A novel fracture-cavity reservoir outcrop geological knowledge base construction method considering parameter collection and processing,mutual transformation of data-knowledge,application and update

This study endeavors to formulate a comprehensive methodology for establishing a Geological Knowledge Base(GKB)tailored to fracture-cavity reservoir outcrops within the North Tarim Basin.The acquisition of quantitative geological parameters was accomplished through diverse means such as outcrop observations,thin section studies,unmanned aerial vehicle scanning,and high-resolution cameras.Subsequently,a three-dimensional digital outcrop model was generated,and the parameters were standardized.An assessment of traditional geological knowledge was conducted to delineate the knowledge framework,content,and system of the GKB.The basic parameter knowledge was extracted using multiscale fine characterization techniques,including core statistics,field observations,and microscopic thin section analysis.Key mechanism knowledge was identified by integrating trace elements from filling,isotope geochemical tests,and water-rock simulation experiments.Significant representational knowledge was then extracted by employing various methods such as multiple linear regression,neural network technology,and discriminant classification.Subsequently,an analogy study was performed on the karst fracture-cavity system(KFCS)in both outcrop and underground reservoir settings.The results underscored several key findings:(1)Utilization of a diverse range of techniques,including outcrop observations,core statistics,unmanned aerial vehicle scanning,high-resolution cameras,thin section analysis,and electron scanning imaging,enabled the acquisition and standardization of data.This facilitated effective management and integration of geological parameter data from multiple sources and scales.(2)The GKB for fracture-cavity reservoir outcrops,encompassing basic parameter knowledge,key mechanism knowledge,and significant representational knowledge,provides robust data support and systematic geological insights for the intricate and in-depth examination of the genetic mechanisms of fracture-cavity reservoirs.(3)The developmental characteristics of fracturecavities in karst outcrops offer effective,efficient,and accurate guidance for fracture-cavity research in underground karst reservoirs.The outlined construction method of the outcrop geological knowledge base is applicable to various fracture-cavity reservoirs in different layers and regions worldwide.

A Survey of Knowledge Graph Construction Using Machine Learning

Knowledge graph(KG)serves as a specialized semantic network that encapsulates intricate relationships among real-world entities within a structured framework.This framework facilitates a transformation in information retrieval,transitioning it from mere string matching to far more sophisticated entity matching.In this transformative process,the advancement of artificial intelligence and intelligent information services is invigorated.Meanwhile,the role ofmachine learningmethod in the construction of KG is important,and these techniques have already achieved initial success.This article embarks on a comprehensive journey through the last strides in the field of KG via machine learning.With a profound amalgamation of cutting-edge research in machine learning,this article undertakes a systematical exploration of KG construction methods in three distinct phases:entity learning,ontology learning,and knowledge reasoning.Especially,a meticulous dissection of machine learningdriven algorithms is conducted,spotlighting their contributions to critical facets such as entity extraction,relation extraction,entity linking,and link prediction.Moreover,this article also provides an analysis of the unresolved challenges and emerging trajectories that beckon within the expansive application of machine learning-fueled,large-scale KG construction.

Combining Deep Learning with Knowledge Graph for Design Knowledge Acquisition in Conceptual Product Design

The acquisition of valuable design knowledge from massive fragmentary data is challenging for designers in conceptual product design.This study proposes a novel method for acquiring design knowledge by combining deep learning with knowledge graph.Specifically,the design knowledge acquisition method utilises the knowledge extraction model to extract design-related entities and relations from fragmentary data,and further constructs the knowledge graph to support design knowledge acquisition for conceptual product design.Moreover,the knowledge extraction model introduces ALBERT to solve memory limitation and communication overhead in the entity extraction module,and uses multi-granularity information to overcome segmentation errors and polysemy ambiguity in the relation extraction module.Experimental comparison verified the effectiveness and accuracy of the proposed knowledge extraction model.The case study demonstrated the feasibility of the knowledge graph construction with real fragmentary porcelain data and showed the capability to provide designers with interconnected and visualised design knowledge.

A new evolutional model for institutional field knowledge flow network

Purpose:This paper aims to address the limitations in existing research on the evolution of knowledge flow networks by proposing a meso-level institutional field knowledge flow network evolution model(IKM).The purpose is to simulate the construction process of a knowledge flow network using knowledge organizations as units and to investigate its effectiveness in replicating institutional field knowledge flow networks.Design/Methodology/Approach:The IKM model enhances the preferential attachment and growth observed in scale-free BA networks,while incorporating three adjustment parameters to simulate the selection of connection targets and the types of nodes involved in the network evolution process Using the PageRank algorithm to calculate the significance of nodes within the knowledge flow network.To compare its performance,the BA and DMS models are also employed for simulating the network.Pearson coefficient analysis is conducted on the simulated networks generated by the IKM,BA and DMS models,as well as on the actual network.Findings:The research findings demonstrate that the IKM model outperforms the BA and DMS models in replicating the institutional field knowledge flow network.It provides comprehensive insights into the evolution mechanism of knowledge flow networks in the scientific research realm.The model also exhibits potential applicability to other knowledge networks that involve knowledge organizations as node units.Research Limitations:This study has some limitations.Firstly,it primarily focuses on the evolution of knowledge flow networks within the field of physics,neglecting other fields.Additionally,the analysis is based on a specific set of data,which may limit the generalizability of the findings.Future research could address these limitations by exploring knowledge flow networks in diverse fields and utilizing broader datasets.Practical Implications:The proposed IKM model offers practical implications for the construction and analysis of knowledge flow networks within institutions.It provides a valuable tool for understanding and managing knowledge exchange between knowledge organizations.The model can aid in optimizing knowledge flow and enhancing collaboration within organizations.Originality/value:This research highlights the significance of meso-level studies in understanding knowledge organization and its impact on knowledge flow networks.The IKM model demonstrates its effectiveness in replicating institutional field knowledge flow networks and offers practical implications for knowledge management in institutions.Moreover,the model has the potential to be applied to other knowledge networks,which are formed by knowledge organizations as node units.

GATiT:An Intelligent Diagnosis Model Based on Graph Attention Network Incorporating Text Representation in Knowledge Reasoning

The growing prevalence of knowledge reasoning using knowledge graphs(KGs)has substantially improved the accuracy and efficiency of intelligent medical diagnosis.However,current models primarily integrate electronic medical records(EMRs)and KGs into the knowledge reasoning process,ignoring the differing significance of various types of knowledge in EMRs and the diverse data types present in the text.To better integrate EMR text information,we propose a novel intelligent diagnostic model named the Graph ATtention network incorporating Text representation in knowledge reasoning(GATiT),which comprises text representation,subgraph construction,knowledge reasoning,and diagnostic classification.In the text representation process,GATiT uses a pre-trained model to obtain text representations of the EMRs and additionally enhances embeddings by including chief complaint information and numerical information in the input.In the subgraph construction process,GATiT constructs text subgraphs and disease subgraphs from the KG,utilizing EMR text and the disease to be diagnosed.To differentiate the varying importance of nodes within the subgraphs features such as node categories,relevance scores,and other relevant factors are introduced into the text subgraph.Themessage-passing strategy and attention weight calculation of the graph attention network are adjusted to learn these features in the knowledge reasoning process.Finally,in the diagnostic classification process,the interactive attention-based fusion method integrates the results of knowledge reasoning with text representations to produce the final diagnosis results.Experimental results on multi-label and single-label EMR datasets demonstrate the model’s superiority over several state-of-theart methods.

Hyperbolic hierarchical graph attention network for knowledge graph completion

Utilizing graph neural networks for knowledge embedding to accomplish the task of knowledge graph completion(KGC)has become an important research area in knowledge graph completion.However,the number of nodes in the knowledge graph increases exponentially with the depth of the tree,whereas the distances of nodes in Euclidean space are second-order polynomial distances,whereby knowledge embedding using graph neural networks in Euclidean space will not represent the distances between nodes well.This paper introduces a novel approach called hyperbolic hierarchical graph attention network(H2GAT)to rectify this limitation.Firstly,the paper conducts knowledge representation in the hyperbolic space,effectively mitigating the issue of exponential growth of nodes with tree depth and consequent information loss.Secondly,it introduces a hierarchical graph atten-tion mechanism specifically designed for the hyperbolic space,allowing for enhanced capture of the network structure inherent in the knowledge graph.Finally,the efficacy of the proposed H2GAT model is evaluated on benchmark datasets,namely WN18RR and FB15K-237,thereby validating its effectiveness.The H2GAT model achieved 0.445,0.515,and 0.586 in the Hits@1,Hits@3 and Hits@10 metrics respectively on the WN18RR dataset and 0.243,0.367 and 0.518 on the FB15K-237 dataset.By incorporating hyperbolic space embedding and hierarchical graph attention,the H2GAT model successfully addresses the limitations of existing hyperbolic knowledge embedding models,exhibiting its competence in knowledge graph completion tasks.

Low-Cost Federated Broad Learning for Privacy-Preserved Knowledge Sharing in the RIS-Aided Internet of Vehicles

High-efficiency and low-cost knowledge sharing can improve the decision-making ability of autonomous vehicles by mining knowledge from the Internet of Vehicles(IoVs).However,it is challenging to ensure high efficiency of local data learning models while preventing privacy leakage in a high mobility environment.In order to protect data privacy and improve data learning efficiency in knowledge sharing,we propose an asynchronous federated broad learning(FBL)framework that integrates broad learning(BL)into federated learning(FL).In FBL,we design a broad fully connected model(BFCM)as a local model for training client data.To enhance the wireless channel quality for knowledge sharing and reduce the communication and computation cost of participating clients,we construct a joint resource allocation and reconfigurable intelligent surface(RIS)configuration optimization framework for FBL.The problem is decoupled into two convex subproblems.Aiming to improve the resource scheduling efficiency in FBL,a double Davidon–Fletcher–Powell(DDFP)algorithm is presented to solve the time slot allocation and RIS configuration problem.Based on the results of resource scheduling,we design a reward-allocation algorithm based on federated incentive learning(FIL)in FBL to compensate clients for their costs.The simulation results show that the proposed FBL framework achieves better performance than the comparison models in terms of efficiency,accuracy,and cost for knowledge sharing in the IoV.

Incorporating empirical knowledge into data-driven variable selection for quantitative analysis of coal ash content by laser-induced breakdown spectroscopy

Laser-induced breakdown spectroscopy(LIBS)has become a widely used atomic spectroscopic technique for rapid coal analysis.However,the vast amount of spectral information in LIBS contains signal uncertainty,which can affect its quantification performance.In this work,we propose a hybrid variable selection method to improve the performance of LIBS quantification.Important variables are first identified using Pearson's correlation coefficient,mutual information,least absolute shrinkage and selection operator(LASSO)and random forest,and then filtered and combined with empirical variables related to fingerprint elements of coal ash content.Subsequently,these variables are fed into a partial least squares regression(PLSR).Additionally,in some models,certain variables unrelated to ash content are removed manually to study the impact of variable deselection on model performance.The proposed hybrid strategy was tested on three LIBS datasets for quantitative analysis of coal ash content and compared with the corresponding data-driven baseline method.It is significantly better than the variable selection only method based on empirical knowledge and in most cases outperforms the baseline method.The results showed that on all three datasets the hybrid strategy for variable selection combining empirical knowledge and data-driven algorithms achieved the lowest root mean square error of prediction(RMSEP)values of 1.605,3.478 and 1.647,respectively,which were significantly lower than those obtained from multiple linear regression using only 12 empirical variables,which are 1.959,3.718 and 2.181,respectively.The LASSO-PLSR model with empirical support and 20 selected variables exhibited a significantly improved performance after variable deselection,with RMSEP values dropping from 1.635,3.962 and 1.647 to 1.483,3.086 and 1.567,respectively.Such results demonstrate that using empirical knowledge as a support for datadriven variable selection can be a viable approach to improve the accuracy and reliability of LIBS quantification.

Heterogeneous Image Knowledge Driven Visual Perception

Dear Editor,This letter is concerned with visual perception closely related to heterogeneous images.Facing the huge challenge brought by different image modalities,we propose a visual perception framework based on heterogeneous image knowledge,i.e.,the domain knowledge associated with specific vision tasks,to better address the corresponding visual perception problems.

Application of sparse S transform network with knowledge distillation in seismic attenuation delineation

Time-frequency analysis is a successfully used tool for analyzing the local features of seismic data.However,it suffers from several inevitable limitations,such as the restricted time-frequency resolution,the difficulty in selecting parameters,and the low computational efficiency.Inspired by deep learning,we suggest a deep learning-based workflow for seismic time-frequency analysis.The sparse S transform network(SSTNet)is first built to map the relationship between synthetic traces and sparse S transform spectra,which can be easily pre-trained by using synthetic traces and training labels.Next,we introduce knowledge distillation(KD)based transfer learning to re-train SSTNet by using a field data set without training labels,which is named the sparse S transform network with knowledge distillation(KD-SSTNet).In this way,we can effectively calculate the sparse time-frequency spectra of field data and avoid the use of field training labels.To test the availability of the suggested KD-SSTNet,we apply it to field data to estimate seismic attenuation for reservoir characterization and make detailed comparisons with the traditional time-frequency analysis methods.

A deep learning method based on prior knowledge with dual training for solving FPK equation

The evolution of the probability density function of a stochastic dynamical system over time can be described by a Fokker–Planck–Kolmogorov(FPK) equation, the solution of which determines the distribution of macroscopic variables in the stochastic dynamic system. Traditional methods for solving these equations often struggle with computational efficiency and scalability, particularly in high-dimensional contexts. To address these challenges, this paper proposes a novel deep learning method based on prior knowledge with dual training to solve the stationary FPK equations. Initially, the neural network is pre-trained through the prior knowledge obtained by Monte Carlo simulation(MCS). Subsequently, the second training phase incorporates the FPK differential operator into the loss function, while a supervisory term consisting of local maximum points is specifically included to mitigate the generation of zero solutions. This dual-training strategy not only expedites convergence but also enhances computational efficiency, making the method well-suited for high-dimensional systems. Numerical examples, including two different two-dimensional(2D), six-dimensional(6D), and eight-dimensional(8D) systems, are conducted to assess the efficacy of the proposed method. The results demonstrate robust performance in terms of both computational speed and accuracy for solving FPK equations in the first three systems. While the method is also applicable to high-dimensional systems, such as 8D, it should be noted that computational efficiency may be marginally compromised due to data volume constraints.

RepDNet:A re-parameterization despeckling network for autonomous underwater side-scan sonar imaging with prior-knowledge customized convolution

Side-scan sonar(SSS)is now a prevalent instrument for large-scale seafloor topography measurements,deployable on an autonomous underwater vehicle(AUV)to execute fully automated underwater acoustic scanning imaging along a predetermined trajectory.However,SSS images often suffer from speckle noise caused by mutual interference between echoes,and limited AUV computational resources further hinder noise suppression.Existing approaches for SSS image processing and speckle noise reduction rely heavily on complex network structures and fail to combine the benefits of deep learning and domain knowledge.To address the problem,Rep DNet,a novel and effective despeckling convolutional neural network is proposed.Rep DNet introduces two re-parameterized blocks:the Pixel Smoothing Block(PSB)and Edge Enhancement Block(EEB),preserving edge information while attenuating speckle noise.During training,PSB and EEB manifest as double-layered multi-branch structures,integrating first-order and secondorder derivatives and smoothing functions.During inference,the branches are re-parameterized into a 3×3 convolution,enabling efficient inference without sacrificing accuracy.Rep DNet comprises three computational operations:3×3 convolution,element-wise summation and Rectified Linear Unit activation.Evaluations on benchmark datasets,a real SSS dataset and Data collected at Lake Mulan aestablish Rep DNet as a well-balanced network,meeting the AUV computational constraints in terms of performance and latency.

Survey and Prospect for Applying Knowledge Graph in Enterprise Risk Management

Enterprise risk management holds significant importance in fostering sustainable growth of businesses and in serving as a critical element for regulatory bodies to uphold market order.Amidst the challenges posed by intricate and unpredictable risk factors,knowledge graph technology is effectively driving risk management,leveraging its ability to associate and infer knowledge from diverse sources.This review aims to comprehensively summarize the construction techniques of enterprise risk knowledge graphs and their prominent applications across various business scenarios.Firstly,employing bibliometric methods,the aim is to uncover the developmental trends and current research hotspots within the domain of enterprise risk knowledge graphs.In the succeeding section,systematically delineate the technical methods for knowledge extraction and fusion in the standardized construction process of enterprise risk knowledge graphs.Objectively comparing and summarizing the strengths and weaknesses of each method,we provide recommendations for addressing the existing challenges in the construction process.Subsequently,categorizing the applied research of enterprise risk knowledge graphs based on research hotspots and risk category standards,and furnishing a detailed exposition on the applicability of technical routes and methods.Finally,the future research directions that still need to be explored in enterprise risk knowledge graphs were discussed,and relevant improvement suggestions were proposed.Practitioners and researchers can gain insights into the construction of technical theories and practical guidance of enterprise risk knowledge graphs based on this foundation.

Knowledge, attitudes, and practices regarding Covid-19 and their relationship with Covid-19 booster vaccination status among women with infertility

Objective:To elucidate the relationship among knowledge,attitudes,and practices regarding Covid-19 and their relationship with booster vaccination status among women with infertility.Methods:This questionnaire-based cross-sectional study was performed online and offline among women with infertility who visited an infertility clinic in Jakarta,Indonesia.We assessed the patient’s knowledge,attitudes,and practices regarding Covid-19 and their relationship with booster vaccination status and sociodemographic profile.Results:A total of 178 subjects participated in this study,and most participants(92.6%)had received booster Covid-19 vaccines.From the questionnaire,74.2%had good knowledge,and 99.4%had good attitudes regarding Covid-19;however,only 57.9%of patients had good practices.A weak positive correlation existed between knowledge and attitudes(r=0.11,P=0.13)and a moderate negative correlation between attitudes and practices(r=-0.44,P=0.56).Participants’knowledge about vaccines and infertility was correlated with booster vaccination status(P=0.04).Academic background(P=0.01)and attitudes(P=0.01)were also correlated with booster vaccination status.The significant determinants of hesitance of receiving Covid-19 booster vaccines were high school education or below(OR=0.08,95%CI 0.02-0.36)and poor practices(OR=0.21,95%CI 0.05-0.95).Conclusions:The majority of the participants had received the Covid-19 booster vaccine and had good knowledge and attitudes but poor practices regarding Covid-19.Most participants had poor knowledge about the relationship between infertility and the Covid-19 vaccine.The general population should be more informed and reminded about practices to prevent Covid-19 and the relationship between vaccination and fertility to increase the number of people who receive Covid-19 booster vaccines.

A cross-sectional study to assess medication safety,knowledge,attitude,and practices regarding nutrition and medication among pregnant women

Objective:To assess pregnant women's knowledge,attitude,and practice regarding nutrition and medication usage,analyse the prescribing pattern,and categorize them based on the Food and Drug Administration(FDA)guidelines.Methods:A cross-sectional study was conducted with 264 pregnant women in the obstetrics and gynaecology department of a tertiary care hospital from October 2022 to August 2023.A knowledge,attitude,and practice(KAP)questionnaire was prepared in English language by the researchers and validated by an expert panel consisting of 12 members.The validated questionnaire was then translated into regional languages,Kannada and Malayalam.The reliability of the questionnaire was assessed with test-retest method with a representative sample population of 30 subjects(10 subjects for each language).The subjects'knowledge,attitude,and practice were evaluated using the validated KAP questionnaire.The safety of the medication was assessed using the FDA drug safety classification for pregnancy.Results:The mean scores for nutritional and medication usage knowledge,attitude,and practice were 4.14±1.15,4.50±1.09,and 3.00±1.47,respectively.Among 30 prescribed medications,3 belong to category A(no risk in human studies),8 belong to category B(no risk in animal studies),18 belong to category C(risk cannot be ruled out)and 1 drug is not classified.A significant association was observed between medication knowledge and practice(r=0.159,P=0.010).Conclusions:Most of the study population knows the need to maintain good dietary and medication practices during pregnancy.Counselling pregnant women regarding diet and medication usage is crucial in maternal care.

Global systematic review and meta-analysis of knowledge, attitudes, and practices towards dengue fever among the general population

Objective:To determine the global level of knowledge,attitudes,and practices towards dengue fever among the general population.Methods:To complete this systematic review and meta-analysis,a thorough search for pertinent English-language literature was undertaken during the study's extension until October 2023.The search used Google Scholar,Scopus,PubMed/MEDLINE,Science Direct,Web of Science,EMBASE,Springer,and ProQuest.A quality assessment checklist developed using a modified Newcastle-Ottawa Scale for the cross-sectional study was used to evaluate the risk of bias in the included papers.Inverse variance and Cochran Q statistics were employed in the STATA software version 14 to assess study heterogeneity.When there was heterogeneity,the Dersimonian and Liard random-effects models were used.Results:59 Studies totaling 87353 participants were included in this meta-analysis.These investigations included 86278 participants in 55 studies on knowledge,20196 in 33 studies on attitudes,and 74881 in 29 studies on practices.The pooled estimates for sufficient knowledge,positive attitudes,and dengue fever preventive behaviors among the general population were determined as 40.1%(95%CI 33.8%-46.5%),46.8%(95%CI 35.8%-58.9%),and 38.3%(95%CI 28.4%-48.2%),respectively.Europe exhibits the highest knowledge level at 63.5%,and Africa shows the lowest at 20.3%.Positive attitudes are most prevalent in the Eastern Mediterranean(54.1%)and Southeast Asia(53.6%),contrasting sharply with the Americas,where attitudes are notably lower at 9.05%.Regarding preventive behaviors,the Americas demonstrate a prevalence of 12.1%,Southeast Asia at 28.1%,Western Pacific at 49.6%,Eastern Mediterranean at 44.8%,and Africa at 47.4%.Conclusions:Regional disparities about the knowledge,attitude and preventive bahaviors are evident with Europe exhibiting the highest knowledge level while Africa has the lowest.These findings emphasize the importance of targeted public health interventions tailored to regional contexts,highlighting the need for region-specific strategies to enhance dengue-related knowledge and encourage positive attitudes and preventive behaviors.

KGTLIR:An Air Target Intention Recognition Model Based on Knowledge Graph and Deep Learning

As a core part of battlefield situational awareness,air target intention recognition plays an important role in modern air operations.Aiming at the problems of insufficient feature extraction and misclassification in intention recognition,this paper designs an air target intention recognition method(KGTLIR)based on Knowledge Graph and Deep Learning.Firstly,the intention recognition model based on Deep Learning is constructed to mine the temporal relationship of intention features using dilated causal convolution and the spatial relationship of intention features using a graph attention mechanism.Meanwhile,the accuracy,recall,and F1-score after iteration are introduced to dynamically adjust the sample weights to reduce the probability of misclassification.After that,an intention recognition model based on Knowledge Graph is constructed to predict the probability of the occurrence of different intentions of the target.Finally,the results of the two models are fused by evidence theory to obtain the target’s operational intention.Experiments show that the intention recognition accuracy of the KGTLIRmodel can reach 98.48%,which is not only better than most of the air target intention recognition methods,but also demonstrates better interpretability and trustworthiness.

Knowledge Reasoning Method Based on Deep Transfer Reinforcement Learning:DTRLpath

In recent years,with the continuous development of deep learning and knowledge graph reasoning methods,more and more researchers have shown great interest in improving knowledge graph reasoning methods by inferring missing facts through reasoning.By searching paths on the knowledge graph and making fact and link predictions based on these paths,deep learning-based Reinforcement Learning(RL)agents can demonstrate good performance and interpretability.Therefore,deep reinforcement learning-based knowledge reasoning methods have rapidly emerged in recent years and have become a hot research topic.However,even in a small and fixed knowledge graph reasoning action space,there are still a large number of invalid actions.It often leads to the interruption of RL agents’wandering due to the selection of invalid actions,resulting in a significant decrease in the success rate of path mining.In order to improve the success rate of RL agents in the early stages of path search,this article proposes a knowledge reasoning method based on Deep Transfer Reinforcement Learning path(DTRLpath).Before supervised pre-training and retraining,a pre-task of searching for effective actions in a single step is added.The RL agent is first trained in the pre-task to improve its ability to search for effective actions.Then,the trained agent is transferred to the target reasoning task for path search training,which improves its success rate in searching for target task paths.Finally,based on the comparative experimental results on the FB15K-237 and NELL-995 datasets,it can be concluded that the proposed method significantly improves the success rate of path search and outperforms similar methods in most reasoning tasks.

A Novel Tensor Decomposition-Based Efficient Detector for Low-Altitude Aerial Objects With Knowledge Distillation Scheme

Unmanned aerial vehicles(UAVs) have gained significant attention in practical applications, especially the low-altitude aerial(LAA) object detection imposes stringent requirements on recognition accuracy and computational resources. In this paper, the LAA images-oriented tensor decomposition and knowledge distillation-based network(TDKD-Net) is proposed,where the TT-format TD(tensor decomposition) and equalweighted response-based KD(knowledge distillation) methods are designed to minimize redundant parameters while ensuring comparable performance. Moreover, some robust network structures are developed, including the small object detection head and the dual-domain attention mechanism, which enable the model to leverage the learned knowledge from small-scale targets and selectively focus on salient features. Considering the imbalance of bounding box regression samples and the inaccuracy of regression geometric factors, the focal and efficient IoU(intersection of union) loss with optimal transport assignment(F-EIoU-OTA)mechanism is proposed to improve the detection accuracy. The proposed TDKD-Net is comprehensively evaluated through extensive experiments, and the results have demonstrated the effectiveness and superiority of the developed methods in comparison to other advanced detection algorithms, which also present high generalization and strong robustness. As a resource-efficient precise network, the complex detection of small and occluded LAA objects is also well addressed by TDKD-Net, which provides useful insights on handling imbalanced issues and realizing domain adaptation.

De-biased knowledge distillation framework based on knowledge infusion and label de-biasing techniques

Knowledge distillation,as a pivotal technique in the field of model compression,has been widely applied across various domains.However,the problem of student model performance being limited due to inherent biases in the teacher model during the distillation process still persists.To address the inherent biases in knowledge distillation,we propose a de-biased knowledge distillation framework tailored for binary classification tasks.For the pre-trained teacher model,biases in the soft labels are mitigated through knowledge infusion and label de-biasing techniques.Based on this,a de-biased distillation loss is introduced,allowing the de-biased labels to replace the soft labels as the fitting target for the student model.This approach enables the student model to learn from the corrected model information,achieving high-performance deployment on lightweight student models.Experiments conducted on multiple real-world datasets demonstrate that deep learning models compressed under the de-biased knowledge distillation framework significantly outperform traditional response-based and feature-based knowledge distillation models across various evaluation metrics,highlighting the effectiveness and superiority of the de-biased knowledge distillation framework in model compression.