Traditional methods for selecting models in experimental data analysis are susceptible to researcher bias, hindering exploration of alternative explanations and potentially leading to overfitting. The Finite Informati...Traditional methods for selecting models in experimental data analysis are susceptible to researcher bias, hindering exploration of alternative explanations and potentially leading to overfitting. The Finite Information Quantity (FIQ) approach offers a novel solution by acknowledging the inherent limitations in information processing capacity of physical systems. This framework facilitates the development of objective criteria for model selection (comparative uncertainty) and paves the way for a more comprehensive understanding of phenomena through exploring diverse explanations. This work presents a detailed comparison of the FIQ approach with ten established model selection methods, highlighting the advantages and limitations of each. We demonstrate the potential of FIQ to enhance the objectivity and robustness of scientific inquiry through three practical examples: selecting appropriate models for measuring fundamental constants, sound velocity, and underwater electrical discharges. Further research is warranted to explore the full applicability of FIQ across various scientific disciplines.展开更多
An effective model(image to wrinkle, ITW) for garment fitting evaluation is presented. The proposed model is to improve the accuracy of garment fitting evaluation based on dressing image. The ITW model is an objective...An effective model(image to wrinkle, ITW) for garment fitting evaluation is presented. The proposed model is to improve the accuracy of garment fitting evaluation based on dressing image. The ITW model is an objective evaluation model of fitting based on the wrinkle index of dressing image. The ITW model consists of two main steps, the gray curve-fitting(GCF) threshold segmentation algorithm and Canny edge detection algorithm. In the ITW model, three types of wrinkle trends are defined. And the network dressing image is evaluated and simulated by three quantitative indexes: wrinkle number, wrinkle regularity and wrinkle unevenness. Finally, the fitness of three kinds of dress effects(tight, fit and loose) is quantified by objective fitting evaluation model.展开更多
Based on auditory peripheral simulation model, a new Sound Quality Objective Evaluation (SQOE) method is presented,which can be used to model and analyze the impacts of head, shoulder and other parts of human body on ...Based on auditory peripheral simulation model, a new Sound Quality Objective Evaluation (SQOE) method is presented,which can be used to model and analyze the impacts of head, shoulder and other parts of human body on sound wave trans-mission.This method employs the artificial head technique, in which the head related transfer function was taken into account tothe outer ear simulation phase.First, a bionic artificial head was designed as the outer ear model with considering the outersound field in view of theory and physical explanations.Then the auditory peripheral simulation model was built, which mimicsthe physiological functions of the human hearing, simulating the acoustic signal transfer process and conversion mechanismsfrom the free field to the peripheral auditory system.Finally, performance comparison was made between the proposed SQOEmethod and ArtemiS software, and the verifications of subjective and objective related analysis were made.Results show thatthe proposed method was economical, simple, and with good evaluation quality.展开更多
Virtual reality(VR) environment can provide immersive experience to viewers.Under the VR environment, providing a good quality of experience is extremely important.Therefore, in this paper, we present an image quality...Virtual reality(VR) environment can provide immersive experience to viewers.Under the VR environment, providing a good quality of experience is extremely important.Therefore, in this paper, we present an image quality assessment(IQA) study on omnidirectional images. We first build an omnidirectional IQA(OIQA) database, including 16 source images with their corresponding 320 distorted images. We add four commonly encountered distortions. These distortions are JPEG compression, JPEG2000 compression, Gaussian blur, and Gaussian noise. Then we conduct a subjective quality evaluation study in the VR environment based on the OIQA database. Considering that visual attention is more important in VR environment, head and eye movement data are also tracked and collected during the quality rating experiments. The 16 raw and their corresponding distorted images,subjective quality assessment scores, and the head-orientation data and eye-gaze data together constitute the OIQA database. Based on the OIQA database, we test some state-of-the-art full-reference IQA(FR-IQA) measures on equirectangular format or cubic formatomnidirectional images. The results show that applying FR-IQA metrics on cubic format omnidirectional images could improve their performance. The performance of some FR-IQA metrics combining the saliency weight of three different types are also tested based on our database. Some new phenomena different from traditional IQA are observed.展开更多
As two independent problems,scheduling for parts fabrication line and sequencing for mixed-model assembly line have been addressed respectively by many researchers.However,these two problems should be considered simul...As two independent problems,scheduling for parts fabrication line and sequencing for mixed-model assembly line have been addressed respectively by many researchers.However,these two problems should be considered simultaneously to improve the efficiency of the whole fabrication/assembly systems.By far,little research effort is devoted to sequencing problems for mixed-model fabrication/assembly systems.This paper is concerned about the sequencing problems in pull production systems which are composed of one mixed-model assembly line with limited intermediate buffers and two flexible parts fabrication flow lines with identical parallel machines and limited intermediate buffers.Two objectives are considered simultaneously：minimizing the total variation in parts consumption in the assembly line and minimizing the total makespan cost in the fabrication/assembly system.The integrated optimization framework,mathematical models and the method to construct the complete schedules for the fabrication lines according to the production sequences for the first stage in fabrication lines are presented.Since the above problems are non-deterministic polynomial-hard（NP-hard）,a modified multi-objective genetic algorithm is proposed for solving the models,in which a method to generate the production sequences for the fabrication lines from the production sequences for the assembly line and a method to generate the initial population are put forward,new selection,crossover and mutation operators are designed,and Pareto ranking method and sharing function method are employed to evaluate the individuals＇ fitness.The feasibility and efficiency of the multi-objective genetic algorithm is shown by computational comparison with a multi-objective simulated annealing algorithm.The sequencing problems for mixed-model production systems can be solved effectively by the proposed modified multi-objective genetic algorithm.展开更多
Evolutionary algorithm is time-consuming because of the large number of evolutions and much times of finite element analysis, when it is used to optimize the wing structure of a certain high altitude long endurance un...Evolutionary algorithm is time-consuming because of the large number of evolutions and much times of finite element analysis, when it is used to optimize the wing structure of a certain high altitude long endurance unmanned aviation vehicle（UAV）. In order to improve efficiency it is proposed to construct a model management framework to perform the multi-objective optimization design of wing structure. The sufficient accurate approximation models of objective and constraint functions in the wing structure optimization model are built when using the model management framework, therefore in the evolutionary algorithm a number of finite element analyses can he avoided and the satisfactory multi-objective optimization results of the wing structure of the high altitude long endurance UAV are obtained.展开更多
The principal-subordinate hierarchical multi-objective programming model of initial water rights allocation was developed based on the principle of coordinated and sustainable development of different regions and wate...The principal-subordinate hierarchical multi-objective programming model of initial water rights allocation was developed based on the principle of coordinated and sustainable development of different regions and water sectors within a basin. With the precondition of strictly controlling maximum emissions rights, initial water rights were allocated between the first and the second levels of the hierarchy in order to promote fair and coordinated development across different regions of the basin and coordinated and efficient water use across different water sectors, realize the maximum comprehensive benefits to the basin, promote the unity of quantity and quality of initial water rights allocation, and eliminate water conflict across different regions and water sectors. According to interactive decision-making theory, a principal-subordinate hierarchical interactive iterative algorithm based on the satisfaction degree was developed and used to solve the initial water rights allocation model. A case study verified the validity of the model.展开更多
We present a new definition (Evolving Solutions) for Multi-objective Optimization Problem (MOP) to answer the basic question (what's multi-objective optimal solution?) and advance an asynchronous evolutionary mode...We present a new definition (Evolving Solutions) for Multi-objective Optimization Problem (MOP) to answer the basic question (what's multi-objective optimal solution?) and advance an asynchronous evolutionary model (MINT Model) to solve MOPs. The new theory is based on our understanding of the natural evolution and the analysis of the difference between natural evolution and MOP, thus it is not only different from the Converting Optimization but also different from Pareto Optimization. Some tests prove that our new theory may conquer disadvantages of the upper two methods to some extent.展开更多
Knowledge distillation(KD)is an emerging model compression technique for learning compact object detector models.Previous KD often focused solely on distilling from the logits layer or the feature intermediate layers,...Knowledge distillation(KD)is an emerging model compression technique for learning compact object detector models.Previous KD often focused solely on distilling from the logits layer or the feature intermediate layers,which may limit the comprehensive learning of the student network.Additionally,the imbalance between the foreground and background also affects the performance of the model.To address these issues,this paper employs feature-based distillation to enhance the detection performance of the bounding box localization part,and logit-based distillation to improve the detection performance of the category prediction part.Specifically,for the intermediate layer feature distillation,we introduce feature resampling to reduce the risk of the student model merely imitating the teacher model.At the same time,we incorporate a Spatial Attention Mechanism(SAM)to highlight the foreground features learned by the student model.In terms of output layer feature distillation,we divide the traditional distillation targets into target-class objects and non-target-class objects,aiming to improve overall distillation performance.Furthermore,we introduce a one-to-many matching distillation strategy based on Feature Alignment Module(FAM),which further enhances the studentmodel’s feature representation ability,making its feature distribution closer to that of the teacher model,and thus demonstrating superior localization and classification capabilities in object detection tasks.Experimental results demonstrate that our proposedmethodology outperforms conventional distillation techniques in terms of object detecting performance.展开更多
In the calibration of hydrological models, evaluation criteria are explicitly and quantitatively defined as single-or multi-objective functions when utilizing automatic calibration approaches.In most previous studies,...In the calibration of hydrological models, evaluation criteria are explicitly and quantitatively defined as single-or multi-objective functions when utilizing automatic calibration approaches.In most previous studies, there is a general opinion that no single-objective function can represent all important characteristics of even one specific hydrological variable(e.g., streamflow).Thus hydrologists must turn to multi-objective calibration.In this study, we demonstrated that an optimized single-objective function can compromise multi-response modes(i.e., multi-objective functions) of the hydrograph, which is defined as summation of a power function of the absolute error between observed and simulated streamflow with the exponent of power function optimized for specific watersheds.The new objective function was applied to 196 model parameter estimation experiment(MOPEX) watersheds across the eastern United States using the semi-distributed Xinanjiang hydrological model.The optimized exponent value for each watershed was obtained by targeting four popular objective functions focusing on peak flows, low flows, water balance, and flashiness, respectively.Results showed that the optimized single-objective function can achieve a better hydrograph simulation compared to the traditional single-objective function Nash-Sutcliffe efficiency coefficient for most watersheds, and balance high flow part and low flow part of the hydrograph without substantial differences compared to multi-objective calibration.The proposed optimal single-objective function can be practically adopted in the hydrological modeling if the optimal exponent value could be determined a priori according to hydrological/climatic/landscape characteristics in a specific watershed.展开更多
An important decision for policy makers is selecting strategic petroleum reserve sites. However, policy makers may not choose the most suitable and efficient locations for strategic petroleum reserve（SPR） due to the...An important decision for policy makers is selecting strategic petroleum reserve sites. However, policy makers may not choose the most suitable and efficient locations for strategic petroleum reserve（SPR） due to the complexity in the choice of sites. This paper proposes a multi-objective programming model to determine the optimal locations for China＇s SPR storage sites. This model considers not only the minimum response time but also the minimum transportation cost based on a series of reasonable assumptions and constraint conditions. The factors influencing SPR sites are identified to determine potential demand points and candidate storage sites. Estimation and suggestions are made for the selection of China＇s future SPR storage sites based on the results of this model. When the number of petroleum storage sites is less than or equals 25 and the maximum capacity of storage sites is restricted to 10 million tonnes, the model＇s result best fit for the current layout scheme selected thirteen storage sites in four scenarios. Considering the current status of SPR in China,Tianjin, Qingdao, Dalian, Daqing and Zhanjiang, Chengdu,Xi＇an, and Yueyang are suggested to be the candidate locations for the third phase of the construction plan. The locations of petroleum storage sites suggested in this work could be used as a reference for decision makers.展开更多
In this paper, the sugarcane and sugar industry in Thailand is studied. The government determines the sugarcane prices which is based on the two main factors: 1) weight and 2) commercial cane sugar (standard value equ...In this paper, the sugarcane and sugar industry in Thailand is studied. The government determines the sugarcane prices which is based on the two main factors: 1) weight and 2) commercial cane sugar (standard value equal 10 C.C.S.). Usually, the C.C.S. will increase with time and the weight will decrease. The main purpose of this research is to find the optimal harvest time to maximize revenue and minimize gathering cost. The mathematical model is first formulated under the regulations of the Office of the Cane and Sugar Board (OCSB). The -constraints method is then applied to solve the multi-objective mathematical model. The optimal harvest times in the four regions of Thailand (Northern, Central, Eastern, North-Eastern) for crop years 2012/ 13, 2013/14 and 2014/15 are obtained for comparison.展开更多
Active shape models (ASM), consisting of a shape model and a local gray-level appearance model, can be used to locate the objects in images. In original ASM scheme, the model of object′s gray-level variations is base...Active shape models (ASM), consisting of a shape model and a local gray-level appearance model, can be used to locate the objects in images. In original ASM scheme, the model of object′s gray-level variations is based on the assumption of one-dimensional sampling and searching method. In this work a new way to model the gray-level appearance of the objects is explored, using a two-dimensional sampling and searching technique in a rectangular area around each landmark of object shape. The ASM based on this improvement is compared with the original ASM on an identical medical image set for task of spine localization. Experiments demonstrate that the method produces significantly fast, effective, accurate results for spine localization in medical images.展开更多
An object oriented data modelling in computer aided design (CAD) databases is focused. Starting with the discussion of data modelling requirements for CAD applications, appropriate data modelling features are introdu...An object oriented data modelling in computer aided design (CAD) databases is focused. Starting with the discussion of data modelling requirements for CAD applications, appropriate data modelling features are introduced herewith. A feasible approach to select the “best” data model for an application is to analyze the data which has to be stored in the database. A data model is appropriate for modelling a given task if the information of the application environment can be easily mapped to the data model. Thus, the involved data are analyzed and then object oriented data model appropriate for CAD applications are derived. Based on the reviewed object oriented techniques applied in CAD, object oriented data modelling in CAD is addressed in details. At last 3D geometrical data models and implementation of their data model using the object oriented method are presented.展开更多
To improve the agility, dynamics, composability, reusability, and development efficiency restricted by monolithic federation object model （FOM）, a modular FOM is proposed by high level architecture （HLA） evolved p...To improve the agility, dynamics, composability, reusability, and development efficiency restricted by monolithic federation object model （FOM）, a modular FOM is proposed by high level architecture （HLA） evolved product development group. This paper reviews the state-of-the-art of HLA evolved modular FOM. In particular, related concepts, the overall impact on HLA standards, extension principles, and merging processes are discussed. Also permitted and restricted combinations, and merging rules are provided, and the influence on HLA interface specification is given. The comparison between modular FOM and base object model （BOM） is performed to illustrate the importance of their combination. The applications of modular FOM are summarized. Finally, the significance to facilitate compoable simulation both in academia and practice is presented and future directions are pointed out.展开更多
A large number of 3D models are created on computers and available for networks. Some content-based retrieval technologies are indispensable to find out particular data from such anonymous datasets. Though several sha...A large number of 3D models are created on computers and available for networks. Some content-based retrieval technologies are indispensable to find out particular data from such anonymous datasets. Though several shape retrieval technologies have been developed, little attention has been given to the points on human＇s sense and impression （as known as Kansei） in the conventional techniques, In this paper, the authors propose a novel method of shape retrieval based on shape impression of human＇s Kansei. The key to the method is the Gaussian curvature distribution from 3D models as features for shape retrieval. Then it classifies the 3D models by extracted feature and measures similarity among models in storage.展开更多
This paper proposes a method to recognize human-object interactions by modeling context between human actions and interacted objects.Human-object interaction recognition is a challenging task due to severe occlusion b...This paper proposes a method to recognize human-object interactions by modeling context between human actions and interacted objects.Human-object interaction recognition is a challenging task due to severe occlusion between human and objects during the interacting process.Since that human actions and interacted objects provide strong context information,i.e.some actions are usually related to some specific objects,the accuracy of recognition is significantly improved for both of them.Through the proposed method,both global and local temporal features from skeleton sequences are extracted to model human actions.In the meantime,kernel features are utilized to describe interacted objects.Finally,all possible solutions from actions and objects are optimized by modeling the context between them.The results of experiments demonstrate the effectiveness of our method.展开更多
A novel moving object detection method was proposed in order to adapt the difficulties caused by intermittent object motion,thermal and dynamic background sequences.Two groups of complementary Gaussian mixture models ...A novel moving object detection method was proposed in order to adapt the difficulties caused by intermittent object motion,thermal and dynamic background sequences.Two groups of complementary Gaussian mixture models were used.The ghost and real static object could be classified by comparing the similarity of the edge images further.In each group,the multi resolution Gaussian mixture models were used and dual thresholds were applied in every resolution in order to get a complete object mask without much noise.The computational color model was also used to depress illustration variations and light shadows.The proposed method was verified by the public test sequences provided by the IEEE Change Detection Workshop and compared with three state-of-the-art methods.Experimental results demonstrate that the proposed method is better than others for all of the evaluation parameters in intermittent object motion sequences.Four and two in the seven evaluation parameters are better than the others in thermal and dynamic background sequences,respectively.The proposed method shows a relatively good performance,especially for the intermittent object motion sequences.展开更多
Foreground moving object detection is an important process in various computer vision applications such as intelligent visual surveillance, HCI, object-based video compression, etc. One of the most successful moving o...Foreground moving object detection is an important process in various computer vision applications such as intelligent visual surveillance, HCI, object-based video compression, etc. One of the most successful moving object detection algorithms is based on Adaptive Gaussian Mixture Model （AGMM）. Although ACMM-hased object detection shows very good performance with respect to object detection accuracy, AGMM is very complex model requiring lots of floatingpoint arithmetic so that it should pay for expensive computational cost. Thus, direct implementation of the AGMM-based object detection for embedded DSPs without floating-point arithmetic HW support cannot satisfy the real-time processing requirement. This paper presents a novel rcal-time implementation of adaptive Gaussian mixture model-based moving object detection algorithm for fixed-point DSPs. In the proposed implementation, in addition to changes of data types into fixed-point ones, magnification of the Gaussian distribution technique is introduced so that the integer and fixed-point arithmetic can be easily and consistently utilized instead of real nmnher and floatingpoint arithmetic in processing of AGMM algorithm. Experimental results shows that the proposed implementation have a high potential in real-time applications.展开更多
文摘Traditional methods for selecting models in experimental data analysis are susceptible to researcher bias, hindering exploration of alternative explanations and potentially leading to overfitting. The Finite Information Quantity (FIQ) approach offers a novel solution by acknowledging the inherent limitations in information processing capacity of physical systems. This framework facilitates the development of objective criteria for model selection (comparative uncertainty) and paves the way for a more comprehensive understanding of phenomena through exploring diverse explanations. This work presents a detailed comparison of the FIQ approach with ten established model selection methods, highlighting the advantages and limitations of each. We demonstrate the potential of FIQ to enhance the objectivity and robustness of scientific inquiry through three practical examples: selecting appropriate models for measuring fundamental constants, sound velocity, and underwater electrical discharges. Further research is warranted to explore the full applicability of FIQ across various scientific disciplines.
文摘An effective model(image to wrinkle, ITW) for garment fitting evaluation is presented. The proposed model is to improve the accuracy of garment fitting evaluation based on dressing image. The ITW model is an objective evaluation model of fitting based on the wrinkle index of dressing image. The ITW model consists of two main steps, the gray curve-fitting(GCF) threshold segmentation algorithm and Canny edge detection algorithm. In the ITW model, three types of wrinkle trends are defined. And the network dressing image is evaluated and simulated by three quantitative indexes: wrinkle number, wrinkle regularity and wrinkle unevenness. Finally, the fitness of three kinds of dress effects(tight, fit and loose) is quantified by objective fitting evaluation model.
文摘Based on auditory peripheral simulation model, a new Sound Quality Objective Evaluation (SQOE) method is presented,which can be used to model and analyze the impacts of head, shoulder and other parts of human body on sound wave trans-mission.This method employs the artificial head technique, in which the head related transfer function was taken into account tothe outer ear simulation phase.First, a bionic artificial head was designed as the outer ear model with considering the outersound field in view of theory and physical explanations.Then the auditory peripheral simulation model was built, which mimicsthe physiological functions of the human hearing, simulating the acoustic signal transfer process and conversion mechanismsfrom the free field to the peripheral auditory system.Finally, performance comparison was made between the proposed SQOEmethod and ArtemiS software, and the verifications of subjective and objective related analysis were made.Results show thatthe proposed method was economical, simple, and with good evaluation quality.
文摘Virtual reality(VR) environment can provide immersive experience to viewers.Under the VR environment, providing a good quality of experience is extremely important.Therefore, in this paper, we present an image quality assessment(IQA) study on omnidirectional images. We first build an omnidirectional IQA(OIQA) database, including 16 source images with their corresponding 320 distorted images. We add four commonly encountered distortions. These distortions are JPEG compression, JPEG2000 compression, Gaussian blur, and Gaussian noise. Then we conduct a subjective quality evaluation study in the VR environment based on the OIQA database. Considering that visual attention is more important in VR environment, head and eye movement data are also tracked and collected during the quality rating experiments. The 16 raw and their corresponding distorted images,subjective quality assessment scores, and the head-orientation data and eye-gaze data together constitute the OIQA database. Based on the OIQA database, we test some state-of-the-art full-reference IQA(FR-IQA) measures on equirectangular format or cubic formatomnidirectional images. The results show that applying FR-IQA metrics on cubic format omnidirectional images could improve their performance. The performance of some FR-IQA metrics combining the saliency weight of three different types are also tested based on our database. Some new phenomena different from traditional IQA are observed.
基金supported by National Natural Science Foundation of China (Grant No.50875101)National Hi-tech Research and Development Program of China (863 Program,Grant No.2007AA04Z186)
文摘As two independent problems,scheduling for parts fabrication line and sequencing for mixed-model assembly line have been addressed respectively by many researchers.However,these two problems should be considered simultaneously to improve the efficiency of the whole fabrication/assembly systems.By far,little research effort is devoted to sequencing problems for mixed-model fabrication/assembly systems.This paper is concerned about the sequencing problems in pull production systems which are composed of one mixed-model assembly line with limited intermediate buffers and two flexible parts fabrication flow lines with identical parallel machines and limited intermediate buffers.Two objectives are considered simultaneously：minimizing the total variation in parts consumption in the assembly line and minimizing the total makespan cost in the fabrication/assembly system.The integrated optimization framework,mathematical models and the method to construct the complete schedules for the fabrication lines according to the production sequences for the first stage in fabrication lines are presented.Since the above problems are non-deterministic polynomial-hard（NP-hard）,a modified multi-objective genetic algorithm is proposed for solving the models,in which a method to generate the production sequences for the fabrication lines from the production sequences for the assembly line and a method to generate the initial population are put forward,new selection,crossover and mutation operators are designed,and Pareto ranking method and sharing function method are employed to evaluate the individuals＇ fitness.The feasibility and efficiency of the multi-objective genetic algorithm is shown by computational comparison with a multi-objective simulated annealing algorithm.The sequencing problems for mixed-model production systems can be solved effectively by the proposed modified multi-objective genetic algorithm.
文摘Evolutionary algorithm is time-consuming because of the large number of evolutions and much times of finite element analysis, when it is used to optimize the wing structure of a certain high altitude long endurance unmanned aviation vehicle（UAV）. In order to improve efficiency it is proposed to construct a model management framework to perform the multi-objective optimization design of wing structure. The sufficient accurate approximation models of objective and constraint functions in the wing structure optimization model are built when using the model management framework, therefore in the evolutionary algorithm a number of finite element analyses can he avoided and the satisfactory multi-objective optimization results of the wing structure of the high altitude long endurance UAV are obtained.
基金supported by the Public Welfare Industry Special Fund Project of the Ministry of Water Resources of China (Grant No. 200701028)the Humanities and Social Science Foundation Program of Hohai University (Grant No. 2008421411)
文摘The principal-subordinate hierarchical multi-objective programming model of initial water rights allocation was developed based on the principle of coordinated and sustainable development of different regions and water sectors within a basin. With the precondition of strictly controlling maximum emissions rights, initial water rights were allocated between the first and the second levels of the hierarchy in order to promote fair and coordinated development across different regions of the basin and coordinated and efficient water use across different water sectors, realize the maximum comprehensive benefits to the basin, promote the unity of quantity and quality of initial water rights allocation, and eliminate water conflict across different regions and water sectors. According to interactive decision-making theory, a principal-subordinate hierarchical interactive iterative algorithm based on the satisfaction degree was developed and used to solve the initial water rights allocation model. A case study verified the validity of the model.
基金Supported by the National Natural Science Foundation of China(70071042,60073043,60133010)
文摘We present a new definition (Evolving Solutions) for Multi-objective Optimization Problem (MOP) to answer the basic question (what's multi-objective optimal solution?) and advance an asynchronous evolutionary model (MINT Model) to solve MOPs. The new theory is based on our understanding of the natural evolution and the analysis of the difference between natural evolution and MOP, thus it is not only different from the Converting Optimization but also different from Pareto Optimization. Some tests prove that our new theory may conquer disadvantages of the upper two methods to some extent.
基金funded by National Natural Science Foundation of China(61603245).
文摘Knowledge distillation(KD)is an emerging model compression technique for learning compact object detector models.Previous KD often focused solely on distilling from the logits layer or the feature intermediate layers,which may limit the comprehensive learning of the student network.Additionally,the imbalance between the foreground and background also affects the performance of the model.To address these issues,this paper employs feature-based distillation to enhance the detection performance of the bounding box localization part,and logit-based distillation to improve the detection performance of the category prediction part.Specifically,for the intermediate layer feature distillation,we introduce feature resampling to reduce the risk of the student model merely imitating the teacher model.At the same time,we incorporate a Spatial Attention Mechanism(SAM)to highlight the foreground features learned by the student model.In terms of output layer feature distillation,we divide the traditional distillation targets into target-class objects and non-target-class objects,aiming to improve overall distillation performance.Furthermore,we introduce a one-to-many matching distillation strategy based on Feature Alignment Module(FAM),which further enhances the studentmodel’s feature representation ability,making its feature distribution closer to that of the teacher model,and thus demonstrating superior localization and classification capabilities in object detection tasks.Experimental results demonstrate that our proposedmethodology outperforms conventional distillation techniques in terms of object detecting performance.
基金Under the auspices of National Key Research and Development Program of China(No.2016YFC0402701)National Natural Science Foundation of China(No.51825902)
文摘In the calibration of hydrological models, evaluation criteria are explicitly and quantitatively defined as single-or multi-objective functions when utilizing automatic calibration approaches.In most previous studies, there is a general opinion that no single-objective function can represent all important characteristics of even one specific hydrological variable(e.g., streamflow).Thus hydrologists must turn to multi-objective calibration.In this study, we demonstrated that an optimized single-objective function can compromise multi-response modes(i.e., multi-objective functions) of the hydrograph, which is defined as summation of a power function of the absolute error between observed and simulated streamflow with the exponent of power function optimized for specific watersheds.The new objective function was applied to 196 model parameter estimation experiment(MOPEX) watersheds across the eastern United States using the semi-distributed Xinanjiang hydrological model.The optimized exponent value for each watershed was obtained by targeting four popular objective functions focusing on peak flows, low flows, water balance, and flashiness, respectively.Results showed that the optimized single-objective function can achieve a better hydrograph simulation compared to the traditional single-objective function Nash-Sutcliffe efficiency coefficient for most watersheds, and balance high flow part and low flow part of the hydrograph without substantial differences compared to multi-objective calibration.The proposed optimal single-objective function can be practically adopted in the hydrological modeling if the optimal exponent value could be determined a priori according to hydrological/climatic/landscape characteristics in a specific watershed.
基金supported by the National Natural Science Foundation of China (Nos. 71273277/71373285/71303258)the Philosophy and Social Sciences Major Research Project of the Ministry of Education (No. 11JZD048)
文摘An important decision for policy makers is selecting strategic petroleum reserve sites. However, policy makers may not choose the most suitable and efficient locations for strategic petroleum reserve（SPR） due to the complexity in the choice of sites. This paper proposes a multi-objective programming model to determine the optimal locations for China＇s SPR storage sites. This model considers not only the minimum response time but also the minimum transportation cost based on a series of reasonable assumptions and constraint conditions. The factors influencing SPR sites are identified to determine potential demand points and candidate storage sites. Estimation and suggestions are made for the selection of China＇s future SPR storage sites based on the results of this model. When the number of petroleum storage sites is less than or equals 25 and the maximum capacity of storage sites is restricted to 10 million tonnes, the model＇s result best fit for the current layout scheme selected thirteen storage sites in four scenarios. Considering the current status of SPR in China,Tianjin, Qingdao, Dalian, Daqing and Zhanjiang, Chengdu,Xi＇an, and Yueyang are suggested to be the candidate locations for the third phase of the construction plan. The locations of petroleum storage sites suggested in this work could be used as a reference for decision makers.
文摘In this paper, the sugarcane and sugar industry in Thailand is studied. The government determines the sugarcane prices which is based on the two main factors: 1) weight and 2) commercial cane sugar (standard value equal 10 C.C.S.). Usually, the C.C.S. will increase with time and the weight will decrease. The main purpose of this research is to find the optimal harvest time to maximize revenue and minimize gathering cost. The mathematical model is first formulated under the regulations of the Office of the Cane and Sugar Board (OCSB). The -constraints method is then applied to solve the multi-objective mathematical model. The optimal harvest times in the four regions of Thailand (Northern, Central, Eastern, North-Eastern) for crop years 2012/ 13, 2013/14 and 2014/15 are obtained for comparison.
文摘Active shape models (ASM), consisting of a shape model and a local gray-level appearance model, can be used to locate the objects in images. In original ASM scheme, the model of object′s gray-level variations is based on the assumption of one-dimensional sampling and searching method. In this work a new way to model the gray-level appearance of the objects is explored, using a two-dimensional sampling and searching technique in a rectangular area around each landmark of object shape. The ASM based on this improvement is compared with the original ASM on an identical medical image set for task of spine localization. Experiments demonstrate that the method produces significantly fast, effective, accurate results for spine localization in medical images.
文摘An object oriented data modelling in computer aided design (CAD) databases is focused. Starting with the discussion of data modelling requirements for CAD applications, appropriate data modelling features are introduced herewith. A feasible approach to select the “best” data model for an application is to analyze the data which has to be stored in the database. A data model is appropriate for modelling a given task if the information of the application environment can be easily mapped to the data model. Thus, the involved data are analyzed and then object oriented data model appropriate for CAD applications are derived. Based on the reviewed object oriented techniques applied in CAD, object oriented data modelling in CAD is addressed in details. At last 3D geometrical data models and implementation of their data model using the object oriented method are presented.
基金supported by the National Natural Science Foundation of China(6067406960574056).
文摘To improve the agility, dynamics, composability, reusability, and development efficiency restricted by monolithic federation object model （FOM）, a modular FOM is proposed by high level architecture （HLA） evolved product development group. This paper reviews the state-of-the-art of HLA evolved modular FOM. In particular, related concepts, the overall impact on HLA standards, extension principles, and merging processes are discussed. Also permitted and restricted combinations, and merging rules are provided, and the influence on HLA interface specification is given. The comparison between modular FOM and base object model （BOM） is performed to illustrate the importance of their combination. The applications of modular FOM are summarized. Finally, the significance to facilitate compoable simulation both in academia and practice is presented and future directions are pointed out.
文摘A large number of 3D models are created on computers and available for networks. Some content-based retrieval technologies are indispensable to find out particular data from such anonymous datasets. Though several shape retrieval technologies have been developed, little attention has been given to the points on human＇s sense and impression （as known as Kansei） in the conventional techniques, In this paper, the authors propose a novel method of shape retrieval based on shape impression of human＇s Kansei. The key to the method is the Gaussian curvature distribution from 3D models as features for shape retrieval. Then it classifies the 3D models by extracted feature and measures similarity among models in storage.
文摘This paper proposes a method to recognize human-object interactions by modeling context between human actions and interacted objects.Human-object interaction recognition is a challenging task due to severe occlusion between human and objects during the interacting process.Since that human actions and interacted objects provide strong context information,i.e.some actions are usually related to some specific objects,the accuracy of recognition is significantly improved for both of them.Through the proposed method,both global and local temporal features from skeleton sequences are extracted to model human actions.In the meantime,kernel features are utilized to describe interacted objects.Finally,all possible solutions from actions and objects are optimized by modeling the context between them.The results of experiments demonstrate the effectiveness of our method.
基金Project(T201221207)supported by the Fundamental Research Fund for the Central Universities,ChinaProject(2012CB725301)supported by National Basic Research and Development Program,China
文摘A novel moving object detection method was proposed in order to adapt the difficulties caused by intermittent object motion,thermal and dynamic background sequences.Two groups of complementary Gaussian mixture models were used.The ghost and real static object could be classified by comparing the similarity of the edge images further.In each group,the multi resolution Gaussian mixture models were used and dual thresholds were applied in every resolution in order to get a complete object mask without much noise.The computational color model was also used to depress illustration variations and light shadows.The proposed method was verified by the public test sequences provided by the IEEE Change Detection Workshop and compared with three state-of-the-art methods.Experimental results demonstrate that the proposed method is better than others for all of the evaluation parameters in intermittent object motion sequences.Four and two in the seven evaluation parameters are better than the others in thermal and dynamic background sequences,respectively.The proposed method shows a relatively good performance,especially for the intermittent object motion sequences.
基金supported by Soongsil University Research Fund and BK 21 of Korea
文摘Foreground moving object detection is an important process in various computer vision applications such as intelligent visual surveillance, HCI, object-based video compression, etc. One of the most successful moving object detection algorithms is based on Adaptive Gaussian Mixture Model （AGMM）. Although ACMM-hased object detection shows very good performance with respect to object detection accuracy, AGMM is very complex model requiring lots of floatingpoint arithmetic so that it should pay for expensive computational cost. Thus, direct implementation of the AGMM-based object detection for embedded DSPs without floating-point arithmetic HW support cannot satisfy the real-time processing requirement. This paper presents a novel rcal-time implementation of adaptive Gaussian mixture model-based moving object detection algorithm for fixed-point DSPs. In the proposed implementation, in addition to changes of data types into fixed-point ones, magnification of the Gaussian distribution technique is introduced so that the integer and fixed-point arithmetic can be easily and consistently utilized instead of real nmnher and floatingpoint arithmetic in processing of AGMM algorithm. Experimental results shows that the proposed implementation have a high potential in real-time applications.
