Visible and infrared(RGB-IR)fusion object detection plays an important role in security,disaster relief,etc.In recent years,deep-learning-based RGB-IR fusion detection methods have been developing rapidly,but still st...Visible and infrared(RGB-IR)fusion object detection plays an important role in security,disaster relief,etc.In recent years,deep-learning-based RGB-IR fusion detection methods have been developing rapidly,but still struggle to deal with the complex and changing scenarios captured by drones,mainly due to two reasons:(A)RGB-IR fusion detectors are susceptible to inferior inputs that degrade performance and stability.(B)RGB-IR fusion detectors are susceptible to redundant features that reduce accuracy and efficiency.In this paper,an innovative RGB-IR fusion detection framework based on global-local feature optimization,named GLFDet,is proposed to improve the detection performance and efficiency of drone-captured objects.The key components of GLFDet include a Global Feature Optimization(GFO)module,a Local Feature Optimization(LFO)module and a Channel Separation Fusion(CSF)module.Specifically,GFO calculates the information content of the input image from the frequency domain and optimizes the features holistically.Then,LFO dynamically selects high-value features and filters out low-value features before fusion,which significantly improves the efficiency of fusion.Finally,CSF fuses the RGB and IR features across the corresponding channels,which avoids the rearrangement of the channel relationships and enhances the model stability.Extensive experimental results show that the proposed method achieves the best performance on three popular RGB-IR datasets Drone Vehicle,VEDAI,and LLVIP.In addition,GLFDet is more lightweight than other comparable models,making it more appealing to edge devices such as drones.The code is available at https://github.com/lao chen330/GLFDet.展开更多
Deep learning has made significant progress in the field of oriented object detection for remote sensing images.However,existing methods still face challenges when dealing with difficult tasks such as multi-scale targ...Deep learning has made significant progress in the field of oriented object detection for remote sensing images.However,existing methods still face challenges when dealing with difficult tasks such as multi-scale targets,complex backgrounds,and small objects in remote sensing.Maintaining model lightweight to address resource constraints in remote sensing scenarios while improving task completion for remote sensing tasks remains a research hotspot.Therefore,we propose an enhanced multi-scale feature extraction lightweight network EM-YOLO based on the YOLOv8s architecture,specifically optimized for the characteristics of large target scale variations,diverse orientations,and numerous small objects in remote sensing images.Our innovations lie in two main aspects:First,a dynamic snake convolution(DSC)is introduced into the backbone network to enhance the model’s feature extraction capability for oriented targets.Second,an innovative focusing-diffusion module is designed in the feature fusion neck to effectively integrate multi-scale feature information.Finally,we introduce Layer-Adaptive Sparsity for magnitude-based Pruning(LASP)method to perform lightweight network pruning to better complete tasks in resource-constrained scenarios.Experimental results on the lightweight platform Orin demonstrate that the proposed method significantly outperforms the original YOLOv8s model in oriented remote sensing object detection tasks,and achieves comparable or superior performance to state-of-the-art methods on three authoritative remote sensing datasets(DOTA v1.0,DOTA v1.5,and HRSC2016).展开更多
Accurate detection of smoke and fire sources is critical for early fire warning and environmental monitoring.However,conventional detection approaches are highly susceptible to noise,illumination variations,and comple...Accurate detection of smoke and fire sources is critical for early fire warning and environmental monitoring.However,conventional detection approaches are highly susceptible to noise,illumination variations,and complex environmental conditions,which often reduce detection accuracy and real-time performance.To address these limitations,we propose Lightweight and Precise YOLO(LP-YOLO),a high-precision detection framework that integrates a self-attention mechanism with a feature pyramid,built upon YOLOv8.First,to overcome the restricted receptive field and parameter redundancy of conventional Convolutional Neural Networks(CNNs),we design an enhanced backbone based on Wavelet Convolutions(WTConv),which expands the receptive field through multifrequency convolutional processing.Second,a Bidirectional Feature Pyramid Network(BiFPN)is employed to achieve bidirectional feature fusion,enhancing the representation of smoke features across scales.Third,to mitigate the challenge of ambiguous object boundaries,we introduce the Frequency-aware Feature Fusion(FreqFusion)module,in which the Adaptive Low-Pass Filter(ALPF)reduces intra-class inconsistencies,the offset generator refines boundary localization,and the Adaptive High-Pass Filter(AHPF)recovers high-frequency details lost during down-sampling.Experimental evaluations demonstrate that LP-YOLO significantly outperforms the baseline YOLOv8,achieving an improvement of 9.3%in mAP@50 and 9.2%in F1-score.Moreover,the model is 56.6%and 32.4%smaller than YOLOv7-tiny and EfficientDet,respectively,while maintaining real-time inference speed at 238 frames per second(FPS).Validation on multiple benchmark datasets,including D-Fire,FIRESENSE,and BoWFire,further confirms its robustness and generalization ability,with detection accuracy consistently exceeding 82%.These results highlight the potential of LP-YOLO as a practical solution with high accuracy,robustness,and real-time performance for smoke and fire source detection.展开更多
At inference time,deep neural networks are susceptible to backdoor attacks,which can produce attackercontrolled outputs when inputs contain carefully crafted triggers.Existing defense methods often focus on specific a...At inference time,deep neural networks are susceptible to backdoor attacks,which can produce attackercontrolled outputs when inputs contain carefully crafted triggers.Existing defense methods often focus on specific attack types or incur high costs,such as data cleaning or model fine-tuning.In contrast,we argue that it is possible to achieve effective and generalizable defense without removing triggers or incurring high model-cleaning costs.Fromthe attacker’s perspective and based on characteristics of vulnerable neuron activation anomalies,we propose an Adaptive Feature Injection(AFI)method for black-box backdoor detection.AFI employs a pre-trained image encoder to extract multi-level deep features and constructs a dynamic weight fusionmechanism for precise identification and interception of poisoned samples.Specifically,we select the control samples with the largest feature differences fromthe clean dataset via feature-space analysis,and generate blended sample pairs with the test sample using dynamic linear interpolation.The detection statistic is computed by measuring the divergence G(x)in model output responses.We systematically evaluate the effectiveness of AFI against representative backdoor attacks,including BadNets,Blend,WaNet,and IAB,on three benchmark datasets:MNIST,CIFAR-10,and ImageNet.Experimental results show that AFI can effectively detect poisoned samples,achieving average detection rates of 95.20%,94.15%,and 86.49%on these datasets,respectively.Compared with existing methods,AFI demonstrates strong cross-domain generalization ability and robustness to unknown attacks.展开更多
Biometric characteristics are playing a vital role in security for the last few years.Human gait classification in video sequences is an important biometrics attribute and is used for security purposes.A new framework...Biometric characteristics are playing a vital role in security for the last few years.Human gait classification in video sequences is an important biometrics attribute and is used for security purposes.A new framework for human gait classification in video sequences using deep learning(DL)fusion assisted and posterior probability-based moth flames optimization(MFO)is proposed.In the first step,the video frames are resized and finetuned by two pre-trained lightweight DL models,EfficientNetB0 and MobileNetV2.Both models are selected based on the top-5 accuracy and less number of parameters.Later,both models are trained through deep transfer learning and extracted deep features fused using a voting scheme.In the last step,the authors develop a posterior probabilitybased MFO feature selection algorithm to select the best features.The selected features are classified using several supervised learning methods.The CASIA-B publicly available dataset has been employed for the experimental process.On this dataset,the authors selected six angles such as 0°,18°,90°,108°,162°,and 180°and obtained an average accuracy of 96.9%,95.7%,86.8%,90.0%,95.1%,and 99.7%.Results demonstrate comparable improvement in accuracy and significantly minimize the computational time with recent state-of-the-art techniques.展开更多
Accurate and robust navigation in complex surgical environments is crucial for bronchoscopic surgeries.This study purposes a bronchoscopic lumen feature matching network(BLFM-Net)based on deep learning to address the ...Accurate and robust navigation in complex surgical environments is crucial for bronchoscopic surgeries.This study purposes a bronchoscopic lumen feature matching network(BLFM-Net)based on deep learning to address the challenges of image noise,anatomical complexity,and the stringent real-time requirements.The BLFM-Net enhances bronchoscopic image processing by integrating several functional modules.The FFA-Net preprocessing module mitigates image fogging and improves visual clarity for subsequent processing.The feature extraction module derives multi-dimensional features,such as centroids,area,and shape descriptors,from dehazed images.The Faster RCNN Object detection module detects bronchial regions of interest and generates bounding boxes to localize key areas.The feature matching module accelerates the process by combining detection boxes,extracted features,and a KD-Tree(K-Dimensional Tree)-based algorithm,ensuring efficient and accurate regional feature associations.The BLFM-Net was evaluated on 5212 bronchoscopic images,demonstrating superior performance compared to traditional and other deep learning-based image matching methods.It achieved real-time matching with an average frame time of 6 ms,with a matching accuracy of over 96%.The method remained robust under challenging conditions including frame dropping(0,5,10,20),shadowed regions,and variable lighting,maintaining accuracy of above 94%even with the frame dropping of 20.This study presents BLFM-Net,a deep learning-based matching network designed to enhance and match bronchial features in bronchoscopic images.The BLFM-Net shows improved accuracy,real-time performance,and reliability,making a valuable tool for bronchoscopic surgeries.展开更多
In recent years,the heterogeneous SAR image classification task of"training on simulated data and testing on measured data"has garnered increasing attention in the field of Synthetic Aperture Radar Automatic...In recent years,the heterogeneous SAR image classification task of"training on simulated data and testing on measured data"has garnered increasing attention in the field of Synthetic Aperture Radar Automatic Target Recognition(SAR-ATR).Although current mainstream domain adaptation methods have made significant breakthroughs in addressing domain shift problems,the escalating model complexity and task complexity have constrained their deployment in real-world applications.To tackle this challenge,this paper proposes a domain adaptation framework based on linear-kernel Maximum Mean Discrepancy(MMD),integrated with a near-zero-cost pseudo-label denoising technique leveraging deep feature clustering.Our method completely eliminates the need for data augmentation and handcrafted feature design,achieving endto-end pseudo-label self-training.Competitive performance is demonstrated across three typical scenarios in the SAMPLE dataset,with the highest accuracy of 98.65%achieved in ScenarioⅢ.The relevant code is available at:https://github.com/TheGreatTreatsby/SAMPLE_MMD.展开更多
Acute lymphoblastic leukemia(ALL)is characterized by overgrowth of immature lymphoid cells in the bone marrow at the expense of normal hematopoiesis.One of the most prioritized tasks is the early and correct diagnosis...Acute lymphoblastic leukemia(ALL)is characterized by overgrowth of immature lymphoid cells in the bone marrow at the expense of normal hematopoiesis.One of the most prioritized tasks is the early and correct diagnosis of this malignancy;however,manual observation of the blood smear is very time-consuming and requires labor and expertise.Transfer learning in deep neural networks is of growing importance to intricate medical tasks such as medical imaging.Our work proposes an application of a novel ensemble architecture that puts together Vision Transformer and EfficientNetV2.This approach fuses deep and spatial features to optimize discriminative power by selecting features accurately,reducing redundancy,and promoting sparsity.Besides the architecture of the ensemble,the advanced feature selection is performed by the Frog-Snake Prey-Predation Relationship Optimization(FSRO)algorithm.FSRO prioritizes the most relevant features while dynamically reducing redundant and noisy data,hence improving the efficiency and accuracy of the classification model.We have compared our method for feature selection against state-of-the-art techniques and recorded an accuracy of 94.88%,a recall of 94.38%,a precision of 96.18%,and an F1-score of 95.63%.These figures are therefore better than the classical methods for deep learning.Though our dataset,collected from four different hospitals,is non-standard and heterogeneous,making the analysis more challenging,although computationally expensive,our approach proves diagnostically superior in cancer detection.Source codes and datasets are available on GitHub.展开更多
Heart disease prediction is a critical issue in healthcare,where accurate early diagnosis can save lives and reduce healthcare costs.The problem is inherently complex due to the high dimensionality of medical data,irr...Heart disease prediction is a critical issue in healthcare,where accurate early diagnosis can save lives and reduce healthcare costs.The problem is inherently complex due to the high dimensionality of medical data,irrelevant or redundant features,and the variability in risk factors such as age,lifestyle,andmedical history.These challenges often lead to inefficient and less accuratemodels.Traditional predictionmethodologies face limitations in effectively handling large feature sets and optimizing classification performance,which can result in overfitting poor generalization,and high computational cost.This work proposes a novel classification model for heart disease prediction that addresses these challenges by integrating feature selection through a Genetic Algorithm(GA)with an ensemble deep learning approach optimized using the Tunicate Swarm Algorithm(TSA).GA selects the most relevant features,reducing dimensionality and improvingmodel efficiency.Theselected features are then used to train an ensemble of deep learning models,where the TSA optimizes the weight of each model in the ensemble to enhance prediction accuracy.This hybrid approach addresses key challenges in the field,such as high dimensionality,redundant features,and classification performance,by introducing an efficient feature selection mechanism and optimizing the weighting of deep learning models in the ensemble.These enhancements result in a model that achieves superior accuracy,generalization,and efficiency compared to traditional methods.The proposed model demonstrated notable advancements in both prediction accuracy and computational efficiency over traditionalmodels.Specifically,it achieved an accuracy of 97.5%,a sensitivity of 97.2%,and a specificity of 97.8%.Additionally,with a 60-40 data split and 5-fold cross-validation,the model showed a significant reduction in training time(90 s),memory consumption(950 MB),and CPU usage(80%),highlighting its effectiveness in processing large,complex medical datasets for heart disease prediction.展开更多
Hematoxylin and Eosin(H&E)images,popularly used in the field of digital pathology,often pose challenges due to their limited color richness,hindering the differentiation of subtle cell features crucial for accurat...Hematoxylin and Eosin(H&E)images,popularly used in the field of digital pathology,often pose challenges due to their limited color richness,hindering the differentiation of subtle cell features crucial for accurate classification.Enhancing the visibility of these elusive cell features helps train robust deep-learning models.However,the selection and application of image processing techniques for such enhancement have not been systematically explored in the research community.To address this challenge,we introduce Salient Features Guided Augmentation(SFGA),an approach that strategically integrates machine learning and image processing.SFGA utilizes machine learning algorithms to identify crucial features within cell images,subsequently mapping these features to appropriate image processing techniques to enhance training images.By emphasizing salient features and aligning them with corresponding image processing methods,SFGA is designed to enhance the discriminating power of deep learning models in cell classification tasks.Our research undertakes a series of experiments,each exploring the performance of different datasets and data enhancement techniques in classifying cell types,highlighting the significance of data quality and enhancement in mitigating overfitting and distinguishing cell characteristics.Specifically,SFGA focuses on identifying tumor cells from tissue for extranodal extension detection,with the SFGA-enhanced dataset showing notable advantages in accuracy.We conducted a preliminary study of five experiments,among which the accuracy of the pleomorphism experiment improved significantly from 50.81%to 95.15%.The accuracy of the other four experiments also increased,with improvements ranging from 3 to 43 percentage points.Our preliminary study shows the possibilities to enhance the diagnostic accuracy of deep learning models and proposes a systematic approach that could enhance cancer diagnosis,contributing as a first step in using SFGA in medical image enhancement.展开更多
Brain tumor classification is crucial for personalized treatment planning.Although deep learning-based Artificial Intelligence(AI)models can automatically analyze tumor images,fine details of small tumor regions may b...Brain tumor classification is crucial for personalized treatment planning.Although deep learning-based Artificial Intelligence(AI)models can automatically analyze tumor images,fine details of small tumor regions may be overlooked during global feature extraction.Therefore,we propose a brain tumor Magnetic Resonance Imaging(MRI)classification model based on a global-local parallel dual-branch structure.The global branch employs ResNet50 with a Multi-Head Self-Attention(MHSA)to capture global contextual information from whole brain images,while the local branch utilizes VGG16 to extract fine-grained features from segmented brain tumor regions.The features from both branches are processed through designed attention-enhanced feature fusion module to filter and integrate important features.Additionally,to address sample imbalance in the dataset,we introduce a category attention block to improve the recognition of minority classes.Experimental results indicate that our method achieved a classification accuracy of 98.04%and a micro-average Area Under the Curve(AUC)of 0.989 in the classification of three types of brain tumors,surpassing several existing pre-trained Convolutional Neural Network(CNN)models.Additionally,feature interpretability analysis validated the effectiveness of the proposed model.This suggests that the method holds significant potential for brain tumor image classification.展开更多
Deep forgery detection technologies are crucial for image and video recognition tasks,with their performance heavily reliant on the features extracted from both real and fake images.However,most existing methods prima...Deep forgery detection technologies are crucial for image and video recognition tasks,with their performance heavily reliant on the features extracted from both real and fake images.However,most existing methods primarily focus on spatial domain features,which limits their accuracy.To address this limitation,we propose an adaptive dual-domain feature representation method for enhanced deep forgery detection.Specifically,an adaptive region dynamic convolution module is established to efficiently extract facial features from the spatial domain.Then,we introduce an adaptive frequency dynamic filter to capture effective frequency domain features.By fusing both spatial and frequency domain features,our approach significantly improves the accuracy of classifying real and fake facial images.Finally,experimental results on three real-world datasets validate the effectiveness of our dual-domain feature representation method,which substantially improves classification precision.展开更多
The human ear has been substantiated as a viable nonintrusive biometric modality for identification or verification.Among many feasible techniques for ear biometric recognition,convolutional neural network(CNN)models ...The human ear has been substantiated as a viable nonintrusive biometric modality for identification or verification.Among many feasible techniques for ear biometric recognition,convolutional neural network(CNN)models have recently offered high-performance and reliable systems.However,their performance can still be further improved using the capabilities of soft biometrics,a research question yet to be investigated.This research aims to augment the traditional CNN-based ear recognition performance by adding increased discriminatory ear soft biometric traits.It proposes a novel framework of augmented ear identification/verification using a group of discriminative categorical soft biometrics and deriving new,more perceptive,comparative soft biometrics for feature-level fusion with hard biometric deep features.It conducts several identification and verification experiments for performance evaluation,analysis,and comparison while varying ear image datasets,hard biometric deep-feature extractors,soft biometric augmentation methods,and classifiers used.The experimental work yields promising results,reaching up to 99.94%accuracy and up to 14%improvement using the AMI and AMIC datasets,along with their corresponding soft biometric label data.The results confirm the proposed augmented approaches’superiority over their standard counterparts and emphasize the robustness of the new ear comparative soft biometrics over their categorical peers.展开更多
Human Activity Recognition(HAR)has become increasingly critical in civic surveillance,medical care monitoring,and institutional protection.Current deep learning-based approaches often suffer from excessive computation...Human Activity Recognition(HAR)has become increasingly critical in civic surveillance,medical care monitoring,and institutional protection.Current deep learning-based approaches often suffer from excessive computational complexity,limited generalizability under varying conditions,and compromised real-time performance.To counter these,this paper introduces an Active Learning-aided Heuristic Deep Spatio-Textural Ensemble Learning(ALH-DSEL)framework.The model initially identifies keyframes from the surveillance videos with a Multi-Constraint Active Learning(MCAL)approach,with features extracted from DenseNet121.The frames are then segmented employing an optimized Fuzzy C-Means clustering algorithm with Firefly to identify areas of interest.A deep ensemble feature extractor,comprising DenseNet121,EfficientNet-B7,MobileNet,and GLCM,extracts varied spatial and textural features.Fused characteristics are enhanced through PCA and Min-Max normalization and discriminated by a maximum voting ensemble of RF,AdaBoost,and XGBoost.The experimental results show that ALH-DSEL provides higher accuracy,precision,recall,and F1-score,validating its superiority for real-time HAR in surveillance scenarios.展开更多
The Quadric Error Metrics(QEM)algorithm is a widely used method for mesh simplification;however,it often struggles to preserve high-frequency geometric details,leading to the loss of salient features.To address this l...The Quadric Error Metrics(QEM)algorithm is a widely used method for mesh simplification;however,it often struggles to preserve high-frequency geometric details,leading to the loss of salient features.To address this limitation,we propose the Salient Feature Sampling Points-based QEM(SFSP-QEM)—also referred to as the Deep Learning-Based Salient Feature-Preserving Algorithm for Mesh Simplification—which incorporates a Salient Feature-Preserving Point Sampler(SFSP).This module leverages deep learning techniques to prioritize the preservation of key geometric features during simplification.Experimental results demonstrate that SFSP-QEM significantly outperforms traditional QEM in preserving geometric details.Specifically,for general models from the Stanford 3D Scanning Repository,which represent typical mesh structures used in mesh simplification benchmarks,the Hausdorff distance of simplified models using SFSP-QEM is reduced by an average of 46.58% compared to those simplified using traditional QEM.In customized models such as the Zigong Lantern used in cultural heritage preservation,SFSP-QEM achieves an average reduction of 28.99% in Hausdorff distance.Moreover,the running time of this method is only 6%longer than that of traditional QEM while significantly improving the preservation of geometric details.These results demonstrate that SFSP-QEMis particularly effective for applications requiring high-fidelity simplification while retaining critical features.展开更多
Deep Underground Science and Engineering(DUSE)is pleased to release this issue with feature articles reporting the advancement in several research topics related to deep underground.This issue contains one perspective...Deep Underground Science and Engineering(DUSE)is pleased to release this issue with feature articles reporting the advancement in several research topics related to deep underground.This issue contains one perspective article,two review articles,six research articles,and one case study article.These articles focus on underground energy storage,multiscale modeling for correlation between micro-scale damage and macro-scale structural degradation,mineralization and formation of gold mine,interface and fracture seepage,experimental study on tunnel-sand-pile interaction,and high water-content materials for deep underground space backfilling,analytical solutions for the crack evolution direction in brittle rocks,and a case study on the squeezing-induced failure in a water drainage tunnel and the rehabilitation measures.展开更多
As petroleum exploration advances and as most of the oil-gas reservoirs in shallow layers have been explored, petroleum exploration starts to move toward deep basins, which has become an inevitable choice. In this pap...As petroleum exploration advances and as most of the oil-gas reservoirs in shallow layers have been explored, petroleum exploration starts to move toward deep basins, which has become an inevitable choice. In this paper, the petroleum geology features and research progress on oil-gas reservoirs in deep petroliferous basins across the world are characterized by using the latest results of worldwide deep petroleum exploration. Research has demonstrated that the deep petroleum shows ten major geological features. （1） While oil-gas reservoirs have been discovered in many different types of deep petroliferous basins, most have been discovered in low heat flux deep basins. （2） Many types of petroliferous traps are developed in deep basins, and tight oil-gas reservoirs in deep basin traps are arousing increasing attention. （3） Deep petroleum normally has more natural gas than liquid oil, and the natural gas ratio increases with the burial depth. （4） The residual organic matter in deep source rocks reduces but the hydrocarbon expulsion rate and efficiency increase with the burial depth. （5） There are many types of rocks in deep hydrocarbon reservoirs, and most are clastic rocks and carbonates. （6） The age of deep hydrocarbon reservoirs is widely different, but those recently discovered are pre- dominantly Paleogene and Upper Paleozoic. （7） The porosity and permeability of deep hydrocarbon reservoirs differ widely, but they vary in a regular way with lithology and burial depth. （8） The temperatures of deep oil-gas reservoirs are widely different, but they typically vary with the burial depth and basin geothermal gradient. （9） The pressures of deep oil-gas reservoirs differ significantly, but they typically vary with burial depth, genesis, and evolu- tion period. （10） Deep oil-gas reservoirs may exist with or without a cap, and those without a cap are typically of unconventional genesis. Over the past decade, six major steps have been made in the understanding of deep hydrocarbon reservoir formation. （1） Deep petroleum in petroliferous basins has multiple sources and many dif- ferent genetic mechanisms. （2） There are high-porosity, high-permeability reservoirs in deep basins, the formation of which is associated with tectonic events and subsurface fluid movement. （3） Capillary pressure differences inside and outside the target reservoir are the principal driving force of hydrocarbon enrichment in deep basins. （4） There are three dynamic boundaries for deep oil-gas reservoirs; a buoyancy-controlled threshold, hydrocarbon accumulation limits, and the upper limit of hydrocarbon generation. （5） The formation and distribution of deep hydrocarbon res- ervoirs are controlled by free, limited, and bound fluid dynamic fields. And （6） tight conventional, tight deep, tight superimposed, and related reconstructed hydrocarbon reservoirs formed in deep-limited fluid dynamic fields have great resource potential and vast scope for exploration. Compared with middle-shallow strata, the petroleum geology and accumulation in deep basins are more complex, which overlap the feature of basin evolution in different stages. We recommend that further study should pay more attention to four aspects： （1） identification of deep petroleum sources and evaluation of their relative contributions; （2） preservation conditions and genetic mechanisms of deep high-quality reservoirs with high permeability and high porosity; （3） facies feature and transformation of deep petroleum and their potential distribution; and （4） economic feasibility evaluation of deep tight petroleum exploration and development.展开更多
Fine-grained image classification, which aims to distinguish images with subtle distinctions, is a challenging task for two main reasons: lack of sufficient training data for every class and difficulty in learning dis...Fine-grained image classification, which aims to distinguish images with subtle distinctions, is a challenging task for two main reasons: lack of sufficient training data for every class and difficulty in learning discriminative features for representation. In this paper, to address the two issues, we propose a two-phase framework for recognizing images from unseen fine-grained classes, i.e., zeroshot fine-grained classification. In the first feature learning phase, we finetune deep convolutional neural networks using hierarchical semantic structure among fine-grained classes to extract discriminative deep visual features. Meanwhile, a domain adaptation structure is induced into deep convolutional neural networks to avoid domain shift from training data to test data. In the second label inference phase, a semantic directed graph is constructed over attributes of fine-grained classes. Based on this graph, we develop a label propagation algorithm to infer the labels of images in the unseen classes. Experimental results on two benchmark datasets demonstrate that our model outperforms the state-of-the-art zero-shot learning models. In addition, the features obtained by our feature learning model also yield significant gains when they are used by other zero-shot learning models, which shows the flexility of our model in zero-shot finegrained classification.展开更多
The rapid rise of cyberattacks and the gradual failure of traditional defense systems and approaches led to using artificial intelligence(AI)techniques(such as machine learning(ML)and deep learning(DL))to build more e...The rapid rise of cyberattacks and the gradual failure of traditional defense systems and approaches led to using artificial intelligence(AI)techniques(such as machine learning(ML)and deep learning(DL))to build more efficient and reliable intrusion detection systems(IDSs).However,the advent of larger IDS datasets has negatively impacted the performance and computational complexity of AI-based IDSs.Many researchers used data preprocessing techniques such as feature selection and normalization to overcome such issues.While most of these researchers reported the success of these preprocessing techniques on a shallow level,very few studies have been performed on their effects on a wider scale.Furthermore,the performance of an IDS model is subject to not only the utilized preprocessing techniques but also the dataset and the ML/DL algorithm used,which most of the existing studies give little emphasis on.Thus,this study provides an in-depth analysis of feature selection and normalization effects on IDS models built using three IDS datasets:NSL-KDD,UNSW-NB15,and CSE–CIC–IDS2018,and various AI algorithms.A wrapper-based approach,which tends to give superior performance,and min-max normalization methods were used for feature selection and normalization,respectively.Numerous IDS models were implemented using the full and feature-selected copies of the datasets with and without normalization.The models were evaluated using popular evaluation metrics in IDS modeling,intra-and inter-model comparisons were performed between models and with state-of-the-art works.Random forest(RF)models performed better on NSL-KDD and UNSW-NB15 datasets with accuracies of 99.86%and 96.01%,respectively,whereas artificial neural network(ANN)achieved the best accuracy of 95.43%on the CSE–CIC–IDS2018 dataset.The RF models also achieved an excellent performance compared to recent works.The results show that normalization and feature selection positively affect IDS modeling.Furthermore,while feature selection benefits simpler algorithms(such as RF),normalization is more useful for complex algorithms like ANNs and deep neural networks(DNNs),and algorithms such as Naive Bayes are unsuitable for IDS modeling.The study also found that the UNSW-NB15 and CSE–CIC–IDS2018 datasets are more complex and more suitable for building and evaluating modern-day IDS than the NSL-KDD dataset.Our findings suggest that prioritizing robust algorithms like RF,alongside complex models such as ANN and DNN,can significantly enhance IDS performance.These insights provide valuable guidance for managers to develop more effective security measures by focusing on high detection rates and low false alert rates.展开更多
基金supported by the National Natural Science Foundation of China(No.62276204)the Fundamental Research Funds for the Central Universities,China(No.YJSJ24011)+1 种基金the Natural Science Basic Research Program of Shaanxi,China(Nos.2022JM-340 and 2023-JC-QN-0710)the China Postdoctoral Science Foundation(Nos.2020T130494 and 2018M633470)。
文摘Visible and infrared(RGB-IR)fusion object detection plays an important role in security,disaster relief,etc.In recent years,deep-learning-based RGB-IR fusion detection methods have been developing rapidly,but still struggle to deal with the complex and changing scenarios captured by drones,mainly due to two reasons:(A)RGB-IR fusion detectors are susceptible to inferior inputs that degrade performance and stability.(B)RGB-IR fusion detectors are susceptible to redundant features that reduce accuracy and efficiency.In this paper,an innovative RGB-IR fusion detection framework based on global-local feature optimization,named GLFDet,is proposed to improve the detection performance and efficiency of drone-captured objects.The key components of GLFDet include a Global Feature Optimization(GFO)module,a Local Feature Optimization(LFO)module and a Channel Separation Fusion(CSF)module.Specifically,GFO calculates the information content of the input image from the frequency domain and optimizes the features holistically.Then,LFO dynamically selects high-value features and filters out low-value features before fusion,which significantly improves the efficiency of fusion.Finally,CSF fuses the RGB and IR features across the corresponding channels,which avoids the rearrangement of the channel relationships and enhances the model stability.Extensive experimental results show that the proposed method achieves the best performance on three popular RGB-IR datasets Drone Vehicle,VEDAI,and LLVIP.In addition,GLFDet is more lightweight than other comparable models,making it more appealing to edge devices such as drones.The code is available at https://github.com/lao chen330/GLFDet.
基金funded by the Hainan Province Science and Technology Special Fund under Grant ZDYF2024GXJS292.
文摘Deep learning has made significant progress in the field of oriented object detection for remote sensing images.However,existing methods still face challenges when dealing with difficult tasks such as multi-scale targets,complex backgrounds,and small objects in remote sensing.Maintaining model lightweight to address resource constraints in remote sensing scenarios while improving task completion for remote sensing tasks remains a research hotspot.Therefore,we propose an enhanced multi-scale feature extraction lightweight network EM-YOLO based on the YOLOv8s architecture,specifically optimized for the characteristics of large target scale variations,diverse orientations,and numerous small objects in remote sensing images.Our innovations lie in two main aspects:First,a dynamic snake convolution(DSC)is introduced into the backbone network to enhance the model’s feature extraction capability for oriented targets.Second,an innovative focusing-diffusion module is designed in the feature fusion neck to effectively integrate multi-scale feature information.Finally,we introduce Layer-Adaptive Sparsity for magnitude-based Pruning(LASP)method to perform lightweight network pruning to better complete tasks in resource-constrained scenarios.Experimental results on the lightweight platform Orin demonstrate that the proposed method significantly outperforms the original YOLOv8s model in oriented remote sensing object detection tasks,and achieves comparable or superior performance to state-of-the-art methods on three authoritative remote sensing datasets(DOTA v1.0,DOTA v1.5,and HRSC2016).
基金supported by the National Natural Science Foundation of China(No.62203163)the Scientific Research Project of Hunan Provincial Education Department(No.24A0519)+1 种基金the Hunan Provincial Natural Science Foundation(No.2025JJ60407)the Postgraduate Scientific Research Innovation Project of Hunan Province(No.CX2024100).
文摘Accurate detection of smoke and fire sources is critical for early fire warning and environmental monitoring.However,conventional detection approaches are highly susceptible to noise,illumination variations,and complex environmental conditions,which often reduce detection accuracy and real-time performance.To address these limitations,we propose Lightweight and Precise YOLO(LP-YOLO),a high-precision detection framework that integrates a self-attention mechanism with a feature pyramid,built upon YOLOv8.First,to overcome the restricted receptive field and parameter redundancy of conventional Convolutional Neural Networks(CNNs),we design an enhanced backbone based on Wavelet Convolutions(WTConv),which expands the receptive field through multifrequency convolutional processing.Second,a Bidirectional Feature Pyramid Network(BiFPN)is employed to achieve bidirectional feature fusion,enhancing the representation of smoke features across scales.Third,to mitigate the challenge of ambiguous object boundaries,we introduce the Frequency-aware Feature Fusion(FreqFusion)module,in which the Adaptive Low-Pass Filter(ALPF)reduces intra-class inconsistencies,the offset generator refines boundary localization,and the Adaptive High-Pass Filter(AHPF)recovers high-frequency details lost during down-sampling.Experimental evaluations demonstrate that LP-YOLO significantly outperforms the baseline YOLOv8,achieving an improvement of 9.3%in mAP@50 and 9.2%in F1-score.Moreover,the model is 56.6%and 32.4%smaller than YOLOv7-tiny and EfficientDet,respectively,while maintaining real-time inference speed at 238 frames per second(FPS).Validation on multiple benchmark datasets,including D-Fire,FIRESENSE,and BoWFire,further confirms its robustness and generalization ability,with detection accuracy consistently exceeding 82%.These results highlight the potential of LP-YOLO as a practical solution with high accuracy,robustness,and real-time performance for smoke and fire source detection.
基金supported by the National Natural Science Foundation of China Grant(No.61972133)Project of Leading Talents in Science and Technology Innovation for Thousands of People Plan in Henan Province Grant(No.204200510021)the Key Research and Development Plan Special Project of Henan Province Grant(No.241111211400).
文摘At inference time,deep neural networks are susceptible to backdoor attacks,which can produce attackercontrolled outputs when inputs contain carefully crafted triggers.Existing defense methods often focus on specific attack types or incur high costs,such as data cleaning or model fine-tuning.In contrast,we argue that it is possible to achieve effective and generalizable defense without removing triggers or incurring high model-cleaning costs.Fromthe attacker’s perspective and based on characteristics of vulnerable neuron activation anomalies,we propose an Adaptive Feature Injection(AFI)method for black-box backdoor detection.AFI employs a pre-trained image encoder to extract multi-level deep features and constructs a dynamic weight fusionmechanism for precise identification and interception of poisoned samples.Specifically,we select the control samples with the largest feature differences fromthe clean dataset via feature-space analysis,and generate blended sample pairs with the test sample using dynamic linear interpolation.The detection statistic is computed by measuring the divergence G(x)in model output responses.We systematically evaluate the effectiveness of AFI against representative backdoor attacks,including BadNets,Blend,WaNet,and IAB,on three benchmark datasets:MNIST,CIFAR-10,and ImageNet.Experimental results show that AFI can effectively detect poisoned samples,achieving average detection rates of 95.20%,94.15%,and 86.49%on these datasets,respectively.Compared with existing methods,AFI demonstrates strong cross-domain generalization ability and robustness to unknown attacks.
基金King Saud University,Grant/Award Number:RSP2024R157。
文摘Biometric characteristics are playing a vital role in security for the last few years.Human gait classification in video sequences is an important biometrics attribute and is used for security purposes.A new framework for human gait classification in video sequences using deep learning(DL)fusion assisted and posterior probability-based moth flames optimization(MFO)is proposed.In the first step,the video frames are resized and finetuned by two pre-trained lightweight DL models,EfficientNetB0 and MobileNetV2.Both models are selected based on the top-5 accuracy and less number of parameters.Later,both models are trained through deep transfer learning and extracted deep features fused using a voting scheme.In the last step,the authors develop a posterior probabilitybased MFO feature selection algorithm to select the best features.The selected features are classified using several supervised learning methods.The CASIA-B publicly available dataset has been employed for the experimental process.On this dataset,the authors selected six angles such as 0°,18°,90°,108°,162°,and 180°and obtained an average accuracy of 96.9%,95.7%,86.8%,90.0%,95.1%,and 99.7%.Results demonstrate comparable improvement in accuracy and significantly minimize the computational time with recent state-of-the-art techniques.
基金funded by the National Natural Science Foundation of China(Grant No.52175028).
文摘Accurate and robust navigation in complex surgical environments is crucial for bronchoscopic surgeries.This study purposes a bronchoscopic lumen feature matching network(BLFM-Net)based on deep learning to address the challenges of image noise,anatomical complexity,and the stringent real-time requirements.The BLFM-Net enhances bronchoscopic image processing by integrating several functional modules.The FFA-Net preprocessing module mitigates image fogging and improves visual clarity for subsequent processing.The feature extraction module derives multi-dimensional features,such as centroids,area,and shape descriptors,from dehazed images.The Faster RCNN Object detection module detects bronchial regions of interest and generates bounding boxes to localize key areas.The feature matching module accelerates the process by combining detection boxes,extracted features,and a KD-Tree(K-Dimensional Tree)-based algorithm,ensuring efficient and accurate regional feature associations.The BLFM-Net was evaluated on 5212 bronchoscopic images,demonstrating superior performance compared to traditional and other deep learning-based image matching methods.It achieved real-time matching with an average frame time of 6 ms,with a matching accuracy of over 96%.The method remained robust under challenging conditions including frame dropping(0,5,10,20),shadowed regions,and variable lighting,maintaining accuracy of above 94%even with the frame dropping of 20.This study presents BLFM-Net,a deep learning-based matching network designed to enhance and match bronchial features in bronchoscopic images.The BLFM-Net shows improved accuracy,real-time performance,and reliability,making a valuable tool for bronchoscopic surgeries.
文摘In recent years,the heterogeneous SAR image classification task of"training on simulated data and testing on measured data"has garnered increasing attention in the field of Synthetic Aperture Radar Automatic Target Recognition(SAR-ATR).Although current mainstream domain adaptation methods have made significant breakthroughs in addressing domain shift problems,the escalating model complexity and task complexity have constrained their deployment in real-world applications.To tackle this challenge,this paper proposes a domain adaptation framework based on linear-kernel Maximum Mean Discrepancy(MMD),integrated with a near-zero-cost pseudo-label denoising technique leveraging deep feature clustering.Our method completely eliminates the need for data augmentation and handcrafted feature design,achieving endto-end pseudo-label self-training.Competitive performance is demonstrated across three typical scenarios in the SAMPLE dataset,with the highest accuracy of 98.65%achieved in ScenarioⅢ.The relevant code is available at:https://github.com/TheGreatTreatsby/SAMPLE_MMD.
文摘Acute lymphoblastic leukemia(ALL)is characterized by overgrowth of immature lymphoid cells in the bone marrow at the expense of normal hematopoiesis.One of the most prioritized tasks is the early and correct diagnosis of this malignancy;however,manual observation of the blood smear is very time-consuming and requires labor and expertise.Transfer learning in deep neural networks is of growing importance to intricate medical tasks such as medical imaging.Our work proposes an application of a novel ensemble architecture that puts together Vision Transformer and EfficientNetV2.This approach fuses deep and spatial features to optimize discriminative power by selecting features accurately,reducing redundancy,and promoting sparsity.Besides the architecture of the ensemble,the advanced feature selection is performed by the Frog-Snake Prey-Predation Relationship Optimization(FSRO)algorithm.FSRO prioritizes the most relevant features while dynamically reducing redundant and noisy data,hence improving the efficiency and accuracy of the classification model.We have compared our method for feature selection against state-of-the-art techniques and recorded an accuracy of 94.88%,a recall of 94.38%,a precision of 96.18%,and an F1-score of 95.63%.These figures are therefore better than the classical methods for deep learning.Though our dataset,collected from four different hospitals,is non-standard and heterogeneous,making the analysis more challenging,although computationally expensive,our approach proves diagnostically superior in cancer detection.Source codes and datasets are available on GitHub.
文摘Heart disease prediction is a critical issue in healthcare,where accurate early diagnosis can save lives and reduce healthcare costs.The problem is inherently complex due to the high dimensionality of medical data,irrelevant or redundant features,and the variability in risk factors such as age,lifestyle,andmedical history.These challenges often lead to inefficient and less accuratemodels.Traditional predictionmethodologies face limitations in effectively handling large feature sets and optimizing classification performance,which can result in overfitting poor generalization,and high computational cost.This work proposes a novel classification model for heart disease prediction that addresses these challenges by integrating feature selection through a Genetic Algorithm(GA)with an ensemble deep learning approach optimized using the Tunicate Swarm Algorithm(TSA).GA selects the most relevant features,reducing dimensionality and improvingmodel efficiency.Theselected features are then used to train an ensemble of deep learning models,where the TSA optimizes the weight of each model in the ensemble to enhance prediction accuracy.This hybrid approach addresses key challenges in the field,such as high dimensionality,redundant features,and classification performance,by introducing an efficient feature selection mechanism and optimizing the weighting of deep learning models in the ensemble.These enhancements result in a model that achieves superior accuracy,generalization,and efficiency compared to traditional methods.The proposed model demonstrated notable advancements in both prediction accuracy and computational efficiency over traditionalmodels.Specifically,it achieved an accuracy of 97.5%,a sensitivity of 97.2%,and a specificity of 97.8%.Additionally,with a 60-40 data split and 5-fold cross-validation,the model showed a significant reduction in training time(90 s),memory consumption(950 MB),and CPU usage(80%),highlighting its effectiveness in processing large,complex medical datasets for heart disease prediction.
基金supported by grants fromthe North China University of Technology Research Start-Up Fund(11005136024XN147-14)and(110051360024XN151-97)Guangzhou Development Zone Science and Technology Project(2023GH02)+4 种基金the National Key R&D Program of China(2021YFE0201100 and 2022YFA1103401 to Juntao Gao)National Natural Science Foundation of China(981890991 to Juntao Gao)Beijing Municipal Natural Science Foundation(Z200021 to Juntao Gao)CAS Interdisciplinary Innovation Team(JCTD-2020-04 to Juntao Gao)0032/2022/A,by Macao FDCT,and MYRG2022-00271-FST.
文摘Hematoxylin and Eosin(H&E)images,popularly used in the field of digital pathology,often pose challenges due to their limited color richness,hindering the differentiation of subtle cell features crucial for accurate classification.Enhancing the visibility of these elusive cell features helps train robust deep-learning models.However,the selection and application of image processing techniques for such enhancement have not been systematically explored in the research community.To address this challenge,we introduce Salient Features Guided Augmentation(SFGA),an approach that strategically integrates machine learning and image processing.SFGA utilizes machine learning algorithms to identify crucial features within cell images,subsequently mapping these features to appropriate image processing techniques to enhance training images.By emphasizing salient features and aligning them with corresponding image processing methods,SFGA is designed to enhance the discriminating power of deep learning models in cell classification tasks.Our research undertakes a series of experiments,each exploring the performance of different datasets and data enhancement techniques in classifying cell types,highlighting the significance of data quality and enhancement in mitigating overfitting and distinguishing cell characteristics.Specifically,SFGA focuses on identifying tumor cells from tissue for extranodal extension detection,with the SFGA-enhanced dataset showing notable advantages in accuracy.We conducted a preliminary study of five experiments,among which the accuracy of the pleomorphism experiment improved significantly from 50.81%to 95.15%.The accuracy of the other four experiments also increased,with improvements ranging from 3 to 43 percentage points.Our preliminary study shows the possibilities to enhance the diagnostic accuracy of deep learning models and proposes a systematic approach that could enhance cancer diagnosis,contributing as a first step in using SFGA in medical image enhancement.
文摘Brain tumor classification is crucial for personalized treatment planning.Although deep learning-based Artificial Intelligence(AI)models can automatically analyze tumor images,fine details of small tumor regions may be overlooked during global feature extraction.Therefore,we propose a brain tumor Magnetic Resonance Imaging(MRI)classification model based on a global-local parallel dual-branch structure.The global branch employs ResNet50 with a Multi-Head Self-Attention(MHSA)to capture global contextual information from whole brain images,while the local branch utilizes VGG16 to extract fine-grained features from segmented brain tumor regions.The features from both branches are processed through designed attention-enhanced feature fusion module to filter and integrate important features.Additionally,to address sample imbalance in the dataset,we introduce a category attention block to improve the recognition of minority classes.Experimental results indicate that our method achieved a classification accuracy of 98.04%and a micro-average Area Under the Curve(AUC)of 0.989 in the classification of three types of brain tumors,surpassing several existing pre-trained Convolutional Neural Network(CNN)models.Additionally,feature interpretability analysis validated the effectiveness of the proposed model.This suggests that the method holds significant potential for brain tumor image classification.
基金supported in part by the National Natural Science Foundation of China under No.12401679the Nature Science Foundation of the Jiangsu Higher Education Institutions of China under No.23KJB520006the Haizhou Bay Talent Innovation Program of Jiangsu Ocean University under No.PD2024026。
文摘Deep forgery detection technologies are crucial for image and video recognition tasks,with their performance heavily reliant on the features extracted from both real and fake images.However,most existing methods primarily focus on spatial domain features,which limits their accuracy.To address this limitation,we propose an adaptive dual-domain feature representation method for enhanced deep forgery detection.Specifically,an adaptive region dynamic convolution module is established to efficiently extract facial features from the spatial domain.Then,we introduce an adaptive frequency dynamic filter to capture effective frequency domain features.By fusing both spatial and frequency domain features,our approach significantly improves the accuracy of classifying real and fake facial images.Finally,experimental results on three real-world datasets validate the effectiveness of our dual-domain feature representation method,which substantially improves classification precision.
基金funded by WAQF at King Abdulaziz University,Jeddah,Saudi Arabia.
文摘The human ear has been substantiated as a viable nonintrusive biometric modality for identification or verification.Among many feasible techniques for ear biometric recognition,convolutional neural network(CNN)models have recently offered high-performance and reliable systems.However,their performance can still be further improved using the capabilities of soft biometrics,a research question yet to be investigated.This research aims to augment the traditional CNN-based ear recognition performance by adding increased discriminatory ear soft biometric traits.It proposes a novel framework of augmented ear identification/verification using a group of discriminative categorical soft biometrics and deriving new,more perceptive,comparative soft biometrics for feature-level fusion with hard biometric deep features.It conducts several identification and verification experiments for performance evaluation,analysis,and comparison while varying ear image datasets,hard biometric deep-feature extractors,soft biometric augmentation methods,and classifiers used.The experimental work yields promising results,reaching up to 99.94%accuracy and up to 14%improvement using the AMI and AMIC datasets,along with their corresponding soft biometric label data.The results confirm the proposed augmented approaches’superiority over their standard counterparts and emphasize the robustness of the new ear comparative soft biometrics over their categorical peers.
文摘Human Activity Recognition(HAR)has become increasingly critical in civic surveillance,medical care monitoring,and institutional protection.Current deep learning-based approaches often suffer from excessive computational complexity,limited generalizability under varying conditions,and compromised real-time performance.To counter these,this paper introduces an Active Learning-aided Heuristic Deep Spatio-Textural Ensemble Learning(ALH-DSEL)framework.The model initially identifies keyframes from the surveillance videos with a Multi-Constraint Active Learning(MCAL)approach,with features extracted from DenseNet121.The frames are then segmented employing an optimized Fuzzy C-Means clustering algorithm with Firefly to identify areas of interest.A deep ensemble feature extractor,comprising DenseNet121,EfficientNet-B7,MobileNet,and GLCM,extracts varied spatial and textural features.Fused characteristics are enhanced through PCA and Min-Max normalization and discriminated by a maximum voting ensemble of RF,AdaBoost,and XGBoost.The experimental results show that ALH-DSEL provides higher accuracy,precision,recall,and F1-score,validating its superiority for real-time HAR in surveillance scenarios.
基金Our research was funded by the Sichuan Key Provincial Research Base of Intelligent Tourism(No.ZHZJ23-02)supported by the Scientific Research and Innovation Team Program of Sichuan University of Science and Engineering(No.SUSE652A006)+1 种基金Additional support was provided by the National Cultural and Tourism Science and Technology Innovation Research andDevelopment Project(No.202417)the Lantern Culture and Crafts Innovation Key Laboratory Project of the Sichuan ProvincialDepartment of Culture and Tourism(No.SCWLCD-A02).
文摘The Quadric Error Metrics(QEM)algorithm is a widely used method for mesh simplification;however,it often struggles to preserve high-frequency geometric details,leading to the loss of salient features.To address this limitation,we propose the Salient Feature Sampling Points-based QEM(SFSP-QEM)—also referred to as the Deep Learning-Based Salient Feature-Preserving Algorithm for Mesh Simplification—which incorporates a Salient Feature-Preserving Point Sampler(SFSP).This module leverages deep learning techniques to prioritize the preservation of key geometric features during simplification.Experimental results demonstrate that SFSP-QEM significantly outperforms traditional QEM in preserving geometric details.Specifically,for general models from the Stanford 3D Scanning Repository,which represent typical mesh structures used in mesh simplification benchmarks,the Hausdorff distance of simplified models using SFSP-QEM is reduced by an average of 46.58% compared to those simplified using traditional QEM.In customized models such as the Zigong Lantern used in cultural heritage preservation,SFSP-QEM achieves an average reduction of 28.99% in Hausdorff distance.Moreover,the running time of this method is only 6%longer than that of traditional QEM while significantly improving the preservation of geometric details.These results demonstrate that SFSP-QEMis particularly effective for applications requiring high-fidelity simplification while retaining critical features.
文摘Deep Underground Science and Engineering(DUSE)is pleased to release this issue with feature articles reporting the advancement in several research topics related to deep underground.This issue contains one perspective article,two review articles,six research articles,and one case study article.These articles focus on underground energy storage,multiscale modeling for correlation between micro-scale damage and macro-scale structural degradation,mineralization and formation of gold mine,interface and fracture seepage,experimental study on tunnel-sand-pile interaction,and high water-content materials for deep underground space backfilling,analytical solutions for the crack evolution direction in brittle rocks,and a case study on the squeezing-induced failure in a water drainage tunnel and the rehabilitation measures.
基金the National Basic Research Program of China (973 Program, 2011CB201100)‘‘Complex hydrocarbon accumulation mechanism and enrichmentregularities of deep superimposed basins in Western China’’ National Natural Science Foundation of China (U1262205) under the guidance of related department heads and experts
文摘As petroleum exploration advances and as most of the oil-gas reservoirs in shallow layers have been explored, petroleum exploration starts to move toward deep basins, which has become an inevitable choice. In this paper, the petroleum geology features and research progress on oil-gas reservoirs in deep petroliferous basins across the world are characterized by using the latest results of worldwide deep petroleum exploration. Research has demonstrated that the deep petroleum shows ten major geological features. （1） While oil-gas reservoirs have been discovered in many different types of deep petroliferous basins, most have been discovered in low heat flux deep basins. （2） Many types of petroliferous traps are developed in deep basins, and tight oil-gas reservoirs in deep basin traps are arousing increasing attention. （3） Deep petroleum normally has more natural gas than liquid oil, and the natural gas ratio increases with the burial depth. （4） The residual organic matter in deep source rocks reduces but the hydrocarbon expulsion rate and efficiency increase with the burial depth. （5） There are many types of rocks in deep hydrocarbon reservoirs, and most are clastic rocks and carbonates. （6） The age of deep hydrocarbon reservoirs is widely different, but those recently discovered are pre- dominantly Paleogene and Upper Paleozoic. （7） The porosity and permeability of deep hydrocarbon reservoirs differ widely, but they vary in a regular way with lithology and burial depth. （8） The temperatures of deep oil-gas reservoirs are widely different, but they typically vary with the burial depth and basin geothermal gradient. （9） The pressures of deep oil-gas reservoirs differ significantly, but they typically vary with burial depth, genesis, and evolu- tion period. （10） Deep oil-gas reservoirs may exist with or without a cap, and those without a cap are typically of unconventional genesis. Over the past decade, six major steps have been made in the understanding of deep hydrocarbon reservoir formation. （1） Deep petroleum in petroliferous basins has multiple sources and many dif- ferent genetic mechanisms. （2） There are high-porosity, high-permeability reservoirs in deep basins, the formation of which is associated with tectonic events and subsurface fluid movement. （3） Capillary pressure differences inside and outside the target reservoir are the principal driving force of hydrocarbon enrichment in deep basins. （4） There are three dynamic boundaries for deep oil-gas reservoirs; a buoyancy-controlled threshold, hydrocarbon accumulation limits, and the upper limit of hydrocarbon generation. （5） The formation and distribution of deep hydrocarbon res- ervoirs are controlled by free, limited, and bound fluid dynamic fields. And （6） tight conventional, tight deep, tight superimposed, and related reconstructed hydrocarbon reservoirs formed in deep-limited fluid dynamic fields have great resource potential and vast scope for exploration. Compared with middle-shallow strata, the petroleum geology and accumulation in deep basins are more complex, which overlap the feature of basin evolution in different stages. We recommend that further study should pay more attention to four aspects： （1） identification of deep petroleum sources and evaluation of their relative contributions; （2） preservation conditions and genetic mechanisms of deep high-quality reservoirs with high permeability and high porosity; （3） facies feature and transformation of deep petroleum and their potential distribution; and （4） economic feasibility evaluation of deep tight petroleum exploration and development.
基金supported by National Basic Research Program of China (973 Program) (No. 2015CB352502)National Nature Science Foundation of China (No. 61573026)Beijing Nature Science Foundation (No. L172037)
文摘Fine-grained image classification, which aims to distinguish images with subtle distinctions, is a challenging task for two main reasons: lack of sufficient training data for every class and difficulty in learning discriminative features for representation. In this paper, to address the two issues, we propose a two-phase framework for recognizing images from unseen fine-grained classes, i.e., zeroshot fine-grained classification. In the first feature learning phase, we finetune deep convolutional neural networks using hierarchical semantic structure among fine-grained classes to extract discriminative deep visual features. Meanwhile, a domain adaptation structure is induced into deep convolutional neural networks to avoid domain shift from training data to test data. In the second label inference phase, a semantic directed graph is constructed over attributes of fine-grained classes. Based on this graph, we develop a label propagation algorithm to infer the labels of images in the unseen classes. Experimental results on two benchmark datasets demonstrate that our model outperforms the state-of-the-art zero-shot learning models. In addition, the features obtained by our feature learning model also yield significant gains when they are used by other zero-shot learning models, which shows the flexility of our model in zero-shot finegrained classification.
文摘The rapid rise of cyberattacks and the gradual failure of traditional defense systems and approaches led to using artificial intelligence(AI)techniques(such as machine learning(ML)and deep learning(DL))to build more efficient and reliable intrusion detection systems(IDSs).However,the advent of larger IDS datasets has negatively impacted the performance and computational complexity of AI-based IDSs.Many researchers used data preprocessing techniques such as feature selection and normalization to overcome such issues.While most of these researchers reported the success of these preprocessing techniques on a shallow level,very few studies have been performed on their effects on a wider scale.Furthermore,the performance of an IDS model is subject to not only the utilized preprocessing techniques but also the dataset and the ML/DL algorithm used,which most of the existing studies give little emphasis on.Thus,this study provides an in-depth analysis of feature selection and normalization effects on IDS models built using three IDS datasets:NSL-KDD,UNSW-NB15,and CSE–CIC–IDS2018,and various AI algorithms.A wrapper-based approach,which tends to give superior performance,and min-max normalization methods were used for feature selection and normalization,respectively.Numerous IDS models were implemented using the full and feature-selected copies of the datasets with and without normalization.The models were evaluated using popular evaluation metrics in IDS modeling,intra-and inter-model comparisons were performed between models and with state-of-the-art works.Random forest(RF)models performed better on NSL-KDD and UNSW-NB15 datasets with accuracies of 99.86%and 96.01%,respectively,whereas artificial neural network(ANN)achieved the best accuracy of 95.43%on the CSE–CIC–IDS2018 dataset.The RF models also achieved an excellent performance compared to recent works.The results show that normalization and feature selection positively affect IDS modeling.Furthermore,while feature selection benefits simpler algorithms(such as RF),normalization is more useful for complex algorithms like ANNs and deep neural networks(DNNs),and algorithms such as Naive Bayes are unsuitable for IDS modeling.The study also found that the UNSW-NB15 and CSE–CIC–IDS2018 datasets are more complex and more suitable for building and evaluating modern-day IDS than the NSL-KDD dataset.Our findings suggest that prioritizing robust algorithms like RF,alongside complex models such as ANN and DNN,can significantly enhance IDS performance.These insights provide valuable guidance for managers to develop more effective security measures by focusing on high detection rates and low false alert rates.
