, and 80% data drop. These results could enable wearable, wireless IMU dynamic motion analysis and assessment with reduced kinematic estimation error in the presence of varying amounts of wireless data drop and thus could further facilitate human-machine interaction and home-based medical assessment and treatment.

Effective encoder-decoder network for pupil light reflex segmentation in facial photographs of ptosis patients

Accurate segmentation of pupil light reflexes is essential for the reliable assessment of ptosis severity, a condition characterized by the drooping of the upper eyelid. This study introduces a novel encoder-decoder network specialized in reflex segmentation by focusing on addressing issues related to very small regions of interest from an architectural perspective. Specifically, the proposed network is designed to exploit low-level features effectively by integrating a multi-level skip connection and a 1 × 1 convolution-enhanced initial encoding stage. Assessed using a photograph image dataset from Chung-Ang University Hospital, which includes 87 healthy subjects, 64 with ptosis, and 257 with Graves’ orbitopathy (collected between January 2010 and February 2023), the proposed network outperforms five conventional encoder-decoders. Over 30 trials, the proposed network achieved a mean Dice coefficient of 0.767 and an Intersection over Union of 0.653, indicating a statistically significant improvement in the segmentation of reflex. Our findings show that an elaborate design based on the lowest-level skip connection and 1 × 1 convolution at initial stage enhances the segmentation of pupil light reflexes. The source code of the proposed network is available at https://github.com/tkdgur658/ReflexNet.

Research on Land Use and Land Cover Information Extraction Methods for Remote Sensing Images Based on Improved Convolutional Neural Networks

To address the challenges that convolutional neural networks (CNNs) face in extracting small objects and handling class imbalance in remote sensing imagery, this paper proposes a novel spatial contextual information and multiscale feature fusion encoding–decoding network, SCIMF-Net. Firstly, SCIMF-Net employs an improved ResNeXt-101 deep backbone network, significantly enhancing the extraction capability of small object features. Next, a novel PMFF module is designed to effectively promote the fusion of features at different scales, deepening the model’s understanding of global and local spatial contextual information. Finally, introducing a weighted joint loss function improves the SCIMF-Net model’s performance in extracting LULC information under class imbalance conditions. Experimental results show that compared to other CNNs such as Res-FCN, U-Net, SE-U-Net, and U-Net++, SCIMF-Net improves PA by 0.68%, 0.54%, 1.61%, and 3.39%, respectively; MPA by 2.96%, 4.51%, 2.37%, and 3.45%, respectively; and MIOU by 3.27%, 4.89%, 4.2%, and 5.68%, respectively. Detailed comparisons of locally visualized LULC information extraction results indicate that SCIMF-Net can accurately extract information from imbalanced classes and small objects.

Efficient Metal Corrosion Area Detection Model Combining Convolution and Transformer

In the context of rapid industrialization, efficiently detecting metal corrosion areas has become a critical task in preventing material damage. Unlike conventional semantic segmentation targets, metal corrosion characteristics vary significantly in color, texture, and size. Traditional image segmentation methods need improvement in scenarios involving occlusions, shadows, and defects. This paper proposes a convolution and sequence encoding combined network, MCD-Net, for metal corrosion area segmentation. First, a visual Transformer sequence encoder is introduced into the convolutional encoder–decoder network to enhance global information processing capabilities and establish long-range feature dependencies. A feature fusion method based on an attention module is proposed to enhance the model’s ability to recognize corrosion boundaries, thereby enhancing segmentation accuracy and model robustness. Finally, in the model’s decoding stage, a score-based multi-scale feature enhancement method is employed to emphasize significant features in the corrosion areas. Experimental results indicate that this method attained an F1 score of 84.53% on a public corrosion dataset, demonstrating the model’s deeper understanding and reasoning capabilities for shadow and defect features, as well as excellent noise resistance performance.

A Multi-Hierarchical Complementary Feature Interaction Network for Accelerated Multi-Modal MR Imaging

Magnetic resonance (MR) imaging is widely used in the clinical field due to its non-invasiveness, but the long scanning time is still a bottleneck for its popularization. Using the complementary information between multi-modal imaging to accelerate imaging provides a novel and effective MR fast imaging solution. However, previous technologies mostly use simple fusion methods and fail to fully utilize their potential sharable knowledge. In this study, we introduced a novel multi-hierarchical complementary feature interaction network (MHCFIN) to realize joint reconstruction of multi-modal MR images with undersampled data and thus accelerate multi-modal imaging. Firstly, multiple attention mechanisms are integrated with a dual-branch encoder–decoder network to represent shared features and complementary features of different modalities. In the decoding stage, the multi-modal feature interaction module (MMFIM) acts as a bridge between the two branches, realizing complementary knowledge transfer between different modalities through cross-level fusion. The single-modal feature fusion module (SMFFM) carries out multi-scale feature representation and optimization of the single modality, preserving better anatomical details. Extensive experiments are conducted under different sampling patterns and acceleration factors. The results show that this proposed method achieves obvious improvement compared with existing state-of-the-art reconstruction methods in both visual quality and quantity.

Remote Sensing LiDAR and Hyperspectral Classification with Multi-Scale Graph Encoder–Decoder Network

The rapid development of sensor technology has made multi-modal remote sensing data valuable for land cover classification due to its diverse and complementary information. Many feature extraction methods for multi-modal data, combining light detection and ranging (LiDAR) and hyperspectral imaging (HSI), have recognized the importance of incorporating multiple spatial scales. However, effectively capturing both long-range global correlations and short-range local features simultaneously on different scales remains a challenge, particularly in large-scale, complex ground scenes. To address this limitation, we propose a multi-scale graph encoder–decoder network (MGEN) for multi-modal data classification. The MGEN adopts a graph model that maintains global sample correlations to fuse multi-scale features, enabling simultaneous extraction of local and global information. The graph encoder maps multi-modal data from different scales to the graph space and completes feature extraction in the graph space. The graph decoder maps the features of multiple scales back to the original data space and completes multi-scale feature fusion and classification. Experimental results on three HSI-LiDAR datasets demonstrate that the proposed MGEN achieves considerable classification accuracies and outperforms state-of-the-art methods.

Invisible backdoor attack with attention and steganography

Recently, with the development and widespread application of deep neural networks (DNNs), backdoor attacks have posed new security threats to the training process of DNNs. Backdoor attacks on neural networks undermine the security and trustworthiness of DNNs by implanting hidden, unauthorized triggers, leading to benign behavior on clean samples while exhibiting malicious behavior on samples containing backdoor triggers. Existing backdoor attacks typically employ triggers that are sample-agnostic and identical for each sample, resulting in poisoned images that lack naturalness and are ineffective against existing backdoor defenses. To address these issues, this paper proposes a novel stealthy backdoor attack, where the backdoor trigger is dynamic and specific to each sample. Specifically, we leverage spatial attention on images and pre-trained models to obtain dynamic triggers, which are then injected using an encoder–decoder network. The design of the injection network benefits from recent advances in steganography research. To demonstrate the effectiveness of the proposed steganographic network, we design two backdoor attack modes named ASBA and ATBA, where ASBA utilizes the steganographic network for attack, while ATBA is a backdoor attack without steganography. Subsequently, we conducted attacks on Deep Neural Networks (DNNs) using four standard datasets. Our extensive experiments show that ASBA surpasses ATBA in terms of stealthiness and resilience against current defensive measures. Furthermore, both ASBA and ATBA demonstrate superior attack efficiency.

P10.22.B PREDICTING INTRAOPERATIVE 5-ALA-INDUCED TUMOR FLUORESCENCE VIA MRI AND DEEP LEARNING IN GLIOMAS WITH RADIOGRAPHIC LOWER-GRADE CHARACTERISTICS

Abstract BACKGROUND Lower-grade gliomas typically exhibit 5-aminolevulinic acid (5-ALA)-induced fluorescence in only 20-30% of cases, a rate that can be increased by doubling the administered dose of 5-ALA. Fluorescence can depict anaplastic foci, which can be precisely resected to avoid undergrading. We aimed to analyze whether a deep learning model can predict intraoperative fluorescence based on preoperative magnetic resonance imaging (MRI). Material and Methods: The MRI images of gliomas lacking high-grade characteristics (necrosis, extended contrast-enhancement, a.o.) consisted of T1, T1-post gadolinium, and FLAIR sequences. The preprocessed MRIs were fed into an encoder-decoder convolutional neural network (U-Net), pre-trained for tumor segmentation using those three MRI sequences. We used the outputs of the bottleneck layer of the U-Net in the Variational Autoencoder (VAE) as features for classification. We identified and utilized the most effective features in a Random Forest classifier using the principal component analysis (PCA) and the partial least square discriminant analysis (PLS-DA) algorithms. We evaluated the performance of the classifier using a 10-fold cross-validation procedure. RESULTS We evaluated a cohort of 163 glioma patients categorized as fluorescent (n=83) or non-fluorescent (n=80). Our proposed approach’s performance was evaluated using metrics such as mean balanced accuracy, mean sensitivity, and mean specificity. The optimal results were obtained by employing top-performing features selected by PCA, resulting in a mean balanced accuracy of 80% and mean sensitivity and specificity of 84% and 76%, respectively. CONCLUSION Our findings highlight the potential of a U-Net model, coupled with a random forest classifier, for intraoperative fluorescence prediction. We achieved good accuracy using advanced techniques such as deep learning-based tumor segmentation and Variational Autoencoder for radiomics feature extraction. While the model can still be improved, it has the potential for evaluating when to administer 5-ALA to gliomas lacking typical high-grade radiographic features.

Precision Segmentation of Subretinal Fluids in OCT Using Multiscale Attention-Based U-Net Architecture.

This paper presents a deep-learning architecture for segmenting retinal fluids in patients with Diabetic Macular Oedema (DME) and Age-related Macular Degeneration (AMD). Accurate segmentation of multiple fluid types is critical for diagnosis and treatment planning, but existing techniques often struggle with precision. We propose an encoder-decoder network inspired by U-Net, processing enhanced OCT images and their edge maps. The encoder incorporates Residual and Inception modules with an autoencoder-based multiscale attention mechanism to extract detailed features. Our method shows superior performance across several datasets. On the RETOUCH dataset, the network achieved F1 Scores of 0.82 for intraretinal fluid (IRF), 0.93 for subretinal fluid (SRF), and 0.94 for pigment epithelial detachment (PED). The model also performed well on the OPTIMA and DUKE datasets, demonstrating high precision, recall, and F1 Scores. This architecture significantly enhances segmentation accuracy and edge precision, offering a valuable tool for diagnosing and managing retinal diseases. Its integration of dual-input processing, multiscale attention, and advanced encoder modules highlights its potential to improve clinical outcomes and advance retinal disease treatment.

HiCDiffusion - diffusion-enhanced, transformer-based prediction of chromatin interactions from DNA sequences

Prediction of chromatin interactions from DNA sequence has been a significant research challenge in the last couple of years. Several solutions have been proposed, most of which are based on encoder-decoder architecture, where 1D sequence is convoluted, encoded into the latent representation, and then decoded using 2D convolutions into the Hi-C pairwise chromatin spatial proximity matrix. Those methods, while obtaining high correlation scores and improved metrics, produce Hi-C matrices that are artificial - they are blurred due to the deep learning model architecture. In our study, we propose the HiCDiffusion, sequence-only model that addresses this problem. We first train the encoder-decoder neural network and then use it as a component of the diffusion model - where we guide the diffusion using a latent representation of the sequence, as well as the final output from the encoder-decoder. That way, we obtain the high-resolution Hi-C matrices that not only better resemble the experimental results - improving the Fréchet inception distance by an average of 11 times, with the highest improvement of 56 times - but also obtain similar classic metrics to current state-of-the-art encoder-decoder architectures used for the task.

Efficient Biomedical Waste Management: Optimizing Segmentation and Classification with EnU-Net-DNN-BMWC

&lt;p style="margin-bottom:8px;text-align:justify;"&gt;&lt;span style="font-family:&amp;quot;Times New Roman&amp;quot;,serif;font-size:12.0pt;line-height:200%;tab-stops:0in 21.3pt;"&gt;In India, biomedical waste (BMW) management is governed by strict regulations to mitigate health and environmental risks. It includes materials such as sharps, infectious wastes, pharmaceuticals, and non-hazardous items contaminated with potentially infectious substances. Proper management and disposal of BMW are critical to prevent environmental contamination and health risks.&amp;nbsp; This article introduces an Enhanced U-Network (EnU-Net) integrated with Deep Neural Network BMW Classification (EnU-Net-DNN-BMWC) to enhance accuracy in this critical task. Leveraging the U-Net framework with an Encoder-Decoder Network (EDN) and pixel-wise classification layer initially optimizes image segmentation. Bayesian functions mitigate segmentation uncertainties, while Content-Sensitive Sampling (CSS) refines pixel sampling to prioritize data-sparse regions. Data collected from G. Kuppuswamy Naidu Memorial Hospital and Kovai Medical Center and Hospital (KMCH) in Coimbatore over six months, categorizing sharps, infectious materials, pharmaceuticals, and non-hazardous waste, informs waste management strategies. Experimental validation using 100 biomedical waste images demonstrates EnU-Net-DNN-BMWC achieving good accuracy, surpassing standalone DNN-BMWC using Matlab 2022. The comparative analysis across different metrics such as accuracy, precision, F-measure, recall, error rate, and RMSE between DNN-BMWC and the proposed EnU-Net-DNN-BMWC framework were evaluated in this study, highlighting EnU-Net-DNN-BMWC's superior performance. Finally, this study underscores EnU-Net-DNN-BMWC’s efficacy in enhancing biomedical waste classification, crucial for sustainable waste management practices and regulatory compliance in healthcare settings.&lt;/span&gt;&lt;/p&gt;

Non-resonant background removal in broadband CARS microscopy using deep-learning algorithms

Broadband Coherent anti-Stokes Raman (BCARS) microscopy is an imaging technique that can acquire full Raman spectra (400–3200 cm−1) of biological samples within a few milliseconds. However, the CARS signal suffers from an undesired non-resonant background (NRB), deriving from four-wave-mixing processes, which distorts the peak line shapes and reduces the chemical contrast. Traditionally, the NRB is removed using numerical algorithms that require expert users and knowledge of the NRB spectral profile. Recently, deep-learning models proved to be powerful tools for unsupervised automation and acceleration of NRB removal. Here, we thoroughly review the existing NRB removal deep-learning models (SpecNet, VECTOR, LSTM, Bi-LSTM) and present two novel architectures. The first one combines convolutional layers with Gated Recurrent Units (CNN + GRU); the second one is a Generative Adversarial Network (GAN) that trains an encoder-decoder network and an adversarial convolutional neural network. We also introduce an improved training dataset, generalized on different BCARS experimental configurations. We compare the performances of all these networks on test and experimental data, using them in the pipeline for spectral unmixing of BCARS images. Our analyses show that CNN + GRU and VECTOR are the networks giving the highest accuracy, GAN is the one that predicts the highest number of true positive peaks in experimental data, whereas GAN and VECTOR are the most suitable ones for real-time processing of BCARS images.

CEDNet: A cascade encoder–decoder network for dense prediction

The prevailing methods for dense prediction tasks typically utilize a heavy classification backbone to extract multi-scale features and then fuse these features using a lightweight module. However, these methods allocate most computational resources to the classification backbone, which delays the multi-scale feature fusion and potentially leads to inadequate feature fusion. Although some methods perform feature fusion from early stages, they either fail to fully leverage high-level features to guide low-level feature learning or have complex structures, resulting in sub-optimal performance. We propose a streamlined cascade encoder–decoder network, named CEDNet, tailored for dense prediction tasks. All stages in CEDNet share the same encoder–decoder structure and perform multi-scale feature fusion within each decoder, thereby enhancing the effectiveness of multi-scale feature fusion. We explored three well-known encoder–decoder structures: Hourglass, UNet, and FPN, all of which yielded promising results. Experiments on various dense prediction tasks demonstrated the effectiveness of our method.11Code: https://github.com/zhanggang001/CEDNet.

Detection and classification on MRI images of brain tumor using YOLO NAS deep learning model

If a brain tumor is not properly diagnosed, it might result in fatal consequences and major health issues. As a result, a key component of diagnosis is the early identification of brain tumors and the precise categorization of brain tumor types. This research work focusses on detection and classification such as pituitary, meningioma, glioma, and non-tumorous tumors from brain tumor MRI image using YOLO NAS model. Advances in deep learning have led to an increasing awareness of computer-aided diagnosis technology. To improve classification performance, the input data set is acquired from the REMBRANDT repository using the Digital Database of Brain Tumor Magnetic Resonance Images. The primary phases of this task include segmentation, classification, and pre-processing. The researcher preprocessed the RGB image to exclude any undesired spots before locating the ROI. For each brain tumor image, we used the hybrid anisotropic diffusion filtering (HADF) technique to remove noise. The Encoder-Decoder Network (En–DeNet), which uses a deep neural network based on U-Net as the encoder and a pre-trained EfficientNet as the decoder, is then used to segment the MRI images. A proposed model was developed using a deep learning-based YOLO NAS technique to identify brain cancers from MRI images such as meningioma tumors, non-tumor, glioma tumors, and pituitary tumors. The suggested model's classification performance is weighed based on parameters such as precision, F1-score, sensitivity, accuracy, and specificity. The proposed fusion method YOLO NAS has improved classification results of accuracy (AC = 0.997%), specificity (SP = 0.985%), precision (PR = 0.982%), F1-score (F1 = 0.992%), and sensitivity (SE = 0.985%) using 2570 MRI data for training and 630 data for testing and validation of brain tumor cases. The results show that the brain tumor type classification system based on the proposed YOLO NAS technique works better than the DNN, PDCNN, DenseNet-161, and DCNN-SGD model classifiers.

Physics-informed neural networks for efficient aeroacoustic computational based on two time sequence prediction models

Physics-informed neural networks (PINNs) have been proven powerful for solving partial differential equations (PDEs). However, conventional PINNs fail handling time/space variables in the training data distinctly and overlook the temporal relationships among data points, which is critical for accurately modeling dynamic systems. To address this issue, this work proposes two novel PINN models based on the transformer and the convolutional long short-term memory (ConvLSTM) architectures, respectively. An encoder-decoder neural network structure is adopted to enhance handling of time-space variables and a high-order finite-difference method is used to compute partial derivatives. These computations are implemented using the convolution within the PyTorch framework that incorporates both physical and mathematical information into the neural networks. The efficacy of the proposed methods has been evaluated for the wave equation and the Reynolds-Averaged Navier-Stokes equations. Results suggest that the transformer-based PINN outperforms both the conventional and ConvLSTM-based PINN in terms of accuracy, efficiency and generalizability.