In this paper we discuss policy iteration methods for approximate solution of a finite-state discounted Markov decision problem, with a focus on feature-based aggregation methods and their connection with deep reinfor...In this paper we discuss policy iteration methods for approximate solution of a finite-state discounted Markov decision problem, with a focus on feature-based aggregation methods and their connection with deep reinforcement learning schemes. We introduce features of the states of the original problem, and we formulate a smaller "aggregate" Markov decision problem, whose states relate to the features. We discuss properties and possible implementations of this type of aggregation, including a new approach to approximate policy iteration. In this approach the policy improvement operation combines feature-based aggregation with feature construction using deep neural networks or other calculations. We argue that the cost function of a policy may be approximated much more accurately by the nonlinear function of the features provided by aggregation, than by the linear function of the features provided by neural networkbased reinforcement learning, thereby potentially leading to more effective policy improvement.展开更多
A novel compressing method for video teleconference applications is presented. Semantic-based coding based on human image feature is realized, where human features are adopted as parameters. Model-based coding and the...A novel compressing method for video teleconference applications is presented. Semantic-based coding based on human image feature is realized, where human features are adopted as parameters. Model-based coding and the concept of vector coding are combined with the work on image feature extraction to obtain the result.展开更多
Analyzed the issues of stability of workpiece during clamping and machining. Discussed classification of the stability problem according to the forces acting on the part in the commonly used machining processes; gave ...Analyzed the issues of stability of workpiece during clamping and machining. Discussed classification of the stability problem according to the forces acting on the part in the commonly used machining processes; gave the methods of calculating clamping force and measures to guarantee the stability of workpiece in the feature-based fixture planning design system.展开更多
How to identify topological entities during rebuilding features is a critical problem in Feature-Based Parametric Modeling System (FBPMS). In the article, authors proposes a new coding approach to distinguish differen...How to identify topological entities during rebuilding features is a critical problem in Feature-Based Parametric Modeling System (FBPMS). In the article, authors proposes a new coding approach to distinguish different entities. The coding mechanism is expatiated,and some typical examples are presented. At last, the algorithm of decoding is put forward based on set theory.展开更多
To the editor:The comprehensive exploration of natural products and metabolites is essential for unraveling the complexities of natural drug therapies.Inadequate tracking and separation methods result in increased res...To the editor:The comprehensive exploration of natural products and metabolites is essential for unraveling the complexities of natural drug therapies.Inadequate tracking and separation methods result in increased research costs and reduced scientific output,significantly hindering the healthy advancement of related research fields.Emerging molecular networking(MN)technologies help minimize the redundant discovery of known natural products or metabolites.展开更多
High-speed single-carrier transmission can be achieved by increasing the modulation format cardinality for higher spectral efficiency.However,ultrahigh-order QAM signals are usually more susceptible to various impairm...High-speed single-carrier transmission can be achieved by increasing the modulation format cardinality for higher spectral efficiency.However,ultrahigh-order QAM signals are usually more susceptible to various impairments.Hence,we propose a temporal feature-based memory(TFM)neural network(NN)equalizer to effectively mitigate signals'impairments in ultrahigh-order QAM.The temporal convolutional network is utilized as a feature extraction layer to significantly improve the performance of the bidirectional long short-term memory network.The TFM-NN equalizer was experimentally validated in a probabilistically shaped polarization-division multiplexed 1024/4096-QAM coherent optical transmission system,and raw spectral efficiencies of 16.190 and 21.188 bit/s/Hz have been achieved at normalized generalized mutual information thresholds.展开更多
Detecting faces under occlusion remains a significant challenge in computer vision due to variations caused by masks,sunglasses,and other obstructions.Addressing this issue is crucial for applications such as surveill...Detecting faces under occlusion remains a significant challenge in computer vision due to variations caused by masks,sunglasses,and other obstructions.Addressing this issue is crucial for applications such as surveillance,biometric authentication,and human-computer interaction.This paper provides a comprehensive review of face detection techniques developed to handle occluded faces.Studies are categorized into four main approaches:feature-based,machine learning-based,deep learning-based,and hybrid methods.We analyzed state-of-the-art studies within each category,examining their methodologies,strengths,and limitations based on widely used benchmark datasets,highlighting their adaptability to partial and severe occlusions.The review also identifies key challenges,including dataset diversity,model generalization,and computational efficiency.Our findings reveal that deep learning methods dominate recent studies,benefiting from their ability to extract hierarchical features and handle complex occlusion patterns.More recently,researchers have increasingly explored Transformer-based architectures,such as Vision Transformer(ViT)and Swin Transformer,to further improve detection robustness under challenging occlusion scenarios.In addition,hybrid approaches,which aim to combine traditional andmodern techniques,are emerging as a promising direction for improving robustness.This review provides valuable insights for researchers aiming to develop more robust face detection systems and for practitioners seeking to deploy reliable solutions in real-world,occlusionprone environments.Further improvements and the proposal of broader datasets are required to developmore scalable,robust,and efficient models that can handle complex occlusions in real-world scenarios.展开更多
The utilization of Lactobacillus plantarum(LP)in chili sauce production is well-known for its capacity to enhance product quality and sensory attributes.However,there is still limited knowledge regarding the taste-act...The utilization of Lactobacillus plantarum(LP)in chili sauce production is well-known for its capacity to enhance product quality and sensory attributes.However,there is still limited knowledge regarding the taste-active metabolites in the sauce.To bridge this gap,our study employed metabolomics and webbased computational tools to investigate the dynamic changes of taste-active metabolites during chili sauce fermentation.By leveraging the advantages of the feature-based molecular network(FBMN),we conducted a rapid annotation of metabolites,successfully identifying 205 metabolites,a considerable portion of which were previously unreported.Through the utilization of the Virtual Taste tool,we identified dihydrosphingosine,lactic acid,isoleucine,phytosphingosine,and gluconic acid as potential taste indicators for quality control.Pathway enrichment analysis further supported their primary involvement in key biochemical pathways,including amino acid t RNA biosynthesis,phenylalanine,tyrosine,tryptophan biosynthesis,and sphingolipid metabolism.This investigation provides valuable insights into the underlying mechanisms contributing to the distinctive flavor profile of chili sauce.展开更多
Accurate assessment of blast furnace conditions is a crucial component in the blast furnace control decision-making process.However,most adversarial models in the field currently update the parameters of the label pre...Accurate assessment of blast furnace conditions is a crucial component in the blast furnace control decision-making process.However,most adversarial models in the field currently update the parameters of the label predictor by minimising the objective function while maximising the objective function to update the domain discriminator's parameters.This strategy results in an excessive maximisation of the domain discriminator's loss.To address this,a friendly adversarial training-based tri-training furnace condition diagnosis model was proposed.This model employed a convolutional neural network-long short-term memory-attention mechanism network as a single-view feature extractor and used decision tree methods as three classifiers to compute the cosine similarity between features and representative vectors of each class.During the knowledge transfer process,the classifiers in this model have a specific goal;they not only seek to maximise the entropy of the target domain samples but also aim to minimise the entropy of the target domain samples when they are misclassified,thus resolving the trade-off in traditional models where robustness is improved at the expense of accuracy.Experimental results indicate that the diagnostic accuracy of this model reaches 96%,with an approximately 8%improvement over existing methods due to the inner optimisation approach.This model provides an effective and feasible solution for the efficient monitoring and diagnosis of blast furnace processes.展开更多
The controller in software-defined networking(SDN)acts as strategic point of control for the underlying network.Multiple controllers are available,and every single controller retains a number of features such as the O...The controller in software-defined networking(SDN)acts as strategic point of control for the underlying network.Multiple controllers are available,and every single controller retains a number of features such as the OpenFlow version,clustering,modularity,platform,and partnership support,etc.They are regarded as vital when making a selection among a set of controllers.As such,the selection of the controller becomes a multi-criteria decision making(MCDM)problem with several features.Hence,an increase in this number will increase the computational complexity of the controller selection process.Previously,the selection of controllers based on features has been studied by the researchers.However,the prioritization of features has gotten less attention.Moreover,several features increase the computational complexity of the selection process.In this paper,we propose a mathematical modeling for feature prioritization with analytical network process(ANP)bridge model for SDN controllers.The results indicate that a prioritized features model lead to a reduction in the computational complexity of the selection of SDN controller.In addition,our model generates prioritized features for SDN controllers.展开更多
In recent years, there are many types of semantic similarity measures, which are used to measure the similarity between two concepts. It is necessary to define the differences between the measures, performance, and ev...In recent years, there are many types of semantic similarity measures, which are used to measure the similarity between two concepts. It is necessary to define the differences between the measures, performance, and evaluations. The major contribution of this paper is to choose the best measure among different similarity measures that give us good result with less error rate. The experiment was done on a taxonomy built to measure the semantic distance between two concepts in the health domain, which are represented as nodes in the taxonomy. Similarity measures methods were evaluated relative to human experts’ ratings. Our experiment was applied on the ICD10 taxonomy to determine the similarity value between two concepts. The similarity between 30 pairs of the health domains has been evaluated using different types of semantic similarity measures equations. The experimental results discussed in this paper have shown that the Hoa A. Nguyen and Hisham Al-Mubaid measure has achieved high matching score by the expert’s judgment.展开更多
A unified feature definition is proposed.Feature is form-concentrated,and can be used to model product func- tionalities,assembly relations,and part geometries.The feature model is given and a feature classification i...A unified feature definition is proposed.Feature is form-concentrated,and can be used to model product func- tionalities,assembly relations,and part geometries.The feature model is given and a feature classification is introduced including functional,assembly,structural,and manufacturing features.A prototype modeling system is developed in Pro/ENGINEER that can define the assembly and user-defined form features.展开更多
Die casting process is one of the prime options for m anufacturing precisely dimensioned, sharply defined metal parts. The design of d ie casting dies comprises several stages and entails a large amount of time. Tra d...Die casting process is one of the prime options for m anufacturing precisely dimensioned, sharply defined metal parts. The design of d ie casting dies comprises several stages and entails a large amount of time. Tra ditionally, the different stages of the die design were not integrated but exist as separate entities. Moreover, recurring modifications or even redesigns are r equired due to the complexity in achieving an accurate initial die design. As a result, die design is usually time-consuming and costly with respect to resourc es. The die casting industry will greatly benefit if proper application software are developed that integrates the different die design stages and allows editin g of die design as and when needed. Hence it is imperative to create an integrat ed die design system that shortens the die design time. This paper presents a research that establishes a prototype of an integrated die design system. It is developed using the commercial SolidWorks CAD system and n amed DiWorks. The aim of building the system on a commercial CAD system is to ut ilise the resources and features of the CAD system to speed up the die design pr ocess. DiWorks consists of six distinct modules: Project Manager, Cavity Insert Builder, Gating System Constructor, Die Base Designer, Ejector System Constructo r and Standard Components Library. Through these six modules, the die designer c an create a complete die casting die beginning from a product part model. It is a user-friendly system that allows both experienced and novice die designers to easily accomplish the task of die design. The practical goal of this research is twofold: to develop a system that integra tes the die design process and at the same time facilitates the editing of d ie design during or after the course of the design process. The research approac h includes (i) parametric design, (ii) feature-based design (iii) system modeli ng and implementation. Parametric design deals with variable dimensions as contr ol parameters, and it is an efficient tool for creating models based on paramete rs. Parametric design not only increases the design efficiency, but also makes t he updates and modifications of existing designs easier and faster, since these can be achieved by changing the parameters of the parametric model. Feature-bas ed design is used to design a product with features that are functionally define d by attributes and are geometrically represented by a set of parameters. The re sults of this research will aid the automation of the die design process, thus i mproving the efficiency and quality of, and reducing the cost of die design.展开更多
An advanced edge-based method of feature detection and extraction is developed for object description in digital images. It is useful for the comparison of different images of the same scene in aerial imagery, for des...An advanced edge-based method of feature detection and extraction is developed for object description in digital images. It is useful for the comparison of different images of the same scene in aerial imagery, for describing and recognizing categories, for automatic building extraction and for finding the mutual regions in image matching. The method includes directional filtering and searching for straight edge segments in every direction and scale, taking into account edge gradient signs. Line segments are ordered with respect to their orientation and average gradients in the region in question. These segments are used for the construction of an object descriptor. A hierarchical set of feature descriptors is developed, taking into consideration the proposed straight line segment detector. Comparative performance is evaluated on the noisy model and in real aerial and satellite imagery.展开更多
To make a bridge between engineering information and the geometry of product model, it is crucial to manipulate product model with form features containing high-level engineering information. In recent years much rese...To make a bridge between engineering information and the geometry of product model, it is crucial to manipulate product model with form features containing high-level engineering information. In recent years much research has been undergone in the area of form feature recognition. In many previous works form feature recognition usually starts with a finished CAD model. The shape of a finished model consisted of a number of features is much more complex than that of a single feature. This problem was ignored by many previous works. In this paper a completely context-independed method is provided. In designing the part,. the feature-based model is decomposed into a quasi-feature-based one that can be converted into various context-oriented feature models required by specific context-oriented applications. In order to decompose features into quasi-features which have convex volumes, this paper proposes a method which integrates modelling with decomposition.展开更多
Virtual globes are technologies for visual navigation through a threedimensional,multi-resolution model of the entire planet.Data representations used in virtual globes,however,lack geometric flexibility at high-resol...Virtual globes are technologies for visual navigation through a threedimensional,multi-resolution model of the entire planet.Data representations used in virtual globes,however,lack geometric flexibility at high-resolution levels of the planet-wide terrain surface.This is a problem especially if boundaries between individual geospatial features and the terrain are important.A novel integration of individual polygonal boundaries with a specific multi-resolution representation of the planet-wide terrain is developed in this article.In the preparation stage,the integration relies on an original simplification algorithm applied to the polygonal boundaries between geospatial features and the terrain.Its output is a multiple level-of-detail(LOD)geometry,which can be combined with a known multi-LOD representation of the terrain that uses run-time triangulation.This data representation is suitable for storage in existing database systems,avoids any data redundancy across LODs,and is even independent of the subdivision schema that partitions the planet’s surface for the sake of dealing with LODs.At runtime,a novel reconstruction algorithm stitches geometric parts from different LODs together in a manner that augments the multi-LOD representation of the terrain.Within a certain proximity range from a given position,the method reconstructs a scene that preserves topological relations between the boundaries of geospatial features with the terrain.The method also guarantees that certain nearest proximity to the given position consists of the best geometries that correspond to the original datasets.Such properties of the method close up the gap between a mere exploratory visualization of static,pre-generated models and the models supporting geospatial analysis,which is deemed crucial for applications in Geographic Information Systems,Building Information Modelling and other software industries.A prototype implementation and experiment results that prove this method are also presented.展开更多
Knowledge distillation aims to distill knowledge from teacher networks to train student networks.Distilling intermediate features has attracted much attention in recent years as it can beflexibly applied in variousfiel...Knowledge distillation aims to distill knowledge from teacher networks to train student networks.Distilling intermediate features has attracted much attention in recent years as it can beflexibly applied in variousfields such as image classification,object detection and semantic segmentation.A critical obstacle of feature-based knowledge distillation is the dimension gap between the intermediate features of teacher and student,and plenty of methods have been proposed to resolve this problem.However,these works usually implement feature uniformization in an unsupervised way,lacking guidance to help the student network learn meaningful mapping functions in the uniformization process.Moreover,the dimension uniformization process of the student and teacher network is usually not equivalent as the mapping functions are different.To this end,some factors of the feature are discarded during parametric feature alignment,or some factors are blended in some non-parametric operations.In this paper,we propose a novel semantic-aware knowledge distillation scheme to solve these problems.We build a standalone feature-based classification branch to extract semantic-aware knowledge for better guiding the learning process of the student network.In addition,to avoid the inequivalence of feature uniformization between teacher and student,we design a novel parameter-free self-attention operation that can convert features of different dimensions into vectors of the same length.Experimental results show that the proposed knowledge distillation scheme outperforms existing feature-based distillation methods on the widely used CIFAR-100 and CINIC-10 datasets.展开更多
文摘In this paper we discuss policy iteration methods for approximate solution of a finite-state discounted Markov decision problem, with a focus on feature-based aggregation methods and their connection with deep reinforcement learning schemes. We introduce features of the states of the original problem, and we formulate a smaller "aggregate" Markov decision problem, whose states relate to the features. We discuss properties and possible implementations of this type of aggregation, including a new approach to approximate policy iteration. In this approach the policy improvement operation combines feature-based aggregation with feature construction using deep neural networks or other calculations. We argue that the cost function of a policy may be approximated much more accurately by the nonlinear function of the features provided by aggregation, than by the linear function of the features provided by neural networkbased reinforcement learning, thereby potentially leading to more effective policy improvement.
文摘A novel compressing method for video teleconference applications is presented. Semantic-based coding based on human image feature is realized, where human features are adopted as parameters. Model-based coding and the concept of vector coding are combined with the work on image feature extraction to obtain the result.
文摘Analyzed the issues of stability of workpiece during clamping and machining. Discussed classification of the stability problem according to the forces acting on the part in the commonly used machining processes; gave the methods of calculating clamping force and measures to guarantee the stability of workpiece in the feature-based fixture planning design system.
文摘How to identify topological entities during rebuilding features is a critical problem in Feature-Based Parametric Modeling System (FBPMS). In the article, authors proposes a new coding approach to distinguish different entities. The coding mechanism is expatiated,and some typical examples are presented. At last, the algorithm of decoding is put forward based on set theory.
基金supported by grants from the National Natural Science Foundation of China(82430116 and 82204607)The special fund of Central committee high level Chinese medicine hospital(CZ015-DZMG-LJRC-0014,DZMG-LJRC0013,China)Young Elite Scientists Sponsorship Program by CACM(2023-QNRC2-B18,China).
文摘To the editor:The comprehensive exploration of natural products and metabolites is essential for unraveling the complexities of natural drug therapies.Inadequate tracking and separation methods result in increased research costs and reduced scientific output,significantly hindering the healthy advancement of related research fields.Emerging molecular networking(MN)technologies help minimize the redundant discovery of known natural products or metabolites.
基金supported by the National Key R&D Program of China(No.2020YFB1805805)the National Natural Science Foundation of China(No.62075147)the Suzhou Industry Technological Innovation Projects(No.SYG202348)。
文摘High-speed single-carrier transmission can be achieved by increasing the modulation format cardinality for higher spectral efficiency.However,ultrahigh-order QAM signals are usually more susceptible to various impairments.Hence,we propose a temporal feature-based memory(TFM)neural network(NN)equalizer to effectively mitigate signals'impairments in ultrahigh-order QAM.The temporal convolutional network is utilized as a feature extraction layer to significantly improve the performance of the bidirectional long short-term memory network.The TFM-NN equalizer was experimentally validated in a probabilistically shaped polarization-division multiplexed 1024/4096-QAM coherent optical transmission system,and raw spectral efficiencies of 16.190 and 21.188 bit/s/Hz have been achieved at normalized generalized mutual information thresholds.
基金funded by A’Sharqiyah University,Sultanate of Oman,under Research Project grant number(BFP/RGP/ICT/22/490).
文摘Detecting faces under occlusion remains a significant challenge in computer vision due to variations caused by masks,sunglasses,and other obstructions.Addressing this issue is crucial for applications such as surveillance,biometric authentication,and human-computer interaction.This paper provides a comprehensive review of face detection techniques developed to handle occluded faces.Studies are categorized into four main approaches:feature-based,machine learning-based,deep learning-based,and hybrid methods.We analyzed state-of-the-art studies within each category,examining their methodologies,strengths,and limitations based on widely used benchmark datasets,highlighting their adaptability to partial and severe occlusions.The review also identifies key challenges,including dataset diversity,model generalization,and computational efficiency.Our findings reveal that deep learning methods dominate recent studies,benefiting from their ability to extract hierarchical features and handle complex occlusion patterns.More recently,researchers have increasingly explored Transformer-based architectures,such as Vision Transformer(ViT)and Swin Transformer,to further improve detection robustness under challenging occlusion scenarios.In addition,hybrid approaches,which aim to combine traditional andmodern techniques,are emerging as a promising direction for improving robustness.This review provides valuable insights for researchers aiming to develop more robust face detection systems and for practitioners seeking to deploy reliable solutions in real-world,occlusionprone environments.Further improvements and the proposal of broader datasets are required to developmore scalable,robust,and efficient models that can handle complex occlusions in real-world scenarios.
基金the financial support from Sichuan Technology Development Program,China(2020YFN0056,2021ZHCG0051,2020YFN0094,2021YFN0048,2020YFN0151)the Natural Science Foundation of Sichuan Province(2022NSFSC0105)Pidu 100 Innovative Talents Program(2022)。
文摘The utilization of Lactobacillus plantarum(LP)in chili sauce production is well-known for its capacity to enhance product quality and sensory attributes.However,there is still limited knowledge regarding the taste-active metabolites in the sauce.To bridge this gap,our study employed metabolomics and webbased computational tools to investigate the dynamic changes of taste-active metabolites during chili sauce fermentation.By leveraging the advantages of the feature-based molecular network(FBMN),we conducted a rapid annotation of metabolites,successfully identifying 205 metabolites,a considerable portion of which were previously unreported.Through the utilization of the Virtual Taste tool,we identified dihydrosphingosine,lactic acid,isoleucine,phytosphingosine,and gluconic acid as potential taste indicators for quality control.Pathway enrichment analysis further supported their primary involvement in key biochemical pathways,including amino acid t RNA biosynthesis,phenylalanine,tyrosine,tryptophan biosynthesis,and sphingolipid metabolism.This investigation provides valuable insights into the underlying mechanisms contributing to the distinctive flavor profile of chili sauce.
基金Thanks are given to Hebei Province Innovation Capacity Enhancement Programme Project(23560301D)the Natural Science Foundation of Hebei Province(E2024105036)the Tangshan Talent Funding Project(B202302007).
文摘Accurate assessment of blast furnace conditions is a crucial component in the blast furnace control decision-making process.However,most adversarial models in the field currently update the parameters of the label predictor by minimising the objective function while maximising the objective function to update the domain discriminator's parameters.This strategy results in an excessive maximisation of the domain discriminator's loss.To address this,a friendly adversarial training-based tri-training furnace condition diagnosis model was proposed.This model employed a convolutional neural network-long short-term memory-attention mechanism network as a single-view feature extractor and used decision tree methods as three classifiers to compute the cosine similarity between features and representative vectors of each class.During the knowledge transfer process,the classifiers in this model have a specific goal;they not only seek to maximise the entropy of the target domain samples but also aim to minimise the entropy of the target domain samples when they are misclassified,thus resolving the trade-off in traditional models where robustness is improved at the expense of accuracy.Experimental results indicate that the diagnostic accuracy of this model reaches 96%,with an approximately 8%improvement over existing methods due to the inner optimisation approach.This model provides an effective and feasible solution for the efficient monitoring and diagnosis of blast furnace processes.
基金This research was supported partially by LIG Nex1It was also supported partially by the MSIT(Ministry of Science and ICT),Korea,under the ITRC(Information Technology Research Center)support program(IITP-2021-2018-0-01431)supervised by the IITP(Institute for Information&Communications Technology Planning Evaluation).
文摘The controller in software-defined networking(SDN)acts as strategic point of control for the underlying network.Multiple controllers are available,and every single controller retains a number of features such as the OpenFlow version,clustering,modularity,platform,and partnership support,etc.They are regarded as vital when making a selection among a set of controllers.As such,the selection of the controller becomes a multi-criteria decision making(MCDM)problem with several features.Hence,an increase in this number will increase the computational complexity of the controller selection process.Previously,the selection of controllers based on features has been studied by the researchers.However,the prioritization of features has gotten less attention.Moreover,several features increase the computational complexity of the selection process.In this paper,we propose a mathematical modeling for feature prioritization with analytical network process(ANP)bridge model for SDN controllers.The results indicate that a prioritized features model lead to a reduction in the computational complexity of the selection of SDN controller.In addition,our model generates prioritized features for SDN controllers.
文摘In recent years, there are many types of semantic similarity measures, which are used to measure the similarity between two concepts. It is necessary to define the differences between the measures, performance, and evaluations. The major contribution of this paper is to choose the best measure among different similarity measures that give us good result with less error rate. The experiment was done on a taxonomy built to measure the semantic distance between two concepts in the health domain, which are represented as nodes in the taxonomy. Similarity measures methods were evaluated relative to human experts’ ratings. Our experiment was applied on the ICD10 taxonomy to determine the similarity value between two concepts. The similarity between 30 pairs of the health domains has been evaluated using different types of semantic similarity measures equations. The experimental results discussed in this paper have shown that the Hoa A. Nguyen and Hisham Al-Mubaid measure has achieved high matching score by the expert’s judgment.
文摘A unified feature definition is proposed.Feature is form-concentrated,and can be used to model product func- tionalities,assembly relations,and part geometries.The feature model is given and a feature classification is introduced including functional,assembly,structural,and manufacturing features.A prototype modeling system is developed in Pro/ENGINEER that can define the assembly and user-defined form features.
文摘Die casting process is one of the prime options for m anufacturing precisely dimensioned, sharply defined metal parts. The design of d ie casting dies comprises several stages and entails a large amount of time. Tra ditionally, the different stages of the die design were not integrated but exist as separate entities. Moreover, recurring modifications or even redesigns are r equired due to the complexity in achieving an accurate initial die design. As a result, die design is usually time-consuming and costly with respect to resourc es. The die casting industry will greatly benefit if proper application software are developed that integrates the different die design stages and allows editin g of die design as and when needed. Hence it is imperative to create an integrat ed die design system that shortens the die design time. This paper presents a research that establishes a prototype of an integrated die design system. It is developed using the commercial SolidWorks CAD system and n amed DiWorks. The aim of building the system on a commercial CAD system is to ut ilise the resources and features of the CAD system to speed up the die design pr ocess. DiWorks consists of six distinct modules: Project Manager, Cavity Insert Builder, Gating System Constructor, Die Base Designer, Ejector System Constructo r and Standard Components Library. Through these six modules, the die designer c an create a complete die casting die beginning from a product part model. It is a user-friendly system that allows both experienced and novice die designers to easily accomplish the task of die design. The practical goal of this research is twofold: to develop a system that integra tes the die design process and at the same time facilitates the editing of d ie design during or after the course of the design process. The research approac h includes (i) parametric design, (ii) feature-based design (iii) system modeli ng and implementation. Parametric design deals with variable dimensions as contr ol parameters, and it is an efficient tool for creating models based on paramete rs. Parametric design not only increases the design efficiency, but also makes t he updates and modifications of existing designs easier and faster, since these can be achieved by changing the parameters of the parametric model. Feature-bas ed design is used to design a product with features that are functionally define d by attributes and are geometrically represented by a set of parameters. The re sults of this research will aid the automation of the die design process, thus i mproving the efficiency and quality of, and reducing the cost of die design.
文摘An advanced edge-based method of feature detection and extraction is developed for object description in digital images. It is useful for the comparison of different images of the same scene in aerial imagery, for describing and recognizing categories, for automatic building extraction and for finding the mutual regions in image matching. The method includes directional filtering and searching for straight edge segments in every direction and scale, taking into account edge gradient signs. Line segments are ordered with respect to their orientation and average gradients in the region in question. These segments are used for the construction of an object descriptor. A hierarchical set of feature descriptors is developed, taking into consideration the proposed straight line segment detector. Comparative performance is evaluated on the noisy model and in real aerial and satellite imagery.
文摘To make a bridge between engineering information and the geometry of product model, it is crucial to manipulate product model with form features containing high-level engineering information. In recent years much research has been undergone in the area of form feature recognition. In many previous works form feature recognition usually starts with a finished CAD model. The shape of a finished model consisted of a number of features is much more complex than that of a single feature. This problem was ignored by many previous works. In this paper a completely context-independed method is provided. In designing the part,. the feature-based model is decomposed into a quasi-feature-based one that can be converted into various context-oriented feature models required by specific context-oriented applications. In order to decompose features into quasi-features which have convex volumes, this paper proposes a method which integrates modelling with decomposition.
基金This work has been supported by Charles University Research Centre program UNCE/HUM/018.
文摘Virtual globes are technologies for visual navigation through a threedimensional,multi-resolution model of the entire planet.Data representations used in virtual globes,however,lack geometric flexibility at high-resolution levels of the planet-wide terrain surface.This is a problem especially if boundaries between individual geospatial features and the terrain are important.A novel integration of individual polygonal boundaries with a specific multi-resolution representation of the planet-wide terrain is developed in this article.In the preparation stage,the integration relies on an original simplification algorithm applied to the polygonal boundaries between geospatial features and the terrain.Its output is a multiple level-of-detail(LOD)geometry,which can be combined with a known multi-LOD representation of the terrain that uses run-time triangulation.This data representation is suitable for storage in existing database systems,avoids any data redundancy across LODs,and is even independent of the subdivision schema that partitions the planet’s surface for the sake of dealing with LODs.At runtime,a novel reconstruction algorithm stitches geometric parts from different LODs together in a manner that augments the multi-LOD representation of the terrain.Within a certain proximity range from a given position,the method reconstructs a scene that preserves topological relations between the boundaries of geospatial features with the terrain.The method also guarantees that certain nearest proximity to the given position consists of the best geometries that correspond to the original datasets.Such properties of the method close up the gap between a mere exploratory visualization of static,pre-generated models and the models supporting geospatial analysis,which is deemed crucial for applications in Geographic Information Systems,Building Information Modelling and other software industries.A prototype implementation and experiment results that prove this method are also presented.
基金supported in part by Key-Area Research and Development Program of Guangdong Province(Grant No.2021B0101200001)the National Natural Science Foundation of China(Grant No.62293543)+1 种基金the National Natural Science Foundation of China(Grant No.U21B2048)the Open Research Projects of Zhejiang Lab(Grant No.2019KD0AD01/010).
文摘Knowledge distillation aims to distill knowledge from teacher networks to train student networks.Distilling intermediate features has attracted much attention in recent years as it can beflexibly applied in variousfields such as image classification,object detection and semantic segmentation.A critical obstacle of feature-based knowledge distillation is the dimension gap between the intermediate features of teacher and student,and plenty of methods have been proposed to resolve this problem.However,these works usually implement feature uniformization in an unsupervised way,lacking guidance to help the student network learn meaningful mapping functions in the uniformization process.Moreover,the dimension uniformization process of the student and teacher network is usually not equivalent as the mapping functions are different.To this end,some factors of the feature are discarded during parametric feature alignment,or some factors are blended in some non-parametric operations.In this paper,we propose a novel semantic-aware knowledge distillation scheme to solve these problems.We build a standalone feature-based classification branch to extract semantic-aware knowledge for better guiding the learning process of the student network.In addition,to avoid the inequivalence of feature uniformization between teacher and student,we design a novel parameter-free self-attention operation that can convert features of different dimensions into vectors of the same length.Experimental results show that the proposed knowledge distillation scheme outperforms existing feature-based distillation methods on the widely used CIFAR-100 and CINIC-10 datasets.
