Accurately identifying building distribution from remote sensing images with complex background information is challenging.The emergence of diffusion models has prompted the innovative idea of employing the reverse de...Accurately identifying building distribution from remote sensing images with complex background information is challenging.The emergence of diffusion models has prompted the innovative idea of employing the reverse denoising process to distill building distribution from these complex backgrounds.Building on this concept,we propose a novel framework,building extraction diffusion model(BEDiff),which meticulously refines the extraction of building footprints from remote sensing images in a stepwise fashion.Our approach begins with the design of booster guidance,a mechanism that extracts structural and semantic features from remote sensing images to serve as priors,thereby providing targeted guidance for the diffusion process.Additionally,we introduce a cross-feature fusion module(CFM)that bridges the semantic gap between different types of features,facilitating the integration of the attributes extracted by booster guidance into the diffusion process more effectively.Our proposed BEDiff marks the first application of diffusion models to the task of building extraction.Empirical evidence from extensive experiments on the Beijing building dataset demonstrates the superior performance of BEDiff,affirming its effectiveness and potential for enhancing the accuracy of building extraction in complex urban landscapes.展开更多
Processing police incident data in public security involves complex natural language processing(NLP)tasks,including information extraction.This data contains extensive entity information—such as people,locations,and ...Processing police incident data in public security involves complex natural language processing(NLP)tasks,including information extraction.This data contains extensive entity information—such as people,locations,and events—while also involving reasoning tasks like personnel classification,relationship judgment,and implicit inference.Moreover,utilizing models for extracting information from police incident data poses a significant challenge—data scarcity,which limits the effectiveness of traditional rule-based and machine-learning methods.To address these,we propose TIPS.In collaboration with public security experts,we used de-identified police incident data to create templates that enable large language models(LLMs)to populate data slots and generate simulated data,enhancing data density and diversity.We then designed schemas to efficiently manage complex extraction and reasoning tasks,constructing a high-quality dataset and fine-tuning multiple open-source LLMs.Experiments showed that the fine-tuned ChatGLM-4-9B model achieved an F1 score of 87.14%,nearly 30%higher than the base model,significantly reducing error rates.Manual corrections further improved performance by 9.39%.This study demonstrates that combining largescale pre-trained models with limited high-quality domain-specific data can greatly enhance information extraction in low-resource environments,offering a new approach for intelligent public security applications.展开更多
Detecting cyber attacks in networks connected to the Internet of Things(IoT)is of utmost importance because of the growing vulnerabilities in the smart environment.Conventional models,such as Naive Bayes and support v...Detecting cyber attacks in networks connected to the Internet of Things(IoT)is of utmost importance because of the growing vulnerabilities in the smart environment.Conventional models,such as Naive Bayes and support vector machine(SVM),as well as ensemble methods,such as Gradient Boosting and eXtreme gradient boosting(XGBoost),are often plagued by high computational costs,which makes it challenging for them to perform real-time detection.In this regard,we suggested an attack detection approach that integrates Visual Geometry Group 16(VGG16),Artificial Rabbits Optimizer(ARO),and Random Forest Model to increase detection accuracy and operational efficiency in Internet of Things(IoT)networks.In the suggested model,the extraction of features from malware pictures was accomplished with the help of VGG16.The prediction process is carried out by the random forest model using the extracted features from the VGG16.Additionally,ARO is used to improve the hyper-parameters of the random forest model of the random forest.With an accuracy of 96.36%,the suggested model outperforms the standard models in terms of accuracy,F1-score,precision,and recall.The comparative research highlights our strategy’s success,which improves performance while maintaining a lower computational cost.This method is ideal for real-time applications,but it is effective.展开更多
Accurate vector extraction from design drawings is required first to automatically create 3D models from pixel-level engineering design drawings. However, this task faces the challenges of complicated design shapes as...Accurate vector extraction from design drawings is required first to automatically create 3D models from pixel-level engineering design drawings. However, this task faces the challenges of complicated design shapes as well as cumbersome and cluttered annotations on drawings, which interfere with the vector extraction heavily. In this article, the transmission tower containing the most complex structure is taken as the research object, and a semantic segmentation network is constructed to first segment the shape masks from the pixel-level drawings. Preprocessing and postprocessing are also proposed to ensure the stability and accuracy of the shape mask segmentation. Then, based on the obtained shape masks, a vector extraction network guided by heatmaps is designed to extract structural vectors by fusing the features from node heatmap and skeleton heatmap, respectively. Compared with the state-of-the-art methods, experiment results illustrate that the proposed semantic segmentation method can effectively eliminate the interference of many elements on drawings to segment the shape masks effectively, meanwhile, the model trained by the proposed vector extraction network can accurately extract the vectors such as nodes and line connections, avoiding redundant vector detection. The proposed method lays a solid foundation for automatic 3D model reconstruction and contributes to technological advancements in relevant fields.展开更多
Background:Acquiring relevant information about procurement targets is fundamental to procuring medical devices.Although traditional Natural Language Processing(NLP)and Machine Learning(ML)methods have improved inform...Background:Acquiring relevant information about procurement targets is fundamental to procuring medical devices.Although traditional Natural Language Processing(NLP)and Machine Learning(ML)methods have improved information retrieval efficiency to a certain extent,they exhibit significant limitations in adaptability and accuracy when dealing with procurement documents characterized by diverse formats and a high degree of unstructured content.The emergence of Large Language Models(LLMs)offers new possibilities for efficient procurement information processing and extraction.Methods:This study collected procurement transaction documents from public procurement websites,and proposed a procurement Information Extraction(IE)method based on LLMs.Unlike traditional approaches,this study systematically explores the applicability of LLMs in both structured and unstructured entities in procurement documents,addressing the challenges posed by format variability and content complexity.Furthermore,an optimized prompt framework tailored for procurement document extraction tasks is developed to enhance the accuracy and robustness of IE.The aim is to process and extract key information from medical device procurement quickly and accurately,meeting stakeholders'demands for precision and timeliness in information retrieval.Results:Experimental results demonstrate that,compared to traditional methods,the proposed approach achieves an F1 Score of 0.9698,representing a 4.85%improvement over the best baseline model.Moreover,both recall and precision rates are close to 97%,significantly outperforming other models and exhibiting exceptional overall recognition capabilities.Notably,further analysis reveals that the proposed method consistently maintains high performance across both structured and unstructured entities in procurement documents while balancing recall and precision effectively,demonstrating its adaptability in handling varying document formats.The results of ablation experiments validate the effectiveness of the proposed prompting strategy.Conclusion:Additionally,this study explores the challenges and potential improvements of the proposed method in IE tasks and provides insights into its feasibility for real-world deployment and application directions,further clarifying its adaptability and value.This method not only exhibits significant advantages in medical device procurement but also holds promise for providing new approaches to information processing and decision support in various domains.展开更多
In the process of constructing domain-specific knowledge graphs,the task of relational triple extraction plays a critical role in transforming unstructured text into structured information.Existing relational triple e...In the process of constructing domain-specific knowledge graphs,the task of relational triple extraction plays a critical role in transforming unstructured text into structured information.Existing relational triple extraction models facemultiple challenges when processing domain-specific data,including insufficient utilization of semantic interaction information between entities and relations,difficulties in handling challenging samples,and the scarcity of domain-specific datasets.To address these issues,our study introduces three innovative components:Relation semantic enhancement,data augmentation,and a voting strategy,all designed to significantly improve the model’s performance in tackling domain-specific relational triple extraction tasks.We first propose an innovative attention interaction module.This method significantly enhances the semantic interaction capabilities between entities and relations by integrating semantic information fromrelation labels.Second,we propose a voting strategy that effectively combines the strengths of large languagemodels(LLMs)and fine-tuned small pre-trained language models(SLMs)to reevaluate challenging samples,thereby improving the model’s adaptability in specific domains.Additionally,we explore the use of LLMs for data augmentation,aiming to generate domain-specific datasets to alleviate the scarcity of domain data.Experiments conducted on three domain-specific datasets demonstrate that our model outperforms existing comparative models in several aspects,with F1 scores exceeding the State of the Art models by 2%,1.6%,and 0.6%,respectively,validating the effectiveness and generalizability of our approach.展开更多
Since Google introduced the concept of Knowledge Graphs(KGs)in 2012,their construction technologies have evolved into a comprehensive methodological framework encompassing knowledge acquisition,extraction,representati...Since Google introduced the concept of Knowledge Graphs(KGs)in 2012,their construction technologies have evolved into a comprehensive methodological framework encompassing knowledge acquisition,extraction,representation,modeling,fusion,computation,and storage.Within this framework,knowledge extraction,as the core component,directly determines KG quality.In military domains,traditional manual curation models face efficiency constraints due to data fragmentation,complex knowledge architectures,and confidentiality protocols.Meanwhile,crowdsourced ontology construction approaches from general domains prove non-transferable,while human-crafted ontologies struggle with generalization deficiencies.To address these challenges,this study proposes an OntologyAware LLM Methodology for Military Domain Knowledge Extraction(LLM-KE).This approach leverages the deep semantic comprehension capabilities of Large Language Models(LLMs)to simulate human experts’cognitive processes in crowdsourced ontology construction,enabling automated extraction of military textual knowledge.It concurrently enhances knowledge processing efficiency and improves KG completeness.Empirical analysis demonstrates that this method effectively resolves scalability and dynamic adaptation challenges in military KG construction,establishing a novel technological pathway for advancing military intelligence development.展开更多
Objective:To study the therapeutic effect of the Extract of Wuwei Xiaodu Drink on spinal infection and provide the scientific basis for clinical application.Methods:By establishing a rabbit model of spinal infection,t...Objective:To study the therapeutic effect of the Extract of Wuwei Xiaodu Drink on spinal infection and provide the scientific basis for clinical application.Methods:By establishing a rabbit model of spinal infection,this paper observed and analyzed the changes in body mass before and after the intervention and the comparison of inflammation-related factors and blood leukocyte counts among the three groups.Results:There was a significant difference in the changes in body mass of rabbits before and after intervention in the experimental group,control group and blank group(P<0.05);there was no statistically significant difference in calcitoninogen,C-reactive protein and routine blood leukocyte counts between the experimental group and the control group(P>0.05),and there was a statistically significant difference in calcitoninogen,C-reactive protein and routine blood leukocyte counts between the experimental group and the blank group(P<0.05).Conclusion:The Extract of Wuwei Xiaodu Drink can play a protective role by regulating the level of inflammatory factors in blood routine leukocyte count and reducing the inflammatory reaction in the spinal cord injury area.展开更多
Purpose–This study aims to enhance the accuracy of key entity extraction from railway accident report texts and address challenges such as complex domain-specific semantics,data sparsity and strong inter-sentence sem...Purpose–This study aims to enhance the accuracy of key entity extraction from railway accident report texts and address challenges such as complex domain-specific semantics,data sparsity and strong inter-sentence semantic dependencies.A robust entity extraction method tailored for accident texts is proposed.Design/methodology/approach–This method is implemented through a dual-branch multi-task mutual learning model named R-MLP,which jointly performs entity recognition and accident phase classification.The model leverages a shared BERT encoder to extract contextual features and incorporates a sentence span indexing module to align feature granularity.A cross-task mutual learning mechanism is also introduced to strengthen semantic representation.Findings–R-MLP effectively mitigates the impact of semantic complexity and data sparsity in domain entities and enhances the model’s ability to capture inter-sentence semantic dependencies.Experimental results show that R-MLP achieves a maximum F1-score of 0.736 in extracting six types of key railway accident entities,significantly outperforming baseline models such as RoBERTa and MacBERT.Originality/value–This demonstrates the proposed method’s superior generalization and accuracy in domainspecific entity extraction tasks,confirming its effectiveness and practical value.展开更多
[Objective]Accurate prediction of tomato growth height is crucial for optimizing production environments in smart farming.However,current prediction methods predominantly rely on empirical,mechanistic,or learning-base...[Objective]Accurate prediction of tomato growth height is crucial for optimizing production environments in smart farming.However,current prediction methods predominantly rely on empirical,mechanistic,or learning-based models that utilize either images data or environmental data.These methods fail to fully leverage multi-modal data to capture the diverse aspects of plant growth comprehensively.[Methods]To address this limitation,a two-stage phenotypic feature extraction(PFE)model based on deep learning algorithm of recurrent neural network(RNN)and long short-term memory(LSTM)was developed.The model integrated environment and plant information to provide a holistic understanding of the growth process,emploied phenotypic and temporal feature extractors to comprehensively capture both types of features,enabled a deeper understanding of the interaction between tomato plants and their environment,ultimately leading to highly accurate predictions of growth height.[Results and Discussions]The experimental results showed the model's ef‐fectiveness:When predicting the next two days based on the past five days,the PFE-based RNN and LSTM models achieved mean absolute percentage error(MAPE)of 0.81%and 0.40%,respectively,which were significantly lower than the 8.00%MAPE of the large language model(LLM)and 6.72%MAPE of the Transformer-based model.In longer-term predictions,the 10-day prediction for 4 days ahead and the 30-day prediction for 12 days ahead,the PFE-RNN model continued to outperform the other two baseline models,with MAPE of 2.66%and 14.05%,respectively.[Conclusions]The proposed method,which leverages phenotypic-temporal collaboration,shows great potential for intelligent,data-driven management of tomato cultivation,making it a promising approach for enhancing the efficiency and precision of smart tomato planting management.展开更多
This article proposes a document-level prompt learning approach using LLMs to extract the timeline-based storyline. Through verification tests on datasets such as ESCv1.2 and Timeline17, the results show that the prom...This article proposes a document-level prompt learning approach using LLMs to extract the timeline-based storyline. Through verification tests on datasets such as ESCv1.2 and Timeline17, the results show that the prompt + one-shot learning proposed in this article works well. Meanwhile, our research findings indicate that although timeline-based storyline extraction has shown promising prospects in the practical applications of LLMs, it is still a complex natural language processing task that requires further research.展开更多
Boundary extraction of watershed is an important step in forest landscape research. The boundary of the upriver wa-tershed of the Hunhe River in the sub-alpine Qingyuan County of eastern Liaoning Province, China was e...Boundary extraction of watershed is an important step in forest landscape research. The boundary of the upriver wa-tershed of the Hunhe River in the sub-alpine Qingyuan County of eastern Liaoning Province, China was extracted by digital elevation modeling (DEM) data in ArcInfo8.1. Remote sensing image of the corresponding region was applied to help modify its copy according to Enhanced Thematic Mapper (ETM) image抯 profuse geomorphological structure information. Both the DEM-dependent boundary and modified copy were overlapped with county map and drainage network map to visually check the effects of result. Overlap of county map suggested a nice extraction of the boundary line since the two layers matched precisely, which indicated the DEM-dependent boundary by program was effective and precise. Further upload of drainage network showed discrepancies between the boundary and the drainage network. Altogether, there were three sections of the extraction result that needed to correct. Compared with this extraction boundary, the modified boundary had a better match to the drainage network as well as to the county map. Comprehensive analysis demonstrated that the program extraction has generally fine precision in position and excels the digitized result by hand. The errors of the DEM-dependant extraction are due to the fact that it is difficult for program to recognize sections of complex landform especially altered by human activities, but these errors are discernable and adjustable because the spatial resolution of ETM image is less than that of DEM. This study result proved that application of remote sensing information could help obtain better result when DEM method is used in extraction of watershed boundary.展开更多
A novel parameter extraction method with rational functions is presented for the 2-πequivalent circuit model of RF CMOS spiral inductors. The final S-parameters simulated by the circuit model closely match experiment...A novel parameter extraction method with rational functions is presented for the 2-πequivalent circuit model of RF CMOS spiral inductors. The final S-parameters simulated by the circuit model closely match experimental data. The extraction strategy is straightforward and can be easily implemented as a CAD tool to model spiral inductors. The resulting circuit models will be very useful for RF circuit designers.展开更多
It is well known that the human auditory system possesses remarkable capabilities to analyze and identify signals. Therefore, it would be significant to build an auditory model based on the mechanism of human auditory...It is well known that the human auditory system possesses remarkable capabilities to analyze and identify signals. Therefore, it would be significant to build an auditory model based on the mechanism of human auditory systems, which may improve the effects of mechanical signal analysis and enrich the methods of mechanical faults features extraction. However the existing methods are all based on explicit senses of mathematics or physics, and have some shortages on distinguishing different faults, stability, and suppressing the disturbance noise, etc. For the purpose of improving the performances of the work of feature extraction, an auditory model, early auditory（EA） model, is introduced for the first time. This auditory model transforms time domain signal into auditory spectrum via bandpass filtering, nonlinear compressing, and lateral inhibiting by simulating the principle of the human auditory system. The EA model is developed with the Gammatone filterbank as the basilar membrane. According to the characteristics of vibration signals, a method is proposed for determining the parameter of inner hair cells model of EA model. The performance of EA model is evaluated through experiments on four rotor faults, including misalignment, rotor-to-stator rubbing, oil film whirl, and pedestal looseness. The results show that the auditory spectrum, output of EA model, can effectively distinguish different faults with satisfactory stability and has the ability to suppress the disturbance noise. Then, it is feasible to apply auditory model, as a new method, to the feature extraction for mechanical faults diagnosis with effect.展开更多
This paper presents an accurate small-signal model for multi-gate GaAs pHEMTs in switching-mode.The extraction method for the proposed model is developed.A 2-gate switch structure is fabricated on a commercial 0.5μm ...This paper presents an accurate small-signal model for multi-gate GaAs pHEMTs in switching-mode.The extraction method for the proposed model is developed.A 2-gate switch structure is fabricated on a commercial 0.5μm AlGaAs/GaAs pHEMT technology to verify the proposed model.Excellent agreement has been obtained between the measured and simulated results over a wide frequency range.展开更多
Ultrasonically assisted extraction of isoflavones from the stem of Pueraria lobata （Willd.） Ohwi has been carried out with an ultrasonic extracting apparatus （20kHz, electrical power input to the transducer in 0-6...Ultrasonically assisted extraction of isoflavones from the stem of Pueraria lobata （Willd.） Ohwi has been carried out with an ultrasonic extracting apparatus （20kHz, electrical power input to the transducer in 0-650W）. The influence of the electrical power input and extraction time on the＇extraction yield is investigated in water, n-butanol, and 95% （by volume） and 50% （by volume） ethanol aqueous solution. The experimental results indicate that the yields of total isoflavones are higher in ultrasonically assisted extraction than those obtained from con-ventional extraction.Moreover,a mathematical model is proposed,by introducing the electrical power input to index the ultrsound intensity,to describe the behavior of ultrasonically assisted extraction.It is found that the model calcuations are in good agreement with the experimental data.展开更多
In China′s Loess Plateau area, gully head is the most active zone of a drainage system in gully areas. The differentiation of loess gully head follows geospatial patterns and reflects the process of the loess landfor...In China′s Loess Plateau area, gully head is the most active zone of a drainage system in gully areas. The differentiation of loess gully head follows geospatial patterns and reflects the process of the loess landform development and evolution of its drainage system to some extent. In this study, the geomorphic meaning, basic characteristics, morphological structure and the basic types of loess gully heads were systematically analysed. Then, the loess gully head′s conceptual model was established, and an extraction method based on Digital Elevation Model(DEM) for loess gully head features and elements was proposed. Through analysing the achieved statistics of loess gully head features, loess gully heads have apparently similar and different characteristics depending on the different loess landforms where they are found. The loess head characteristics reflect their growth period and evolution tendency to a certain degree, and they indirectly represent evolutionary mechanisms. In addition, the loess gully developmental stages and the evolutionary processes can be deduced by using loess gully head characteristics. This study is of great significance for development and improvement of the theoretical system for describing loess gully landforms.展开更多
The supercritical carbon dioxide extraction was applied to obtain essential oil from Pogostemon cablin in this work.Effect of extraction parameters including temperature,pressure,extraction time and particle size on e...The supercritical carbon dioxide extraction was applied to obtain essential oil from Pogostemon cablin in this work.Effect of extraction parameters including temperature,pressure,extraction time and particle size on extraction yield was investigated,and the response surface methodology with a Box–Behnken Design was used to achieve the optimized extraction conditions.The maximum yield of essential oil was 2.4356%under the conditions of extraction temperature 47°C,pressure 24.5 MPa and extraction time 119 min.Moreover,based on the Brunauer–Emmett–Teller theory of adsorption,a mathematical modeling was performed to correlate the measured data.The model shows a function relationship between extraction yield and time by a simple equation with three significantly adjustable parameters.These model parameters have been optimized through simulated annealing algorithm.The predicted data from the mathematical model show a good agreement with the experimental data of the different extraction parameters.展开更多
A sub circuit model for VDMOS is built according to its physical structure.Parameters and formulas describing the device are also derived from this model.Comparing to former results,this model avoids too many technic...A sub circuit model for VDMOS is built according to its physical structure.Parameters and formulas describing the device are also derived from this model.Comparing to former results,this model avoids too many technical parameters and simplify the sub circuit efficiently.As a result of numeric computation,this simple model with clear physical conception demonstrates excellent agreements between measured and modeled response (DC error within 5%,AC error within 10%).Such a model is now available for circuit simulation and parameter extraction.展开更多
In consideration of the online measurement of the component content in rare earth countercurrent extraction separation process, the soft sensor method based on hybrid modeling was proposed to measure the rare earth co...In consideration of the online measurement of the component content in rare earth countercurrent extraction separation process, the soft sensor method based on hybrid modeling was proposed to measure the rare earth component content. The hybrid models were composed of the extraction equilibrium calculation model and the Radial Basis Function (RBF) Neural Network (NN) error compensation model; the parameters of compensation model were optimized by the hierarchical genetic algorithms (HGA). In addition, application experiment research of this proposed method was carried out in the rare earth separation production process of a corporation. The result shows that this method is effective and can realize online measurement for the component content of rare earth in the countercurrent extraction.展开更多
基金supported by the National Natural Science Foundation of China(Nos.61906168,62202429 and 62272267)the Zhejiang Provincial Natural Science Foundation of China(No.LY23F020023)the Construction of Hubei Provincial Key Laboratory for Intelligent Visual Monitoring of Hydropower Projects(No.2022SDSJ01)。
文摘Accurately identifying building distribution from remote sensing images with complex background information is challenging.The emergence of diffusion models has prompted the innovative idea of employing the reverse denoising process to distill building distribution from these complex backgrounds.Building on this concept,we propose a novel framework,building extraction diffusion model(BEDiff),which meticulously refines the extraction of building footprints from remote sensing images in a stepwise fashion.Our approach begins with the design of booster guidance,a mechanism that extracts structural and semantic features from remote sensing images to serve as priors,thereby providing targeted guidance for the diffusion process.Additionally,we introduce a cross-feature fusion module(CFM)that bridges the semantic gap between different types of features,facilitating the integration of the attributes extracted by booster guidance into the diffusion process more effectively.Our proposed BEDiff marks the first application of diffusion models to the task of building extraction.Empirical evidence from extensive experiments on the Beijing building dataset demonstrates the superior performance of BEDiff,affirming its effectiveness and potential for enhancing the accuracy of building extraction in complex urban landscapes.
文摘Processing police incident data in public security involves complex natural language processing(NLP)tasks,including information extraction.This data contains extensive entity information—such as people,locations,and events—while also involving reasoning tasks like personnel classification,relationship judgment,and implicit inference.Moreover,utilizing models for extracting information from police incident data poses a significant challenge—data scarcity,which limits the effectiveness of traditional rule-based and machine-learning methods.To address these,we propose TIPS.In collaboration with public security experts,we used de-identified police incident data to create templates that enable large language models(LLMs)to populate data slots and generate simulated data,enhancing data density and diversity.We then designed schemas to efficiently manage complex extraction and reasoning tasks,constructing a high-quality dataset and fine-tuning multiple open-source LLMs.Experiments showed that the fine-tuned ChatGLM-4-9B model achieved an F1 score of 87.14%,nearly 30%higher than the base model,significantly reducing error rates.Manual corrections further improved performance by 9.39%.This study demonstrates that combining largescale pre-trained models with limited high-quality domain-specific data can greatly enhance information extraction in low-resource environments,offering a new approach for intelligent public security applications.
基金funded by Institutional Fund Projects under grant no.(IFPDP-261-22)。
文摘Detecting cyber attacks in networks connected to the Internet of Things(IoT)is of utmost importance because of the growing vulnerabilities in the smart environment.Conventional models,such as Naive Bayes and support vector machine(SVM),as well as ensemble methods,such as Gradient Boosting and eXtreme gradient boosting(XGBoost),are often plagued by high computational costs,which makes it challenging for them to perform real-time detection.In this regard,we suggested an attack detection approach that integrates Visual Geometry Group 16(VGG16),Artificial Rabbits Optimizer(ARO),and Random Forest Model to increase detection accuracy and operational efficiency in Internet of Things(IoT)networks.In the suggested model,the extraction of features from malware pictures was accomplished with the help of VGG16.The prediction process is carried out by the random forest model using the extracted features from the VGG16.Additionally,ARO is used to improve the hyper-parameters of the random forest model of the random forest.With an accuracy of 96.36%,the suggested model outperforms the standard models in terms of accuracy,F1-score,precision,and recall.The comparative research highlights our strategy’s success,which improves performance while maintaining a lower computational cost.This method is ideal for real-time applications,but it is effective.
基金funded by the Chinese State Grid Jiangsu Electric Power Co.,Ltd.Science and Technology Project Funding,Grant Number J2023031.
文摘Accurate vector extraction from design drawings is required first to automatically create 3D models from pixel-level engineering design drawings. However, this task faces the challenges of complicated design shapes as well as cumbersome and cluttered annotations on drawings, which interfere with the vector extraction heavily. In this article, the transmission tower containing the most complex structure is taken as the research object, and a semantic segmentation network is constructed to first segment the shape masks from the pixel-level drawings. Preprocessing and postprocessing are also proposed to ensure the stability and accuracy of the shape mask segmentation. Then, based on the obtained shape masks, a vector extraction network guided by heatmaps is designed to extract structural vectors by fusing the features from node heatmap and skeleton heatmap, respectively. Compared with the state-of-the-art methods, experiment results illustrate that the proposed semantic segmentation method can effectively eliminate the interference of many elements on drawings to segment the shape masks effectively, meanwhile, the model trained by the proposed vector extraction network can accurately extract the vectors such as nodes and line connections, avoiding redundant vector detection. The proposed method lays a solid foundation for automatic 3D model reconstruction and contributes to technological advancements in relevant fields.
文摘Background:Acquiring relevant information about procurement targets is fundamental to procuring medical devices.Although traditional Natural Language Processing(NLP)and Machine Learning(ML)methods have improved information retrieval efficiency to a certain extent,they exhibit significant limitations in adaptability and accuracy when dealing with procurement documents characterized by diverse formats and a high degree of unstructured content.The emergence of Large Language Models(LLMs)offers new possibilities for efficient procurement information processing and extraction.Methods:This study collected procurement transaction documents from public procurement websites,and proposed a procurement Information Extraction(IE)method based on LLMs.Unlike traditional approaches,this study systematically explores the applicability of LLMs in both structured and unstructured entities in procurement documents,addressing the challenges posed by format variability and content complexity.Furthermore,an optimized prompt framework tailored for procurement document extraction tasks is developed to enhance the accuracy and robustness of IE.The aim is to process and extract key information from medical device procurement quickly and accurately,meeting stakeholders'demands for precision and timeliness in information retrieval.Results:Experimental results demonstrate that,compared to traditional methods,the proposed approach achieves an F1 Score of 0.9698,representing a 4.85%improvement over the best baseline model.Moreover,both recall and precision rates are close to 97%,significantly outperforming other models and exhibiting exceptional overall recognition capabilities.Notably,further analysis reveals that the proposed method consistently maintains high performance across both structured and unstructured entities in procurement documents while balancing recall and precision effectively,demonstrating its adaptability in handling varying document formats.The results of ablation experiments validate the effectiveness of the proposed prompting strategy.Conclusion:Additionally,this study explores the challenges and potential improvements of the proposed method in IE tasks and provides insights into its feasibility for real-world deployment and application directions,further clarifying its adaptability and value.This method not only exhibits significant advantages in medical device procurement but also holds promise for providing new approaches to information processing and decision support in various domains.
基金Science and Technology Innovation 2030-Major Project of“New Generation Artificial Intelligence”granted by Ministry of Science and Technology,Grant Number 2020AAA0109300.
文摘In the process of constructing domain-specific knowledge graphs,the task of relational triple extraction plays a critical role in transforming unstructured text into structured information.Existing relational triple extraction models facemultiple challenges when processing domain-specific data,including insufficient utilization of semantic interaction information between entities and relations,difficulties in handling challenging samples,and the scarcity of domain-specific datasets.To address these issues,our study introduces three innovative components:Relation semantic enhancement,data augmentation,and a voting strategy,all designed to significantly improve the model’s performance in tackling domain-specific relational triple extraction tasks.We first propose an innovative attention interaction module.This method significantly enhances the semantic interaction capabilities between entities and relations by integrating semantic information fromrelation labels.Second,we propose a voting strategy that effectively combines the strengths of large languagemodels(LLMs)and fine-tuned small pre-trained language models(SLMs)to reevaluate challenging samples,thereby improving the model’s adaptability in specific domains.Additionally,we explore the use of LLMs for data augmentation,aiming to generate domain-specific datasets to alleviate the scarcity of domain data.Experiments conducted on three domain-specific datasets demonstrate that our model outperforms existing comparative models in several aspects,with F1 scores exceeding the State of the Art models by 2%,1.6%,and 0.6%,respectively,validating the effectiveness and generalizability of our approach.
文摘Since Google introduced the concept of Knowledge Graphs(KGs)in 2012,their construction technologies have evolved into a comprehensive methodological framework encompassing knowledge acquisition,extraction,representation,modeling,fusion,computation,and storage.Within this framework,knowledge extraction,as the core component,directly determines KG quality.In military domains,traditional manual curation models face efficiency constraints due to data fragmentation,complex knowledge architectures,and confidentiality protocols.Meanwhile,crowdsourced ontology construction approaches from general domains prove non-transferable,while human-crafted ontologies struggle with generalization deficiencies.To address these challenges,this study proposes an OntologyAware LLM Methodology for Military Domain Knowledge Extraction(LLM-KE).This approach leverages the deep semantic comprehension capabilities of Large Language Models(LLMs)to simulate human experts’cognitive processes in crowdsourced ontology construction,enabling automated extraction of military textual knowledge.It concurrently enhances knowledge processing efficiency and improves KG completeness.Empirical analysis demonstrates that this method effectively resolves scalability and dynamic adaptation challenges in military KG construction,establishing a novel technological pathway for advancing military intelligence development.
基金Shandong Province Traditional Chinese Medicine Science and Technology Project Task Book Number(Project No.:M-2022178)2024 Shandong Provincial Traditional Chinese Medicine Science and Technology Project(Project No.:Z20242407)。
文摘Objective:To study the therapeutic effect of the Extract of Wuwei Xiaodu Drink on spinal infection and provide the scientific basis for clinical application.Methods:By establishing a rabbit model of spinal infection,this paper observed and analyzed the changes in body mass before and after the intervention and the comparison of inflammation-related factors and blood leukocyte counts among the three groups.Results:There was a significant difference in the changes in body mass of rabbits before and after intervention in the experimental group,control group and blank group(P<0.05);there was no statistically significant difference in calcitoninogen,C-reactive protein and routine blood leukocyte counts between the experimental group and the control group(P>0.05),and there was a statistically significant difference in calcitoninogen,C-reactive protein and routine blood leukocyte counts between the experimental group and the blank group(P<0.05).Conclusion:The Extract of Wuwei Xiaodu Drink can play a protective role by regulating the level of inflammatory factors in blood routine leukocyte count and reducing the inflammatory reaction in the spinal cord injury area.
基金funded by the Technology Research and Development Plan Program of China State Railway Group Co.,Ltd.(No.Q2024T001)the Foundation of China Academy of Railway Sciences Co.,Ltd.(No:2024YJ259).
文摘Purpose–This study aims to enhance the accuracy of key entity extraction from railway accident report texts and address challenges such as complex domain-specific semantics,data sparsity and strong inter-sentence semantic dependencies.A robust entity extraction method tailored for accident texts is proposed.Design/methodology/approach–This method is implemented through a dual-branch multi-task mutual learning model named R-MLP,which jointly performs entity recognition and accident phase classification.The model leverages a shared BERT encoder to extract contextual features and incorporates a sentence span indexing module to align feature granularity.A cross-task mutual learning mechanism is also introduced to strengthen semantic representation.Findings–R-MLP effectively mitigates the impact of semantic complexity and data sparsity in domain entities and enhances the model’s ability to capture inter-sentence semantic dependencies.Experimental results show that R-MLP achieves a maximum F1-score of 0.736 in extracting six types of key railway accident entities,significantly outperforming baseline models such as RoBERTa and MacBERT.Originality/value–This demonstrates the proposed method’s superior generalization and accuracy in domainspecific entity extraction tasks,confirming its effectiveness and practical value.
文摘[Objective]Accurate prediction of tomato growth height is crucial for optimizing production environments in smart farming.However,current prediction methods predominantly rely on empirical,mechanistic,or learning-based models that utilize either images data or environmental data.These methods fail to fully leverage multi-modal data to capture the diverse aspects of plant growth comprehensively.[Methods]To address this limitation,a two-stage phenotypic feature extraction(PFE)model based on deep learning algorithm of recurrent neural network(RNN)and long short-term memory(LSTM)was developed.The model integrated environment and plant information to provide a holistic understanding of the growth process,emploied phenotypic and temporal feature extractors to comprehensively capture both types of features,enabled a deeper understanding of the interaction between tomato plants and their environment,ultimately leading to highly accurate predictions of growth height.[Results and Discussions]The experimental results showed the model's ef‐fectiveness:When predicting the next two days based on the past five days,the PFE-based RNN and LSTM models achieved mean absolute percentage error(MAPE)of 0.81%and 0.40%,respectively,which were significantly lower than the 8.00%MAPE of the large language model(LLM)and 6.72%MAPE of the Transformer-based model.In longer-term predictions,the 10-day prediction for 4 days ahead and the 30-day prediction for 12 days ahead,the PFE-RNN model continued to outperform the other two baseline models,with MAPE of 2.66%and 14.05%,respectively.[Conclusions]The proposed method,which leverages phenotypic-temporal collaboration,shows great potential for intelligent,data-driven management of tomato cultivation,making it a promising approach for enhancing the efficiency and precision of smart tomato planting management.
文摘This article proposes a document-level prompt learning approach using LLMs to extract the timeline-based storyline. Through verification tests on datasets such as ESCv1.2 and Timeline17, the results show that the prompt + one-shot learning proposed in this article works well. Meanwhile, our research findings indicate that although timeline-based storyline extraction has shown promising prospects in the practical applications of LLMs, it is still a complex natural language processing task that requires further research.
基金This work was supported by Knowledge Innovation Pro-gram Chinese Academy of Sciences (No. KZCX2-SW-320-3 & KZCX3-SW-425).
文摘Boundary extraction of watershed is an important step in forest landscape research. The boundary of the upriver wa-tershed of the Hunhe River in the sub-alpine Qingyuan County of eastern Liaoning Province, China was extracted by digital elevation modeling (DEM) data in ArcInfo8.1. Remote sensing image of the corresponding region was applied to help modify its copy according to Enhanced Thematic Mapper (ETM) image抯 profuse geomorphological structure information. Both the DEM-dependent boundary and modified copy were overlapped with county map and drainage network map to visually check the effects of result. Overlap of county map suggested a nice extraction of the boundary line since the two layers matched precisely, which indicated the DEM-dependent boundary by program was effective and precise. Further upload of drainage network showed discrepancies between the boundary and the drainage network. Altogether, there were three sections of the extraction result that needed to correct. Compared with this extraction boundary, the modified boundary had a better match to the drainage network as well as to the county map. Comprehensive analysis demonstrated that the program extraction has generally fine precision in position and excels the digitized result by hand. The errors of the DEM-dependant extraction are due to the fact that it is difficult for program to recognize sections of complex landform especially altered by human activities, but these errors are discernable and adjustable because the spatial resolution of ETM image is less than that of DEM. This study result proved that application of remote sensing information could help obtain better result when DEM method is used in extraction of watershed boundary.
文摘A novel parameter extraction method with rational functions is presented for the 2-πequivalent circuit model of RF CMOS spiral inductors. The final S-parameters simulated by the circuit model closely match experimental data. The extraction strategy is straightforward and can be easily implemented as a CAD tool to model spiral inductors. The resulting circuit models will be very useful for RF circuit designers.
基金supported by National Natural Science Foundation of China (Grant No. 50805021)
文摘It is well known that the human auditory system possesses remarkable capabilities to analyze and identify signals. Therefore, it would be significant to build an auditory model based on the mechanism of human auditory systems, which may improve the effects of mechanical signal analysis and enrich the methods of mechanical faults features extraction. However the existing methods are all based on explicit senses of mathematics or physics, and have some shortages on distinguishing different faults, stability, and suppressing the disturbance noise, etc. For the purpose of improving the performances of the work of feature extraction, an auditory model, early auditory（EA） model, is introduced for the first time. This auditory model transforms time domain signal into auditory spectrum via bandpass filtering, nonlinear compressing, and lateral inhibiting by simulating the principle of the human auditory system. The EA model is developed with the Gammatone filterbank as the basilar membrane. According to the characteristics of vibration signals, a method is proposed for determining the parameter of inner hair cells model of EA model. The performance of EA model is evaluated through experiments on four rotor faults, including misalignment, rotor-to-stator rubbing, oil film whirl, and pedestal looseness. The results show that the auditory spectrum, output of EA model, can effectively distinguish different faults with satisfactory stability and has the ability to suppress the disturbance noise. Then, it is feasible to apply auditory model, as a new method, to the feature extraction for mechanical faults diagnosis with effect.
文摘This paper presents an accurate small-signal model for multi-gate GaAs pHEMTs in switching-mode.The extraction method for the proposed model is developed.A 2-gate switch structure is fabricated on a commercial 0.5μm AlGaAs/GaAs pHEMT technology to verify the proposed model.Excellent agreement has been obtained between the measured and simulated results over a wide frequency range.
基金Supported by the National Natural Science Foundation of China（Nos.20176049 and 20576113）
文摘Ultrasonically assisted extraction of isoflavones from the stem of Pueraria lobata （Willd.） Ohwi has been carried out with an ultrasonic extracting apparatus （20kHz, electrical power input to the transducer in 0-650W）. The influence of the electrical power input and extraction time on the＇extraction yield is investigated in water, n-butanol, and 95% （by volume） and 50% （by volume） ethanol aqueous solution. The experimental results indicate that the yields of total isoflavones are higher in ultrasonically assisted extraction than those obtained from con-ventional extraction.Moreover,a mathematical model is proposed,by introducing the electrical power input to index the ultrsound intensity,to describe the behavior of ultrasonically assisted extraction.It is found that the model calcuations are in good agreement with the experimental data.
基金Under the auspices of National Youth Science Foundation of China(No.41001294)Key Project of National Natural Science Foundation of China(No.40930531)Research Fund of State Key Laboratory Resources and Environment Information System(No.2010KF0002SA)
文摘In China′s Loess Plateau area, gully head is the most active zone of a drainage system in gully areas. The differentiation of loess gully head follows geospatial patterns and reflects the process of the loess landform development and evolution of its drainage system to some extent. In this study, the geomorphic meaning, basic characteristics, morphological structure and the basic types of loess gully heads were systematically analysed. Then, the loess gully head′s conceptual model was established, and an extraction method based on Digital Elevation Model(DEM) for loess gully head features and elements was proposed. Through analysing the achieved statistics of loess gully head features, loess gully heads have apparently similar and different characteristics depending on the different loess landforms where they are found. The loess head characteristics reflect their growth period and evolution tendency to a certain degree, and they indirectly represent evolutionary mechanisms. In addition, the loess gully developmental stages and the evolutionary processes can be deduced by using loess gully head characteristics. This study is of great significance for development and improvement of the theoretical system for describing loess gully landforms.
文摘The supercritical carbon dioxide extraction was applied to obtain essential oil from Pogostemon cablin in this work.Effect of extraction parameters including temperature,pressure,extraction time and particle size on extraction yield was investigated,and the response surface methodology with a Box–Behnken Design was used to achieve the optimized extraction conditions.The maximum yield of essential oil was 2.4356%under the conditions of extraction temperature 47°C,pressure 24.5 MPa and extraction time 119 min.Moreover,based on the Brunauer–Emmett–Teller theory of adsorption,a mathematical modeling was performed to correlate the measured data.The model shows a function relationship between extraction yield and time by a simple equation with three significantly adjustable parameters.These model parameters have been optimized through simulated annealing algorithm.The predicted data from the mathematical model show a good agreement with the experimental data of the different extraction parameters.
文摘A sub circuit model for VDMOS is built according to its physical structure.Parameters and formulas describing the device are also derived from this model.Comparing to former results,this model avoids too many technical parameters and simplify the sub circuit efficiently.As a result of numeric computation,this simple model with clear physical conception demonstrates excellent agreements between measured and modeled response (DC error within 5%,AC error within 10%).Such a model is now available for circuit simulation and parameter extraction.
文摘In consideration of the online measurement of the component content in rare earth countercurrent extraction separation process, the soft sensor method based on hybrid modeling was proposed to measure the rare earth component content. The hybrid models were composed of the extraction equilibrium calculation model and the Radial Basis Function (RBF) Neural Network (NN) error compensation model; the parameters of compensation model were optimized by the hierarchical genetic algorithms (HGA). In addition, application experiment research of this proposed method was carried out in the rare earth separation production process of a corporation. The result shows that this method is effective and can realize online measurement for the component content of rare earth in the countercurrent extraction.
