[Objective]Accurate prediction of tomato growth height is crucial for optimizing production environments in smart farming.However,current prediction methods predominantly rely on empirical,mechanistic,or learning-base...[Objective]Accurate prediction of tomato growth height is crucial for optimizing production environments in smart farming.However,current prediction methods predominantly rely on empirical,mechanistic,or learning-based models that utilize either images data or environmental data.These methods fail to fully leverage multi-modal data to capture the diverse aspects of plant growth comprehensively.[Methods]To address this limitation,a two-stage phenotypic feature extraction(PFE)model based on deep learning algorithm of recurrent neural network(RNN)and long short-term memory(LSTM)was developed.The model integrated environment and plant information to provide a holistic understanding of the growth process,emploied phenotypic and temporal feature extractors to comprehensively capture both types of features,enabled a deeper understanding of the interaction between tomato plants and their environment,ultimately leading to highly accurate predictions of growth height.[Results and Discussions]The experimental results showed the model's ef‐fectiveness:When predicting the next two days based on the past five days,the PFE-based RNN and LSTM models achieved mean absolute percentage error(MAPE)of 0.81%and 0.40%,respectively,which were significantly lower than the 8.00%MAPE of the large language model(LLM)and 6.72%MAPE of the Transformer-based model.In longer-term predictions,the 10-day prediction for 4 days ahead and the 30-day prediction for 12 days ahead,the PFE-RNN model continued to outperform the other two baseline models,with MAPE of 2.66%and 14.05%,respectively.[Conclusions]The proposed method,which leverages phenotypic-temporal collaboration,shows great potential for intelligent,data-driven management of tomato cultivation,making it a promising approach for enhancing the efficiency and precision of smart tomato planting management.展开更多
Aerodynamic surrogate modeling mostly relies only on integrated loads data obtained from simulation or experiment,while neglecting and wasting the valuable distributed physical information on the surface.To make full ...Aerodynamic surrogate modeling mostly relies only on integrated loads data obtained from simulation or experiment,while neglecting and wasting the valuable distributed physical information on the surface.To make full use of both integrated and distributed loads,a modeling paradigm,called the heterogeneous data-driven aerodynamic modeling,is presented.The essential concept is to incorporate the physical information of distributed loads as additional constraints within the end-to-end aerodynamic modeling.Towards heterogenous data,a novel and easily applicable physical feature embedding modeling framework is designed.This framework extracts lowdimensional physical features from pressure distribution and then effectively enhances the modeling of the integrated loads via feature embedding.The proposed framework can be coupled with multiple feature extraction methods,and the well-performed generalization capabilities over different airfoils are verified through a transonic case.Compared with traditional direct modeling,the proposed framework can reduce testing errors by almost 50%.Given the same prediction accuracy,it can save more than half of the training samples.Furthermore,the visualization analysis has revealed a significant correlation between the discovered low-dimensional physical features and the heterogeneous aerodynamic loads,which shows the interpretability and credibility of the superior performance offered by the proposed deep learning framework.展开更多
A novel face recognition method, which is a fusion of muhi-modal face parts based on Gabor feature （MMP-GF）, is proposed in this paper. Firstly, the bare face image detached from the normalized image was convolved w...A novel face recognition method, which is a fusion of muhi-modal face parts based on Gabor feature （MMP-GF）, is proposed in this paper. Firstly, the bare face image detached from the normalized image was convolved with a family of Gabor kernels, and then according to the face structure and the key-points locations, the calculated Gabor images were divided into five parts： Gabor face, Gabor eyebrow, Gabor eye, Gabor nose and Gabor mouth. After that multi-modal Gabor features were spatially partitioned into non-overlapping regions and the averages of regions were concatenated to be a low dimension feature vector, whose dimension was further reduced by principal component analysis （PCA）. In the decision level fusion, match results respectively calculated based on the five parts were combined according to linear discriminant analysis （LDA） and a normalized matching algorithm was used to improve the performance. Experiments on FERET database show that the proposed MMP-GF method achieves good robustness to the expression and age variations.展开更多
The unsupervised multi-modal image translation is an emerging domain of computer vision whose goal is to transform an image from the source domain into many diverse styles in the target domain.However,the multi-genera...The unsupervised multi-modal image translation is an emerging domain of computer vision whose goal is to transform an image from the source domain into many diverse styles in the target domain.However,the multi-generator mechanism is employed among the advanced approaches available to model different domain mappings,which results in inefficient training of neural networks and pattern collapse,leading to inefficient generation of image diversity.To address this issue,this paper introduces a multi-modal unsupervised image translation framework that uses a generator to perform multi-modal image translation.Specifically,firstly,the domain code is introduced in this paper to explicitly control the different generation tasks.Secondly,this paper brings in the squeeze-and-excitation(SE)mechanism and feature attention(FA)module.Finally,the model integrates multiple optimization objectives to ensure efficient multi-modal translation.This paper performs qualitative and quantitative experiments on multiple non-paired benchmark image translation datasets while demonstrating the benefits of the proposed method over existing technologies.Overall,experimental results have shown that the proposed method is versatile and scalable.展开更多
Visual Question Answering(VQA)has sparked widespread interest as a crucial task in integrating vision and language.VQA primarily uses attention mechanisms to effectively answer questions to associate relevant visual r...Visual Question Answering(VQA)has sparked widespread interest as a crucial task in integrating vision and language.VQA primarily uses attention mechanisms to effectively answer questions to associate relevant visual regions with input questions.The detection-based features extracted by the object detection network aim to acquire the visual attention distribution on a predetermined detection frame and provide object-level insights to answer questions about foreground objects more effectively.However,it cannot answer the question about the background forms without detection boxes due to the lack of fine-grained details,which is the advantage of grid-based features.In this paper,we propose a Dual-Level Feature Embedding(DLFE)network,which effectively integrates grid-based and detection-based image features in a unified architecture to realize the complementary advantages of both features.Specifically,in DLFE,In DLFE,firstly,a novel Dual-Level Self-Attention(DLSA)modular is proposed to mine the intrinsic properties of the two features,where Positional Relation Attention(PRA)is designed to model the position information.Then,we propose a Feature Fusion Attention(FFA)to address the semantic noise caused by the fusion of two features and construct an alignment graph to enhance and align the grid and detection features.Finally,we use co-attention to learn the interactive features of the image and question and answer questions more accurately.Our method has significantly improved compared to the baseline,increasing accuracy from 66.01%to 70.63%on the test-std dataset of VQA 1.0 and from 66.24%to 70.91%for the test-std dataset of VQA 2.0.展开更多
In geometry processing,symmetry research benefits from global geo-metric features of complete shapes,but the shape of an object captured in real-world applications is often incomplete due to the limited sensor resoluti...In geometry processing,symmetry research benefits from global geo-metric features of complete shapes,but the shape of an object captured in real-world applications is often incomplete due to the limited sensor resolution,single viewpoint,and occlusion.Different from the existing works predicting symmetry from the complete shape,we propose a learning approach for symmetry predic-tion based on a single RGB-D image.Instead of directly predicting the symmetry from incomplete shapes,our method consists of two modules,i.e.,the multi-mod-al feature fusion module and the detection-by-reconstruction module.Firstly,we build a channel-transformer network(CTN)to extract cross-fusion features from the RGB-D as the multi-modal feature fusion module,which helps us aggregate features from the color and the depth separately.Then,our self-reconstruction net-work based on a 3D variational auto-encoder(3D-VAE)takes the global geo-metric features as input,followed by a prediction symmetry network to detect the symmetry.Our experiments are conducted on three public datasets:ShapeNet,YCB,and ScanNet,we demonstrate that our method can produce reliable and accurate results.展开更多
In order to solve difficult detection of far and hard objects due to the sparseness and insufficient semantic information of LiDAR point cloud,a 3D object detection network with multi-modal data adaptive fusion is pro...In order to solve difficult detection of far and hard objects due to the sparseness and insufficient semantic information of LiDAR point cloud,a 3D object detection network with multi-modal data adaptive fusion is proposed,which makes use of multi-neighborhood information of voxel and image information.Firstly,design an improved ResNet that maintains the structure information of far and hard objects in low-resolution feature maps,which is more suitable for detection task.Meanwhile,semantema of each image feature map is enhanced by semantic information from all subsequent feature maps.Secondly,extract multi-neighborhood context information with different receptive field sizes to make up for the defect of sparseness of point cloud which improves the ability of voxel features to represent the spatial structure and semantic information of objects.Finally,propose a multi-modal feature adaptive fusion strategy which uses learnable weights to express the contribution of different modal features to the detection task,and voxel attention further enhances the fused feature expression of effective target objects.The experimental results on the KITTI benchmark show that this method outperforms VoxelNet with remarkable margins,i.e.increasing the AP by 8.78%and 5.49%on medium and hard difficulty levels.Meanwhile,our method achieves greater detection performance compared with many mainstream multi-modal methods,i.e.outperforming the AP by 1%compared with that of MVX-Net on medium and hard difficulty levels.展开更多
The multi-modal characteristics of mineral particles play a pivotal role in enhancing the classification accuracy,which is critical for obtaining a profound understanding of the Earth's composition and ensuring ef...The multi-modal characteristics of mineral particles play a pivotal role in enhancing the classification accuracy,which is critical for obtaining a profound understanding of the Earth's composition and ensuring effective exploitation utilization of its resources.However,the existing methods for classifying mineral particles do not fully utilize these multi-modal features,thereby limiting the classification accuracy.Furthermore,when conventional multi-modal image classification methods are applied to planepolarized and cross-polarized sequence images of mineral particles,they encounter issues such as information loss,misaligned features,and challenges in spatiotemporal feature extraction.To address these challenges,we propose a multi-modal mineral particle polarization image classification network(MMGC-Net)for precise mineral particle classification.Initially,MMGC-Net employs a two-dimensional(2D)backbone network with shared parameters to extract features from two types of polarized images to ensure feature alignment.Subsequently,a cross-polarized intra-modal feature fusion module is designed to refine the spatiotemporal features from the extracted features of the cross-polarized sequence images.Ultimately,the inter-modal feature fusion module integrates the two types of modal features to enhance the classification precision.Quantitative and qualitative experimental results indicate that when compared with the current state-of-the-art multi-modal image classification methods,MMGC-Net demonstrates marked superiority in terms of mineral particle multi-modal feature learning and four classification evaluation metrics.It also demonstrates better stability than the existing models.展开更多
To avoid the curse of dimensionality, text categorization （TC） algorithms based on machine learning （ML） have to use an feature selection （FS） method to reduce the dimensionality of feature space. Although havin...To avoid the curse of dimensionality, text categorization （TC） algorithms based on machine learning （ML） have to use an feature selection （FS） method to reduce the dimensionality of feature space. Although having been widely used, FS process will generally cause information losing and then have much side-effect on the whole performance of TC algorithms. On the basis of the sparsity characteristic of text vectors, a new TC algorithm based on lazy feature selection （LFS） is presented. As a new type of embedded feature selection approach, the LFS method can greatly reduce the dimension of features without any information losing, which can improve both efficiency and performance of algorithms greatly. The experiments show the new algorithm can simultaneously achieve much higher both performance and efficiency than some of other classical TC algorithms.展开更多
To address the challenge of missing modal information in entity alignment and to mitigate information loss or bias arising frommodal heterogeneity during fusion,while also capturing shared information acrossmodalities...To address the challenge of missing modal information in entity alignment and to mitigate information loss or bias arising frommodal heterogeneity during fusion,while also capturing shared information acrossmodalities,this paper proposes a Multi-modal Pre-synergistic Entity Alignmentmodel based on Cross-modalMutual Information Strategy Optimization(MPSEA).The model first employs independent encoders to process multi-modal features,including text,images,and numerical values.Next,a multi-modal pre-synergistic fusion mechanism integrates graph structural and visual modal features into the textual modality as preparatory information.This pre-fusion strategy enables unified perception of heterogeneous modalities at the model’s initial stage,reducing discrepancies during the fusion process.Finally,using cross-modal deep perception reinforcement learning,the model achieves adaptive multilevel feature fusion between modalities,supporting learningmore effective alignment strategies.Extensive experiments on multiple public datasets show that the MPSEA method achieves gains of up to 7% in Hits@1 and 8.2% in MRR on the FBDB15K dataset,and up to 9.1% in Hits@1 and 7.7% in MRR on the FBYG15K dataset,compared to existing state-of-the-art methods.These results confirm the effectiveness of the proposed model.展开更多
Acute Bilirubin Encephalopathy(ABE)is a significant threat to neonates and it leads to disability and high mortality rates.Detecting and treating ABE promptly is important to prevent further complications and long-ter...Acute Bilirubin Encephalopathy(ABE)is a significant threat to neonates and it leads to disability and high mortality rates.Detecting and treating ABE promptly is important to prevent further complications and long-term issues.Recent studies have explored ABE diagnosis.However,they often face limitations in classification due to reliance on a single modality of Magnetic Resonance Imaging(MRI).To tackle this problem,the authors propose a Tri-M2MT model for precise ABE detection by using tri-modality MRI scans.The scans include T1-weighted imaging(T1WI),T2-weighted imaging(T2WI),and apparent diffusion coefficient maps to get indepth information.Initially,the tri-modality MRI scans are collected and preprocessesed by using an Advanced Gaussian Filter for noise reduction and Z-score normalisation for data standardisation.An Advanced Capsule Network was utilised to extract relevant features by using Snake Optimization Algorithm to select optimal features based on feature correlation with the aim of minimising complexity and enhancing detection accuracy.Furthermore,a multi-transformer approach was used for feature fusion and identify feature correlations effectively.Finally,accurate ABE diagnosis is achieved through the utilisation of a SoftMax layer.The performance of the proposed Tri-M2MT model is evaluated across various metrics,including accuracy,specificity,sensitivity,F1-score,and ROC curve analysis,and the proposed methodology provides better performance compared to existing methodologies.展开更多
Multimodal sentiment analysis aims to understand emotions from text,speech,and video data.However,current methods often overlook the dominant role of text and suffer from feature loss during integration.Given the vary...Multimodal sentiment analysis aims to understand emotions from text,speech,and video data.However,current methods often overlook the dominant role of text and suffer from feature loss during integration.Given the varying importance of each modality across different contexts,a central and pressing challenge in multimodal sentiment analysis lies in maximizing the use of rich intra-modal features while minimizing information loss during the fusion process.In response to these critical limitations,we propose a novel framework that integrates spatial position encoding and fusion embedding modules to address these issues.In our model,text is treated as the core modality,while speech and video features are selectively incorporated through a unique position-aware fusion process.The spatial position encoding strategy preserves the internal structural information of speech and visual modalities,enabling the model to capture localized intra-modal dependencies that are often overlooked.This design enhances the richness and discriminative power of the fused representation,enabling more accurate and context-aware sentiment prediction.Finally,we conduct comprehensive evaluations on two widely recognized standard datasets in the field—CMU-MOSI and CMU-MOSEI to validate the performance of the proposed model.The experimental results demonstrate that our model exhibits good performance and effectiveness for sentiment analysis tasks.展开更多
Feature selection(FS)plays a crucial role in medical imaging by reducing dimensionality,improving computational efficiency,and enhancing diagnostic accuracy.Traditional FS techniques,including filter,wrapper,and embed...Feature selection(FS)plays a crucial role in medical imaging by reducing dimensionality,improving computational efficiency,and enhancing diagnostic accuracy.Traditional FS techniques,including filter,wrapper,and embedded methods,have been widely used but often struggle with high-dimensional and heterogeneous medical imaging data.Deep learning-based FS methods,particularly Convolutional Neural Networks(CNNs)and autoencoders,have demonstrated superior performance but lack interpretability.Hybrid approaches that combine classical and deep learning techniques have emerged as a promising solution,offering improved accuracy and explainability.Furthermore,integratingmulti-modal imaging data(e.g.,MagneticResonance Imaging(MRI),ComputedTomography(CT),Positron Emission Tomography(PET),and Ultrasound(US))poses additional challenges in FS,necessitating advanced feature fusion strategies.Multi-modal feature fusion combines information fromdifferent imagingmodalities to improve diagnostic accuracy.Recently,quantum computing has gained attention as a revolutionary approach for FS,providing the potential to handle high-dimensional medical data more efficiently.This systematic literature review comprehensively examines classical,Deep Learning(DL),hybrid,and quantum-based FS techniques inmedical imaging.Key outcomes include a structured taxonomy of FS methods,a critical evaluation of their performance across modalities,and identification of core challenges such as computational burden,interpretability,and ethical considerations.Future research directions—such as explainable AI(XAI),federated learning,and quantum-enhanced FS—are also emphasized to bridge the current gaps.This review provides actionable insights for developing scalable,interpretable,and clinically applicable FS methods in the evolving landscape of medical imaging.展开更多
BACKGROUND ： Some studies demonstrate that allogenic peripheral nerve segment embedded subcutaneously significantly reduce the infiltration of lymphocyte and decrease immunological reaction.OBJECTIVE ： To observe th...BACKGROUND ： Some studies demonstrate that allogenic peripheral nerve segment embedded subcutaneously significantly reduce the infiltration of lymphocyte and decrease immunological reaction.OBJECTIVE ： To observe the gross shape, optical and electron microscope results of allogenic nerve segment in rats 2 weeks after subcutaneous embedment, and compare with subcutaneous emdedment of autologous nerve segment. DESIGN ： A randomized and controlled experiment.SETTING ： Department of Orthopaedics of Fifth People＇s Hospital of Zhengzhou; Department of Orthopaedics,First Hospital Affiliated to Chongqing Medical University.MATERIALS ： Totally 30 adult healthy Wistar male rats, with body mass of （200±20） g, were enrolled. Ten rats were chosen as the donors of allogenic nerve transplantation. The other 20 rats were randomly divided into 2 groups： allogenic nerve embedment group and autologous nerve embedment group, with 10 rats in each one. JEM-1220 transmission electron microscope （Japan） and Olympus BX50 optical microscope （Japan） were used. METHODS ： This experiment was carried out at the laboratory of Orthopaedic Department, Chongqing Medical University from October 2000 to April 2002. ① Sciatic nerve of donor rats for allogenic nerve transplantation was cut off at 5 mm distant from pelvic strait.15 mm sciatic nerve segment was chosen from lateral part as graft, allogenic nerve embedment group： 15 mm sciatic nerve form the donor rats was embedded in the posterior part of right legs. Autologous nerve embedment group： 15 mm sciatic nerve segment of autologous left side was embedded in the posterior side of right legs. ② Nerve segment embedded subcutaneously was taken out at postoperative 2 weeks and performed gross observation; then 5 samples chosen randomly respectively from 2 groups and given haematoxylin-eosin staining and observation under optical microscope （×400）;The other 5 samples were made into ultrathin sections （0.5μm）and observed under transmission electron microscope（×17 000）. MAIN OUTCOME MEASURES ： Gross shape, optical and electron microscope results of nerve segments of rats between two groups at 2 weeks after subcutaneous embedment. RESULTS ： ① Results of gross observation： Appearance of nerve segment was similar between 2 groups. ② Results of optical observation： medullary sheath denaturation, axonotmesis, vascular engorgement, desmoplasia of adventitia and infiltration of inflammatory cells were all found in both 2 groups. Inflammatory reaction was a little more severe in the allogenic nerve embedment group than in the autologous nerve embedment groups.③Results of electron microscope ： Similar cataplasia and denaturation of medullary sheath and cataplasia of Schwann cell were all found in the 2 groups. CONCLUSION： Some inflammatory reaction occurs after allogenic nerve embedment, but the activity of Schwann cell is similar to that of peripheral nerve after autologous nerve embedment.展开更多
Unsupervised feature selection is fundamental in statistical pattern recognition,and has drawn persistent attention in the past several decades.Recently,much work has shown that feature selection can be formulated as ...Unsupervised feature selection is fundamental in statistical pattern recognition,and has drawn persistent attention in the past several decades.Recently,much work has shown that feature selection can be formulated as nonlinear dimensionality reduction with discrete constraints.This line of research emphasizes utilizing the manifold learning techniques,where feature selection and learning can be studied based on the manifold assumption in data distribution.Many existing feature selection methods such as Laplacian score,SPEC(spectrum decomposition of graph Laplacian),TR(trace ratio)criterion,MSFS(multi-cluster feature selection)and EVSC(eigenvalue sensitive criterion)apply the basic properties of graph Laplacian,and select the optimal feature subsets which best preserve the manifold structure defined on the graph Laplacian.In this paper,we propose a new feature selection perspective from locally linear embedding(LLE),which is another popular manifold learning method.The main difficulty of using LLE for feature selection is that its optimization involves quadratic programming and eigenvalue decomposition,both of which are continuous procedures and different from discrete feature selection.We prove that the LLE objective can be decomposed with respect to data dimensionalities in the subset selection problem,which also facilitates constructing better coordinates from data using the principal component analysis(PCA)technique.Based on these results,we propose a novel unsupervised feature selection algorithm,called locally linear selection(LLS),to select a feature subset representing the underlying data manifold.The local relationship among samples is computed from the LLE formulation,which is then used to estimate the contribution of each individual feature to the underlying manifold structure.These contributions,represented as LLS scores,are ranked and selected as the candidate solution to feature selection.We further develop a locally linear rotation-selection(LLRS)algorithm which extends LLS to identify the optimal coordinate subset from a new space.Experimental results on real-world datasets show that our method can be more effective than Laplacian eigenmap based feature selection methods.展开更多
Image feature optimization is an important means to deal with high-dimensional image data in image semantic understanding and its applications. We formulate image feature optimization as the establishment of a mapping...Image feature optimization is an important means to deal with high-dimensional image data in image semantic understanding and its applications. We formulate image feature optimization as the establishment of a mapping between highand low-dimensional space via a five-tuple model. Nonlinear dimensionality reduction based on manifold learning provides a feasible way for solving such a problem. We propose a novel globular neighborhood based locally linear embedding (GNLLE) algorithm using neighborhood update and an incremental neighbor search scheme, which not only can handle sparse datasets but also has strong anti-noise capability and good topological stability. Given that the distance measure adopted in nonlinear dimensionality reduction is usually based on pairwise similarity calculation, we also present a globular neighborhood and path clustering based locally linear embedding (GNPCLLE) algorithm based on path-based clustering. Due to its full consideration of correlations between image data, GNPCLLE can eliminate the distortion of the overall topological structure within the dataset on the manifold. Experimental results on two image sets show the effectiveness and efficiency of the proposed algorithms.展开更多
For the analysis of spinal and disc diseases,automated tissue segmentation of the lumbar spine is vital.Due to the continuous and concentrated location of the target,the abundance of edge features,and individual diffe...For the analysis of spinal and disc diseases,automated tissue segmentation of the lumbar spine is vital.Due to the continuous and concentrated location of the target,the abundance of edge features,and individual differences,conventional automatic segmentation methods perform poorly.Since the success of deep learning in the segmentation of medical images has been shown in the past few years,it has been applied to this task in a number of ways.The multi-scale and multi-modal features of lumbar tissues,however,are rarely explored by methodologies of deep learning.Because of the inadequacies in medical images availability,it is crucial to effectively fuse various modes of data collection for model training to alleviate the problem of insufficient samples.In this paper,we propose a novel multi-modality hierarchical fusion network(MHFN)for improving lumbar spine segmentation by learning robust feature representations from multi-modality magnetic resonance images.An adaptive group fusion module(AGFM)is introduced in this paper to fuse features from various modes to extract cross-modality features that could be valuable.Furthermore,to combine features from low to high levels of cross-modality,we design a hierarchical fusion structure based on AGFM.Compared to the other feature fusion methods,AGFM is more effective based on experimental results on multi-modality MR images of the lumbar spine.To further enhance segmentation accuracy,we compare our network with baseline fusion structures.Compared to the baseline fusion structures(input-level:76.27%,layer-level:78.10%,decision-level:79.14%),our network was able to segment fractured vertebrae more accurately(85.05%).展开更多
Cross-project software defect prediction(CPDP)aims to enhance defect prediction in target projects with limited or no historical data by leveraging information from related source projects.The existing CPDP approaches...Cross-project software defect prediction(CPDP)aims to enhance defect prediction in target projects with limited or no historical data by leveraging information from related source projects.The existing CPDP approaches rely on static metrics or dynamic syntactic features,which have shown limited effectiveness in CPDP due to their inability to capture higher-level system properties,such as complex design patterns,relationships between multiple functions,and dependencies in different software projects,that are important for CPDP.This paper introduces a novel approach,a graph-based feature learning model for CPDP(GB-CPDP),that utilizes NetworkX to extract features and learn representations of program entities from control flow graphs(CFGs)and data dependency graphs(DDGs).These graphs capture the structural and data dependencies within the source code.The proposed approach employs Node2Vec to transform CFGs and DDGs into numerical vectors and leverages Long Short-Term Memory(LSTM)networks to learn predictive models.The process involves graph construction,feature learning through graph embedding and LSTM,and defect prediction.Experimental evaluation using nine open-source Java projects from the PROMISE dataset demonstrates that GB-CPDP outperforms state-of-the-art CPDP methods in terms of F1-measure and Area Under the Curve(AUC).The results showcase the effectiveness of GB-CPDP in improving the performance of cross-project defect prediction.展开更多
文摘[Objective]Accurate prediction of tomato growth height is crucial for optimizing production environments in smart farming.However,current prediction methods predominantly rely on empirical,mechanistic,or learning-based models that utilize either images data or environmental data.These methods fail to fully leverage multi-modal data to capture the diverse aspects of plant growth comprehensively.[Methods]To address this limitation,a two-stage phenotypic feature extraction(PFE)model based on deep learning algorithm of recurrent neural network(RNN)and long short-term memory(LSTM)was developed.The model integrated environment and plant information to provide a holistic understanding of the growth process,emploied phenotypic and temporal feature extractors to comprehensively capture both types of features,enabled a deeper understanding of the interaction between tomato plants and their environment,ultimately leading to highly accurate predictions of growth height.[Results and Discussions]The experimental results showed the model's ef‐fectiveness:When predicting the next two days based on the past five days,the PFE-based RNN and LSTM models achieved mean absolute percentage error(MAPE)of 0.81%and 0.40%,respectively,which were significantly lower than the 8.00%MAPE of the large language model(LLM)and 6.72%MAPE of the Transformer-based model.In longer-term predictions,the 10-day prediction for 4 days ahead and the 30-day prediction for 12 days ahead,the PFE-RNN model continued to outperform the other two baseline models,with MAPE of 2.66%and 14.05%,respectively.[Conclusions]The proposed method,which leverages phenotypic-temporal collaboration,shows great potential for intelligent,data-driven management of tomato cultivation,making it a promising approach for enhancing the efficiency and precision of smart tomato planting management.
基金supported by the National Natural Science Foundation of China(Nos.92152301,12072282)。
文摘Aerodynamic surrogate modeling mostly relies only on integrated loads data obtained from simulation or experiment,while neglecting and wasting the valuable distributed physical information on the surface.To make full use of both integrated and distributed loads,a modeling paradigm,called the heterogeneous data-driven aerodynamic modeling,is presented.The essential concept is to incorporate the physical information of distributed loads as additional constraints within the end-to-end aerodynamic modeling.Towards heterogenous data,a novel and easily applicable physical feature embedding modeling framework is designed.This framework extracts lowdimensional physical features from pressure distribution and then effectively enhances the modeling of the integrated loads via feature embedding.The proposed framework can be coupled with multiple feature extraction methods,and the well-performed generalization capabilities over different airfoils are verified through a transonic case.Compared with traditional direct modeling,the proposed framework can reduce testing errors by almost 50%.Given the same prediction accuracy,it can save more than half of the training samples.Furthermore,the visualization analysis has revealed a significant correlation between the discovered low-dimensional physical features and the heterogeneous aerodynamic loads,which shows the interpretability and credibility of the superior performance offered by the proposed deep learning framework.
基金Supported by the National Key Technology R&D Program (No. 2006BAK08B07)
文摘A novel face recognition method, which is a fusion of muhi-modal face parts based on Gabor feature （MMP-GF）, is proposed in this paper. Firstly, the bare face image detached from the normalized image was convolved with a family of Gabor kernels, and then according to the face structure and the key-points locations, the calculated Gabor images were divided into five parts： Gabor face, Gabor eyebrow, Gabor eye, Gabor nose and Gabor mouth. After that multi-modal Gabor features were spatially partitioned into non-overlapping regions and the averages of regions were concatenated to be a low dimension feature vector, whose dimension was further reduced by principal component analysis （PCA）. In the decision level fusion, match results respectively calculated based on the five parts were combined according to linear discriminant analysis （LDA） and a normalized matching algorithm was used to improve the performance. Experiments on FERET database show that the proposed MMP-GF method achieves good robustness to the expression and age variations.
基金the National Natural Science Foundation of China(No.61976080)the Academic Degrees&Graduate Education Reform Project of Henan Province(No.2021SJGLX195Y)+1 种基金the Teaching Reform Research and Practice Project of Henan Undergraduate Universities(No.2022SYJXLX008)the Key Project on Research and Practice of Henan University Graduate Education and Teaching Reform(No.YJSJG2023XJ006)。
文摘The unsupervised multi-modal image translation is an emerging domain of computer vision whose goal is to transform an image from the source domain into many diverse styles in the target domain.However,the multi-generator mechanism is employed among the advanced approaches available to model different domain mappings,which results in inefficient training of neural networks and pattern collapse,leading to inefficient generation of image diversity.To address this issue,this paper introduces a multi-modal unsupervised image translation framework that uses a generator to perform multi-modal image translation.Specifically,firstly,the domain code is introduced in this paper to explicitly control the different generation tasks.Secondly,this paper brings in the squeeze-and-excitation(SE)mechanism and feature attention(FA)module.Finally,the model integrates multiple optimization objectives to ensure efficient multi-modal translation.This paper performs qualitative and quantitative experiments on multiple non-paired benchmark image translation datasets while demonstrating the benefits of the proposed method over existing technologies.Overall,experimental results have shown that the proposed method is versatile and scalable.
文摘Visual Question Answering(VQA)has sparked widespread interest as a crucial task in integrating vision and language.VQA primarily uses attention mechanisms to effectively answer questions to associate relevant visual regions with input questions.The detection-based features extracted by the object detection network aim to acquire the visual attention distribution on a predetermined detection frame and provide object-level insights to answer questions about foreground objects more effectively.However,it cannot answer the question about the background forms without detection boxes due to the lack of fine-grained details,which is the advantage of grid-based features.In this paper,we propose a Dual-Level Feature Embedding(DLFE)network,which effectively integrates grid-based and detection-based image features in a unified architecture to realize the complementary advantages of both features.Specifically,in DLFE,In DLFE,firstly,a novel Dual-Level Self-Attention(DLSA)modular is proposed to mine the intrinsic properties of the two features,where Positional Relation Attention(PRA)is designed to model the position information.Then,we propose a Feature Fusion Attention(FFA)to address the semantic noise caused by the fusion of two features and construct an alignment graph to enhance and align the grid and detection features.Finally,we use co-attention to learn the interactive features of the image and question and answer questions more accurately.Our method has significantly improved compared to the baseline,increasing accuracy from 66.01%to 70.63%on the test-std dataset of VQA 1.0 and from 66.24%to 70.91%for the test-std dataset of VQA 2.0.
文摘In geometry processing,symmetry research benefits from global geo-metric features of complete shapes,but the shape of an object captured in real-world applications is often incomplete due to the limited sensor resolution,single viewpoint,and occlusion.Different from the existing works predicting symmetry from the complete shape,we propose a learning approach for symmetry predic-tion based on a single RGB-D image.Instead of directly predicting the symmetry from incomplete shapes,our method consists of two modules,i.e.,the multi-mod-al feature fusion module and the detection-by-reconstruction module.Firstly,we build a channel-transformer network(CTN)to extract cross-fusion features from the RGB-D as the multi-modal feature fusion module,which helps us aggregate features from the color and the depth separately.Then,our self-reconstruction net-work based on a 3D variational auto-encoder(3D-VAE)takes the global geo-metric features as input,followed by a prediction symmetry network to detect the symmetry.Our experiments are conducted on three public datasets:ShapeNet,YCB,and ScanNet,we demonstrate that our method can produce reliable and accurate results.
基金National Youth Natural Science Foundation of China(No.61806006)Innovation Program for Graduate of Jiangsu Province(No.KYLX160-781)Jiangsu University Superior Discipline Construction Project。
文摘In order to solve difficult detection of far and hard objects due to the sparseness and insufficient semantic information of LiDAR point cloud,a 3D object detection network with multi-modal data adaptive fusion is proposed,which makes use of multi-neighborhood information of voxel and image information.Firstly,design an improved ResNet that maintains the structure information of far and hard objects in low-resolution feature maps,which is more suitable for detection task.Meanwhile,semantema of each image feature map is enhanced by semantic information from all subsequent feature maps.Secondly,extract multi-neighborhood context information with different receptive field sizes to make up for the defect of sparseness of point cloud which improves the ability of voxel features to represent the spatial structure and semantic information of objects.Finally,propose a multi-modal feature adaptive fusion strategy which uses learnable weights to express the contribution of different modal features to the detection task,and voxel attention further enhances the fused feature expression of effective target objects.The experimental results on the KITTI benchmark show that this method outperforms VoxelNet with remarkable margins,i.e.increasing the AP by 8.78%and 5.49%on medium and hard difficulty levels.Meanwhile,our method achieves greater detection performance compared with many mainstream multi-modal methods,i.e.outperforming the AP by 1%compared with that of MVX-Net on medium and hard difficulty levels.
基金supported by the National Natural Science Foundation of China(Grant Nos.62071315 and 62271336).
文摘The multi-modal characteristics of mineral particles play a pivotal role in enhancing the classification accuracy,which is critical for obtaining a profound understanding of the Earth's composition and ensuring effective exploitation utilization of its resources.However,the existing methods for classifying mineral particles do not fully utilize these multi-modal features,thereby limiting the classification accuracy.Furthermore,when conventional multi-modal image classification methods are applied to planepolarized and cross-polarized sequence images of mineral particles,they encounter issues such as information loss,misaligned features,and challenges in spatiotemporal feature extraction.To address these challenges,we propose a multi-modal mineral particle polarization image classification network(MMGC-Net)for precise mineral particle classification.Initially,MMGC-Net employs a two-dimensional(2D)backbone network with shared parameters to extract features from two types of polarized images to ensure feature alignment.Subsequently,a cross-polarized intra-modal feature fusion module is designed to refine the spatiotemporal features from the extracted features of the cross-polarized sequence images.Ultimately,the inter-modal feature fusion module integrates the two types of modal features to enhance the classification precision.Quantitative and qualitative experimental results indicate that when compared with the current state-of-the-art multi-modal image classification methods,MMGC-Net demonstrates marked superiority in terms of mineral particle multi-modal feature learning and four classification evaluation metrics.It also demonstrates better stability than the existing models.
文摘To avoid the curse of dimensionality, text categorization （TC） algorithms based on machine learning （ML） have to use an feature selection （FS） method to reduce the dimensionality of feature space. Although having been widely used, FS process will generally cause information losing and then have much side-effect on the whole performance of TC algorithms. On the basis of the sparsity characteristic of text vectors, a new TC algorithm based on lazy feature selection （LFS） is presented. As a new type of embedded feature selection approach, the LFS method can greatly reduce the dimension of features without any information losing, which can improve both efficiency and performance of algorithms greatly. The experiments show the new algorithm can simultaneously achieve much higher both performance and efficiency than some of other classical TC algorithms.
基金partially supported by the National Natural Science Foundation of China under Grants 62471493 and 62402257(for conceptualization and investigation)partially supported by the Natural Science Foundation of Shandong Province,China under Grants ZR2023LZH017,ZR2024MF066,and 2023QF025(for formal analysis and validation)+1 种基金partially supported by the Open Foundation of Key Laboratory of Computing Power Network and Information Security,Ministry of Education,Qilu University of Technology(Shandong Academy of Sciences)under Grant 2023ZD010(for methodology and model design)partially supported by the Russian Science Foundation(RSF)Project under Grant 22-71-10095-P(for validation and results verification).
文摘To address the challenge of missing modal information in entity alignment and to mitigate information loss or bias arising frommodal heterogeneity during fusion,while also capturing shared information acrossmodalities,this paper proposes a Multi-modal Pre-synergistic Entity Alignmentmodel based on Cross-modalMutual Information Strategy Optimization(MPSEA).The model first employs independent encoders to process multi-modal features,including text,images,and numerical values.Next,a multi-modal pre-synergistic fusion mechanism integrates graph structural and visual modal features into the textual modality as preparatory information.This pre-fusion strategy enables unified perception of heterogeneous modalities at the model’s initial stage,reducing discrepancies during the fusion process.Finally,using cross-modal deep perception reinforcement learning,the model achieves adaptive multilevel feature fusion between modalities,supporting learningmore effective alignment strategies.Extensive experiments on multiple public datasets show that the MPSEA method achieves gains of up to 7% in Hits@1 and 8.2% in MRR on the FBDB15K dataset,and up to 9.1% in Hits@1 and 7.7% in MRR on the FBYG15K dataset,compared to existing state-of-the-art methods.These results confirm the effectiveness of the proposed model.
文摘Acute Bilirubin Encephalopathy(ABE)is a significant threat to neonates and it leads to disability and high mortality rates.Detecting and treating ABE promptly is important to prevent further complications and long-term issues.Recent studies have explored ABE diagnosis.However,they often face limitations in classification due to reliance on a single modality of Magnetic Resonance Imaging(MRI).To tackle this problem,the authors propose a Tri-M2MT model for precise ABE detection by using tri-modality MRI scans.The scans include T1-weighted imaging(T1WI),T2-weighted imaging(T2WI),and apparent diffusion coefficient maps to get indepth information.Initially,the tri-modality MRI scans are collected and preprocessesed by using an Advanced Gaussian Filter for noise reduction and Z-score normalisation for data standardisation.An Advanced Capsule Network was utilised to extract relevant features by using Snake Optimization Algorithm to select optimal features based on feature correlation with the aim of minimising complexity and enhancing detection accuracy.Furthermore,a multi-transformer approach was used for feature fusion and identify feature correlations effectively.Finally,accurate ABE diagnosis is achieved through the utilisation of a SoftMax layer.The performance of the proposed Tri-M2MT model is evaluated across various metrics,including accuracy,specificity,sensitivity,F1-score,and ROC curve analysis,and the proposed methodology provides better performance compared to existing methodologies.
基金supported by the Collaborative Tackling Project of the Yangtze River Delta SciTech Innovation Community(Nos.2024CSJGG01503,2024CSJGG01500)Guangxi Key Research and Development Program(No.AB24010317)Jiangxi Provincial Key Laboratory of Electronic Data Control and Forensics(Jiangxi Police College)(No.2025JXJYKFJJ002).
文摘Multimodal sentiment analysis aims to understand emotions from text,speech,and video data.However,current methods often overlook the dominant role of text and suffer from feature loss during integration.Given the varying importance of each modality across different contexts,a central and pressing challenge in multimodal sentiment analysis lies in maximizing the use of rich intra-modal features while minimizing information loss during the fusion process.In response to these critical limitations,we propose a novel framework that integrates spatial position encoding and fusion embedding modules to address these issues.In our model,text is treated as the core modality,while speech and video features are selectively incorporated through a unique position-aware fusion process.The spatial position encoding strategy preserves the internal structural information of speech and visual modalities,enabling the model to capture localized intra-modal dependencies that are often overlooked.This design enhances the richness and discriminative power of the fused representation,enabling more accurate and context-aware sentiment prediction.Finally,we conduct comprehensive evaluations on two widely recognized standard datasets in the field—CMU-MOSI and CMU-MOSEI to validate the performance of the proposed model.The experimental results demonstrate that our model exhibits good performance and effectiveness for sentiment analysis tasks.
文摘Feature selection(FS)plays a crucial role in medical imaging by reducing dimensionality,improving computational efficiency,and enhancing diagnostic accuracy.Traditional FS techniques,including filter,wrapper,and embedded methods,have been widely used but often struggle with high-dimensional and heterogeneous medical imaging data.Deep learning-based FS methods,particularly Convolutional Neural Networks(CNNs)and autoencoders,have demonstrated superior performance but lack interpretability.Hybrid approaches that combine classical and deep learning techniques have emerged as a promising solution,offering improved accuracy and explainability.Furthermore,integratingmulti-modal imaging data(e.g.,MagneticResonance Imaging(MRI),ComputedTomography(CT),Positron Emission Tomography(PET),and Ultrasound(US))poses additional challenges in FS,necessitating advanced feature fusion strategies.Multi-modal feature fusion combines information fromdifferent imagingmodalities to improve diagnostic accuracy.Recently,quantum computing has gained attention as a revolutionary approach for FS,providing the potential to handle high-dimensional medical data more efficiently.This systematic literature review comprehensively examines classical,Deep Learning(DL),hybrid,and quantum-based FS techniques inmedical imaging.Key outcomes include a structured taxonomy of FS methods,a critical evaluation of their performance across modalities,and identification of core challenges such as computational burden,interpretability,and ethical considerations.Future research directions—such as explainable AI(XAI),federated learning,and quantum-enhanced FS—are also emphasized to bridge the current gaps.This review provides actionable insights for developing scalable,interpretable,and clinically applicable FS methods in the evolving landscape of medical imaging.
文摘BACKGROUND ： Some studies demonstrate that allogenic peripheral nerve segment embedded subcutaneously significantly reduce the infiltration of lymphocyte and decrease immunological reaction.OBJECTIVE ： To observe the gross shape, optical and electron microscope results of allogenic nerve segment in rats 2 weeks after subcutaneous embedment, and compare with subcutaneous emdedment of autologous nerve segment. DESIGN ： A randomized and controlled experiment.SETTING ： Department of Orthopaedics of Fifth People＇s Hospital of Zhengzhou; Department of Orthopaedics,First Hospital Affiliated to Chongqing Medical University.MATERIALS ： Totally 30 adult healthy Wistar male rats, with body mass of （200±20） g, were enrolled. Ten rats were chosen as the donors of allogenic nerve transplantation. The other 20 rats were randomly divided into 2 groups： allogenic nerve embedment group and autologous nerve embedment group, with 10 rats in each one. JEM-1220 transmission electron microscope （Japan） and Olympus BX50 optical microscope （Japan） were used. METHODS ： This experiment was carried out at the laboratory of Orthopaedic Department, Chongqing Medical University from October 2000 to April 2002. ① Sciatic nerve of donor rats for allogenic nerve transplantation was cut off at 5 mm distant from pelvic strait.15 mm sciatic nerve segment was chosen from lateral part as graft, allogenic nerve embedment group： 15 mm sciatic nerve form the donor rats was embedded in the posterior part of right legs. Autologous nerve embedment group： 15 mm sciatic nerve segment of autologous left side was embedded in the posterior side of right legs. ② Nerve segment embedded subcutaneously was taken out at postoperative 2 weeks and performed gross observation; then 5 samples chosen randomly respectively from 2 groups and given haematoxylin-eosin staining and observation under optical microscope （×400）;The other 5 samples were made into ultrathin sections （0.5μm）and observed under transmission electron microscope（×17 000）. MAIN OUTCOME MEASURES ： Gross shape, optical and electron microscope results of nerve segments of rats between two groups at 2 weeks after subcutaneous embedment. RESULTS ： ① Results of gross observation： Appearance of nerve segment was similar between 2 groups. ② Results of optical observation： medullary sheath denaturation, axonotmesis, vascular engorgement, desmoplasia of adventitia and infiltration of inflammatory cells were all found in both 2 groups. Inflammatory reaction was a little more severe in the allogenic nerve embedment group than in the autologous nerve embedment groups.③Results of electron microscope ： Similar cataplasia and denaturation of medullary sheath and cataplasia of Schwann cell were all found in the 2 groups. CONCLUSION： Some inflammatory reaction occurs after allogenic nerve embedment, but the activity of Schwann cell is similar to that of peripheral nerve after autologous nerve embedment.
基金Supported by National Natural Science Foundation of China(61071131,61271388)Natural Science Foundation of Beijing(4122040)+1 种基金Research Project of Tsinghua University(2012Z01011)Doctoral Fund of Ministry of Education of China(20120002110036)
文摘Unsupervised feature selection is fundamental in statistical pattern recognition,and has drawn persistent attention in the past several decades.Recently,much work has shown that feature selection can be formulated as nonlinear dimensionality reduction with discrete constraints.This line of research emphasizes utilizing the manifold learning techniques,where feature selection and learning can be studied based on the manifold assumption in data distribution.Many existing feature selection methods such as Laplacian score,SPEC(spectrum decomposition of graph Laplacian),TR(trace ratio)criterion,MSFS(multi-cluster feature selection)and EVSC(eigenvalue sensitive criterion)apply the basic properties of graph Laplacian,and select the optimal feature subsets which best preserve the manifold structure defined on the graph Laplacian.In this paper,we propose a new feature selection perspective from locally linear embedding(LLE),which is another popular manifold learning method.The main difficulty of using LLE for feature selection is that its optimization involves quadratic programming and eigenvalue decomposition,both of which are continuous procedures and different from discrete feature selection.We prove that the LLE objective can be decomposed with respect to data dimensionalities in the subset selection problem,which also facilitates constructing better coordinates from data using the principal component analysis(PCA)technique.Based on these results,we propose a novel unsupervised feature selection algorithm,called locally linear selection(LLS),to select a feature subset representing the underlying data manifold.The local relationship among samples is computed from the LLE formulation,which is then used to estimate the contribution of each individual feature to the underlying manifold structure.These contributions,represented as LLS scores,are ranked and selected as the candidate solution to feature selection.We further develop a locally linear rotation-selection(LLRS)algorithm which extends LLS to identify the optimal coordinate subset from a new space.Experimental results on real-world datasets show that our method can be more effective than Laplacian eigenmap based feature selection methods.
基金Project (No 2008AA01Z132) supported by the National High-Tech Research and Development Program of China
文摘Image feature optimization is an important means to deal with high-dimensional image data in image semantic understanding and its applications. We formulate image feature optimization as the establishment of a mapping between highand low-dimensional space via a five-tuple model. Nonlinear dimensionality reduction based on manifold learning provides a feasible way for solving such a problem. We propose a novel globular neighborhood based locally linear embedding (GNLLE) algorithm using neighborhood update and an incremental neighbor search scheme, which not only can handle sparse datasets but also has strong anti-noise capability and good topological stability. Given that the distance measure adopted in nonlinear dimensionality reduction is usually based on pairwise similarity calculation, we also present a globular neighborhood and path clustering based locally linear embedding (GNPCLLE) algorithm based on path-based clustering. Due to its full consideration of correlations between image data, GNPCLLE can eliminate the distortion of the overall topological structure within the dataset on the manifold. Experimental results on two image sets show the effectiveness and efficiency of the proposed algorithms.
基金supported in part by the Technology Innovation 2030 under Grant 2022ZD0211700.
文摘For the analysis of spinal and disc diseases,automated tissue segmentation of the lumbar spine is vital.Due to the continuous and concentrated location of the target,the abundance of edge features,and individual differences,conventional automatic segmentation methods perform poorly.Since the success of deep learning in the segmentation of medical images has been shown in the past few years,it has been applied to this task in a number of ways.The multi-scale and multi-modal features of lumbar tissues,however,are rarely explored by methodologies of deep learning.Because of the inadequacies in medical images availability,it is crucial to effectively fuse various modes of data collection for model training to alleviate the problem of insufficient samples.In this paper,we propose a novel multi-modality hierarchical fusion network(MHFN)for improving lumbar spine segmentation by learning robust feature representations from multi-modality magnetic resonance images.An adaptive group fusion module(AGFM)is introduced in this paper to fuse features from various modes to extract cross-modality features that could be valuable.Furthermore,to combine features from low to high levels of cross-modality,we design a hierarchical fusion structure based on AGFM.Compared to the other feature fusion methods,AGFM is more effective based on experimental results on multi-modality MR images of the lumbar spine.To further enhance segmentation accuracy,we compare our network with baseline fusion structures.Compared to the baseline fusion structures(input-level:76.27%,layer-level:78.10%,decision-level:79.14%),our network was able to segment fractured vertebrae more accurately(85.05%).
基金supported by Institute of Information&Communications Technology Planning&Evaluation(IITP)grant funded by the Korea government(MSIT)(No.RS-2022-00155885).
文摘Cross-project software defect prediction(CPDP)aims to enhance defect prediction in target projects with limited or no historical data by leveraging information from related source projects.The existing CPDP approaches rely on static metrics or dynamic syntactic features,which have shown limited effectiveness in CPDP due to their inability to capture higher-level system properties,such as complex design patterns,relationships between multiple functions,and dependencies in different software projects,that are important for CPDP.This paper introduces a novel approach,a graph-based feature learning model for CPDP(GB-CPDP),that utilizes NetworkX to extract features and learn representations of program entities from control flow graphs(CFGs)and data dependency graphs(DDGs).These graphs capture the structural and data dependencies within the source code.The proposed approach employs Node2Vec to transform CFGs and DDGs into numerical vectors and leverages Long Short-Term Memory(LSTM)networks to learn predictive models.The process involves graph construction,feature learning through graph embedding and LSTM,and defect prediction.Experimental evaluation using nine open-source Java projects from the PROMISE dataset demonstrates that GB-CPDP outperforms state-of-the-art CPDP methods in terms of F1-measure and Area Under the Curve(AUC).The results showcase the effectiveness of GB-CPDP in improving the performance of cross-project defect prediction.
