Multi-layer Feature Extraction Research Articles

Predicting lncRNA-Disease Associations Based on a Dual-Path Feature Extraction Network with Multiple Sources of Information Integration.

Identifying the associations between long noncoding RNAs (lncRNAs) and disease is critical for disease prevention, diagnosis and treatment. However, conducting wet experiments to discover these associations is time-consuming and costly. Therefore, computational modeling for predicting lncRNA-disease associations (LDAs) has become an important alternative. To enhance the accuracy of LDAs prediction and alleviate the issue of node feature oversmoothing when exploring the potential features of nodes using graph neural networks, we introduce DPFELDA, a dual-path feature extraction network that leverages the integration of information from multiple sources to predict LDA. Initially, we establish a dual-view structure of lncRNAs and disease and a heterogeneous network of lncRNA-disease-microRNA (miRNA) interactions. Subsequently, features are extracted using a dual-path feature extraction network. In particular, we employ a combination of a graph convolutional network, a convolutional block attention module, and a node aggregation layer to perform multilayer topology feature extraction for the dual-view structure of lncRNAs and diseases. Additionally, we utilize a Transformer model to construct the node topology feature residual network for obtaining node-specific features in heterogeneous networks. Finally, XGBoost is employed for LDA prediction. The experimental results demonstrate that DPFELDA outperforms the benchmark model on various benchmark data sets. In the course of model exploration, it becomes evident that DPFELDA successfully alleviates the issue of node feature oversmoothing induced by graph-based learning. Ablation experiments confirm the effectiveness of the innovative module, and a case study substantiates the accuracy of DPFELDA model in predicting novel LDAs for characteristic diseases.

RCRFNet: Enhancing Object Detection with Self-Supervised Radar-Camera Fusion and Open-Set Recognition.

Robust object detection in complex environments, poor visual conditions, and open scenarios presents significant technical challenges in autonomous driving. These challenges necessitate the development of advanced fusion methods for millimeter-wave (mmWave) radar point cloud data and visual images. To address these issues, this paper proposes a radar-camera robust fusion network (RCRFNet), which leverages self-supervised learning and open-set recognition to effectively utilise the complementary information from both sensors. Specifically, the network uses matched radar-camera data through a frustum association approach to generate self-supervised signals, enhancing network training. The integration of global and local depth consistencies between radar point clouds and visual images, along with image features, helps construct object class confidence levels for detecting unknown targets. Additionally, these techniques are combined with a multi-layer feature extraction backbone and a multimodal feature detection head to achieve robust object detection. Experiments on the nuScenes public dataset demonstrate that RCRFNet outperforms state-of-the-art (SOTA) methods, particularly in conditions of low visual visibility and when detecting unknown class objects.

ALdamage-seg: A Lightweight Model for Instance Segmentation of Aluminum Profiles

Aluminum profiles are widely used in various manufacturing sectors due to their flexibility and chemical properties. However, these profiles are susceptible to defects during manufacturing and transportation. Detecting these defects is crucial, but existing object detection models like Mask R-CNN and YOLOv8-seg are not optimized for this task. These models are large and computationally intensive, making them unsuitable for edge devices used in industrial inspections. To address this issue, this study proposes a novel lightweight instance segmentation model called AL-damage-seg, inspired by the YOLOv8n-seg architecture. This model utilizes MobileNetV3 as the backbone. In YOLOv8n-seg, the role of C2f is to enhance the nonlinear representation of the model to capture complex image features more efficiently. We upgraded and improved it to form multilayer feature extraction module (MFEM) and integrates a large separable kernel attention (LSKA) mechanism in the C2f module, resulting in C2f_LSKA, to further optimize the performance of the model. Additionally, depth-wise separable convolutions are employed in the feature fusion process. The ALdamage-seg’s weight on the Alibaba Tian-chi aluminum profile dataset constitutes 43.9% of that of YOLOv8n-seg, with its GFLOPs reduced to 53% relative to YOLOv8-seg, all the while achieving an average precision (mAP) of 99% relative to YOLOv8-seg. With its compact size and lower computational requirements, this model is well-suited for deployment on edge devices with limited processing capabilities.

Differentiable double clustering with edge-aware superpixel fitting for unsupervised image segmentation

Unsupervised image segmentation is an essential topic in the field of computer vision, which broke the limitation of training data and expanded application scenarios. Off-the-shelf clustering methods simply rely on semantic concepts and incomplete boundary cues, resulting in incorrect segmentation in object boundaries. Therefore, this paper proposes an unsupervised image segmentation framework combining differentiable double clustering (DDC) and edge-aware superpixel (EA), which outperform prior work on the accuracy of the prior art. First, a multi-layer feature extraction network is introduced to combine low-level and high-level features for clustering. Then, the DDC module is designed to obtain initial labels of pixels from both local and global perspectives to improve the clustering accuracy. Pixel-wise feature similarity in different classes is pushed away, and one in the same class is brought closer. Finally, we use EA to provide well-fitting boundary cues for DDC label fusion to reduce incorrect segmentation. Extensive experiments on the benchmark datasets PASCAL VOC2012 [34] and BSD500 demonstrate that the proposed method provides competitive segmentation results.

Deep transfer learning with gravitational search algorithm for enhanced plant disease classification

Plant diseases annually cause damage and loss of much of the crop, if not its complete destruction, and this constitutes a significant challenge for farm owners, governments, and consumers alike. Therefore, identifying and classifying diseases at an early stage is very important in order to sustain local and global food security. In this research, we designed a new method to identify plant diseases by combining transfer learning and Gravitational Search Algorithm (GSA). Two state-of-the-art pretrained models have been adopted for extracting features in this study, which are MobileNetV2 and ResNe50V2. Multilayer feature extraction is applied in this study to ensure representations of plant leaves from different levels of abstraction for precise classification. These features are then concatenated and passed to GSA for optimizing them. Finally, optimized features are passed to Multinomial Logistic Regression (MLR) for final classification. This integration is essential for categorizing 18 different types of infected and healthy leaf samples. The performance of our approach is strengthened by a comparative analysis that incorporates features optimized by the Genetic Algorithm (GA). Additionally, the MLR algorithm is contrasted with K-Nearest Neighbors (KNN). The empirical findings indicate that our model, which has been refined using GSA, achieves very high levels of precision. Specifically, the average precision for MLR is 99.2%, while for KNN it is 98.6%. The resulting results significantly exceed those achieved with GA-optimized features, thereby highlighting the superiority of our suggested strategy. One important result of our study is that we were able to decrease the number of features by more than 50%. This reduction greatly reduces the processing requirements without sacrificing the quality of the diagnosis. This work presents a robust and efficient approach to the early detection of plant diseases. The work demonstrates the utilization of sophisticated computational methods in agriculture, enabling the development of novel data-driven strategies for plant health management, therefore enhancing worldwide food security.

Lightweight semantic segmentation network for tumor cell nuclei and skin lesion.

In the field of medical image segmentation, achieving fast and accurate semantic segmentation of tumor cell nuclei and skin lesions is of significant importance. However, the considerable variations in skin lesion forms and cell types pose challenges to attaining high network accuracy and robustness. Additionally, as network depth increases, the growing parameter size and computational complexity make practical implementation difficult. To address these issues, this paper proposes MD-UNet, a fast cell nucleus segmentation network that integrates Tokenized Multi-Layer Perceptron modules, attention mechanisms, and Inception structures. Firstly, tokenized MLP modules are employed to label and project convolutional features, reducing computational complexity. Secondly, the paper introduces Depthwise Attention blocks and Multi-layer Feature Extraction modules. The Depthwise Attention blocks eliminate irrelevant and noisy responses from coarse-scale extracted information, serving as alternatives to skip connections in the UNet architecture. The Multi-layer Feature Extraction modules capture a wider range of high-level and low-level semantic features during decoding and facilitate feature fusion. The proposed MD-UNet approach is evaluated on two datasets: the International Skin Imaging Collaboration (ISIC2018) dataset and the PanNuke dataset. The experimental results demonstrate that MD-UNet achieves the best performance on both datasets.

Semantics-enhanced discriminative descriptor learning for LiDAR-based place recognition

LiDAR-based place recognition (LPR) aims to localize autonomous vehicles and mobile robots relative to pre-built maps or retrieve previously visited places. However, the complexity of real-world scenes and changes in viewpoint are significant challenges for place recognition. As high-level information, semantics makes it easier to distinguish geometrically similar scene situations. Unlike most existing methods that rely solely on a single type of information (geometric or semantic) to construct scene descriptors, we consider the complementary nature of the semantic and geometric information and propose a semantics-enhanced discriminative feature learning method for LPR. Specifically, we first develop a Multi-layer Fusion Feature Extraction Network (MFFEN) based on the transformer encoder to hierarchically fuse local geometric and semantic information and utilize contextual information for extracting discriminative local features. To obtain semantic information, we introduce the dynamic graph convolution network to extract local semantic features with local relations. In addition, to weaken the interference of redundancy and dynamic objects in the scene, we design a semantics-guided local attention network (SLAN) to focus on salient local features that are helpful for recognizing scenes, thereby enhancing the descriptive ability of the global descriptor. Extensive experiments on public datasets KITTI and KITTI-360 demonstrate that the proposed method performs better than recent LiDAR-based methods on the 3D place recognition task. For instance, it achieves the mean F1max score of 96.9% on the KITTI dataset, surpassing the strongest prior model by 2.7%.

MFE-Net: A Multi-Layer Feature Extraction Network for No-Reference Quality Assessment of 3-D Point Clouds

MFE-Net: A Multi-Layer Feature Extraction Network for No-Reference Quality Assessment of 3-D Point Clouds

Multi-Layer Feature Extraction with Deformable Convolution for Fabric Defect Detection

Multi-Layer Feature Extraction with Deformable Convolution for Fabric Defect Detection

A Multiscale and Multilayer Feature Extraction Network With Dual Attention for Tropical Cyclone Intensity Estimation

A Multiscale and Multilayer Feature Extraction Network With Dual Attention for Tropical Cyclone Intensity Estimation

A Multitask Integrated Deep-Learning Probabilistic Prediction for Load Forecasting

Spinning reserve without accurate load forecasting can lead to automatic disconnection of critical loads by under-frequency load shedding devices. Such a predicament poses a grave threat to the economic and social welfare of the affected region, and in extreme scenarios, can result in a debilitating grid collapse. However, existing models lack the deep feature extraction capability and cannot accurately predict the uncertainty of electricity demand. Thus, a multitask integrated deep-learning probabilistic prediction with multidimensional feature extraction based on granularity information and quantile regression is explored in this study to solve the insufficient feature extraction problem in probabilistic prediction. In the proposed scheme, we designed a multi-layer feature extraction framework, which information granularity based on fuzzy rough sets to extract time-domain features, multilayer Laplace operators to extract features globally, and quantile regression recurrent neural network variants to extract time context information. In addition, the Pareto integration method is extended to capture better individuals. The experimental results demonstrate that the proposed system can effectively improve deterministic forecasting and uncertainty analysis of electricity demand and manage daily fluctuations.

Skin-Net: a novel deep residual network for skin lesions classification using multilevel feature extraction and cross-channel correlation with detection of outlier

Human Skin cancer is commonly detected visually through clinical screening followed by a dermoscopic examination. However, automated skin lesion classification remains challenging due to the visual similarities between benign and melanoma lesions. In this work, the authors proposed a new Artificial Intelligence-Based method to classify skin lesions. In this method, we used Residual Deep Convolution Neural Network. We implemented several convolution filters for multi-layer feature extraction and cross-channel correlation by sliding dot product filters instead of sliding filters along the horizontal axis. The proposed method overcomes the imbalanced dataset problem by converting the dataset from image and label to vector of image and weight. The proposed method is tested and evaluated using the challenging datasets ISIC-2019 & ISIC-2020. It outperformed the existing deep convolutional networks in the multiclass classification of skin lesions.Graphical

Multi-State Online Estimation of Lithium-Ion Batteries Based on Multi-Task Learning

Deep learning-based state estimation of lithium batteries is widely used in battery management system (BMS) design. However, due to the limitation of on-board computing resources, multiple single-state estimation models are more difficult to deploy in practice. Therefore, this paper proposes a multi-task learning network (MTL) combining a multi-layer feature extraction structure with separated expert layers for the joint estimation of the state of charge (SOC) and state of energy (SOE) of Li-ion batteries. MTL uses a multi-layer network to extract features, separating task sharing from task-specific parameters. The underlying LSTM initially extracts time-series features. The separated expert layer, consisting of task-specific and shared experts, extracts features specific to different tasks and shared features for multiple tasks. The information extracted by different experts is fused through a gate structure. Tasks are processed based on specific and shared information. Multiple tasks are trained simultaneously to improve performance by sharing the learned knowledge with each other. SOC and SOE are estimated on the Panasonic dataset, and the model is tested for generalization performance on the LG dataset. The Mean Absolute Error (MAE) values for the two tasks are 1.01% and 0.59%, and the Root Mean Square Error (RMSE) values are 1.29% and 0.77%, respectively. For SOE estimation tasks, the MAE and RMSE values are reduced by 0.096% and 0.087%, respectively, when compared with single-task learning models. The MTL model also achieves reductions of up to 0.818% and 0.938% in MAE and RMSE values, respectively, compared to other multi-task learning models. For SOC estimation tasks, the MAE and RMSE values are reduced by 0.051% and 0.078%, respectively, compared to single-task learning models. The MTL model also outperforms other multi-task learning models, achieving reductions of up to 0.398% and 0.578% in MAE and RMSE values, respectively. In the process of simulating online prediction, the MTL model consumes 4.93 ms, which is less than the combined time of multiple single-task learning models and almost the same as that of other multi-task learning models. The results show the effectiveness and superiority of this method.

Fine-grained Vehicle Classification Based on Feature Augmentation

Fine-grained vehicle classification is a hot research topic in the field of computer vision, which aims to recognize different models of vehicles belonging to the same brand. Limited by the large appearance differences of the same vehicle (due to different attitudes and perspectives) and small appearance differences between different vehicles, the vehicle’s reorganization performance is not high and can’t meet the real application requirements. In this paper, a Fine-grained Vehicle Classification is proposed based on Feature Augmentation (FAFCC), which focuses on mining the key discriminative parts of the object. Specifically, the FAFCC first improves the weakly supervised data augmentation network (WSDAN) by using multi-layer feature extraction and fusion instead of single-layer features. Further, the FAFCC assigns local feature weights to select key features, which can solve the problem that the discriminant features in the channel are not prominent enough and realize the high-quality compact fine-grained vehicle recognition task. The performance of the FAFCC on the fine-grained image classification tasks for vehicles has been evaluated through algorithm comparison experiments and ablation experiments. Through visual analysis, it can be seen that the introduction of each new module has optimized the loss function value and convergence speed of the model. In general, our FAFCC algorithm has a certain improvement effect compared with the original algorithm.

Cell Phenotype Classification Based on Joint of Texture Information and Multilayer Feature Extraction in DenseNet.

Cell phenotype classification is a critical task in many medical applications, such as protein localization, gene effect identification, and cancer diagnosis in some types. Fluorescence imaging is the most efficient tool to analyze the biological characteristics of cells. So cell phenotype classification in fluorescence microscopy images has received increased attention from scientists in the last decade. The visible structures of cells are usually different in terms of shape, texture, relationship between intensities, etc. In this scope, most of the presented approaches use one type or joint of low-level and high-level features. In this paper, a new approach is proposed based on a combination of low-level and high-level features. An improved version of local quinary patterns is used to extract low-level texture features. Also, an innovative multilayer deep feature extraction method is performed to extract high-level features from DenseNet. In this respect, an output feature map of dense blocks is entered in a separate way to pooling and flatten layers, and finally, feature vectors are concatenated. The performance of the proposed approach is evaluated on the benchmark dataset 2D-HeLa in terms of accuracy. Also, the proposed approach is compared with state-of-the-art methods in terms of classification accuracy. Comparison of results demonstrates higher performance of the proposed approach in comparison with some efficient methods.

Joint modulation format recognition and optical performance monitoring for efficient fiber-optic communication links using ensemble deep transfer learning

We propose an ensemble deep transfer learning (EDTL) method, which is a more refined multilayer feature extraction achieved by aggregating the convolutional layers of pretrained convolutional neural network models for joint optical modulation format recognition (MFR) and optical performance monitoring (OPM) in fiber-optic communication links. Modulation formats, such as quadrature phase shift keying, 16 quadrature amplitude modulation (QAM), and 64 QAM, are monitored for the optical signal-to-noise ratio (OSNR) range of 20 to 30 dB by considering the dispersive effects of chromatic dispersion from 0 to 1200 ps / nm and polarization mode dispersion from 10 to 70 ps in the fiber-optic transmission path. First, the generated constellation diagrams affected by the impairments are used to optimize and evaluate the pretrained models based on classification targets. Then the proposed EDTL model is designed by aggregating the feature extractor parts of the pretrained models; it is implemented in three phases, and the results are comprehensively studied. Further, data augmentation and aggregation methods are introduced to enhance the performance of joint MFR and OPM. The results obtained prove that the proposed model provides faster convergence of MFR and better identification accuracy of OSNR toward optical signal diagnostics in optical networks for efficient optical link monitoring.

Multilayer Feature Extraction of AGCN on Surface Defect Detection of Steel Plates.

The development of industry is inseparable from the support of steel materials, and the modern industry has increasingly high requirements for the quality of steel plates. But the process of steel plate production produces many types of defects, such as roll marks, scratches, and scars. These defects will directly affect the quality and performance of the steel plate, so it is necessary to effectively detect them. Steel plate surface defects are characterized by their types, shape, and size: the same defect can have different morphologies, and similarities can exist between different defects. In this paper, industrial steel plate surface defect samples are analyzed, and a sample set is established by screening the collected defect images. Then, annotation and classification are performed. A multilayer feature extraction framework is developed in experiments to train a neural network on the sample set of defects. To address the problems of low automation, slow detection speed, and low accuracy of the traditional defect detection methods, the attention graph convolution network (AGCN) is investigated in this paper. Firstly, faster R-CNN is used as the basic network model for defect detection, and the visual features are jointly refined by combining attention mechanism and graph convolution neural network. The latter network enriches the contextual information in the visual features of steel plates and explores the semantic association between vision and defect types for different kinds of defects using the attention mechanism to achieve intelligent detection of defects, thus enabling our method to meet the practical needs of steel plate production.

Multi-step ahead traffic speed prediction based on gated temporal graph convolution network

Improving the traffic efficiency of the existing roads in the city has become an important task for the traffic management department. Timely and accurate traffic prediction is the key to urban traffic control and guidance. The multi-layer automatic feature extraction and expression ability of deep learning is deeply integrated with the non-linearity, multi-modality, and spatiotemporal correlation of traffic flow. A multi-step ahead traffic speed prediction based on gated temporal graph convolution network (GT-GCN) is proposed in this paper. Firstly, a dynamic weighted graph network is constructed according to the traffic road network structure, and then a graph convolutional network is used to process the graph structure data of the traffic road network and capture the spatial characteristics of the traffic flow. Subsequently, a gated temporal convolutional network is applied to capture the short- and long-range temporal correlations of traffic flow. Finally, a multi-step ahead prediction model based on a hybrid deep learning framework GT-GCN is proposed. Experiments using real datasets show that the proposed GT-GCN has a significant multi-step predictive performance compared to the baseline models.

An ensemble-policy non-intrusive load monitoring technique based entirely on deep feature-guided attention mechanism

Non-intrusive load monitoring (NILM), as an important part of intelligent electricity consumption, improves the cognitive level of the load by analyzing the bus power in a specific range to obtain refined electricity consumption data at appliance level in that range, such as the number of loads, load categories, load operating status and corresponding energy consumption. For a long time, the research on NILM algorithm has been quite in depth, especially with the deep learning method being used in NILM, breakthrough progress has been made. In this paper, an integrated policy non-intrusive load monitoring technique based entirely on deep feature-guided attention mechanism is constructed based on sequence-to-point deep neural networks. Firstly, according to the operating cycle characteristics of different appliances, the data are segmented with different sliding windows and the integerized power values are mapped to high-dimensional feature vectors by word embedding, which transforms the value regression problem of decomposed power into a multiclassification problem to find the probability of decomposed power values at each discrete integer power value. Then the encoder composed of deep residual network is used for multi-layer feature extraction, which is used to obtain richer feature information, and the extracted feature quantities will be sent to the decoder through two paths respectively, one is mapped to the power feature space through word embedding as the input to the decoder; the other is sent to the decoder based entirely on the attention mechanism through convolution as the checked vector K and the content vector V. The decoder obtains the information with the highest relevance to the current moment by assigning weights to the before and after information, and thus decodes the final load decomposition result. Finally, this paper introduces a snapshot technique to obtain an inexpensive multi-model integration strategy, which improves the generalization ability of the model and the accuracy of the load decomposition. The effectiveness of the proposed method is verified by experiments on the REDD dataset and UK-DALE dataset.

Deep attentive spatio-temporal feature learning for automatic resting-state fMRI denoising

Resting-state functional magnetic resonance imaging (rs-fMRI) is a non-invasive functional neuroimaging modality that has been widely used to investigate functional connectomes in the brain. Since noise and artifacts generated by non-neuronal physiological activities are predominant in raw rs-fMRI data, effective noise removal is one of the most important preprocessing steps prior to any subsequent analysis. For rs-fMRI denoising, a common trend is to decompose rs-fMRI data into multiple components and then regress out noise-related components. Therefore, various machine learning techniques have been used in such analyses with predefined procedures and manually engineered features. However, the lack of a universal definition of a noise-related source or artifact complicates manual feature engineering. Manual feature selection can result in the failure to capture unknown types of noise. Furthermore, the possibility that the hand-crafted features will only work for the broader population (e.g., healthy adults) but not for “outliers” (e.g., infants or subjects that belong to a disease cohort) is quite high. In practice, we have limited knowledge of which features should be extracted; thus, multi-classifier assembly must be implemented to improve performance, although this process is quite time-consuming. However, in real rs-fMRI applications, fast and accurate automatic identification of noise-related components on different datasets is critical. To solve this problem, we propose a novel, automatic, and end-to-end deep learning framework dedicated to noise-related component identification via a faster and more effective multi-layer feature extraction strategy that learns deeply embedded spatio-temporal features of the components. In this study, we achieved remarkable performance on various rs-fMRI datasets, including multiple adult rs-fMRI datasets from different rs-fMRI studies and an infant rs-fMRI dataset, which is quite heterogeneous and differs from that of adults. Our proposed framework also dramatically increases the noise detection speed owing to its inherent ability for deep learning (< 1s for single-component classification). It can be easily integrated into any preprocessing pipeline, even those that do not use standard procedures but depend on alternative toolboxes.