Feature Hierarchy Research Articles

CapST: Leveraging Capsule Networks and Temporal Attention for Accurate Model Attribution in Deep-fake Videos

Deep-fake videos, generated through AI face-swapping techniques, have garnered considerable attention due to their potential for impactful impersonation attacks. While existing research primarily distinguishes real from fake videos, attributing a deep-fake to its specific generation model or encoder is crucial for forensic investigation, enabling precise source tracing and tailored countermeasures. This approach not only enhances detection accuracy by leveraging unique model-specific artifacts but also provides insights essential for developing proactive defenses against evolving deep-fake techniques. Addressing this gap, this paper investigates the model attribution problem for deep-fake videos using two datasets: Deepfakes from Different Models (DFDM) and GANGen-Detection, which comprise deep-fake videos and images generated by GAN models. We select only fake images from the GANGen-Detection dataset to align with the DFDM dataset, which specifies the goal of this study, focusing on model attribution rather than real/fake classification. This study formulates deep-fake model attribution as a multiclass classification task, introducing a novel Capsule-Spatial-Temporal (CapST) model that effectively integrates a modified VGG19 (utilizing only the first 26 out of 52 layers) for feature extraction, combined with Capsule Networks and a Spatio-Temporal attention mechanism. The Capsule module captures intricate feature hierarchies, enabling robust identification of deep-fake attributes, while a video-level fusion technique leverages temporal attention mechanisms to process concatenated feature vectors and capture temporal dependencies in deep-fake videos. By aggregating insights across frames, our model achieves a comprehensive understanding of video content, resulting in more precise predictions. Experimental results on the DFDM and GANGen-Detection datasets demonstrate the efficacy of CapST, achieving substantial improvements in accurately categorizing deep-fake videos over baseline models, all while demanding fewer computational resources.

Optimising solder joint inspection in printed circuit boards through X-ray imaging and machine learning integration

ABSTRACT This study combines machine learning (ML) and X-ray imaging to evaluate the health of solder joints in printed circuit boards (PCBs). A convolutional neural network (CNN) served as the base framework, with CNN-LSTM and CNN-CapsNet models added to enhance performance. Pre-training with the CNN facilitated feature extraction, boosting the subsequent performance of LSTM and CapsNet models. The research focused on three objectives: identifying the best ML model for limited datasets, addressing class imbalance in defective solder samples with data augmentation, and using image manipulation to assess model strengths and limitations. Data augmentation significantly improved model accuracies, with CNN, LSTM, and CapsNet achieving 87.05%, 91.29%, and 94.65%, respectively, compared to 76.23%, 83.32%, and 88.05% without augmentation. CapsNet outperformed other models, leveraging its dynamic routing mechanism to preserve feature hierarchies and maintain stable performance. LSTM demonstrated rapid learning through memory cells, while CNNs were prone to overfitting. CapsNet also excelled in balancing classification across solder types, highlighting its ability to handle complex feature relationships. Robustness tests showed CapsNet’s resilience to image transformations like rotation, scaling, and flipping, though extreme deformations remained challenging. These results underscore CapsNet’s potential for accurate and reliable solder joint classification in diverse scenarios.

A Joint Network of 3D-2D CNN Feature Hierarchy and Pyramidal Residual Model for Hyperspectral Image Classification

A Joint Network of 3D-2D CNN Feature Hierarchy and Pyramidal Residual Model for Hyperspectral Image Classification

Contrasting Responses to Ethenylbenzene (Styrene) and 2-Ethyl-1-hexanol Suggest their Role as Chemical Cues in Host Selection by the Seed Beetle Zabrotes subfasciatus (Coleoptera: Chrysomelidae: Bruchinae).

Seed beetles spend most of their lives within the seeds of host plants belonging to the Fabaceae family. Evidence suggests the cues that mediate pre-oviposition behaviour in Zabrotes subfasciatus (Boheman) are volatile organic compounds (VOCs) emitted by the seeds and suggests differential abilities in environment sensing between sexes. Here, we tested whether VOCs from different legume species trigger different levels of attraction, whether females and males differ in their ability to respond to VOCs, and whether the seeds promoting different behaviours feature singular VOCs. Finally, we tested females' response to selected VOCs from legume seeds with different levels of attraction. Behavioural assays testing the beetles' response to four Fabaceae species allowing varied levels of fitness (Phaseolus vulgaris, Glycine max, Lens culinaris, and Cicer arietinum) and antenna removal assays confirmed volatiles emitted by the seeds act as chemical cues for females and showed the seeds of the tested legume species trigger different levels of attraction. GC-MS analysis revealed the seeds of two of the species at the extreme of the preference hierarchy feature singular VOCs profiles and abundance. One of the differentially expressed VOCs found in higher quantities in P. vulgaris (ethenylbenzene = styrene) and one in C. arietinum (2-ethyl-1-hexanol) mediate opposing behaviours in Z. subfasciatus females. These results suggest host choice in Z. subfasciatus relies upon at least a two-component kairomone-based system: styrene attracts females to P. vulgaris seeds and 2-ethyl-1-hexanol keeps them from choosing C. arietinum as a substrate for oviposition. The system has evolutionary and agricultural relevance because it may allow for "niche" specialisation in seed stores and natural environments and may help develop pest management strategies.

Contrastive feature hierarchies and Germanic phonology

Abstract I discuss an analysis of changes in the Scandinavian runic alphabet, or futhark, by Jørgen Rischel (1966). Rischel’s article accounts for some puzzling changes in the futhark by employing contrastive feature hierarchies represented as branching trees. Feature hierarchies can be traced back to the work of Roman Jakobson and his colleagues. They enjoyed a brief period of prominence in the 1950s and 1960s, but then disappeared from mainstream phonological theory. However, they were employed in a number of interesting studies of Germanic and other languages whose insights we can still profit from today. The goal of this paper is to bring attention to this largely forgotten approach to phonological analysis, and to spell out the principles that underlie it.

Reconstructing angular light field by learning spatial features from quadrilateral epipolar geometry

Recent research on dense multi-view image reconstruction has attracted considerable attention, due to its enhancement of applications such as 3D reconstruction, de-occlusion, depth sensing, saliency detection, and prominent object identification. This paper introduces a method for reconstructing high-density light field images, addressing the challenge of balancing angular and spatial resolution within the constraints of sensor resolution. We propose a three-stage network architecture for LF reconstruction that processes dense epipolar, spatial, and angular information efficiently. Our network processes epipolar information in the first stage, spatial information in the second stage, and angular information in the third stage. By extracting quadrilateral epipolar features from multiple directions, our model constructs a robust feature hierarchy for accurate reconstruction. We employ weight sharing in the initial stage to enhance feature quality while maintaining a compact model. Experimental results on real-world and synthetic datasets demonstrate that our approach surpasses state-of-the-art methods in both inference time and reconstruction quality.

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.

MPCTrans: Multi-Perspective Cue-Aware Joint Relationship Representation for 3D Hand Pose Estimation via Swin Transformer.

The objective of 3D hand pose estimation (HPE) based on depth images is to accurately locate and predict keypoints of the hand. However, this task remains challenging because of the variations in hand appearance from different viewpoints and severe occlusions. To effectively address these challenges, this study introduces a novel approach, called the multi-perspective cue-aware joint relationship representation for 3D HPE via the Swin Transformer (MPCTrans, for short). This approach is designed to learn multi-perspective cues and essential information from hand depth images. To achieve this goal, three novel modules are proposed to utilize features from multiple virtual views of the hand, namely, the adaptive virtual multi-viewpoint (AVM), hierarchy feature estimation (HFE), and virtual viewpoint evaluation (VVE) modules. The AVM module adaptively adjusts the angles of the virtual viewpoint and learns the ideal virtual viewpoint to generate informative multiple virtual views. The HFE module estimates hand keypoints through hierarchical feature extraction. The VVE module evaluates virtual viewpoints by using chained high-level functions from the HFE module. Transformer is used as a backbone to extract the long-range semantic joint relationships in hand depth images. Extensive experiments demonstrate that the MPCTrans model achieves state-of-the-art performance on four challenging benchmark datasets.

Brief Study on Convolutional Neural Networks

Convolutional Neural Networks (CNNs) have revolutionized the field of computer vision and pattern recognition, offering state-of-the-art performance in tasks such as image classification, object detection, and segmentation. This study explores the architecture, training strategies, and applications of CNNs, focusing on their ability to automatically learn spatial hierarchies of features through layers of convolutional filters. The research evaluates various CNN architectures, including Lent, Alex Net, and ResNet, highlighting their improvements in accuracy and efficiency. Additionally, the study investigates advanced techniques such as data augmentation, transfer learning, and regularization methods (e. g, dropout and batch normalization), which enhance the model's generalization capabilities. Through empirical experiments, we demonstrate the effectiveness of CNNs in real-world scenarios, including medical image analysis, autonomous driving, and facial recognition. The study concludes with a discussion of the future trends of CNNs, particularly in the context of deep learning optimization, hardware acceleration, and integration with emerging technologies like edge computing and quantum machine learning.

HEDN: multi-oriented hierarchical extraction and dual-frequency decoupling network for 3D medical image segmentation.

Previous 3D encoder-decoder segmentation architectures struggled with fine-grained feature decomposition, resulting in unclear feature hierarchies when fused across layers. Furthermore, the blurred nature of contour boundaries in medical imaging limits the focus on high-frequency contour features. To address these challenges, we propose a Multi-oriented Hierarchical Extraction and Dual-frequency Decoupling Network (HEDN), which consists of three modules: Encoder-Decoder Module (E-DM), Multi-oriented Hierarchical Extraction Module (Multi-HEM), and Dual-frequency Decoupling Module (Dual-DM). The E-DM performs the basic encoding and decoding tasks, while Multi-HEM decomposes and fuses spatial and slice-level features in 3D, enriching the feature hierarchy by weighting them through 3D fusion. Dual-DM separates high-frequency features from the reconstructed network using self-supervision. Finally, the self-supervised high-frequency features separated by Dual-DM are inserted into the process following Multi-HEM, enhancing interactions and complementarities between contour features and hierarchical features, thereby mutually reinforcing both aspects. On the Synapse dataset, HEDN outperforms existing methods, boosting Dice Similarity Score (DSC) by 1.38% and decreasing 95% Hausdorff Distance (HD95) by 1.03 mm. Likewise, on the Automatic Cardiac Diagnosis Challenge (ACDC) dataset, HEDN achieves 0.5% performance gains across all categories.

Bayesian optimized multimodal deep hybrid learning approach for tomato leaf disease classification

Manual identification of tomato leaf diseases is a time-consuming and laborious process that may lead to inaccurate results without professional assistance. Therefore, an automated, early, and precise leaf disease recognition system is essential for farmers to ensure the quality and quantity of tomato production by providing timely interventions to mitigate disease spread. In this study, we have proposed seven robust Bayesian optimized deep hybrid learning models leveraging the synergy between deep learning and machine learning for the automated classification of ten types of tomato leaves (nine diseased and one healthy). We customized the popular Convolutional Neural Network (CNN) algorithm for automatic feature extraction due to its ability to capture spatial hierarchies of features directly from raw data and classical machine learning techniques [Random Forest (RF), XGBoost, GaussianNB (GNB), Support Vector Machines (SVM), Multinomial Logistic Regression (MLR), K-Nearest Neighbor (KNN)], and stacking for classifications. Additionally, the study incorported a Boruta feature filtering layer to capture the statistically significant features. The standard, research-oriented PlantVillage dataset was used for the performance testing, which facilitates benchmarking against prior research and enables meaningful comparisons of classification performance across different approaches. We utilized a variety of statistical classification metrics to demonstrate the robustness of our models. Using the CNN-Stacking model, this study achieved the highest classification performance among the seven hybrid models. On an unseen dataset, this model achieved average precision, recall, f1-score, mcc, and accuracy values of 98.527%, 98.533%, 98.527%, 98.525%, and 98.268%, respectively. Our study requires only 0.174 s of testing time to correctly identify noisy, blurry, and transformed images. This indicates our approach's time efficiency and generalizability in images captured under challenging lighting conditions and with complex backgrounds. Based on the comparative analysis, our approach is superior and computationally inexpensive compared to the existing studies. This work will aid in developing a smartphone app to offer farmers a real-time disease diagnosis tool and management strategies.

A Deformable and Multi-Scale Network with Self-Attentive Feature Fusion for SAR Ship Classification

The identification of ships in Synthetic Aperture Radar (SAR) imagery is critical for effective maritime surveillance. The advent of deep learning has significantly improved the accuracy of SAR ship classification and recognition. However, distinguishing features between different ship categories in SAR images remains a challenge, particularly as the number of categories increases. The key to achieving high recognition accuracy lies in effectively extracting and utilizing discriminative features. To address this, we propose DCN-MSFF-TR, a novel recognition model inspired by the Transformer encoder–decoder architecture. Our approach integrates a deformable convolutional module (DCN) within the backbone network to enhance feature extraction. Additionally, we introduce multi-scale self-attention processing from the Transformer into the feature hierarchy and fuse these representations at appropriate levels using a feature pyramid strategy. This enables each layer to leverage both its own information and synthesized features from other layers, enhancing feature representation. Extensive evaluations on the OpenSARShip-3-Complex and OpenSARShip-6-Complex datasets demonstrate the effectiveness of our method. DCN-MSFF-TR achieves average recognition accuracies of 78.1% and 66.7% on the three-class and six-class datasets, respectively, outperforming existing recognition models and showcasing its superior capability in accurately identifying ship categories in SAR images.

Dysphagia in primary progressive aphasia: Clinical predictors and neuroanatomical basis.

Dysphagia is an important feature of neurodegenerative diseases and potentially life-threatening in primary progressive aphasia (PPA) but remains poorly characterized in these syndromes. We hypothesized that dysphagia would be more prevalent in nonfluent/agrammatic variant (nfv)PPA than other PPA syndromes, predicted by accompanying motor features, and associated with atrophy affecting regions implicated in swallowing control. In a retrospective case-control study at our tertiary referral centre, we recruited 56 patients with PPA (21 nfvPPA, 22 semantic variant [sv]PPA, 13 logopenic variant [lv]PPA). Using a pro forma based on caregiver surveys and clinical records, we documented dysphagia (present/absent) and associated, potentially predictive clinical, cognitive, and behavioural features. These were used to train a machine learning model. Patients' brain magnetic resonance imaging scans were assessed using voxel-based morphometry and region-of-interest analyses comparing differential atrophy profiles associated with dysphagia presence/absence. Dysphagia was significantly more prevalent in nfvPPA (43% vs. 5% svPPA and no lvPPA). The machine learning model revealed a hierarchy of features predicting dysphagia in the nfvPPA group, with excellent classification accuracy (90.5%, 95% confidence interval = 77.9-100); the strongest predictor was orofacial apraxia, followed by older age, parkinsonism, more severe behavioural disturbance, and more severe cognitive impairment. Significant grey matter atrophy correlates of dysphagia in nfvPPA were identified in left middle frontal, right superior frontal, and right supramarginal gyri and right caudate. Dysphagia is a common feature of nfvPPA, linked to underlying corticosubcortical network dysfunction. Clinicians should anticipate this symptom particularly in the context of other motor features and more severe disease.

A Moment-Sum-of-Squares Hierarchy for Robust Polynomial Matrix Inequality Optimization with Sum-of-Squares Convexity

We study a class of polynomial optimization problems with a robust polynomial matrix inequality (PMI) constraint where the uncertainty set itself is also defined by a PMI. These can be viewed as matrix generalizations of semi-infinite polynomial programs because they involve actually infinitely many PMI constraints in general. Under certain sum-of-squares (SOS)-convexity assumptions, we construct a hierarchy of increasingly tight moment-SOS relaxations for solving such problems. Most of the nice features of the moment-SOS hierarchy for the usual polynomial optimization are extended to this more complicated setting. In particular, asymptotic convergence of the hierarchy is guaranteed, and finite convergence can be certified if some flat extension condition holds true. To extract global minimizers, we provide a linear algebra procedure for recovering a finitely atomic matrix-valued measure from truncated matrix-valued moments. As an application, we are able to solve the problem of minimizing the smallest eigenvalue of a polynomial matrix subject to a PMI constraint. If SOS convexity is replaced by convexity, we can still approximate the optimal value as closely as desired by solving a sequence of semidefinite programs and certify global optimality in case that certain flat extension conditions hold true. Finally, an extension to the nonconvexity setting is provided under a rank 1 condition. To obtain the above-mentioned results, techniques from real algebraic geometry, matrix-valued measure theory, and convex optimization are employed. Funding: This work was supported by the National Key Research and Development Program of China [Grant 2023YFA1009401] and the National Natural Science Foundation of China [Grants 11571350 and 12201618].

A two-stage regression framework for automated cephalometric landmark detection incorporating semantically fused anatomical features and multi-head refinement loss

Accurate identification and precise localization of cephalometric landmarks provide clinicians with essential insights into craniofacial deformities, aiding in the assessment of treatment strategies for improved patient outcomes. The current methodologies heavily depend on the utilization of multiple CNNs for predicting landmark coordinates, which makes them computationally burdensome and unsuitable for translation to clinical applications. To overcome this limitation, we propose a novel, end-to-end trainable, two-stage regression framework for cephalometric landmark detection. In the initial stage, a single neural network is employed to estimate the locations of all landmarks simultaneously, enabling the identification of potential landmark regions. In the second stage, a semantic fusion block leverages the in-network multi-resolution feature hierarchy to produce high-level semantically rich features. These feature maps are then cropped based on coarsely detected landmark locations and concurrent refinement loss is used to fine-tune and refine the landmark locations. The proposed framework demonstrates the potential for enhancing clinical workflow and treatment outcomes in orthodontics. This is achieved through the utilization of a single CNN backbone augmented with multi-resolution semantically fused anatomical features, which effectively enhances representation learning in a computationally efficient manner. The performance of the proposed framework is evaluated on two publicly available anatomical landmark datasets. The experimental results demonstrate that our framework achieves a state-of-the-art detection accuracy of 87.17% within the clinically accepted range of 2 mm. The source code and the pre-trained weights are made publicly available at this https://github.com/manwaarkhd/CEPHMark-Net, promoting reproducibility and enabling further advancements.

Interaction-and-Response Network for Distantly Supervised Relation Extraction.

Distantly supervised relation extraction (DSRE) aims to identify semantic relations from massive plain texts. A broad range of the prior research has leveraged a series of selective attention mechanisms over sentences in a bag to extract relation features without considering dependencies among the relation features. As a result, potential discriminative information existed in the dependencies is ignored, causing a decline in the performance of extracting entity relations. In this article, we focus on going beyond the selective attention mechanisms and propose a new framework termed interaction-and-response network (IR-Net) that adaptively recalibrates the features of sentence, bag, and group levels by explicitly modeling interdependencies among the features on each level. The IR-Net consists of a series of interactive and responsive modules throughout feature hierarchy, seeking to strengthen its power of learning salient discriminative features for distinguishing entity relations. We conduct extensive experiments on three benchmark DSRE datasets, including NYT-10, NYT-16, and Wiki-20m. The experimental results demonstrate that the IR-Net brings obvious improvements in performance when comparing ten state-of-the-art DSRE methods for entity relation extraction.

NTSM: a non-salient target segmentation model for oral mucosal diseases

BackgroundOral mucosal diseases are similar to the surrounding normal tissues, i.e., their many non-salient features, which poses a challenge for accurate segmentation lesions. Additionally, high-precision large models generate too many parameters, which puts pressure on storage and makes it difficult to deploy on portable devices.MethodsTo address these issues, we design a non-salient target segmentation model (NTSM) to improve segmentation performance while reducing the number of parameters. The NTSM includes a difference association (DA) module and multiple feature hierarchy pyramid attention (FHPA) modules. The DA module enhances feature differences at different levels to learn local context information and extend the segmentation mask to potentially similar areas. It also learns logical semantic relationship information through different receptive fields to determine the actual lesions and further elevates the segmentation performance of non-salient lesions. The FHPA module extracts pathological information from different views by performing the hadamard product attention (HPA) operation on input features, which reduces the number of parameters.ResultsThe experimental results on the oral mucosal diseases (OMD) dataset and international skin imaging collaboration (ISIC) dataset demonstrate that our model outperforms existing state-of-the-art methods. Compared with the nnU-Net backbone, our model has 43.20% fewer parameters while still achieving a 3.14% increase in the Dice score.ConclusionsOur model has high segmentation accuracy on non-salient areas of oral mucosal diseases and can effectively reduce resource consumption.

Unsupervised multi-level spatio-spectral fusion transformer for hyperspectral image super-resolution

Fusing a low spatial resolution hyperspectral image (LR-HSI) with a high spatial resolution multispectral image (HR-MSI) is widely used for HSI super-resolution. Recent works still face problems in exploring global spatio-spectral correlation and lack effective utilization of multi-level features of the inputs (i.e., HR-MSI and LR-HSI), which results in a lack of similarity between the reconstruction and the inputs, ultimately causing significant spatio-spectral distortion. To solve these problems, we design an Unsupervised Multi-level Spatio-spectral Fusion Transformer (UMSFT). In UMSFT, a novel multi-level features fusion strategy is constructed, which fuses the hierarchy features of the inputs via proposed Spatio-spectral Feature Fusion Attention Blocks (S2F-FAB) in a level-by-level manner, thereby fully exploring the interaction between the hierarchical features. The S2F-FAB is specially designed for HSI-MSI fusion consisting of two components: (1) a spatial fusion module (Spa-FM) is designed for spatial domain fusion, and its output is set as Values (V) of a transformer; (2) a novel spectral feature cross attention (Spe- FCA) formulates the features of LR-HSI and HR-MSI as Queries (Q) and Keys (K), respectively, and achieves spectral domain fusion by applying attention mechanism along the spectral dimension. Incorporating spatial detail reconstruction and spectral feature integration into the attention mechanism, the S2F-FAB efficiently exploits the spatio-spectral correlation between target HR-HSI and inputs. Experimental results on three public datasets and our real-world images show the superiority of our method as compared with eleven state-of-the-art methods. Codes will be available at https://github.com/Caoxuheng/HIFtool.

Measurement of aero-engine feature-hierarchy fusion degradation trend based on parameter-adaptive VMD method and improved transformer model

The accumulation of operational time in aero-engines leads to irreversible mechanical wear and tear, necessitating accurate measurement of the health evolution trend for effective predictive maintenance, thus reducing the risk of accidents and ensuring personnel safety. In this paper, a parameter-adaptive variational mode decomposition (VMD) method and improved transformer model are proposed to forecast the degradation trend of aero-engine feature hierarchy fusion. Firstly, in order to quantitatively evaluate the engine health evolution process, the health state aggregate indicator (HSAI) is innovatively constructed by employing the deep blend auto-encoder and self-organizing map network, which facilitate the feature-hierarchy fusion of multi-source sensory data. Secondly, for the significant characteristics with nonlinearity and stochastic fluctuation of the HSAI sequence, the multiscale frequency features are extracted by the parameter-adaptive VMD method with the improved gray wolf optimizer, which analyzes the inherent degradation law. Finally, considering the problem of parameter sharing in the transformer model, a simplified mixture of experts routing algorithm is introduced to implement the switch transformer model to further measure the future aero-engine health trends. Extensive experiments on the multi-source dataset of aero-engine confirm that the proposed method accomplishes the more superior performance for health evolution measurement compared with other available methods.

An Innovative Approach: Sea Ice Types Classification Using Convolutional Neural Networks with DDDTDWT Filter

Studying sea ice and its interaction with climate change is crucial due to its significant impact on the environment, society, and global stability. The pressing need to address the underlying reasons for the rapid melting of Arctic and Antarctic sea ice is underscored by its adverse effects on the environment and society. In this proposed study, a Convolutional Neural Network (CNN) is utilized to predict ice types using data from the NSIDC DAAC Advanced Microwave Scanning Radiometer - Earth Observing System Sensor (AMSR-E) collection. This dataset contains parameters such as sea ice types and spans data products from June 2002, obtained from the NASA Data Centre. By employing hand-crafted features as input and a single layer of hidden nodes, the CNN used in this approach generates improved estimates of ice types, outperforming traditional image analysis methods. At each stage, ConvNets use diverse filter banks, feature extraction pooling layers, and fully connected layers with basic activation functions like Relu. This allows the network to build multifaceted hierarchies of features. The sea ice type estimates produced by the CNN are then compared with those obtained from passive microwave brightness temperature data using existing algorithms as well as a proposed CNN algorithm, resulting in an increased classification accuracy of 98.58%. This improvement is particularly notable in the reduction of the error rate, which has been effectively minimized from 3.01% without feature selection to 1.42% with infinite feature selection. When compared to existing algorithms, the CNN demonstrates superior performance. These findings underscore the impact of input patch size, CNN layer count, and input size on the model's performance.