Network Classifier Research Articles

The development of machine learning approaches in two-dimensional NMR data interpretation for metabolomics applications

Metabolomics has been widely applied in human diseases and environmental science to study the systematic changes of metabolites over diverse types of stimuli. NMR-based metabolomics has been widely used, but the peak overlap problems in the one-dimensional (1D) NMR spectrum could limit the accuracy of quantitative analysis for metabolomics applications. Two-dimensional (2D) NMR has been applied to solve the 1D NMR overlap problem, but the data processing is still challenging. In this study, we built an automatic approach to process the 2D NMR data for quantitative applications using machine learning approaches. Partial least square discriminant analysis (PLS-DA), artificial neural network classification (ANN-DA), gradient boosted trees classification (XGBoost-DA), and artificial deep learning neural network classification (ANNDL-DA) were applied in combination with an automatic peak selection approach. Standard mixtures, sea anemone extracts, and mouse fecal samples were tested to demonstrate the approach. Our results showed that ANN-DA and ANNDL-DA have high accuracy in selecting 2D NMR peaks (around 90 %), which have a high potential application in 2D NMR-based metabolomics quantitively study, while PLS-DA and XGBoost-DA showed limitations in either data variation or overfitting. Our study built an automatic approach to applying 2D NMR data to routine quantitative analysis in metabolomics.

A novel method for the classification of 3D point clouds based on the improved PointNet++

Abstract In deep learning, point clouds are used as the primary input format for 3D data, which can provide detailed geometric information about objects in the original 3D space. PointNet++ is a deep learning network that uses point cloud data as an input format, which avoids the losses associated with the previous conversion of point cloud into 3D voxelization and a collection of 2D images. Although PointNet++ can directly process point cloud data in various ways, due to the disordered, irregular, and unevenly distributed nature of point cloud data, the effect of extracting point cloud features could be better. The large amount of point cloud data also leads to the training model falling into the local optimal solution, which affects the training results. In recent years, some effective methods and strategies have emerged to address these problems. In this thesis, three methods are proposed based on the PointNet++ network: feature similarity-based attention pooling, small kernel convolution, and diverse branch block method to improve the performance of the PointNet++ network. Experiments show that the improvement methods proposed in this paper effectively improve the feature extraction accuracy, which improves the accuracy of the PointNet++ network for classification on the ModelNet40_Normal_Resampled dataset, with an overall improvement of 1% compared with PointNet++.

UB-FineNet: Urban building fine-grained classification network for open-access satellite images

Fine classification of city-scale buildings using satellite imagery is a crucial research area with significant implications for urban planning, infrastructure development, and population distribution analysis. However, the task faces great challenges due to low-resolution overhead images acquired from high-altitude space-borne platforms and the long-tailed sample distribution of fine-grained urban building categories, leading to a severe class imbalance problem. To address these issues, we propose a deep network approach to the fine-grained classification of urban buildings using open-access satellite images. A Denoising Diffusion Probabilistic Model (DDPM) based super-resolution method is first introduced to enhance the spatial resolution of satellite images, which benefits from domain-adaptive knowledge distillation. Then, a new fine-grained classification network with Category Information Balancing Module (CIBM) and Contrastive Supervision (CS) technique is proposed to mitigate the problem of class imbalance and improve the classification robustness and accuracy. Experiments on Hong Kong data set with 11 distinct building types revealed promising classification results with a mean Top-1 accuracy of 60.45%, which is on par with street-view image based approaches. A comprehensive ablation study demonstrates that the CIBM and CS modules improve Top-1 accuracy by 2.6% and 3.5%, respectively, over the baseline approach. In addition, these modules can be easily integrated into other classification networks, achieving similar performance improvements. This research advances urban analysis by providing an effective solution for detailed classification of buildings in complex mega-city environments using only open-access satellite imagery. The proposed technique can serve as a valuable tool for urban planners, aiding in the understanding of economic, industrial, and population distribution within cities and regions, ultimately facilitating informed decision-making in urban development and infrastructure planning. Data and code will be publicly available at https://github.com/ZhiyiHe1997/UB-FineNet.

EEG-CogNet: A deep learning framework for cognitive state assessment using EEG brain connectivity

The assessment of cognitive states such as workload, attention, and fatigue is crucial in cognitive science and human performance fields due to its significant impact on work efficiency and decision-making. This paper introduces a deep learning framework for cognitive state assessment using Electroencephalogram (EEG) brain connectivity. The framework was evaluated using EEG data from 26 participants through three computer-based tasks: the Dual N-Back Task, Visual Search Task, and Continuous Performance Task, each designed to induce varying levels of cognitive workload, attention, and fatigue, respectively. A comprehensive dataset was meticulously compiled, including physiological, behavioral, and subjective data to ensure robust analyses. The EEG data underwent rigorous pre-processing and feature extraction processes, focusing on brain connectivity metrics such as Coherence and Phase-Locking Value across multiple frequency bands and employing three neural network architectures: Convolutional Neural Networks (CNN), Graph Convolutional Networks (GCN), and Convolutional Long Short-Term Memory networks (ConvLSTM) for classification. The proposed work achieved classification accuracies of 96.53% for workload, 98.40% for attention, and 97.86% for fatigue in the combined frequency bands. The study’s findings underscore the potential of EEG-based methods for non-invasive cognitive state monitoring. By addressing existing limitations such as small sample sizes and task-specific models, this research enhances the generalizability and applicability of EEG-based cognitive assessments. The implications of these advancements are significant for fields requiring continuous cognitive monitoring, such as defense, healthcare, and high-risk operational environments.

BCNet: Bronchus Classification via Structure Guided Representation Learning.

CT-based bronchial tree analysis is a key step for the diagnosis of lung and airway diseases. However, the topology of bronchial trees varies across individuals, which presents a challenge to the automatic bronchus classification. To solve this issue, we propose the Bronchus Classification Network (BCNet), a structure-guided framework that exploits the segment-level topological information using point clouds to learn the voxel-level features. BCNet has two branches, a Point-Voxel Graph Neural Network (PV-GNN) for segment classification, and a Convolutional Neural Network (CNN) for voxel labeling. The two branches are simultaneously trained to learn topology-aware features for their shared backbone while it is feasible to run only the CNN branch for the inference. Therefore, BCNet maintains the same inference efficiency as its CNN baseline. Experimental results show that BCNet significantly exceeds the state-of-the-art methods by over 8.0% both on F1-score for classifying bronchus. Furthermore, we contribute BronAtlas: an open-access benchmark of bronchus imaging analysis with high-quality voxel-wise annotations of both anatomical and abnormal bronchial segments. The benchmark is available at link1.

TCPSNet: Transformer and Cross-Pseudo-Siamese Learning Network for Classification of Multi-Source Remote Sensing Images

TCPSNet: Transformer and Cross-Pseudo-Siamese Learning Network for Classification of Multi-Source Remote Sensing Images

A cross-modal feature aggregation and enhancement network for hyperspectral and LiDAR joint classification

Advancements in Earth observation technologies have greatly enhanced the potential of integrating hyperspectral (HS) images with Light Detection and Ranging (LiDAR) data for land use and land cover classification. Despite this, most existing methods primarily focus on employing deep network layers to extract features from two heterogeneous data modalities, often overlooking a gradual modeling data representation approach from shallow to deep layers. Furthermore, excessive network layers can result in the deterioration of modality-specific features, therefore lowering the classification performance. The paper proposed a novel cross-modal feature aggregation and enhancement network for the joint classification of HSI and LiDAR data. Initially, a cross-modal feature fusion module is developed to exploit spatial scale consistency to complete the interchange and fusion of feature embedding at the pixel level, preserving the original information from the two heterogeneous modalities to a certain degree. Then two straightforward strategies (i.e., addition and concatenation) are employed in the shallow network layers before being sent to the transformer encoder. The former facilitates the model’s ability to discern more subtle distinctions and refine spatial location details. The latter ensures the preservation of information integrity, effectively mitigating the risk of feature loss. Moreover, invertible neural networks and a feature enhancement module are introduced, leveraging the complementary information of HSI and LiDAR data to enhance the detail and texture information extracted in deeper layers. Extensive experiments on Houston2013, Trento, and MUUFL datasets demonstrate that the proposed method outperforms several state-of-the-art models in three evaluation metrics, achieving an accuracy improvement of up to 2%. The proposed model brings new inspirations for HSI and LiDAR classification, which is critical for accurate environmental monitoring, urban planning, and precision agriculture. The source code is publicly accessible at https://github.com/zhangyiyan001/CMFAEN.

MTLSC-Diff: Multitask learning with diffusion models for hyperspectral image super-resolution and classification

Hyperspectral image (HSIs) super-resolution (SR) can improve the spatial resolution of images for subsequent application tasks. In recent years, SR methods based on deep learning have gained widespread attention. However, most of the existing SR methods do not take into account the needs of specific application tasks when designing the network structure. These methods may not be able to efficiently generate high-quality images that satisfy the specific application tasks, leading to degradation of the performance of subsequent application tasks. To solve this problem, we propose a multi-task learning architecture based on the diffusion model, namely MTLSC-Diff. MTLSC-Diff combines the SR network and the classification network in a multi-task learning manner on the basis of the diffusion model. MTLSC-Diff achieves mutual guidance of the two tasks by iterating the image super-resolution and classification tasks, thus gradually reconstructing high-quality images and improving classification accuracy. The guided operations for each time step are performed by the specially designed Mutual-Guidance SR-Classification Synergy Module (M-GSCS). M-GSCS refines the multi-scale image obtained at the previous time step and uses the predicted high spatial resolution image for classification. Meanwhile, a class-guided SR dynamic refinement strategy (C-GSR) is proposed in M-GSCS, which uses multi-scale classification results to guide target scale images to learn new knowledge to further reconstruct high-quality images. Experimental results on relevant datasets show that our method significantly improves the super-resolution performance as well as the classification performance.

Disentanglement-inspired single-source domain-generalization network for cross-scene hyperspectral image classification

Cross-scene classification stands as a pivotal frontier in hyperspectral image (HSI) processing, aiming to enhance the generalization capabilities of classification models. However, the diversity of sensor type, shooting environments, and shooting times leads to the spectral heterogeneity problem in HSI. As a result, the same land cover may exhibit varying spectral traits in different domains, posing challenges for cross-scene HSI classification. Drawing inspiration from image disentanglement, we have identified that extracting the latent domain-invariant representation (DIR) of HSI could potentially mitigate the spectral heterogeneity issue. Therefore, we propose a Disentanglement-Inspired Single-Source Domain Generalization Network (DSDGnet) for cross-scene HSI classification in this paper. Firstly, a style transfer module based on a Transformer encoder-transfer-decoder is designed to expand the single source domain to an extended domain. Then, a progressive disentanglement module is proposed to decompose the domain-invariant features and domain-specific features of HSI. Furthermore, a domain combination module is designed to guarantee the accuracy of the progressive disentanglement module and ensure the effectiveness of the domain-invariant feature of HSI. Finally, the domain-invariant features are applied to the classification task, and the domain-specific features are separated to reduce their impact on the generalization ability of classification models. Extensive experiments on three HSI datasets have demonstrated the advanced classification performance of DSDGnet compared to existing domain-generalization methods.

Unbiased Morphometric Assessment of Red Blood Cell Storage Lesion in the Presence of Shear-Induced Stomatocytes

Introduction: Red blood cells (RBCs) undergo progressive biochemical and morphological changes during storage, collectively called storage lesion. The quality of red cell concentrates (RCCs) is typically assessed by quantifying hemolysis. An assessment of morphological changes, associated with low quality RBCs, could give an additional indication of the safety and efficacy of the concentrates. The current standard for determining morphological changes is a manual, laborious, and subjectively biased microscopic process that limits the number of cells that can be examined. When using alternative methods like flow cells, flow and shear-induced morphologies affecting especially stomatocyte morphologies must be taken into account. We already established an automated flow morphometric RBC analysis system as an alternative to manual microscopic evaluation. The goal of the present work is to obtain a robust, automated, morphology-related signal (lesion index) quantifying RBC storage lesion in a laminar flow channel under conditions similar to stasis that is not affected by shear-induced reversible morphology changes. Methods: We use a convolutional neural network (CNN) for high throughput classification of RBCs. We analyzed the morphological changes of 5 RCCs over a period of 12 weeks and classified RBC morphologies, including such that are degradation-induced and reversible. We introduce a lesion index to denote the percentage of irreversible spherical morphologies, known to reduce the post-transfusion survival of erythrocytes. We further addressed shear-induced stomatocyte morphologies in laminar flow and whether these affect CNN-based RBC classification. Results: Our flow morphometry system achieves a high-resolution classification comprising nine morphological classes with an excellent overall accuracy of 92% and F1 scores between 84% and 97%. We generate strong evidence that the morphological lesion index can predict the hemolysis level in RCCs during storage. The power of this new classification technique allowed it, for the first time, to detect and measure the lateral concentration gradient of stomatocytes in a conventional flow chamber. Importantly, we show that reversible shear rate-induced morphologies, typical for microfluidic systems, bear no influence on the lesion index. Conclusion: Flow morphometry combined with evaluation by a CNN allows to reliably assess RBC storage lesion and thus concentrate quality. Additionally, this method reduces the need for complex laboratory procedures.

Multi-Scale Spatial-Temporal Attention Networks for Functional Connectome Classification.

Many neuropsychiatric disorders are considered to be associated with abnormalities in the functional connectivity networks of the brain. The research on the classification of functional connectivity can therefore provide new perspectives for understanding the pathology of disorders and contribute to early diagnosis and treatment. Functional connectivity exhibits a nature of dynamically changing over time, however, the majority of existing methods are unable to collectively reveal the spatial topology and time-varying characteristics. Furthermore, despite the efforts of limited spatial-temporal studies to capture rich information across different spatial scales, they have not delved into the temporal characteristics among different scales. To address above issues, we propose a novel Multi-Scale Spatial-Temporal Attention Networks (MSSTAN) to exploit the multi-scale spatial-temporal information provided by functional connectome for classification. To fully extract spatial features of brain regions, we propose a Topology Enhanced Graph Transformer module to guide the attention calculations in the learning of spatial features by incorporating topology priors. A Multi-Scale Pooling Strategy is introduced to obtain representations of brain connectome at various scales. Considering the temporal dynamic characteristics between dynamic functional connectome, we employ Locality Sensitive Hashing attention to further capture long-term dependencies in time dynamics across multiple scales and reduce the computational complexity of the original attention mechanism. Experiments on three brain fMRI datasets of MDD and ASD demonstrate the superiority of our proposed approach. In addition, benefiting from the attention mechanism in Transformer, our results are interpretable, which can contribute to the discovery of biomarkers. The code is available at https://github.com/LIST-KONG/MSSTAN.

Wide & deep learning for predicting relative mineral compositions of sediment cores solely based on XRF scans, a case study from Pleistocene Paleolake Olduvai, Tanzania

This study develops a method to use deep learning models to predict the mineral assemblages and their relative abundances in paleolake cores using high-resolution XRF core scan elemental data and X-ray diffraction (XRD) mineralogical results from the same core taken at coarser resolution. It uses the XRF core scan data along with published mineralogical information from the Olduvai Gorge Coring Project (OGCP) 2014 sediment cores 1A, 2A, and 3A from Paleolake Olduvai, Tanzania. Both regression and classification models were developed using a Keras deep learning framework to assess the predictability of mineral assemblages with their relative abundances (in regression models) or at least the mineral assemblages (in classification models) using XRF core scan data. Models were created using the Sequential class and Functional API with different model architectures. The correlation matrix of element ratios calculated from XRF element intensity records from the cores and XRD-derived mineralogical information was used to select the most useful features to train the models. 1057 training data records were used for the models. Lithological classes were also used for some models using Wide & Deep neural networks since those combine the benefits of memorization and generalization for mineral prediction. The results were validated using 265 validation data records unseen by the model and discuss the accuracy of models using six test records. The optimized Deep Neural Network (DNN) classification model achieved over 86% binary accuracy while the regression models were also able to predict the relative mineral abundances of samples with high accuracies. Overall, the study shows the efficacy of a carefully crafted Deep Learning (DL) model for predicting mineral assemblages and abundances using high-resolution XRF core scan data.

Retraction Note: A novel multi-layer multi-spiking neural network for EEG signal classification using Mini Batch SGD

Retraction Note: A novel multi-layer multi-spiking neural network for EEG signal classification using Mini Batch SGD

Improved Tunicate Swarm Optimization Based Hybrid Convolutional Neural Network for Classification of Leaf Diseases and Nutrient Deficiencies in Rice (Oryza)

Improved Tunicate Swarm Optimization Based Hybrid Convolutional Neural Network for Classification of Leaf Diseases and Nutrient Deficiencies in Rice (Oryza)

SF-ICNN: Spectral–Fractal Iterative Convolutional Neural Network for Classification of Hyperspectral Images

One primary concern in the field of remote-sensing image processing is the precise classification of hyperspectral images (HSIs). Lately, deep-learning models have demonstrated cutting-edge results in HSI classification. Despite this, researchers continue to study and propose simpler, more robust models. This study presents a novel deep-learning approach, the iterative convolutional neural network (ICNN), which combines spectral–fractal features and classifier probability maps iteratively, aiming to enhance the HSI classification accuracy. Experiments are conducted to prove the accuracy enhancement of the proposed method using HSI benchmark datasets of Indian pine (IP) and the University of Pavia (PU) to evaluate the performance of the proposed technique. The final results show that the proposed approach reaches overall accuracies of 99.16% and 95.5% on the IP and PU datasets, respectively, which are better than some basic methods. Additionally, the end findings demonstrate that greater accuracy levels might be achieved using a primary CNN network that employs the iteration loop than with certain current state-of-the-art spatial–spectral HSI classification techniques.

Hybrid optimal feature selection-based iterative deep convolution learning for COVID-19 classification system

The COVID-19 pandemic has necessitated the development of innovative and efficient methods for early detection and diagnosis. Integrating Internet of Things (IoT) devices and applications in healthcare has facilitated various functions. This work aims to employ practical artificial intelligence (AI) approaches to extract meaningful information from the vast amount of IoT data to perform disease prediction tasks. However, traditional AI methods need help in feature analysis due to the complexity and scale of IoT data. So, this work implements the optimal iterative COVID-19 classification network (OICC-Net) using machine learning optimization and deep learning approaches. Initially, the preprocessing operation normalizes the dataset with uniform values. Here, random forest infused particle swarm-based black widow optimization (RFI-PS-BWO) algorithm was used to get the disease-specific patterns from SARS-CoV-2 (SC2), and other disease classes, where patterns of the SC2 virus are very similar to those of other virus classes. In addition, an iterative deep convolution learning (IDCL) feature selection method is used to distinguish features from the RFI-PS-BWO data. This iterative process enhances the performance of feature selection by providing improved representation and reducing the dimensionality of the input data. Then, a one-dimensional convolutional neural network (1D-CNN) was employed to classify and identify the extracted features from SC2 with no virus classes. The 1D-CNN model is trained using a large dataset of COVID-19 samples, enabling it to learn intricate patterns and make accurate predictions. It was tested and found that the proposed OICC-Net system is more accurate than current methods, with a score of 99.97 % for F1-score, 100 % for sensitivity, 100 % for specificity, 99.98 % for precision, and 99.99 % for recall.

Space-borne DInSAR measurements exploitation for risk classification of bridge networks

Space-borne DInSAR measurements exploitation for risk classification of bridge networks

A multiscale dilated attention network for hyperspectral image classification

Hyperspectral imaging is an image obtained by combining spectral detection technology and imaging technology, which can collect electromagnetic spectra in the wavelength range of visible light to near-infrared. It is an important research content in the field of ground observation in hyperspectral remote sensing. However, hyperspectral image face significant challenges in classification task due to their high spectral dimensions, lack of labeled samples, and strong correlation between bands. In order to fully extract features from both spectral and spatial dimensions and improve classification accuracy in the case of limited training samples, a multiscale dilated attention network is proposed for hyperspectral image classification. First, a three-dimensional convolutional layer is used to extract the shallow features of the image. Then, a multiscale dilated attention module is proposed by combining dilated convolution and channel attention. Using ordinary convolution and dilated convolution to form different receptive fields. Channel attention is used to remodel the obtained multiscale features, enhancing the inter-channel correlation. After that, a multiscale spatial-spectral attention module is constructed using multiple asymmetric convolutions to obtain spatial and spectral attention features at different positions, further enhancing important feature suppression over non-important features. Finally, using softmax to classify the obtained features. Using Indian Pines, Pavia University, KSC and University of Houston as experimental datasets, the overall classification accuracy of this paper’s method achieved 98.97%, 99.14%, 99.45%, and 98.56% respectively, using only 5%, 1%, 10%, and 10% of training samples per class. Compared with seven advanced classification methods, the experimental results show that the proposed method can achieve the highest classification accuracy with limited training samples.

Cutting-edge ensemble framework of deep convolutional neural networks for high-precision insect pest classification

Cutting-edge ensemble framework of deep convolutional neural networks for high-precision insect pest classification

DECNet: Left Atrial Pulmonary Vein Class Imbalance Classification Network.

In clinical practice, the anatomical classification of pulmonary veins plays a crucial role in the preoperative assessment of atrial fibrillation radiofrequency ablation surgery. Accurate classification of pulmonary vein anatomy assists physicians in selecting appropriate mapping electrodes and avoids causing pulmonary arterial hypertension. Due to the diverse and subtly different anatomical classifications of pulmonary veins, as well as the imbalance in data distribution, deep learning models often exhibit poor expression capability in extracting deep features, leading to misjudgments and affecting classification accuracy. Therefore, in order to solve the problem of unbalanced classification of left atrial pulmonary veins, this paper proposes a network integrating multi-scale feature-enhanced attention and dual-feature extraction classifiers, called DECNet. The multi-scale feature-enhanced attention utilizes multi-scale information to guide the reinforcement of deep features, generating channel weights and spatial weights to enhance the expression capability of deep features. The dual-feature extraction classifier assigns a fixed number of channels to each category, equally evaluating all categories, thus alleviating the learning bias and overfitting caused by data imbalance. By combining the two, the expression capability of deep features is strengthened, achieving accurate classification of left atrial pulmonary vein morphology and providing support for subsequent clinical treatment. The proposed method is evaluated on datasets provided by the People's Hospital of Liaoning Province and the publicly available DermaMNIST dataset, achieving average accuracies of 78.81% and 83.44%, respectively, demonstrating the effectiveness of the proposed approach.