AIM:To investigate the clinical features and prognosis of patients with orbital inflammatory myofibroblastic tumor(IMT).METHODS:This retrospective study collected clinical data from 22 patients diagnosed with orbital ...AIM:To investigate the clinical features and prognosis of patients with orbital inflammatory myofibroblastic tumor(IMT).METHODS:This retrospective study collected clinical data from 22 patients diagnosed with orbital IMT based on histopathological examination.The patients were followed up to assess their prognosis.Clinical data from patients,including age,gender,course of disease,past medical history,primary symptoms,ophthalmologic examination findings,general condition,as well as imaging,laboratory,histopathological,and immunohistochemical results from digital records were collected.Orbital magnetic resonance imaging(MRI)and(or)computed tomography(CT)scans were performed to assess bone destruction of the mass,invasion of surrounding tissues,and any inflammatory changes in periorbital areas.RESULTS:The mean age of patients with orbital IMT was 28.24±3.30y,with a male-to-female ratio of 1.2:1.Main clinical manifestations were proptosis,blurred vision,palpable mass,and pain.Bone destruction and surrounding tissue invasion occurred in 72.73%and 54.55%of cases,respectively.Inflammatory changes in the periorbital site were observed in 77.27%of the patients.Hematoxylin and eosin staining showed proliferation of fibroblasts and myofibroblasts,accompanied by infiltration of lymphocytes and plasma cells.Immunohistochemical staining revealed that smooth muscle actin(SMA)and vimentin were positive in 100%of cases,while anaplastic lymphoma kinase(ALK)showed positivity in 47.37%.The recurrence rate of orbital IMT was 27.27%,and sarcomatous degeneration could occur.There were no significant correlations between recurrence and factors such as age,gender,laterality,duration of the disease,periorbital tissue invasion,bone destruction,periorbital inflammation,tumor size,fever,leukocytosis,or treatment(P>0.05).However,lymphadenopathy and a Ki-67 index of 10%or higher may be risk factors for recurrence(P=0.046;P=0.023).CONCLUSION:Orbital IMT is a locally invasive disease that may recur or lead to sarcomatoid degeneration,primarily affecting young and middle-aged patients.The presence of lymphadenopathy and a Ki-67 index of 10%or higher may signify a poor prognosis.展开更多
BACKGROUND SMARCB1/INI1-deficient pancreatic undifferentiated rhabdoid carcinoma is a highly aggressive tumor,and spontaneous splenic rupture(SSR)as its presenting manifestation is rarely reported among pancreatic mal...BACKGROUND SMARCB1/INI1-deficient pancreatic undifferentiated rhabdoid carcinoma is a highly aggressive tumor,and spontaneous splenic rupture(SSR)as its presenting manifestation is rarely reported among pancreatic malignancies.CASE SUMMARY We herein report a rare case of a 59-year-old female who presented with acute left upper quadrant abdominal pain without any history of trauma.Abdominal imaging demonstrated a heterogeneous splenic lesion with hemoperitoneum,raising clinical suspicion of SSR.Emergency laparotomy revealed a pancreatic tumor invading the spleen and left kidney,with associated splenic rupture and dense adhesions,necessitating en bloc resection of the distal pancreas,spleen,and left kidney.Histopathology revealed a biphasic malignancy composed of moderately differentiated pancreatic ductal adenocarcinoma and an undifferentiated carcinoma with rhabdoid morphology and loss of SMARCB1 expression.Immunohistochemical analysis confirmed complete loss of SMARCB1/INI1 in the undifferentiated component,along with a high Ki-67 index(approximately 80%)and CD10 positivity.The ductal adenocarcinoma component retained SMARCB1/INI1 expression and was positive for CK7 and CK-pan.Transitional zones between the two tumor components suggested progressive dedifferentiation and underlying genomic instability.The patient received adjuvant chemotherapy with gemcitabine and nab-paclitaxel and maintained a satisfactory quality of life at the 6-month follow-up.CONCLUSION This study reports a rare case of SMARCB1/INI1-deficient undifferentiated rhabdoid carcinoma of the pancreas combined with ductal adenocarcinoma,presenting as SSR-an exceptionally uncommon initial manifestation of pancreatic malignancy.展开更多
In the field of intelligent air combat,real-time and accurate recognition of within-visual-range(WVR)maneuver actions serves as the foundational cornerstone for constructing autonomous decision-making systems.However,...In the field of intelligent air combat,real-time and accurate recognition of within-visual-range(WVR)maneuver actions serves as the foundational cornerstone for constructing autonomous decision-making systems.However,existing methods face two major challenges:traditional feature engineering suffers from insufficient effective dimensionality in the feature space due to kinematic coupling,making it difficult to distinguish essential differences between maneuvers,while end-to-end deep learning models lack controllability in implicit feature learning and fail to model high-order long-range temporal dependencies.This paper proposes a trajectory feature pre-extraction method based on a Long-range Masked Autoencoder(LMAE),incorporating three key innovations:(1)Random Fragment High-ratio Masking(RFH-Mask),which enforces the model to learn long-range temporal correlations by masking 80%of trajectory data while retaining continuous fragments;(2)Kalman Filter-Guided Objective Function(KFG-OF),integrating trajectory continuity constraints to align the feature space with kinematic principles;and(3)Two-stage Decoupled Architecture,enabling efficient and controllable feature learning through unsupervised pre-training and frozen-feature transfer.Experimental results demonstrate that LMAE significantly improves the average recognition accuracy for 20-class maneuvers compared to traditional end-to-end models,while significantly accelerating convergence speed.The contributions of this work lie in:introducing high-masking-rate autoencoders into low-informationdensity trajectory analysis,proposing a feature engineering framework with enhanced controllability and efficiency,and providing a novel technical pathway for intelligent air combat decision-making systems.展开更多
In the article“A Lightweight Approach for Skin Lesion Detection through Optimal Features Fusion”by Khadija Manzoor,Fiaz Majeed,Ansar Siddique,Talha Meraj,Hafiz Tayyab Rauf,Mohammed A.El-Meligy,Mohamed Sharaf,Abd Ela...In the article“A Lightweight Approach for Skin Lesion Detection through Optimal Features Fusion”by Khadija Manzoor,Fiaz Majeed,Ansar Siddique,Talha Meraj,Hafiz Tayyab Rauf,Mohammed A.El-Meligy,Mohamed Sharaf,Abd Elatty E.Abd Elgawad Computers,Materials&Continua,2022,Vol.70,No.1,pp.1617–1630.DOI:10.32604/cmc.2022.018621,URL:https://www.techscience.com/cmc/v70n1/44361,there was an error regarding the affiliation for the author Hafiz Tayyab Rauf.Instead of“Centre for Smart Systems,AI and Cybersecurity,Staffordshire University,Stoke-on-Trent,UK”,the affiliation should be“Independent Researcher,Bradford,BD80HS,UK”.展开更多
BACKGROUND Pancreatic cancer remains one of the most lethal malignancies worldwide,with a poor prognosis often attributed to late diagnosis.Understanding the correlation between pathological type and imaging features ...BACKGROUND Pancreatic cancer remains one of the most lethal malignancies worldwide,with a poor prognosis often attributed to late diagnosis.Understanding the correlation between pathological type and imaging features is crucial for early detection and appropriate treatment planning.AIM To retrospectively analyze the relationship between different pathological types of pancreatic cancer and their corresponding imaging features.METHODS We retrospectively analyzed the data of 500 patients diagnosed with pancreatic cancer between January 2010 and December 2020 at our institution.Pathological types were determined by histopathological examination of the surgical spe-cimens or biopsy samples.The imaging features were assessed using computed tomography,magnetic resonance imaging,and endoscopic ultrasound.Statistical analyses were performed to identify significant associations between pathological types and specific imaging characteristics.RESULTS There were 320(64%)cases of pancreatic ductal adenocarcinoma,75(15%)of intraductal papillary mucinous neoplasms,50(10%)of neuroendocrine tumors,and 55(11%)of other rare types.Distinct imaging features were identified in each pathological type.Pancreatic ductal adenocarcinoma typically presents as a hypodense mass with poorly defined borders on computed tomography,whereas intraductal papillary mucinous neoplasms present as characteristic cystic lesions with mural nodules.Neuroendocrine tumors often appear as hypervascular lesions in contrast-enhanced imaging.Statistical analysis revealed significant correlations between specific imaging features and pathological types(P<0.001).CONCLUSION This study demonstrated a strong association between the pathological types of pancreatic cancer and imaging features.These findings can enhance the accuracy of noninvasive diagnosis and guide personalized treatment approaches.展开更多
During Donald Trump’s first term,the“Trump Shock”brought world politics into an era of uncertainties and pulled the transatlantic alliance down to its lowest point in history.The Trump 2.0 tsunami brewed by the 202...During Donald Trump’s first term,the“Trump Shock”brought world politics into an era of uncertainties and pulled the transatlantic alliance down to its lowest point in history.The Trump 2.0 tsunami brewed by the 2024 presidential election of the United States has plunged the U.S.-Europe relations into more gloomy waters,ushering in a more complex and turbulent period of adjustment.展开更多
The fusion of infrared and visible images should emphasize the salient targets in the infrared image while preserving the textural details of the visible images.To meet these requirements,an autoencoder-based method f...The fusion of infrared and visible images should emphasize the salient targets in the infrared image while preserving the textural details of the visible images.To meet these requirements,an autoencoder-based method for infrared and visible image fusion is proposed.The encoder designed according to the optimization objective consists of a base encoder and a detail encoder,which is used to extract low-frequency and high-frequency information from the image.This extraction may lead to some information not being captured,so a compensation encoder is proposed to supplement the missing information.Multi-scale decomposition is also employed to extract image features more comprehensively.The decoder combines low-frequency,high-frequency and supplementary information to obtain multi-scale features.Subsequently,the attention strategy and fusion module are introduced to perform multi-scale fusion for image reconstruction.Experimental results on three datasets show that the fused images generated by this network effectively retain salient targets while being more consistent with human visual perception.展开更多
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
With the rapid development of Internet of things technology,the efficiency of data transmission between devices has been significantly improved.However,the open network environment also poses serious security risks.Th...With the rapid development of Internet of things technology,the efficiency of data transmission between devices has been significantly improved.However,the open network environment also poses serious security risks.This paper proposes an innovative fingerprint template protection scheme,which generates key streams through an improved fourdimensional superchaotic system(4CSCS),uses the space-filling property of Hilbert curves to achieve pixel scrambling,and introduces dynamic DNA encoding to improve encryption.Experimental results show that this scheme has a large key space 2^(528),encrypts image information entropy of more than 7.9970,and shows excellent performance in defending against statistical attacks and differential attacks.Compared with existing methods,this scheme has significant advantages in terms of encryption performance and security,and provides a reliable protection mechanism for fingerprint authentication systems in the Internet of things environment.展开更多
Background:Four-dimensional(4D)ultrasound is increasingly being used for prenatal diagnosis of congenital heart disease(CHD).We aimed to perform a systematic review and meta-analysis to evaluate its diagnostic accurac...Background:Four-dimensional(4D)ultrasound is increasingly being used for prenatal diagnosis of congenital heart disease(CHD).We aimed to perform a systematic review and meta-analysis to evaluate its diagnostic accuracy for fetal CHD.Methods:This systematic review was conducted in accordance with the PRISMA-DTA guidelines.We systematically searched eight databases for studies published up to July 22,2025.Data were extracted to calculate diagnostic accuracy metrics,study quality was assessed using QUADAS-2,and a bivariate random-effects model was used for the meta-analysis.Results:A total of 49 studies were included,comprising 45 retrospective and 4 prospective studies,which were mainly(91.8%)conducted in China.These studies involved 23,397 fetuses,among which 2115 were diagnosed with congenital heart disease.The pooled sensitivity of 4D ultrasound for diagnosing fetal congenital heart disease was 0.91(95%CI:0.89-0.93),the pooled specificity was 0.98(95%CI:0.97-0.99),and the area under the summary receiver operating characteristic(SROC)curve(AUC)was 0.98(95%CI:0.96-0.99).Although 4D ultrasound technology can be implemented as early as 11 weeks of gestation,its diagnostic sensitivity and specificity reached a superior level and stabilized at an average of 20 weeks of gestation(range 14-28 weeks).Meta-regression indicated that sample size and prior suspicion of fetal CHD were significant contributors to heterogeneity(p<0.05).Conclusion:Four-dimensional ultrasound has high diagnostic efficacy for fetal CHD and is suitable for prenatal screening of fetal CHD,and the diagnostic effect is optimal and stable at an average gestational age of 20 weeks(range 14-28 weeks).展开更多
Smart contracts are widely used on the blockchain to implement complex transactions,such as decentralized applications on Ethereum.Effective vulnerability detection of large-scale smart contracts is critical,as attack...Smart contracts are widely used on the blockchain to implement complex transactions,such as decentralized applications on Ethereum.Effective vulnerability detection of large-scale smart contracts is critical,as attacks on smart contracts often cause huge economic losses.Since it is difficult to repair and update smart contracts,it is necessary to find the vulnerabilities before they are deployed.However,code analysis,which requires traversal paths,and learning methods,which require many features to be trained,are too time-consuming to detect large-scale on-chain contracts.Learning-based methods will obtain detection models from a feature space compared to code analysis methods such as symbol execution.But the existing features lack the interpretability of the detection results and training model,even worse,the large-scale feature space also affects the efficiency of detection.This paper focuses on improving the detection efficiency by reducing the dimension of the features,combined with expert knowledge.In this paper,a feature extraction model Block-gram is proposed to form low-dimensional knowledge-based features from bytecode.First,the metadata is separated and the runtime code is converted into a sequence of opcodes,which are divided into segments based on some instructions(jumps,etc.).Then,scalable Block-gram features,including 4-dimensional block features and 8-dimensional attribute features,are mined for the learning-based model training.Finally,feature contributions are calculated from SHAP values to measure the relationship between our features and the results of the detection model.In addition,six types of vulnerability labels are made on a dataset containing 33,885 contracts,and these knowledge-based features are evaluated using seven state-of-the-art learning algorithms,which show that the average detection latency speeds up 25×to 650×,compared with the features extracted by N-gram,and also can enhance the interpretability of the detection model.展开更多
Leesmidt et al present a comprehensive analysis of abdominal vascular flow in children using four-dimensional(4D)flow magnetic resonance imaging(MRI),aim to establish normal hemodynamic values for the abdominal viscer...Leesmidt et al present a comprehensive analysis of abdominal vascular flow in children using four-dimensional(4D)flow magnetic resonance imaging(MRI),aim to establish normal hemodynamic values for the abdominal visceral organs and to assess the feasibility of 4D flow MRI(4D-f-MRI)in this population.The researchers performed 4D-f-MRI on 9 pediatric patients with a history or suspi-cion of bowel pathology.Flow velocities were measured in the abdominal aorta and superior and inferior mesenteric arteries.The quality of the 4D-f-MRI images was evaluated,and the agreement between the measured flow velocities and those obtained from Duplex ultrasound was established.However,due to the specific limitations of this work,future studies should address the issues of small sample size and the specific age group design.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
Due to the limitations of existing imaging hardware, obtaining high-resolution hyperspectral images is challenging. Hyperspectral image super-resolution(HSI SR) has been a very attractive research topic in computer vi...Due to the limitations of existing imaging hardware, obtaining high-resolution hyperspectral images is challenging. Hyperspectral image super-resolution(HSI SR) has been a very attractive research topic in computer vision, attracting the attention of many researchers. However, most HSI SR methods focus on the tradeoff between spatial resolution and spectral information, and cannot guarantee the efficient extraction of image information. In this paper, a multidimensional features network(MFNet) for HSI SR is proposed, which simultaneously learns and fuses the spatial,spectral, and frequency multidimensional features of HSI. Spatial features contain rich local details,spectral features contain the information and correlation between spectral bands, and frequency feature can reflect the global information of the image and can be used to obtain the global context of HSI. The fusion of the three features can better guide image super-resolution, to obtain higher-quality high-resolution hyperspectral images. In MFNet, we use the frequency feature extraction module(FFEM) to extract the frequency feature. On this basis, a multidimensional features extraction module(MFEM) is designed to learn and fuse multidimensional features. In addition, experimental results on two public datasets demonstrate that MFNet achieves state-of-the-art performance.展开更多
Drug resistance remains a major challenge in breast cancer chemotherapy,yet the metabolic alterations underlying this phenomenon are not fully understood.There is much evidence indicating the cellular heterogeneity am...Drug resistance remains a major challenge in breast cancer chemotherapy,yet the metabolic alterations underlying this phenomenon are not fully understood.There is much evidence indicating the cellular heterogeneity among cancer cells,which exhibit varying degrees of metabolic reprogramming and thus may result in differential contributions to drug resistance.A home-built single-cell quantitative mass spectrometry(MS)platform,which integrates micromanipulation and electro-osmotic sampling,was developed to quantitatively profile the tricarboxylic acid(TCA)cycle metabolites at the single-cell level.Using this platform,the metabolic profiles of drug-sensitive MCF-7 breast cancer cells and their drug-resistant derivative MCF-7/ADR cells were compared.This results revealed a selective upregulation of downstream TCA cycle metabolites includingα-ketoglutarate,succinate,fumarate,and malate in drug-resistant cancer cells,while early TCA metabolites remained largely unchanged.Furthermore,notable variations in the abundance of the metabolites were observed in individual cells.The comparative analysis also revealed that not all MCF-7/ADR cells exhibit the same degree of metabolic deviation from the parental line in the metabolites during resistance acquisition.The observed metabolic profiles indicate enhanced glutaminolysis,altered mitochondrial electron transport chain activity,and increased metabolic flexibility in drug-resistant cancer cells that support their survival under chemotherapeutic stress.The findings further suggest the potential for incorporating cellular metabolic heterogeneity into future drug resistance studies.展开更多
Addressing the core weaknesses in the innovation and entrepreneurship capabilities of vocational college graduates,such as market insight and risk tolerance,as well as issues with the existing training model,including...Addressing the core weaknesses in the innovation and entrepreneurship capabilities of vocational college graduates,such as market insight and risk tolerance,as well as issues with the existing training model,including courses that are disconnected from industry,a lack of systematic practical training,and superficial school-enterprise cooperation,this paper constructs a“three-dimensional,four-dimensional”training system.The“three-dimensional”foundational framework encompasses three pillars:curriculum,general education layer,professional integration layer,practical application layer,practice as in three stages:introductory,simulated,and practical,and support including dual mentors,policies,and platforms.The“four-dimensional”differentiated strategies include four implementation pathways:professional differentiation,stage differentiation,addressing capability shortcomings,and school-government-industry collaboration.This system is grounded in theories such as multiple intelligences theory and systems theory,forming a closed-loop process of“theoretical input—practical application—support mechanisms”.Based on the practices of Guangdong Vocational Institute of Public Administration,the paper proposes a competency development pathway tailored by major and stage,which can effectively enhance the innovative and entrepreneurial core competencies of vocational college graduates.This provides a replicable systematic solution for vocational college innovative and entrepreneurial education,supporting vocational education reform and regional economic development.展开更多
Recognizing road scene context from a single image remains a critical challenge for intelligent autonomous driving systems,particularly in dynamic and unstructured environments.While recent advancements in deep learni...Recognizing road scene context from a single image remains a critical challenge for intelligent autonomous driving systems,particularly in dynamic and unstructured environments.While recent advancements in deep learning have significantly enhanced road scene classification,simultaneously achieving high accuracy,computational efficiency,and adaptability across diverse conditions continues to be difficult.To address these challenges,this study proposes HybridLSTM,a novel and efficient framework that integrates deep learning-based,object-based,and handcrafted feature extraction methods within a unified architecture.HybridLSTM is designed to classify four distinct road scene categories—crosswalk(CW),highway(HW),overpass/tunnel(OP/T),and parking(P)—by leveraging multiple publicly available datasets,including Places-365,BDD100K,LabelMe,and KITTI,thereby promoting domain generalization.The framework fuses object-level features extracted using YOLOv5 and VGG19,scene-level global representations obtained from a modified VGG19,and fine-grained texture features captured through eight handcrafted descriptors.This hybrid feature fusion enables the model to capture both semantic context and low-level visual cues,which are critical for robust scene understanding.To model spatial arrangements and latent sequential dependencies present even in static imagery,the combined features are processed through a Long Short-Term Memory(LSTM)network,allowing the extraction of discriminative patterns across heterogeneous feature spaces.Extensive experiments conducted on 2725 annotated road scene images,with an 80:20 training-to-testing split,validate the effectiveness of the proposed model.HybridLSTM achieves a classification accuracy of 96.3%,a precision of 95.8%,a recall of 96.1%,and an F1-score of 96.0%,outperforming several existing state-of-the-art methods.These results demonstrate the robustness,scalability,and generalization capability of HybridLSTM across varying environments and scene complexities.Moreover,the framework is optimized to balance classification performance with computational efficiency,making it highly suitable for real-time deployment in embedded autonomous driving systems.Future work will focus on extending the model to multi-class detection within a single frame and optimizing it further for edge-device deployments to reduce computational overhead in practical applications.展开更多
As coal mining progresses to greater depths,controlling the stability of surrounding rock in deep roadways has become an increasingly complex challenge.Although four-dimensional(4D)support theoretically offers unique ...As coal mining progresses to greater depths,controlling the stability of surrounding rock in deep roadways has become an increasingly complex challenge.Although four-dimensional(4D)support theoretically offers unique advantages in maintaining the stability of rock mass,the disaster evolution processes and multi-source information response characteristics in deep roadways with 4D support remain unclear.Consequently,a large-scale physical model testing system and self-designed 4D support components were employed to conduct similarity model tests on the surrounding rock failure process under unsupported(U-1),traditional bolt-mesh-cable support(T-2),and 4D support(4D-R-3)conditions.Combined with multi-source monitoring techniques,including stress–strain,digital image correlation(DIC),acoustic emission(AE),microseismic(MS),parallel electric(PE),and electromagnetic radiation(EMR),the mechanical behavior and multi-source information responses were comprehensively analyzed.The results show that the peak stress and displacement of the models are positively correlated with the support strength.The multi-source information exhibits distinct response characteristics under different supports.The response frequency,energy,and fluctuationsof AE,MS,and EMR signals,along with the apparent resistivity(AR)high-resistivity zone,follow the trend U-1>T-2>4D-R-3.Furthermore,multi-source information exhibits significantdifferences in sensitivity across different phases.The AE,MS,and EMR signals exhibit active responses to rock mass activity at each phase.However,AR signals are only sensitive to the fracture propagation during the plastic yield and failure phases.In summary,the 4D support significantlyenhances the bearing capacity and plastic deformation of the models,while substantially reducing the frequency,energy,and fluctuationsof multi-source signals.展开更多
Multi-Object Tracking(MOT)represents a fundamental but computationally demanding task in computer vision,with particular challenges arising in occluded and densely populated environments.While contemporary tracking sy...Multi-Object Tracking(MOT)represents a fundamental but computationally demanding task in computer vision,with particular challenges arising in occluded and densely populated environments.While contemporary tracking systems have demonstrated considerable progress,persistent limitations—notably frequent occlusion-induced identity switches and tracking inaccuracies—continue to impede reliable real-world deployment.This work introduces an advanced tracking framework that enhances association robustness through a two-stage matching paradigm combining spatial and appearance features.Proposed framework employs:(1)a Height Modulated and Scale Adaptive Spatial Intersection-over-Union(HMSIoU)metric for improved spatial correspondence estimation across variable object scales and partial occlusions;(2)a feature extraction module generating discriminative appearance descriptors for identity maintenance;and(3)a recovery association mechanism for refining matches between unassociated tracks and detections.Comprehensive evaluation on standard MOT17 and MOT20 benchmarks demonstrates significant improvements in tracking consistency,with state-of-the-art performance across key metrics including HOTA(64),MOTA(80.7),IDF1(79.8),and IDs(1379).These results substantiate the efficacy of our Cue-Tracker framework in complex real-world scenarios characterized by occlusions and crowd interactions.展开更多
Remote sensing cross-modal image-text retrieval(RSCIR)can flexibly and subjectively retrieve remote sensing images utilizing query text,which has received more researchers’attention recently.However,with the increasi...Remote sensing cross-modal image-text retrieval(RSCIR)can flexibly and subjectively retrieve remote sensing images utilizing query text,which has received more researchers’attention recently.However,with the increasing volume of visual-language pre-training model parameters,direct transfer learning consumes a substantial amount of computational and storage resources.Moreover,recently proposed parameter-efficient transfer learning methods mainly focus on the reconstruction of channel features,ignoring the spatial features which are vital for modeling key entity relationships.To address these issues,we design an efficient transfer learning framework for RSCIR,which is based on spatial feature efficient reconstruction(SPER).A concise and efficient spatial adapter is introduced to enhance the extraction of spatial relationships.The spatial adapter is able to spatially reconstruct the features in the backbone with few parameters while incorporating the prior information from the channel dimension.We conduct quantitative and qualitative experiments on two different commonly used RSCIR datasets.Compared with traditional methods,our approach achieves an improvement of 3%-11% in sumR metric.Compared with methods finetuning all parameters,our proposed method only trains less than 1% of the parameters,while maintaining an overall performance of about 96%.展开更多
基金Supported by the National Key R&D Program of China(No.2023YFC2410203)Beijing Hospitals Authority Clinical Medicine Development of Special Funding Support(No.ZLRK202503).
文摘AIM:To investigate the clinical features and prognosis of patients with orbital inflammatory myofibroblastic tumor(IMT).METHODS:This retrospective study collected clinical data from 22 patients diagnosed with orbital IMT based on histopathological examination.The patients were followed up to assess their prognosis.Clinical data from patients,including age,gender,course of disease,past medical history,primary symptoms,ophthalmologic examination findings,general condition,as well as imaging,laboratory,histopathological,and immunohistochemical results from digital records were collected.Orbital magnetic resonance imaging(MRI)and(or)computed tomography(CT)scans were performed to assess bone destruction of the mass,invasion of surrounding tissues,and any inflammatory changes in periorbital areas.RESULTS:The mean age of patients with orbital IMT was 28.24±3.30y,with a male-to-female ratio of 1.2:1.Main clinical manifestations were proptosis,blurred vision,palpable mass,and pain.Bone destruction and surrounding tissue invasion occurred in 72.73%and 54.55%of cases,respectively.Inflammatory changes in the periorbital site were observed in 77.27%of the patients.Hematoxylin and eosin staining showed proliferation of fibroblasts and myofibroblasts,accompanied by infiltration of lymphocytes and plasma cells.Immunohistochemical staining revealed that smooth muscle actin(SMA)and vimentin were positive in 100%of cases,while anaplastic lymphoma kinase(ALK)showed positivity in 47.37%.The recurrence rate of orbital IMT was 27.27%,and sarcomatous degeneration could occur.There were no significant correlations between recurrence and factors such as age,gender,laterality,duration of the disease,periorbital tissue invasion,bone destruction,periorbital inflammation,tumor size,fever,leukocytosis,or treatment(P>0.05).However,lymphadenopathy and a Ki-67 index of 10%or higher may be risk factors for recurrence(P=0.046;P=0.023).CONCLUSION:Orbital IMT is a locally invasive disease that may recur or lead to sarcomatoid degeneration,primarily affecting young and middle-aged patients.The presence of lymphadenopathy and a Ki-67 index of 10%or higher may signify a poor prognosis.
文摘BACKGROUND SMARCB1/INI1-deficient pancreatic undifferentiated rhabdoid carcinoma is a highly aggressive tumor,and spontaneous splenic rupture(SSR)as its presenting manifestation is rarely reported among pancreatic malignancies.CASE SUMMARY We herein report a rare case of a 59-year-old female who presented with acute left upper quadrant abdominal pain without any history of trauma.Abdominal imaging demonstrated a heterogeneous splenic lesion with hemoperitoneum,raising clinical suspicion of SSR.Emergency laparotomy revealed a pancreatic tumor invading the spleen and left kidney,with associated splenic rupture and dense adhesions,necessitating en bloc resection of the distal pancreas,spleen,and left kidney.Histopathology revealed a biphasic malignancy composed of moderately differentiated pancreatic ductal adenocarcinoma and an undifferentiated carcinoma with rhabdoid morphology and loss of SMARCB1 expression.Immunohistochemical analysis confirmed complete loss of SMARCB1/INI1 in the undifferentiated component,along with a high Ki-67 index(approximately 80%)and CD10 positivity.The ductal adenocarcinoma component retained SMARCB1/INI1 expression and was positive for CK7 and CK-pan.Transitional zones between the two tumor components suggested progressive dedifferentiation and underlying genomic instability.The patient received adjuvant chemotherapy with gemcitabine and nab-paclitaxel and maintained a satisfactory quality of life at the 6-month follow-up.CONCLUSION This study reports a rare case of SMARCB1/INI1-deficient undifferentiated rhabdoid carcinoma of the pancreas combined with ductal adenocarcinoma,presenting as SSR-an exceptionally uncommon initial manifestation of pancreatic malignancy.
文摘In the field of intelligent air combat,real-time and accurate recognition of within-visual-range(WVR)maneuver actions serves as the foundational cornerstone for constructing autonomous decision-making systems.However,existing methods face two major challenges:traditional feature engineering suffers from insufficient effective dimensionality in the feature space due to kinematic coupling,making it difficult to distinguish essential differences between maneuvers,while end-to-end deep learning models lack controllability in implicit feature learning and fail to model high-order long-range temporal dependencies.This paper proposes a trajectory feature pre-extraction method based on a Long-range Masked Autoencoder(LMAE),incorporating three key innovations:(1)Random Fragment High-ratio Masking(RFH-Mask),which enforces the model to learn long-range temporal correlations by masking 80%of trajectory data while retaining continuous fragments;(2)Kalman Filter-Guided Objective Function(KFG-OF),integrating trajectory continuity constraints to align the feature space with kinematic principles;and(3)Two-stage Decoupled Architecture,enabling efficient and controllable feature learning through unsupervised pre-training and frozen-feature transfer.Experimental results demonstrate that LMAE significantly improves the average recognition accuracy for 20-class maneuvers compared to traditional end-to-end models,while significantly accelerating convergence speed.The contributions of this work lie in:introducing high-masking-rate autoencoders into low-informationdensity trajectory analysis,proposing a feature engineering framework with enhanced controllability and efficiency,and providing a novel technical pathway for intelligent air combat decision-making systems.
文摘In the article“A Lightweight Approach for Skin Lesion Detection through Optimal Features Fusion”by Khadija Manzoor,Fiaz Majeed,Ansar Siddique,Talha Meraj,Hafiz Tayyab Rauf,Mohammed A.El-Meligy,Mohamed Sharaf,Abd Elatty E.Abd Elgawad Computers,Materials&Continua,2022,Vol.70,No.1,pp.1617–1630.DOI:10.32604/cmc.2022.018621,URL:https://www.techscience.com/cmc/v70n1/44361,there was an error regarding the affiliation for the author Hafiz Tayyab Rauf.Instead of“Centre for Smart Systems,AI and Cybersecurity,Staffordshire University,Stoke-on-Trent,UK”,the affiliation should be“Independent Researcher,Bradford,BD80HS,UK”.
文摘BACKGROUND Pancreatic cancer remains one of the most lethal malignancies worldwide,with a poor prognosis often attributed to late diagnosis.Understanding the correlation between pathological type and imaging features is crucial for early detection and appropriate treatment planning.AIM To retrospectively analyze the relationship between different pathological types of pancreatic cancer and their corresponding imaging features.METHODS We retrospectively analyzed the data of 500 patients diagnosed with pancreatic cancer between January 2010 and December 2020 at our institution.Pathological types were determined by histopathological examination of the surgical spe-cimens or biopsy samples.The imaging features were assessed using computed tomography,magnetic resonance imaging,and endoscopic ultrasound.Statistical analyses were performed to identify significant associations between pathological types and specific imaging characteristics.RESULTS There were 320(64%)cases of pancreatic ductal adenocarcinoma,75(15%)of intraductal papillary mucinous neoplasms,50(10%)of neuroendocrine tumors,and 55(11%)of other rare types.Distinct imaging features were identified in each pathological type.Pancreatic ductal adenocarcinoma typically presents as a hypodense mass with poorly defined borders on computed tomography,whereas intraductal papillary mucinous neoplasms present as characteristic cystic lesions with mural nodules.Neuroendocrine tumors often appear as hypervascular lesions in contrast-enhanced imaging.Statistical analysis revealed significant correlations between specific imaging features and pathological types(P<0.001).CONCLUSION This study demonstrated a strong association between the pathological types of pancreatic cancer and imaging features.These findings can enhance the accuracy of noninvasive diagnosis and guide personalized treatment approaches.
文摘During Donald Trump’s first term,the“Trump Shock”brought world politics into an era of uncertainties and pulled the transatlantic alliance down to its lowest point in history.The Trump 2.0 tsunami brewed by the 2024 presidential election of the United States has plunged the U.S.-Europe relations into more gloomy waters,ushering in a more complex and turbulent period of adjustment.
基金Supported by the Henan Province Key Research and Development Project(231111211300)the Central Government of Henan Province Guides Local Science and Technology Development Funds(Z20231811005)+2 种基金Henan Province Key Research and Development Project(231111110100)Henan Provincial Outstanding Foreign Scientist Studio(GZS2024006)Henan Provincial Joint Fund for Scientific and Technological Research and Development Plan(Application and Overcoming Technical Barriers)(242103810028)。
文摘The fusion of infrared and visible images should emphasize the salient targets in the infrared image while preserving the textural details of the visible images.To meet these requirements,an autoencoder-based method for infrared and visible image fusion is proposed.The encoder designed according to the optimization objective consists of a base encoder and a detail encoder,which is used to extract low-frequency and high-frequency information from the image.This extraction may lead to some information not being captured,so a compensation encoder is proposed to supplement the missing information.Multi-scale decomposition is also employed to extract image features more comprehensively.The decoder combines low-frequency,high-frequency and supplementary information to obtain multi-scale features.Subsequently,the attention strategy and fusion module are introduced to perform multi-scale fusion for image reconstruction.Experimental results on three datasets show that the fused images generated by this network effectively retain salient targets while being more consistent with human visual perception.
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.
文摘With the rapid development of Internet of things technology,the efficiency of data transmission between devices has been significantly improved.However,the open network environment also poses serious security risks.This paper proposes an innovative fingerprint template protection scheme,which generates key streams through an improved fourdimensional superchaotic system(4CSCS),uses the space-filling property of Hilbert curves to achieve pixel scrambling,and introduces dynamic DNA encoding to improve encryption.Experimental results show that this scheme has a large key space 2^(528),encrypts image information entropy of more than 7.9970,and shows excellent performance in defending against statistical attacks and differential attacks.Compared with existing methods,this scheme has significant advantages in terms of encryption performance and security,and provides a reliable protection mechanism for fingerprint authentication systems in the Internet of things environment.
基金supported by the Open Research Fund of National Health Commission Key Laboratory of Birth Defects Prevention&Henan Key Laboratory of Population Defects Prevention(ZD202308).
文摘Background:Four-dimensional(4D)ultrasound is increasingly being used for prenatal diagnosis of congenital heart disease(CHD).We aimed to perform a systematic review and meta-analysis to evaluate its diagnostic accuracy for fetal CHD.Methods:This systematic review was conducted in accordance with the PRISMA-DTA guidelines.We systematically searched eight databases for studies published up to July 22,2025.Data were extracted to calculate diagnostic accuracy metrics,study quality was assessed using QUADAS-2,and a bivariate random-effects model was used for the meta-analysis.Results:A total of 49 studies were included,comprising 45 retrospective and 4 prospective studies,which were mainly(91.8%)conducted in China.These studies involved 23,397 fetuses,among which 2115 were diagnosed with congenital heart disease.The pooled sensitivity of 4D ultrasound for diagnosing fetal congenital heart disease was 0.91(95%CI:0.89-0.93),the pooled specificity was 0.98(95%CI:0.97-0.99),and the area under the summary receiver operating characteristic(SROC)curve(AUC)was 0.98(95%CI:0.96-0.99).Although 4D ultrasound technology can be implemented as early as 11 weeks of gestation,its diagnostic sensitivity and specificity reached a superior level and stabilized at an average of 20 weeks of gestation(range 14-28 weeks).Meta-regression indicated that sample size and prior suspicion of fetal CHD were significant contributors to heterogeneity(p<0.05).Conclusion:Four-dimensional ultrasound has high diagnostic efficacy for fetal CHD and is suitable for prenatal screening of fetal CHD,and the diagnostic effect is optimal and stable at an average gestational age of 20 weeks(range 14-28 weeks).
基金partially supported by the National Natural Science Foundation (62272248)the Open Project Fund of State Key Laboratory of Computer Architecture,Institute of Computing Technology,Chinese Academy of Sciences (CARCHA202108,CARCH201905)+1 种基金the Natural Science Foundation of Tianjin (20JCZDJC00610)Sponsored by Zhejiang Lab (2021KF0AB04)。
文摘Smart contracts are widely used on the blockchain to implement complex transactions,such as decentralized applications on Ethereum.Effective vulnerability detection of large-scale smart contracts is critical,as attacks on smart contracts often cause huge economic losses.Since it is difficult to repair and update smart contracts,it is necessary to find the vulnerabilities before they are deployed.However,code analysis,which requires traversal paths,and learning methods,which require many features to be trained,are too time-consuming to detect large-scale on-chain contracts.Learning-based methods will obtain detection models from a feature space compared to code analysis methods such as symbol execution.But the existing features lack the interpretability of the detection results and training model,even worse,the large-scale feature space also affects the efficiency of detection.This paper focuses on improving the detection efficiency by reducing the dimension of the features,combined with expert knowledge.In this paper,a feature extraction model Block-gram is proposed to form low-dimensional knowledge-based features from bytecode.First,the metadata is separated and the runtime code is converted into a sequence of opcodes,which are divided into segments based on some instructions(jumps,etc.).Then,scalable Block-gram features,including 4-dimensional block features and 8-dimensional attribute features,are mined for the learning-based model training.Finally,feature contributions are calculated from SHAP values to measure the relationship between our features and the results of the detection model.In addition,six types of vulnerability labels are made on a dataset containing 33,885 contracts,and these knowledge-based features are evaluated using seven state-of-the-art learning algorithms,which show that the average detection latency speeds up 25×to 650×,compared with the features extracted by N-gram,and also can enhance the interpretability of the detection model.
文摘Leesmidt et al present a comprehensive analysis of abdominal vascular flow in children using four-dimensional(4D)flow magnetic resonance imaging(MRI),aim to establish normal hemodynamic values for the abdominal visceral organs and to assess the feasibility of 4D flow MRI(4D-f-MRI)in this population.The researchers performed 4D-f-MRI on 9 pediatric patients with a history or suspi-cion of bowel pathology.Flow velocities were measured in the abdominal aorta and superior and inferior mesenteric arteries.The quality of the 4D-f-MRI images was evaluated,and the agreement between the measured flow velocities and those obtained from Duplex ultrasound was established.However,due to the specific limitations of this work,future studies should address the issues of small sample size and the specific age group design.
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supported by the Fundamental Research Funds for the Provincial Universities of Zhejiang (No.GK249909299001-036)National Key Research and Development Program of China (No. 2023YFB4502803)Zhejiang Provincial Natural Science Foundation of China (No.LDT23F01014F01)。
文摘Due to the limitations of existing imaging hardware, obtaining high-resolution hyperspectral images is challenging. Hyperspectral image super-resolution(HSI SR) has been a very attractive research topic in computer vision, attracting the attention of many researchers. However, most HSI SR methods focus on the tradeoff between spatial resolution and spectral information, and cannot guarantee the efficient extraction of image information. In this paper, a multidimensional features network(MFNet) for HSI SR is proposed, which simultaneously learns and fuses the spatial,spectral, and frequency multidimensional features of HSI. Spatial features contain rich local details,spectral features contain the information and correlation between spectral bands, and frequency feature can reflect the global information of the image and can be used to obtain the global context of HSI. The fusion of the three features can better guide image super-resolution, to obtain higher-quality high-resolution hyperspectral images. In MFNet, we use the frequency feature extraction module(FFEM) to extract the frequency feature. On this basis, a multidimensional features extraction module(MFEM) is designed to learn and fuse multidimensional features. In addition, experimental results on two public datasets demonstrate that MFNet achieves state-of-the-art performance.
基金supported by National Natural Science Foundation of China(22374080,22174068,21722504)Primary Research&Development Plan of Jiangsu Province(BK20221303,BE2022796)+1 种基金Open Foundation of State Key Laboratory of Reproductive Medicine(SKLRM-2022BP1,JX116GSP20240507)Science and Technology Development Fund of NJMU(NJMUQY2022003)。
文摘Drug resistance remains a major challenge in breast cancer chemotherapy,yet the metabolic alterations underlying this phenomenon are not fully understood.There is much evidence indicating the cellular heterogeneity among cancer cells,which exhibit varying degrees of metabolic reprogramming and thus may result in differential contributions to drug resistance.A home-built single-cell quantitative mass spectrometry(MS)platform,which integrates micromanipulation and electro-osmotic sampling,was developed to quantitatively profile the tricarboxylic acid(TCA)cycle metabolites at the single-cell level.Using this platform,the metabolic profiles of drug-sensitive MCF-7 breast cancer cells and their drug-resistant derivative MCF-7/ADR cells were compared.This results revealed a selective upregulation of downstream TCA cycle metabolites includingα-ketoglutarate,succinate,fumarate,and malate in drug-resistant cancer cells,while early TCA metabolites remained largely unchanged.Furthermore,notable variations in the abundance of the metabolites were observed in individual cells.The comparative analysis also revealed that not all MCF-7/ADR cells exhibit the same degree of metabolic deviation from the parental line in the metabolites during resistance acquisition.The observed metabolic profiles indicate enhanced glutaminolysis,altered mitochondrial electron transport chain activity,and increased metabolic flexibility in drug-resistant cancer cells that support their survival under chemotherapeutic stress.The findings further suggest the potential for incorporating cellular metabolic heterogeneity into future drug resistance studies.
基金2024 University-level Innovation and Entrepreneurship Educational Reform Project,“Research on the Innovation and Entrepreneurship Education Model of Higher Vocational Colleges Based on the Theory of Technological Innovation Diffusion”(Project No.:CYJG202414)Academic Year Higher Education Institution Graduate Employment and Entrepreneurship Research Project,“Research on Strategies for Cultivating Innovation and Entrepreneurship Abilities Among Graduates of Higher Vocational Colleges”(Project No.:GJXY2024N083)2024 Guangdong Province General Higher Education Institution Specialized Innovation Project,“Research on a Specialized-Entrepreneurial Integration Talent Development System Guided by Core Competencies in the Era of Artificial Intelligence”(Project No.:2024WTSCX339)。
文摘Addressing the core weaknesses in the innovation and entrepreneurship capabilities of vocational college graduates,such as market insight and risk tolerance,as well as issues with the existing training model,including courses that are disconnected from industry,a lack of systematic practical training,and superficial school-enterprise cooperation,this paper constructs a“three-dimensional,four-dimensional”training system.The“three-dimensional”foundational framework encompasses three pillars:curriculum,general education layer,professional integration layer,practical application layer,practice as in three stages:introductory,simulated,and practical,and support including dual mentors,policies,and platforms.The“four-dimensional”differentiated strategies include four implementation pathways:professional differentiation,stage differentiation,addressing capability shortcomings,and school-government-industry collaboration.This system is grounded in theories such as multiple intelligences theory and systems theory,forming a closed-loop process of“theoretical input—practical application—support mechanisms”.Based on the practices of Guangdong Vocational Institute of Public Administration,the paper proposes a competency development pathway tailored by major and stage,which can effectively enhance the innovative and entrepreneurial core competencies of vocational college graduates.This provides a replicable systematic solution for vocational college innovative and entrepreneurial education,supporting vocational education reform and regional economic development.
文摘Recognizing road scene context from a single image remains a critical challenge for intelligent autonomous driving systems,particularly in dynamic and unstructured environments.While recent advancements in deep learning have significantly enhanced road scene classification,simultaneously achieving high accuracy,computational efficiency,and adaptability across diverse conditions continues to be difficult.To address these challenges,this study proposes HybridLSTM,a novel and efficient framework that integrates deep learning-based,object-based,and handcrafted feature extraction methods within a unified architecture.HybridLSTM is designed to classify four distinct road scene categories—crosswalk(CW),highway(HW),overpass/tunnel(OP/T),and parking(P)—by leveraging multiple publicly available datasets,including Places-365,BDD100K,LabelMe,and KITTI,thereby promoting domain generalization.The framework fuses object-level features extracted using YOLOv5 and VGG19,scene-level global representations obtained from a modified VGG19,and fine-grained texture features captured through eight handcrafted descriptors.This hybrid feature fusion enables the model to capture both semantic context and low-level visual cues,which are critical for robust scene understanding.To model spatial arrangements and latent sequential dependencies present even in static imagery,the combined features are processed through a Long Short-Term Memory(LSTM)network,allowing the extraction of discriminative patterns across heterogeneous feature spaces.Extensive experiments conducted on 2725 annotated road scene images,with an 80:20 training-to-testing split,validate the effectiveness of the proposed model.HybridLSTM achieves a classification accuracy of 96.3%,a precision of 95.8%,a recall of 96.1%,and an F1-score of 96.0%,outperforming several existing state-of-the-art methods.These results demonstrate the robustness,scalability,and generalization capability of HybridLSTM across varying environments and scene complexities.Moreover,the framework is optimized to balance classification performance with computational efficiency,making it highly suitable for real-time deployment in embedded autonomous driving systems.Future work will focus on extending the model to multi-class detection within a single frame and optimizing it further for edge-device deployments to reduce computational overhead in practical applications.
基金supported by the National Natural Science Foundation of China(Grant Nos.U22A20598 and 52104107)the"Qinglan Project"of Jiangsu Colleges and Universities,Young Elite Scientists Sponsorship Program of Jiangsu Province(Grant No.TJ-2023-086).
文摘As coal mining progresses to greater depths,controlling the stability of surrounding rock in deep roadways has become an increasingly complex challenge.Although four-dimensional(4D)support theoretically offers unique advantages in maintaining the stability of rock mass,the disaster evolution processes and multi-source information response characteristics in deep roadways with 4D support remain unclear.Consequently,a large-scale physical model testing system and self-designed 4D support components were employed to conduct similarity model tests on the surrounding rock failure process under unsupported(U-1),traditional bolt-mesh-cable support(T-2),and 4D support(4D-R-3)conditions.Combined with multi-source monitoring techniques,including stress–strain,digital image correlation(DIC),acoustic emission(AE),microseismic(MS),parallel electric(PE),and electromagnetic radiation(EMR),the mechanical behavior and multi-source information responses were comprehensively analyzed.The results show that the peak stress and displacement of the models are positively correlated with the support strength.The multi-source information exhibits distinct response characteristics under different supports.The response frequency,energy,and fluctuationsof AE,MS,and EMR signals,along with the apparent resistivity(AR)high-resistivity zone,follow the trend U-1>T-2>4D-R-3.Furthermore,multi-source information exhibits significantdifferences in sensitivity across different phases.The AE,MS,and EMR signals exhibit active responses to rock mass activity at each phase.However,AR signals are only sensitive to the fracture propagation during the plastic yield and failure phases.In summary,the 4D support significantlyenhances the bearing capacity and plastic deformation of the models,while substantially reducing the frequency,energy,and fluctuationsof multi-source signals.
文摘Multi-Object Tracking(MOT)represents a fundamental but computationally demanding task in computer vision,with particular challenges arising in occluded and densely populated environments.While contemporary tracking systems have demonstrated considerable progress,persistent limitations—notably frequent occlusion-induced identity switches and tracking inaccuracies—continue to impede reliable real-world deployment.This work introduces an advanced tracking framework that enhances association robustness through a two-stage matching paradigm combining spatial and appearance features.Proposed framework employs:(1)a Height Modulated and Scale Adaptive Spatial Intersection-over-Union(HMSIoU)metric for improved spatial correspondence estimation across variable object scales and partial occlusions;(2)a feature extraction module generating discriminative appearance descriptors for identity maintenance;and(3)a recovery association mechanism for refining matches between unassociated tracks and detections.Comprehensive evaluation on standard MOT17 and MOT20 benchmarks demonstrates significant improvements in tracking consistency,with state-of-the-art performance across key metrics including HOTA(64),MOTA(80.7),IDF1(79.8),and IDs(1379).These results substantiate the efficacy of our Cue-Tracker framework in complex real-world scenarios characterized by occlusions and crowd interactions.
基金supported by the National Key R&D Program of China(No.2022ZD0118402)。
文摘Remote sensing cross-modal image-text retrieval(RSCIR)can flexibly and subjectively retrieve remote sensing images utilizing query text,which has received more researchers’attention recently.However,with the increasing volume of visual-language pre-training model parameters,direct transfer learning consumes a substantial amount of computational and storage resources.Moreover,recently proposed parameter-efficient transfer learning methods mainly focus on the reconstruction of channel features,ignoring the spatial features which are vital for modeling key entity relationships.To address these issues,we design an efficient transfer learning framework for RSCIR,which is based on spatial feature efficient reconstruction(SPER).A concise and efficient spatial adapter is introduced to enhance the extraction of spatial relationships.The spatial adapter is able to spatially reconstruct the features in the backbone with few parameters while incorporating the prior information from the channel dimension.We conduct quantitative and qualitative experiments on two different commonly used RSCIR datasets.Compared with traditional methods,our approach achieves an improvement of 3%-11% in sumR metric.Compared with methods finetuning all parameters,our proposed method only trains less than 1% of the parameters,while maintaining an overall performance of about 96%.
