Personalized social matching systems can be seen as recommender systems that recommend people to others in the social networks, with desirable skills/characteristics. In this work, an algorithm based on Ant Colony is ...Personalized social matching systems can be seen as recommender systems that recommend people to others in the social networks, with desirable skills/characteristics. In this work, an algorithm based on Ant Colony is proposed to solve the optimization problem of clustering/matching people in a social network specifically designed for this purpose;during this process, their personal characteristics and preferences (and the degree of importance thereof) are taken into account. The numerical results indicate that the proposed algorithm can successfully perform clustering with a variable number of individuals.展开更多
The energy-saving electrohydraulic flow matching （EFM） system opens up an opportunity to minimize valve losses by fully opening the control valves, but the controllability is lost under overrunning load conditions. ...The energy-saving electrohydraulic flow matching （EFM） system opens up an opportunity to minimize valve losses by fully opening the control valves, but the controllability is lost under overrunning load conditions. To address this issue, this paper proposes a valve-based compensator to improve the controllability of the energy-saving EFM system. The valve-based compensator consists of a static compensator and a differential dynamic compensator based on load conditions. The energy effi- ciency, the stability performance, and the damping characteristic are analyzed under different control parameters. A parameter selection method is used to improve the efficiency, ensure the stability performance, and obtain good dynamic behavior. A test rig with a 2-t hydraulic excavator is built, and experimental tests are carried out to validate the proposed valve-based compensator. The experimental results indicate that the controllability of the EFM system is improved, and the characteristic of high energy efficiency is obtained by the proposed compensator.展开更多
For the past three decades, interoperability among heterogeneous systems had been a hard nut to crack due to the schematic and semantic perspectives that exist between objects. These systems were built under different...For the past three decades, interoperability among heterogeneous systems had been a hard nut to crack due to the schematic and semantic perspectives that exist between objects. These systems were built under different data models. As such, levels of the local schemas are semantically very poor due to the limited expressiveness of traditional data models in which they were designed. Further more, most of the existing schema integration architectural components are inadequately equipped to handle the mapping schemas, especially when the semantics and structural conflicts are involved. This paper introduces an Intelligent Binary Schema Matching system (IBSMS), which exploits the phenomenon of making its components intelligent. That’s equipping its components such as translators and integrators with adequate knowledge about various data models. This allows the components acquire enough intelligence to maneuver or manipulate the correspondence between constructs from different models. In addition, the system has a Binary Matcher, which compares the attribute correspondences of various databases in a pairwise form, in order to establish the equivalences. With the establishment of the mappings, the users shall be able to access them (mappings) for their desired usage.展开更多
Ground source heat pump systems demonstrate significant potential for northern rural heating applications;however,the effectiveness of these systems is often limited by challenging geological conditions.For instance,i...Ground source heat pump systems demonstrate significant potential for northern rural heating applications;however,the effectiveness of these systems is often limited by challenging geological conditions.For instance,in certain regions,the installation of buried pipes for heat exchangers may be complicated,and these pipes may not always serve as efficient low-temperature heat sources for the heat pumps of the system.To address this issue,the current study explored the use of solar-energy-collecting equipment to supplement buried pipes.In this design,both solar energy and geothermal energy provide low-temperature heat to the heat pump.First,a simulation model of a solar‒ground source heat pump coupling system was established using TRNSYS.The accuracy of this model was validated through experiments and simulations on various system configurations,including varying numbers of buried pipes,different areas of solar collectors,and varying volumes of water tanks.The simulations examined the coupling characteristics of these components and their influence on system performance.The results revealed that the operating parameters of the system remained consistent across the following configurations:three buried pipes,burial depth of 20 m,collector area of 6 m^(2),and water tank volume of 0.5 m^(3);four buried pipes,burial depth of 20 m,collector area of 3 m^(2),and water tank volume of 0.5 m^(3);and five buried pipes with a burial depth of 20 m.Furthermore,the heat collection capacity of the solar collectors spanning an area of 3 m^(2)was found to be equivalent to that of one buried pipe.Moreover,the findings revealed that the solar‒ground source heat pump coupling system demonstrated a lower annual cumulative energy consumption compared to the ground source heat pump system,presenting a reduction of 5.31%compared to the energy consumption of the latter.展开更多
The increased demand for personalized customization calls for new production modes to enhance collaborations among a wide range of manufacturing practitioners who unnecessarily trust each other.In this article,a block...The increased demand for personalized customization calls for new production modes to enhance collaborations among a wide range of manufacturing practitioners who unnecessarily trust each other.In this article,a blockchain-enabled manufacturing collaboration framework is proposed,with a focus on the production capacity matching problem for blockchainbased peer-to-peer(P2P)collaboration.First,a digital model of production capacity description is built for trustworthy and transparent sharing over the blockchain.Second,an optimization problem is formulated for P2P production capacity matching with objectives to maximize both social welfare and individual benefits of all participants.Third,a feasible solution based on an iterative double auction mechanism is designed to determine the optimal price and quantity for production capacity matching with a lack of personal information.It facilitates automation of the matching process while protecting users'privacy via blockchainbased smart contracts.Finally,simulation results from the Hyperledger Fabric-based prototype show that the proposed approach increases social welfare by 1.4%compared to the Bayesian game-based approach,makes all participants profitable,and achieves 90%fairness of enterprises.展开更多
The concept of matching energy was proposed by Gutman and Wagner firstly in 2012. Let G be a simple graph of order n and λ1, λ2, . . . , λn be the zeros of its matching polynomial. The matching energy of a graph G ...The concept of matching energy was proposed by Gutman and Wagner firstly in 2012. Let G be a simple graph of order n and λ1, λ2, . . . , λn be the zeros of its matching polynomial. The matching energy of a graph G is defined as ME(G) = Pni=1 |λi|. By the famous Coulson’s formula, matching energies can also be calculated by an improper integral depending on a parameter. A k-claw attaching graph Gu(k) refers to the graph obtained by attaching k pendent edges to the graph G at the vertex u, where u is called the root of Gu(k). In this paper, we use some theories of mathematical analysis to obtain a new technique to compare the matching energies of two k-claw attaching graphs Gu(k) and Hv(k) with the same order, that is, limk→∞[ME(Gu(k)) − ME(Hv(k))] = ME(G − u) − ME(H − v). By the technique, we finally determine unicyclic graphs of order n with the 9th to 13th minimal matching energies for all n ≥ 58.展开更多
Most existing multi-pattern matching algorithms are designed for single English texts leading to issues such as missed matches and space expansion when applied to Chinese-English mixed-text environments.The Hash Trie-...Most existing multi-pattern matching algorithms are designed for single English texts leading to issues such as missed matches and space expansion when applied to Chinese-English mixed-text environments.The Hash Trie-based matching machine demonstrates strong compatibility with both Chinese and English,ensuring high accuracy in text processing and subtree positioning.In this study,a novel functional framework based on the HashTrie structure is proposed and mechanically verified using Isabelle/HOL.This framework is applied to design Functional Multi-Pattern Matching(FMPM),the first functional multi-pattern matching algorithm for Chinese-English mixed texts.FMPM constructs the HashTrie matching machine using character codes and threads the machine according to the associations between pattern strings.The experimental results show that as the stored string information increases,the proposed algorithm demonstrates more significant optimization in retrieval efficiency.FMPM simplifies the implementation of the Threaded Hash Trie(THT)for Chinese-English mixed texts,effectively reducing the uncertainties in the transition from the algorithm description to code implementation.FMPM addresses the problem of space explosion Chinese-English mixed texts and avoids issues such as bound variable iteration errors.The functional framework of the HashTrie structure serves as a reference for the formal verification of future HashTrie-based algorithms.展开更多
This study investigates how artificial intelligence(AI)algorithms enable mainstream media to achieve precise emotional matching and improve communication efficiency through reconstructed communication logic.As digital...This study investigates how artificial intelligence(AI)algorithms enable mainstream media to achieve precise emotional matching and improve communication efficiency through reconstructed communication logic.As digital intelligence technology rapidly evolves,mainstream media organizations are increasingly leveraging AI-driven empathy algorithms to enhance audience engagement and optimize content delivery.This research employs a mixed-methods approach,combining quantitative analysis of algorithmic performance metrics with qualitative examination of media communication patterns.Through systematic review of 150 academic papers and analysis of data from 12 major media platforms,this study reveals that algorithmic empathy systems can improve emotional resonance by 34.7%and increase audience engagement by 28.3%compared to traditional communication methods.The findings demonstrate that AI algorithms reconstruct media communication logic through three primary pathways:emotional pattern recognition,personalized content curation,and real-time sentiment adaptation.However,the study also identifies significant challenges including algorithmic bias,emotional authenticity concerns,and ethical implications of automated empathy.The research contributes to understanding how mainstream media can leverage AI technology to build high-quality empathetic communication while maintaining journalistic integrity and social responsibility.展开更多
The effects of micro-ridge-furrow planting(MR)on yield and the efficiency of light,water,and thermal resource use in rapeseed were tested in a three-year field experiment comparing MR to conventional flat planting.MR ...The effects of micro-ridge-furrow planting(MR)on yield and the efficiency of light,water,and thermal resource use in rapeseed were tested in a three-year field experiment comparing MR to conventional flat planting.MR enhanced canopy heterogeneity by altering the leaf angle between plants on ridges and furrows.The heterogeneous canopy environment increased intercepted photosynthetic active radiation,alleviated canopy temperature stress,and optimized canopy humidity,leading to improvements in light-nitrogen matching and net photosynthetic rate.Consequently,dry matter and yield increased by 13.0%and 11.0%,respectively,while radiation,thermal,and precipitation utilization efficiency increased by 12.3%-16.2%.The corresponding improvements in yield and resource use efficiency were attributed to a heterogeneous canopy environment that improved microclimatic conditions.展开更多
The cross-modal person re-identification task aims to match visible and infrared images of the same individual.The main challenges in this field arise from significant modality differences between individuals and the ...The cross-modal person re-identification task aims to match visible and infrared images of the same individual.The main challenges in this field arise from significant modality differences between individuals and the lack of high-quality cross-modal correspondence methods.Existing approaches often attempt to establish modality correspondence by extracting shared features across different modalities.However,these methods tend to focus on local information extraction and fail to fully leverage the global identity information in the cross-modal features,resulting in limited correspondence accuracy and suboptimal matching performance.To address this issue,we propose a quadratic graph matching method designed to overcome the challenges posed by modality differences through precise cross-modal relationship alignment.This method transforms the cross-modal correspondence problem into a graph matching task and minimizes the matching cost using a center search mechanism.Building on this approach,we further design a block reasoning module to uncover latent relationships between person identities and optimize the modality correspondence results.The block strategy not only improves the efficiency of updating gallery images but also enhances matching accuracy while reducing computational load.Experimental results demonstrate that our proposed method outperforms the state-of-the-art methods on the SYSU-MM01,RegDB,and RGBNT201 datasets,achieving excellent matching accuracy and robustness,thereby validating its effectiveness in cross-modal person re-identification.展开更多
BACKGROUND Recently,Olympus Corporation released new scopes(XZ1200/EZ1500).However,there have been few reports on this topic,although improvement in adenoma detection rate(ADR)by texture and color enhancement imaging(...BACKGROUND Recently,Olympus Corporation released new scopes(XZ1200/EZ1500).However,there have been few reports on this topic,although improvement in adenoma detection rate(ADR)by texture and color enhancement imaging(TXI)or computer-aided detection system(CAD)has been reported.AIM To investigate the effects of the scope on the detection of adenomas and sessile serrated lesions(SSLs).METHODS The subjects were patients who underwent pancolonic chromoendoscopy using the EVIS X1 video system center between May 2023 and October 2024.The patients were divided into the new(CF-XZ1200/CF-EZ1500)and 290 series(CF-HQ290Z/PCF-H290Z)groups.Propensity score matching was performed for age,sex,examination purpose,endoscopist,preparation,TXI use,and CAD use.The effects of the scope were analyzed in terms of the ADR,SSL detection rate(SDR),and mean number of adenomas per colonoscopy(APC).RESULTS Of the 7014 patients enrolled,2138 pairs were extracted by propensity score matching(mean age 55.4 years,45.5%male).The new scopes group had a significantly higher ADR than the 290 series group[51.5%vs 45.5%,odds ratio(OR)=1.27,95%CI:1.13-1.43,P<0.001].Similarly,the new scopes group had significantly higher SDR(7.8%vs 5.7%,OR=1.41,95%CI:1.11-1.80,P=0.005)and APC(0.90 vs 0.76,OR=1.11,95%CI:1.05-1.17,P<0.001)than the 290 series group.CONCLUSION In conclusion,the new scope(CF-XZ1200/CF-EZ1500)enhanced the detection of adenomas and SSLs compared to the old ones(290 series).展开更多
BACKGROUND Endoscopic full-thickness resection(EFTR)is increasingly used for treating gastrointestinal stromal tumors(GISTs)in the stomach.AIM To compare the efficacy,tolerability,and clinical outcomes of EFTR vs surg...BACKGROUND Endoscopic full-thickness resection(EFTR)is increasingly used for treating gastrointestinal stromal tumors(GISTs)in the stomach.AIM To compare the efficacy,tolerability,and clinical outcomes of EFTR vs surgical resection(SR)for gastric GISTs.METHODS We collected clinical data from patients diagnosed with GISTs who underwent either EFTR or SR at our hospital from October 2011 to July 2024.Patients were matched in a 1:1 ratio based on baseline characteristics and tumor clinical-pathological features using propensity score matching.We analyzed perioperative outcomes and follow-up data.The primary outcome measure was progressionfree survival(PFS).RESULTS Out of 912 patients,573 met the inclusion criteria.After matching,each group included 95 patients.The EFTR group demonstrated statistically significant advantages over the SR group in average operative time(P<0.001),length of hospital stay(P<0.001),time to resume liquid diet(P<0.001),incidence of adverse events(P=0.031),and hospitalization costs(P<0.001).The en bloc resection rate was significantly different,with SR group at 100%and EFTR group at 93.7%(P=0.038).The median follow-up was 2451.50 days.Recurrence occurred in 3 patients in the EFTR group and 4 patients in the SR group,with no statistically significant difference(P=1.000).Factors associated with PFS included age,tumor size,high-risk category in the modified National Institutes of Health(NIH)risk score,and resection status.Resection status was identified as an independent prognostic factor for PFS(P=0.0173,hazard ratios=0.0179,95%CI:0.000655-0.491).Notably,there was no statistically significant difference in PFS between the two groups.CONCLUSION This study is a non-inferiority design.The EFTR group significantly outperformed the SR group in terms of operative time,length of hospital stay,time to resume a liquid diet,incidence of adverse events,and hospitalization costs,demonstrating its higher economic efficiency and better tolerability.Additionally,although the en bloc resection rate was lower in the EFTR group compared to the SR group,there were no significant differences in tumor recurrence rates and progression-free survival between the two groups.This study found no statistical difference in the primary endpoint of postoperative recurrence rates between the two groups.However,due to sample size limitations,this result requires further validation in larger-scale studies.The current results should be viewed as exploratory evidence.展开更多
This paper discusses the design of event-triggered output-feedback controller for a class of nonlinear time-delay systems with multiple uncertainties. In sharp contrast to previous works, the considered systems posses...This paper discusses the design of event-triggered output-feedback controller for a class of nonlinear time-delay systems with multiple uncertainties. In sharp contrast to previous works, the considered systems possess two important characteristics: (i) The uncertain nonlinear terms meet the linearly unmeasurable-states dependent growth with the growth rate being an unknown function of the input and output. (ii) There exist input matching uncertainty and unknown measurement sensitivity. By introducing a single dynamic gain and employing a cleverly devised event-triggering mechanism (ETM), we design a new gain-based event-triggered output-feedback controller, which globally regulates all states of the considered systems and maintains global boundedness of the closed-loop system. Furthermore, the estimation of input matching uncertainty achieves convergence towards its actual value, and Zeno behavior does not happen. Two simulation examples including a practical one show that the proposed approach is effective.展开更多
The impact of location services on people’s lives has grown significantly in the era of widespread smart device usage.Due to global navigation satellite system(GNSS)signal rejection,weak signal strength in indoor env...The impact of location services on people’s lives has grown significantly in the era of widespread smart device usage.Due to global navigation satellite system(GNSS)signal rejection,weak signal strength in indoor environments and radio signal interference caused by multiwall environments,which collectively lead to significant positioning errors,vision-based positioning has emerged as a crucial method in indoor positioning research.This paper introduces a scale hierarchical matching model to tackle challenges associated with large visual databases and high scene similarity,both of which will compromise matching accuracy and lead to prolonged positioning delays.The proposed model establishes an image feature database using GIST features and speeded up robust feature(SURF)in the offline stage.In the online stage,a positioning navigating algorithm is constructed based on Dijkstra’s path planning.Additionally,a corresponding Android application has been developed to facilitate visual positioning and navigation in indoor environments.Experimental results obtained in real indoor environments demonstrate that the proposed method significantly enhances positioning accuracy compared with similar algorithms,while effectively reducing time overhead.This improvement caters to the requirements for indoor positioning and navigation,thereby meeting user needs.展开更多
Objectives This study aimed to analyze the prevalence of long-term central line-associated bloodstream infections(CLABSI)among hospitalized adults with cancer in Italy and compare the characteristics of patients who r...Objectives This study aimed to analyze the prevalence of long-term central line-associated bloodstream infections(CLABSI)among hospitalized adults with cancer in Italy and compare the characteristics of patients who required long-term central venous access device(LCVAD)substitution due to prior CLABSI with those who had never experienced CLABSI.Methods The study was conducted in hospitals across northern and central Italy using a multicenter,observational,cross-sectional design from March to September 2021.A total of 174 adults with cancer were included.Data were collected through electronic case report forms,including demographic,clinical,treatment-related,and catheter-related variables.Propensity score matching(PSM)was used to compare the characteristics of patients who underwent LCVAD substitution due to previous CLABSI with those who never experienced CLABSI.Multiple correspondence analysis(MCA)was conducted to explore the patterns within matched subgroups.Results The prevalence of CLABSI was 3%,and 5.2%of patients required LCVAD substitution due to prior CLABSI.After applying PSM,the groups were successfully balanced for sex,age,presence of metastases,comorbidities,BMI,received treatments,corticosteroid therapy,ongoing antibiotics,hormone therapy,type of LCVAD,lumens,and utilization frequency.Hematologic cancer was more frequent in the CLABSI group(44.4%)compared to the non-infective group(0),with a statistically significant difference(P=0.045).MCA revealed potential patterns among matched subgroups but did not identify statistically significant associations:patients with previous LCVAD substitution were more frequently associated with a history of prior infections,ongoing antibiotic therapy,and unspecified primary lesion locations;conversely,patients who never experienced CLABSI tended to cluster around characteristics such as hormone therapy and corticosteroid therapy.Conclusions These findings emphasize the importance of continuous monitoring,individualized infection prevention strategies in oncology nursing practice.Future research with larger datasets is needed to validate these findings and develop tailored interventions to reduce CLABSI risks.展开更多
BACKGROUND Patients with inflammatory bowel disease(IBD)are at an increased risk of bacterial pneumonia,contributing to significant morbidity and mortality.While previous studies have identified various risk factors,i...BACKGROUND Patients with inflammatory bowel disease(IBD)are at an increased risk of bacterial pneumonia,contributing to significant morbidity and mortality.While previous studies have identified various risk factors,including medications and comorbidities,the independent contribution of IBD to pneumonia risk remains unclear.We hypothesized that the increased pneumonia risk is primarily driven by factors other than IBD itself.AIM To investigate the relative contributions of IBD,comorbidities,and medications to pneumonia risk in patients with IBD.METHODS We conducted a retrospective cohort study using the All of Us Research Program database(2010-2022).We matched 2810 participants with IBD 1:1 with controls using four propensity score models:(1)Demographics/Lifestyle only;(2)Plus comorbidities;(3)Plus medications;and(4)All factors combined.Then we used Cox proportional hazards models to assess pneumonia risk and logistic regression to evaluate risk factors.RESULTS In the primary analysis of 5620 matched participants,IBD was not independently associated with increased pneumonia risk[hazard ratio(HR)=1.07,95%CI:0.84-1.35]when matched for all factors.However,participants with IBD had significantly higher risk(HR=2.08,95%CI:1.56-2.78)when matched only for demographics and lifestyle factors.Within the IBD cohort,a high comorbidity burden(Charlson Comorbidity Index≥10)[odds ratio(OR)=12.20,95%CI:6.69-23.00]and systemic steroid use(OR=2.26,95%CI:1.21-4.64)were independently associated with increased pneumonia risk.CONCLUSION Comorbidities and systemic steroids,rather than IBD itself,drive pneumonia risk.Management should focus on these factors and prioritize vaccination in high-risk patients.展开更多
To enhance network security,this study employs a deep graph matching model for vulnerability similarity detection.The model utilizes a Word Embedding layer to vectorize data words,an Image Embedding layer to vectorize...To enhance network security,this study employs a deep graph matching model for vulnerability similarity detection.The model utilizes a Word Embedding layer to vectorize data words,an Image Embedding layer to vectorize data graphs,and an LSTM layer to extract the associations between word and graph vectors.A Dropout layer is applied to randomly deactivate neurons in the LSTM layer,while a Softmax layer maps the LSTM analysis results.Finally,a fully connected layer outputs the detection results with a dimension of 1.Experimental results demonstrate that the AUC of the deep graph matching vulnerability similarity detection model is 0.9721,indicating good stability.The similarity scores for vulnerabilities such as memory leaks,buffer overflows,and targeted attacks are close to 1,showing significant similarity.In contrast,the similarity scores for vulnerabilities like out-of-bounds memory access and logical design flaws are less than 0.4,indicating good similarity detection performance.The model’s evaluation metrics are all above 97%,with high detection accuracy,which is beneficial for improving network security.展开更多
After the design of aerospace products is completed,a manufacturability assessment needs to be conducted based on 3D model's features in terms of modeling quality and process design,otherwise the cost of design ch...After the design of aerospace products is completed,a manufacturability assessment needs to be conducted based on 3D model's features in terms of modeling quality and process design,otherwise the cost of design changes will increase.Due to the poor structure and low reusability of product manufacturing feature information and assessment knowledge in the current aerospace product manufacturability assessment process,it is difficult to realize automated manufacturability assessment.To address these issues,a domain ontology model is established for aerospace product manufacturability assessment in this paper.On this basis,a structured representation method of manufacturability assessment knowledge and a knowledge graph data layer construction method are proposed.Based on the semantic information and association information expressed by the knowledge graph,a rule matching method based on subgraph matching is proposed to improve the precision and recall.Finally,applications and experiments based on the software platform verify the effectiveness of the proposed knowledge graph construction and rule matching method.展开更多
Under the“dual carbon”goal,local governments in China have strategically focused on enhancing capital utilization efficiency and enforcing environmental regulations to improve carbon emission performance.This dual a...Under the“dual carbon”goal,local governments in China have strategically focused on enhancing capital utilization efficiency and enforcing environmental regulations to improve carbon emission performance.This dual approach targets the intertwined challenges of economic development and environmental protection.Utilizing data from 266 prefecture-level cities in China from 2007 to 2019,this study systematically investigates the effects of capital matching and environmental regulation on carbon emission performance through the spatial Durbin model and the instrumental variable method.The results indicate that both capital matching and environmental regulation significantly enhance carbon emission performance.Capital matching demonstrates positive spatial spillover effects,whereas environmental regulation exhibits negative spatial spillover effects.Furthermore,there are synergistic effects between capital matching and environmental regulation that jointly enhance carbon emission performance.To address potential biases caused by endogenous environmental regulation,the study uses the proportion of environment-related words in provincial government work reports as an instrumental variable for environmental regulation.Additionally,to capture the heterogeneity in the environmental governance willingness and intensity of prefecture-level municipal governments,the study constructs heterogeneous instrumental variables.These variables are derived by multiplying the proportion of a prefecture-level city’s total industrial output value to the province’s total industrial output value with the proportion of environment-related words in the provincial government work reports.Analyses based on these instrumental variables reveal that endogenous issues in environmental regulation lead to an overestimation of its positive impact on carbon emission performance.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
文摘Personalized social matching systems can be seen as recommender systems that recommend people to others in the social networks, with desirable skills/characteristics. In this work, an algorithm based on Ant Colony is proposed to solve the optimization problem of clustering/matching people in a social network specifically designed for this purpose;during this process, their personal characteristics and preferences (and the degree of importance thereof) are taken into account. The numerical results indicate that the proposed algorithm can successfully perform clustering with a variable number of individuals.
基金Project supported by the National Natural Science Foundation of China （No. 51375431）, the Open Fund of the State Key Laboratory of Fluid Power and Mechatronic Systems （No. GZKF-201503）, and the Research Fund of the State Key Laboratory of Mechanical Transmission （No. SKLMT-ZZKT-2015Z10）, China
文摘The energy-saving electrohydraulic flow matching （EFM） system opens up an opportunity to minimize valve losses by fully opening the control valves, but the controllability is lost under overrunning load conditions. To address this issue, this paper proposes a valve-based compensator to improve the controllability of the energy-saving EFM system. The valve-based compensator consists of a static compensator and a differential dynamic compensator based on load conditions. The energy effi- ciency, the stability performance, and the damping characteristic are analyzed under different control parameters. A parameter selection method is used to improve the efficiency, ensure the stability performance, and obtain good dynamic behavior. A test rig with a 2-t hydraulic excavator is built, and experimental tests are carried out to validate the proposed valve-based compensator. The experimental results indicate that the controllability of the EFM system is improved, and the characteristic of high energy efficiency is obtained by the proposed compensator.
文摘For the past three decades, interoperability among heterogeneous systems had been a hard nut to crack due to the schematic and semantic perspectives that exist between objects. These systems were built under different data models. As such, levels of the local schemas are semantically very poor due to the limited expressiveness of traditional data models in which they were designed. Further more, most of the existing schema integration architectural components are inadequately equipped to handle the mapping schemas, especially when the semantics and structural conflicts are involved. This paper introduces an Intelligent Binary Schema Matching system (IBSMS), which exploits the phenomenon of making its components intelligent. That’s equipping its components such as translators and integrators with adequate knowledge about various data models. This allows the components acquire enough intelligence to maneuver or manipulate the correspondence between constructs from different models. In addition, the system has a Binary Matcher, which compares the attribute correspondences of various databases in a pairwise form, in order to establish the equivalences. With the establishment of the mappings, the users shall be able to access them (mappings) for their desired usage.
基金supported by 2024 Central Guidance Local Science and Technology Development Fund Project"Study on the mechanism and evaluation method of thermal pollution in water bodies,as well as research on thermal carrying capacity".(Grant 246Z4506G)Key Research and Development Project in Hebei Province:"Key Technologies and Equipment Research and Demonstration of Multiple Energy Complementary(Electricity,Heat,Cold System)for Solar Energy,Geothermal Energy,Phase Change Energy"(Grant 236Z4310G)the Hebei Academy of Sciences Key Research and Development Program"Research on Heat Transfer Mechanisms and Efficient Applications of Intermediate and Deep Geothermal Energy"(22702)。
文摘Ground source heat pump systems demonstrate significant potential for northern rural heating applications;however,the effectiveness of these systems is often limited by challenging geological conditions.For instance,in certain regions,the installation of buried pipes for heat exchangers may be complicated,and these pipes may not always serve as efficient low-temperature heat sources for the heat pumps of the system.To address this issue,the current study explored the use of solar-energy-collecting equipment to supplement buried pipes.In this design,both solar energy and geothermal energy provide low-temperature heat to the heat pump.First,a simulation model of a solar‒ground source heat pump coupling system was established using TRNSYS.The accuracy of this model was validated through experiments and simulations on various system configurations,including varying numbers of buried pipes,different areas of solar collectors,and varying volumes of water tanks.The simulations examined the coupling characteristics of these components and their influence on system performance.The results revealed that the operating parameters of the system remained consistent across the following configurations:three buried pipes,burial depth of 20 m,collector area of 6 m^(2),and water tank volume of 0.5 m^(3);four buried pipes,burial depth of 20 m,collector area of 3 m^(2),and water tank volume of 0.5 m^(3);and five buried pipes with a burial depth of 20 m.Furthermore,the heat collection capacity of the solar collectors spanning an area of 3 m^(2)was found to be equivalent to that of one buried pipe.Moreover,the findings revealed that the solar‒ground source heat pump coupling system demonstrated a lower annual cumulative energy consumption compared to the ground source heat pump system,presenting a reduction of 5.31%compared to the energy consumption of the latter.
基金supported in part by the National Natural Science Foundation of China(62273310)the Natural Science Foundation of Zhejiang Province of China(LY22F030006,LZ24F030009)
文摘The increased demand for personalized customization calls for new production modes to enhance collaborations among a wide range of manufacturing practitioners who unnecessarily trust each other.In this article,a blockchain-enabled manufacturing collaboration framework is proposed,with a focus on the production capacity matching problem for blockchainbased peer-to-peer(P2P)collaboration.First,a digital model of production capacity description is built for trustworthy and transparent sharing over the blockchain.Second,an optimization problem is formulated for P2P production capacity matching with objectives to maximize both social welfare and individual benefits of all participants.Third,a feasible solution based on an iterative double auction mechanism is designed to determine the optimal price and quantity for production capacity matching with a lack of personal information.It facilitates automation of the matching process while protecting users'privacy via blockchainbased smart contracts.Finally,simulation results from the Hyperledger Fabric-based prototype show that the proposed approach increases social welfare by 1.4%compared to the Bayesian game-based approach,makes all participants profitable,and achieves 90%fairness of enterprises.
基金Supported by the National Natural Science Foundation of China(Nos.12271439,11871398)the National College Students Innovation and Entrepreneurship Training Program(No.201910699173)。
文摘The concept of matching energy was proposed by Gutman and Wagner firstly in 2012. Let G be a simple graph of order n and λ1, λ2, . . . , λn be the zeros of its matching polynomial. The matching energy of a graph G is defined as ME(G) = Pni=1 |λi|. By the famous Coulson’s formula, matching energies can also be calculated by an improper integral depending on a parameter. A k-claw attaching graph Gu(k) refers to the graph obtained by attaching k pendent edges to the graph G at the vertex u, where u is called the root of Gu(k). In this paper, we use some theories of mathematical analysis to obtain a new technique to compare the matching energies of two k-claw attaching graphs Gu(k) and Hv(k) with the same order, that is, limk→∞[ME(Gu(k)) − ME(Hv(k))] = ME(G − u) − ME(H − v). By the technique, we finally determine unicyclic graphs of order n with the 9th to 13th minimal matching energies for all n ≥ 58.
基金Supported by the National Natural Science Foundation of China(62462036,62462037)Jiangxi Provincial Natural Science Foundation(20242BAB26017,20232BAB202010)+1 种基金Cultivation Project for Academic and Technical Leader in Major Disciplines in Jiangxi Province(20232BCJ22013)the Jiangxi Province Graduate Innovation Found Project(YC2024-S214)。
文摘Most existing multi-pattern matching algorithms are designed for single English texts leading to issues such as missed matches and space expansion when applied to Chinese-English mixed-text environments.The Hash Trie-based matching machine demonstrates strong compatibility with both Chinese and English,ensuring high accuracy in text processing and subtree positioning.In this study,a novel functional framework based on the HashTrie structure is proposed and mechanically verified using Isabelle/HOL.This framework is applied to design Functional Multi-Pattern Matching(FMPM),the first functional multi-pattern matching algorithm for Chinese-English mixed texts.FMPM constructs the HashTrie matching machine using character codes and threads the machine according to the associations between pattern strings.The experimental results show that as the stored string information increases,the proposed algorithm demonstrates more significant optimization in retrieval efficiency.FMPM simplifies the implementation of the Threaded Hash Trie(THT)for Chinese-English mixed texts,effectively reducing the uncertainties in the transition from the algorithm description to code implementation.FMPM addresses the problem of space explosion Chinese-English mixed texts and avoids issues such as bound variable iteration errors.The functional framework of the HashTrie structure serves as a reference for the formal verification of future HashTrie-based algorithms.
文摘This study investigates how artificial intelligence(AI)algorithms enable mainstream media to achieve precise emotional matching and improve communication efficiency through reconstructed communication logic.As digital intelligence technology rapidly evolves,mainstream media organizations are increasingly leveraging AI-driven empathy algorithms to enhance audience engagement and optimize content delivery.This research employs a mixed-methods approach,combining quantitative analysis of algorithmic performance metrics with qualitative examination of media communication patterns.Through systematic review of 150 academic papers and analysis of data from 12 major media platforms,this study reveals that algorithmic empathy systems can improve emotional resonance by 34.7%and increase audience engagement by 28.3%compared to traditional communication methods.The findings demonstrate that AI algorithms reconstruct media communication logic through three primary pathways:emotional pattern recognition,personalized content curation,and real-time sentiment adaptation.However,the study also identifies significant challenges including algorithmic bias,emotional authenticity concerns,and ethical implications of automated empathy.The research contributes to understanding how mainstream media can leverage AI technology to build high-quality empathetic communication while maintaining journalistic integrity and social responsibility.
基金supported by the National Key Research and Development Program of China (2021YFD1901200)the Key Research and Development Program of Hubei Province of China (2023BBB028)+1 种基金the Earmarked Fund of Hubei province of Chinathe Fundamental Research Funds for the Central Universities (2662024ZKQD005)
文摘The effects of micro-ridge-furrow planting(MR)on yield and the efficiency of light,water,and thermal resource use in rapeseed were tested in a three-year field experiment comparing MR to conventional flat planting.MR enhanced canopy heterogeneity by altering the leaf angle between plants on ridges and furrows.The heterogeneous canopy environment increased intercepted photosynthetic active radiation,alleviated canopy temperature stress,and optimized canopy humidity,leading to improvements in light-nitrogen matching and net photosynthetic rate.Consequently,dry matter and yield increased by 13.0%and 11.0%,respectively,while radiation,thermal,and precipitation utilization efficiency increased by 12.3%-16.2%.The corresponding improvements in yield and resource use efficiency were attributed to a heterogeneous canopy environment that improved microclimatic conditions.
文摘The cross-modal person re-identification task aims to match visible and infrared images of the same individual.The main challenges in this field arise from significant modality differences between individuals and the lack of high-quality cross-modal correspondence methods.Existing approaches often attempt to establish modality correspondence by extracting shared features across different modalities.However,these methods tend to focus on local information extraction and fail to fully leverage the global identity information in the cross-modal features,resulting in limited correspondence accuracy and suboptimal matching performance.To address this issue,we propose a quadratic graph matching method designed to overcome the challenges posed by modality differences through precise cross-modal relationship alignment.This method transforms the cross-modal correspondence problem into a graph matching task and minimizes the matching cost using a center search mechanism.Building on this approach,we further design a block reasoning module to uncover latent relationships between person identities and optimize the modality correspondence results.The block strategy not only improves the efficiency of updating gallery images but also enhances matching accuracy while reducing computational load.Experimental results demonstrate that our proposed method outperforms the state-of-the-art methods on the SYSU-MM01,RegDB,and RGBNT201 datasets,achieving excellent matching accuracy and robustness,thereby validating its effectiveness in cross-modal person re-identification.
基金Ethics Committee of the Certified Institutional Review Board of the Yoyogi Mental Clinic(No.RKK227).
文摘BACKGROUND Recently,Olympus Corporation released new scopes(XZ1200/EZ1500).However,there have been few reports on this topic,although improvement in adenoma detection rate(ADR)by texture and color enhancement imaging(TXI)or computer-aided detection system(CAD)has been reported.AIM To investigate the effects of the scope on the detection of adenomas and sessile serrated lesions(SSLs).METHODS The subjects were patients who underwent pancolonic chromoendoscopy using the EVIS X1 video system center between May 2023 and October 2024.The patients were divided into the new(CF-XZ1200/CF-EZ1500)and 290 series(CF-HQ290Z/PCF-H290Z)groups.Propensity score matching was performed for age,sex,examination purpose,endoscopist,preparation,TXI use,and CAD use.The effects of the scope were analyzed in terms of the ADR,SSL detection rate(SDR),and mean number of adenomas per colonoscopy(APC).RESULTS Of the 7014 patients enrolled,2138 pairs were extracted by propensity score matching(mean age 55.4 years,45.5%male).The new scopes group had a significantly higher ADR than the 290 series group[51.5%vs 45.5%,odds ratio(OR)=1.27,95%CI:1.13-1.43,P<0.001].Similarly,the new scopes group had significantly higher SDR(7.8%vs 5.7%,OR=1.41,95%CI:1.11-1.80,P=0.005)and APC(0.90 vs 0.76,OR=1.11,95%CI:1.05-1.17,P<0.001)than the 290 series group.CONCLUSION In conclusion,the new scope(CF-XZ1200/CF-EZ1500)enhanced the detection of adenomas and SSLs compared to the old ones(290 series).
文摘BACKGROUND Endoscopic full-thickness resection(EFTR)is increasingly used for treating gastrointestinal stromal tumors(GISTs)in the stomach.AIM To compare the efficacy,tolerability,and clinical outcomes of EFTR vs surgical resection(SR)for gastric GISTs.METHODS We collected clinical data from patients diagnosed with GISTs who underwent either EFTR or SR at our hospital from October 2011 to July 2024.Patients were matched in a 1:1 ratio based on baseline characteristics and tumor clinical-pathological features using propensity score matching.We analyzed perioperative outcomes and follow-up data.The primary outcome measure was progressionfree survival(PFS).RESULTS Out of 912 patients,573 met the inclusion criteria.After matching,each group included 95 patients.The EFTR group demonstrated statistically significant advantages over the SR group in average operative time(P<0.001),length of hospital stay(P<0.001),time to resume liquid diet(P<0.001),incidence of adverse events(P=0.031),and hospitalization costs(P<0.001).The en bloc resection rate was significantly different,with SR group at 100%and EFTR group at 93.7%(P=0.038).The median follow-up was 2451.50 days.Recurrence occurred in 3 patients in the EFTR group and 4 patients in the SR group,with no statistically significant difference(P=1.000).Factors associated with PFS included age,tumor size,high-risk category in the modified National Institutes of Health(NIH)risk score,and resection status.Resection status was identified as an independent prognostic factor for PFS(P=0.0173,hazard ratios=0.0179,95%CI:0.000655-0.491).Notably,there was no statistically significant difference in PFS between the two groups.CONCLUSION This study is a non-inferiority design.The EFTR group significantly outperformed the SR group in terms of operative time,length of hospital stay,time to resume a liquid diet,incidence of adverse events,and hospitalization costs,demonstrating its higher economic efficiency and better tolerability.Additionally,although the en bloc resection rate was lower in the EFTR group compared to the SR group,there were no significant differences in tumor recurrence rates and progression-free survival between the two groups.This study found no statistical difference in the primary endpoint of postoperative recurrence rates between the two groups.However,due to sample size limitations,this result requires further validation in larger-scale studies.The current results should be viewed as exploratory evidence.
基金supported by the fund of Beijing Municipal Commission of Education(KM202210017001 and 22019821001)the Natural Science Foundation of Henan Province(222300420253).
文摘This paper discusses the design of event-triggered output-feedback controller for a class of nonlinear time-delay systems with multiple uncertainties. In sharp contrast to previous works, the considered systems possess two important characteristics: (i) The uncertain nonlinear terms meet the linearly unmeasurable-states dependent growth with the growth rate being an unknown function of the input and output. (ii) There exist input matching uncertainty and unknown measurement sensitivity. By introducing a single dynamic gain and employing a cleverly devised event-triggering mechanism (ETM), we design a new gain-based event-triggered output-feedback controller, which globally regulates all states of the considered systems and maintains global boundedness of the closed-loop system. Furthermore, the estimation of input matching uncertainty achieves convergence towards its actual value, and Zeno behavior does not happen. Two simulation examples including a practical one show that the proposed approach is effective.
基金Supported by the National Natural Science Foundation of China(No.61971162,61771186)the Natural Science Foundation of Heilongjiang Province(No.PL2024F025)+1 种基金the Open Research Fund of National Mobile Communications Research Laboratory in Southeast University(No.2023D07)the Fundamental Scientific Research Funds of Heilongjiang Province(No.2022-KYYWF-1050).
文摘The impact of location services on people’s lives has grown significantly in the era of widespread smart device usage.Due to global navigation satellite system(GNSS)signal rejection,weak signal strength in indoor environments and radio signal interference caused by multiwall environments,which collectively lead to significant positioning errors,vision-based positioning has emerged as a crucial method in indoor positioning research.This paper introduces a scale hierarchical matching model to tackle challenges associated with large visual databases and high scene similarity,both of which will compromise matching accuracy and lead to prolonged positioning delays.The proposed model establishes an image feature database using GIST features and speeded up robust feature(SURF)in the offline stage.In the online stage,a positioning navigating algorithm is constructed based on Dijkstra’s path planning.Additionally,a corresponding Android application has been developed to facilitate visual positioning and navigation in indoor environments.Experimental results obtained in real indoor environments demonstrate that the proposed method significantly enhances positioning accuracy compared with similar algorithms,while effectively reducing time overhead.This improvement caters to the requirements for indoor positioning and navigation,thereby meeting user needs.
基金part of a project that has received funding from the 5x1000 Humanitas funds。
文摘Objectives This study aimed to analyze the prevalence of long-term central line-associated bloodstream infections(CLABSI)among hospitalized adults with cancer in Italy and compare the characteristics of patients who required long-term central venous access device(LCVAD)substitution due to prior CLABSI with those who had never experienced CLABSI.Methods The study was conducted in hospitals across northern and central Italy using a multicenter,observational,cross-sectional design from March to September 2021.A total of 174 adults with cancer were included.Data were collected through electronic case report forms,including demographic,clinical,treatment-related,and catheter-related variables.Propensity score matching(PSM)was used to compare the characteristics of patients who underwent LCVAD substitution due to previous CLABSI with those who never experienced CLABSI.Multiple correspondence analysis(MCA)was conducted to explore the patterns within matched subgroups.Results The prevalence of CLABSI was 3%,and 5.2%of patients required LCVAD substitution due to prior CLABSI.After applying PSM,the groups were successfully balanced for sex,age,presence of metastases,comorbidities,BMI,received treatments,corticosteroid therapy,ongoing antibiotics,hormone therapy,type of LCVAD,lumens,and utilization frequency.Hematologic cancer was more frequent in the CLABSI group(44.4%)compared to the non-infective group(0),with a statistically significant difference(P=0.045).MCA revealed potential patterns among matched subgroups but did not identify statistically significant associations:patients with previous LCVAD substitution were more frequently associated with a history of prior infections,ongoing antibiotic therapy,and unspecified primary lesion locations;conversely,patients who never experienced CLABSI tended to cluster around characteristics such as hormone therapy and corticosteroid therapy.Conclusions These findings emphasize the importance of continuous monitoring,individualized infection prevention strategies in oncology nursing practice.Future research with larger datasets is needed to validate these findings and develop tailored interventions to reduce CLABSI risks.
基金Supported by The Interdisciplinary Guided Network for Investigation,Translation and Equity for the All of Us Research Program,No.OT2 OD031915.
文摘BACKGROUND Patients with inflammatory bowel disease(IBD)are at an increased risk of bacterial pneumonia,contributing to significant morbidity and mortality.While previous studies have identified various risk factors,including medications and comorbidities,the independent contribution of IBD to pneumonia risk remains unclear.We hypothesized that the increased pneumonia risk is primarily driven by factors other than IBD itself.AIM To investigate the relative contributions of IBD,comorbidities,and medications to pneumonia risk in patients with IBD.METHODS We conducted a retrospective cohort study using the All of Us Research Program database(2010-2022).We matched 2810 participants with IBD 1:1 with controls using four propensity score models:(1)Demographics/Lifestyle only;(2)Plus comorbidities;(3)Plus medications;and(4)All factors combined.Then we used Cox proportional hazards models to assess pneumonia risk and logistic regression to evaluate risk factors.RESULTS In the primary analysis of 5620 matched participants,IBD was not independently associated with increased pneumonia risk[hazard ratio(HR)=1.07,95%CI:0.84-1.35]when matched for all factors.However,participants with IBD had significantly higher risk(HR=2.08,95%CI:1.56-2.78)when matched only for demographics and lifestyle factors.Within the IBD cohort,a high comorbidity burden(Charlson Comorbidity Index≥10)[odds ratio(OR)=12.20,95%CI:6.69-23.00]and systemic steroid use(OR=2.26,95%CI:1.21-4.64)were independently associated with increased pneumonia risk.CONCLUSION Comorbidities and systemic steroids,rather than IBD itself,drive pneumonia risk.Management should focus on these factors and prioritize vaccination in high-risk patients.
基金Special Project Funded by Tsinghua University Press:“Engineering Drawing and CAD”Course Construction and Textbook Development。
文摘To enhance network security,this study employs a deep graph matching model for vulnerability similarity detection.The model utilizes a Word Embedding layer to vectorize data words,an Image Embedding layer to vectorize data graphs,and an LSTM layer to extract the associations between word and graph vectors.A Dropout layer is applied to randomly deactivate neurons in the LSTM layer,while a Softmax layer maps the LSTM analysis results.Finally,a fully connected layer outputs the detection results with a dimension of 1.Experimental results demonstrate that the AUC of the deep graph matching vulnerability similarity detection model is 0.9721,indicating good stability.The similarity scores for vulnerabilities such as memory leaks,buffer overflows,and targeted attacks are close to 1,showing significant similarity.In contrast,the similarity scores for vulnerabilities like out-of-bounds memory access and logical design flaws are less than 0.4,indicating good similarity detection performance.The model’s evaluation metrics are all above 97%,with high detection accuracy,which is beneficial for improving network security.
基金Sponsored by the National Key Research and Development Program from Ministry of Science and Technology of the People's Republic of China (Grant No.2020YFB1711403)。
文摘After the design of aerospace products is completed,a manufacturability assessment needs to be conducted based on 3D model's features in terms of modeling quality and process design,otherwise the cost of design changes will increase.Due to the poor structure and low reusability of product manufacturing feature information and assessment knowledge in the current aerospace product manufacturability assessment process,it is difficult to realize automated manufacturability assessment.To address these issues,a domain ontology model is established for aerospace product manufacturability assessment in this paper.On this basis,a structured representation method of manufacturability assessment knowledge and a knowledge graph data layer construction method are proposed.Based on the semantic information and association information expressed by the knowledge graph,a rule matching method based on subgraph matching is proposed to improve the precision and recall.Finally,applications and experiments based on the software platform verify the effectiveness of the proposed knowledge graph construction and rule matching method.
文摘Under the“dual carbon”goal,local governments in China have strategically focused on enhancing capital utilization efficiency and enforcing environmental regulations to improve carbon emission performance.This dual approach targets the intertwined challenges of economic development and environmental protection.Utilizing data from 266 prefecture-level cities in China from 2007 to 2019,this study systematically investigates the effects of capital matching and environmental regulation on carbon emission performance through the spatial Durbin model and the instrumental variable method.The results indicate that both capital matching and environmental regulation significantly enhance carbon emission performance.Capital matching demonstrates positive spatial spillover effects,whereas environmental regulation exhibits negative spatial spillover effects.Furthermore,there are synergistic effects between capital matching and environmental regulation that jointly enhance carbon emission performance.To address potential biases caused by endogenous environmental regulation,the study uses the proportion of environment-related words in provincial government work reports as an instrumental variable for environmental regulation.Additionally,to capture the heterogeneity in the environmental governance willingness and intensity of prefecture-level municipal governments,the study constructs heterogeneous instrumental variables.These variables are derived by multiplying the proportion of a prefecture-level city’s total industrial output value to the province’s total industrial output value with the proportion of environment-related words in the provincial government work reports.Analyses based on these instrumental variables reveal that endogenous issues in environmental regulation lead to an overestimation of its positive impact on carbon emission performance.
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.
