The gears of new energy vehicles are required to withstand higher rotational speeds and greater loads,which puts forward higher precision essentials for gear manufacturing.However,machining process parameters can caus...The gears of new energy vehicles are required to withstand higher rotational speeds and greater loads,which puts forward higher precision essentials for gear manufacturing.However,machining process parameters can cause changes in cutting force/heat,resulting in affecting gear machining precision.Therefore,this paper studies the effect of different process parameters on gear machining precision.A multi-objective optimization model is established for the relationship between process parameters and tooth surface deviations,tooth profile deviations,and tooth lead deviations through the cutting speed,feed rate,and cutting depth of the worm wheel gear grinding machine.The response surface method(RSM)is used for experimental design,and the corresponding experimental results and optimal process parameters are obtained.Subsequently,gray relational analysis-principal component analysis(GRA-PCA),particle swarm optimization(PSO),and genetic algorithm-particle swarm optimization(GA-PSO)methods are used to analyze the experimental results and obtain different optimal process parameters.The results show that optimal process parameters obtained by the GRA-PCA,PSO,and GA-PSO methods improve the gear machining precision.Moreover,the gear machining precision obtained by GA-PSO is superior to other methods.展开更多
To assist readers to have a comprehensive understanding, the classical and intelligent methods roundly based on precursory research achievements are summarized in this paper. First, basic conception and description ab...To assist readers to have a comprehensive understanding, the classical and intelligent methods roundly based on precursory research achievements are summarized in this paper. First, basic conception and description about multi-objective (MO) optimization are introduced. Then some definitions and related terminologies are given. Furthermore several MO optimization methods including classical and current intelligent methods are discussed one by one succinctly. Finally evaluations on advantages and disadvantages about these methods are made at the end of the paper.展开更多
Objective speech quality is difficult to be measured without the input reference speech.Mapping methods using data mining are investigated and designed to improve the output-based speech quality assessment algorithm.T...Objective speech quality is difficult to be measured without the input reference speech.Mapping methods using data mining are investigated and designed to improve the output-based speech quality assessment algorithm.The degraded speech is firstly separated into three classes(unvoiced,voiced and silence),and then the consistency measurement between the degraded speech signal and the pre-trained reference model for each class is calculated and mapped to an objective speech quality score using data mining.Fuzzy Gaussian mixture model(GMM)is used to generate the artificial reference model trained on perceptual linear predictive(PLP)features.The mean opinion score(MOS)mapping methods including multivariate non-linear regression(MNLR),fuzzy neural network(FNN)and support vector regression(SVR)are designed and compared with the standard ITU-T P.563 method.Experimental results show that the assessment methods with data mining perform better than ITU-T P.563.Moreover,FNN and SVR are more efficient than MNLR,and FNN performs best with 14.50% increase in the correlation coefficient and 32.76% decrease in the root-mean-square MOS error.展开更多
With the development of automation in smart grids,network reconfiguration is becoming a feasible approach for improving the operation of distribution systems.A novel reconfiguration strategy was presented to get the o...With the development of automation in smart grids,network reconfiguration is becoming a feasible approach for improving the operation of distribution systems.A novel reconfiguration strategy was presented to get the optimal configuration of improving economy of the system,and then identifying the important nodes.In this strategy,the objectives increase the node importance degree and decrease the active power loss subjected to operational constraints.A compound objective function with weight coefficients is formulated to balance the conflict of the objectives.Then a novel quantum particle swarm optimization based on loop switches hierarchical encoded was employed to address the compound objective reconfiguration problem.Its main contribution is the presentation of the hierarchical encoded scheme which is used to generate the population swarm particles of representing only radial connected solutions.Because the candidate solutions are feasible,the search efficiency would improve dramatically during the optimization process without tedious topology verification.To validate the proposed strategy,simulations are carried out on the test systems.The results are compared with other techniques in order to evaluate the performance of the proposed method.展开更多
The decomposition based approach decomposes a multi-objective problem into a series of single objective subproblems, which are optimized along contours towards the ideal point. But non-dominated solutions cannot sprea...The decomposition based approach decomposes a multi-objective problem into a series of single objective subproblems, which are optimized along contours towards the ideal point. But non-dominated solutions cannot spread uniformly, since the Pareto front shows different features, such as concave and convex. To improve the distribution uniformity of non-dominated solutions, a bidirectional decomposition based approach that constructs two search directions is proposed to provide a uniform distribution no matter what features problems have. Since two populations along two search directions show differently on diversity and convergence, an adaptive neighborhood selection approach is presented to choose suitable parents for the offspring generation. In order to avoid the problem of the shrinking search region caused by the close distance of the ideal and nadir points, a reference point update approach is presented. The performance of the proposed algorithm is validated with four state-of-the-art algorithms. Experimental results demonstrate the superiority of the proposed algorithm on all considered test problems.展开更多
China’s first Mars exploration mission is scheduled to be launched in 2020.It aims not only to conduct global and comprehensive exploration of Mars by use of an orbiter but also to carry out in situ observation of ke...China’s first Mars exploration mission is scheduled to be launched in 2020.It aims not only to conduct global and comprehensive exploration of Mars by use of an orbiter but also to carry out in situ observation of key sites on Mars with a rover.This mission focuses on the following studies:topography,geomorphology,geological structure,soil characteristics,water-ice distribution,material composition,atmosphere and ionosphere,surface climate,environmental characteristics,Mars internal structure,and Martian magnetic field.It is comprised of an orbiter,a lander,and a rover equipped with 13 scientific payloads.This article will give an introduction to the mission including mission plan,scientific objectives,scientific payloads,and its recent development progress.展开更多
Risk management of projects is about the real time ev aluation and making of decisions proactively in order to maximize the probabilit y of achieving or surpassing the targets set for project objectives. Project objec...Risk management of projects is about the real time ev aluation and making of decisions proactively in order to maximize the probabilit y of achieving or surpassing the targets set for project objectives. Project objective generally includes three elements: time, cost, quality. Risk occurrin g in the projects will affect these three factors to some various degrees in the end. There are different emphases in each stage and integrated balanced goals b etween the three factors. A large complex engineering project generally consists of several stages each of which has variable objective combinations leading to variable important risks. In order to achieve strategic goals on the schedule under the restriction of lim ited resources, the paper gives the analysis of the so-called risk identificati on-assessment process on the basis of objective orientation. In this paper the set of involved mostly hazards is presented in terms of given objective weight v ector, and so is the model of risk ranking .By reducing the range of risk factor s step by step, risk manager could pay more attention to important ventures and effectively control of them. According to different objective combination at different stages, primary risk f actor sets at different stages are given. With the probability and their various effects to project objectives, evaluation of these sets is made aiming to r educing of the scope of risks and providing decision maker with a better decisio ns support. Successful projects are those, which focus on the relevant business objectives t hroughout the whole process and seek to information integration across project l ife cycle. This paper also introduces the idea of real time process of risk iden tification-assessment and presents a flow chart as a demonstration.展开更多
Multi-modality sensor fusion has emerged as a prevailing trend in 3D object detection tasks.However,existing research predominantly emphasizes the efficient fusion of data from diverse sensors,overlooking the potentia...Multi-modality sensor fusion has emerged as a prevailing trend in 3D object detection tasks.However,existing research predominantly emphasizes the efficient fusion of data from diverse sensors,overlooking the potential severe consequences of calibration failures.In this paper,we present an innovative analysis and prediction of scenarios that could lead to fusion algorithm failures,along with introducing remedial measures to enhance model robustness.Specifically,leveraging our predicted outcomes,we proactively generate similar hazardous scenarios during the model training phase to facilitate generalization capabilities.Subsequently,we introduce a query mechanism during data fusion to identify the appropriate fusion target in the event of miscalibration.Evaluation on the nuScenes dataset demonstrates that our approach can mitigate model instability by up to 90%,and our framework can be seamlessly adapted to other fusion algorithms.展开更多
Bird's-eye-view(BEV)perception is a core technology for autonomous driving systems.However,existing solutions face the dilemma of high costs associated with multimodal methods and limited performance of vision-onl...Bird's-eye-view(BEV)perception is a core technology for autonomous driving systems.However,existing solutions face the dilemma of high costs associated with multimodal methods and limited performance of vision-only approaches.To address this issue,this paper proposes a framework named“a lightweight pure visual BEV perception method based on dual distillation of spatial-temporal knowledge”.This framework innovatively designs a lightweight vision-only student model based on Res Net,which leverages a dual distillation mechanism to learn from a powerful teacher model that integrates temporal information from both image and light detection and ranging(LiDAR)modalities.Specifically,we distill efficient multi-modal feature extraction and spatial fusion capabilities from the BEVFusion model,and distill advanced temporal information fusion and spatiotemporal attention mechanisms from the BEVFormer model.This dual distillation strategy enables the student model to achieve perception performance close to that of multi-modal models without relying on Li DAR.Experimental results on the nu Scenes dataset demonstrate that the proposed model significantly outperforms classical vision-only algorithms,achieves comparable performance to current state-of-the-art vision-only methods on the nu Scenes detection leaderboard in terms of both mean average precision(mAP)and the nu Scenes detection score(NDS)metrics,and exhibits notable advantages in inference computational efficiency.Although the proposed dual-teacher paradigm incurs higher offline training costs compared to single-model approaches,it yields a streamlined and highly efficient student model suitable for resource-constrained real-time deployment.This provides an effective pathway toward low-cost,high-performance autonomous driving perception systems.展开更多
Cucumber is one of the most important vegetables and economic crops in the world.The occurrence of fungal diseases in cucumbers seriously threatens the safety of cucumber production,with powdery mildew being one of th...Cucumber is one of the most important vegetables and economic crops in the world.The occurrence of fungal diseases in cucumbers seriously threatens the safety of cucumber production,with powdery mildew being one of the most common fungal diseases.With the rapid development of computer technology,more and more deep learning algorithms are being applied to identify powdery mildew fungus.However,existing algorithms suffer from low accuracy in recognizing small and occluded targets,as well as insufficient localization precision.To address this issue,the parallelized patch-aware attention(PPA)module was firstly introduced into the backbone network of YOLO v8s.By employing a parallel multi-branch structure and attention mechanism,it effectively captured multi-scale features of small targets,preserved critical information during multiple downsampling processes,and enhanced the performance of small target detection.Additionally,the global-to-local spatial aggregation(GLSA)module was introduced into the neck,which combined global contextual information with local detail features,significantly improving the model’s feature representation capability.This module enhanced the detection performance for small targets and complex scenes by better capturing multi-scale features.Experimental results showed that PG-YOLO v8s significantly improved powdery mildew fungus detection performance compared with YOLO v8s.The network achieved high precision in detecting powdery mildew fungus,with notable improvements in the detection accuracy of small and occluded targets.The research result can provide a high-throughput method for detecting powdery mildew fungus,enabling precise early detection and guiding early intelligent decision-making in cucumber production.This approach can help to improve disease control efficiency,ensure cucumber yield and quality,and it was of great significance for the sustainable development of agricultural production.展开更多
To address the challenges of low detection accuracy caused by the diverse species,significant size variations,and complex growth environments of wheat pests in natural settings,a PSA-YOLO11n algorithm is proposed to e...To address the challenges of low detection accuracy caused by the diverse species,significant size variations,and complex growth environments of wheat pests in natural settings,a PSA-YOLO11n algorithm is proposed to enhance detection precision.Building upon the YOLO11n framework,the proposed improvements include three key components:1)SimCSPSPPF in Backbone:An improved Spatial Pyramid Pooling-Fast(SPPF)module,SimCSPSPPF,is integrated into the Backbone to reduce the number of channels in the hidden layers,thereby accelerating model training.2)PEC in Neck:The standard convolution layers in the Neck are replaced with Perception Enhancement Convolutions(PEC)to improve multi-scale feature extraction capabilities,enhancing detection speed.3)AWIoU Loss Function:The regression loss function is replaced with Adequate Wise IoU(AWIoU),addressing issues of bounding box distortion caused by the diversity in pest species and size variations,thereby improving the precision of bounding box localization.Experimental evaluations on the IP102 dataset demonstrate that PSA-YOLO11n achieves a mean Average Precision(mAP)of 89.10%,surpassing YOLO11n by 0.8%.Comparisons with other mainstream algorithms,including Faster R-CNN,RetinaNet,YOLOv5s,YOLOv8n,YOLOv10n,and YOLO11n,confirm that PSA-YOLO11n outperforms all baselines in terms of detection performance.These results highlight the algorithm’s capability to significantly improve the detection accuracy of multi-scale wheat pests in natural environments,providing an effective solution for pest management in wheat production.展开更多
Lunar impact crater detection is crucial for lunar surface studies and spacecraft landing missions,yet deep learning still struggles with accurately detecting small craters,especially when relying on incomplete catalo...Lunar impact crater detection is crucial for lunar surface studies and spacecraft landing missions,yet deep learning still struggles with accurately detecting small craters,especially when relying on incomplete catalogs.In this work,we integrate Digital Elevation Model(DEM)data to construct a high-quality dataset enriched with slope information,enabling a detailed analysis of crater features and effectively improving detection performance in complex terrains and low-contrast areas.Based on this foundation,we propose a novel two-stage detection network,MSFNet,which leverages multi-scale adaptive feature fusion and multisize ROI pooling to enhance the recognition of craters across various scales.Experimental results demonstrate that MSFNet achieves an F1 score of 74.8%on Test Region1 and a recall rate of 87%for craters with diameters larger than 2 km.Moreover,it shows exceptional performance in detecting sub-kilometer craters by successfully identifying a large number of high-confidence,previously unlabeled targets with a low false detection rate confirmed through manual review.This approach offers an efficient and reliable deep learning solution for lunar impact crater detection.展开更多
Objective Autism spectrum disorder(ASD)is a neurodevelopmental condition characterized by difficulties with communication and social interaction,restricted and repetitive behaviors.Previous studies have indicated that...Objective Autism spectrum disorder(ASD)is a neurodevelopmental condition characterized by difficulties with communication and social interaction,restricted and repetitive behaviors.Previous studies have indicated that individuals with ASD exhibit early and lifelong attention deficits,which are closely related to the core symptoms of ASD.Basic visual attention processes may provide a critical foundation for their social communication and interaction abilities.Therefore,this study explores the behavior of children with ASD in capturing attention to changes in topological properties.Methods Our study recruited twenty-seven ASD children diagnosed by professional clinicians according to DSM-5 and twenty-eight typically developing(TD)age-matched controls.In an attention capture task,we recorded the saccadic behaviors of children with ASD and TD in response to topological change(TC)and non-topological change(nTC)stimuli.Saccadic reaction time(SRT),visual search time(VS),and first fixation dwell time(FFDT)were used as indicators of attentional bias.Pearson correlation tests between the clinical assessment scales and attentional bias were conducted.Results This study found that TD children had significantly faster SRT(P<0.05)and VS(P<0.05)for the TC stimuli compared to the nTC stimuli,while the children with ASD did not exhibit significant differences in either measure(P>0.05).Additionally,ASD children demonstrated significantly less attention towards the TC targets(measured by FFDT),in comparison to TD children(P<0.05).Furthermore,ASD children exhibited a significant negative linear correlation between their attentional bias(measured by VS)and their scores on the compulsive subscale(P<0.05).Conclusion The results suggest that children with ASD have difficulty shifting their attention to objects with topological changes during change detection.This atypical attention may affect the child’s cognitive and behavioral development,thereby impacting their social communication and interaction.In sum,our findings indicate that difficulties in attentional capture by TC may be a key feature of ASD.展开更多
The subcortical visual pathway is generally thought to be involved in dangerous information processing,such as fear processing and defensive behavior.A recent study,published in Human Brain Mapping,shows a new functio...The subcortical visual pathway is generally thought to be involved in dangerous information processing,such as fear processing and defensive behavior.A recent study,published in Human Brain Mapping,shows a new function of the subcortical pathway involved in the fast processing of non-emotional object perception.Rapid object processing is a critical function of visual system.Topological perception theory proposes that the initial perception of objects begins with the extraction of topological property(TP).However,the mechanism of rapid TP processing remains unclear.The researchers investigated the subcortical mechanism of TP processing with transcranial magnetic stimulation(TMS).They find that a subcortical magnocellular pathway is responsible for the early processing of TP,and this subcortical processing of TP accelerates object recognition.Based on their findings,we propose a novel training approach called subcortical magnocellular pathway training(SMPT),aimed at improving the efficiency of the subcortical M pathway to restore visual and attentional functions in disorders associated with subcortical pathway dysfunction.展开更多
To investigate the applicability of four commonly used color difference formulas(CIELAB,CIE94,CMC(1:1),and CIEDE2000)in the printing field on 3D objects,as well as the impact of four standard light sources(D65,D50,A,a...To investigate the applicability of four commonly used color difference formulas(CIELAB,CIE94,CMC(1:1),and CIEDE2000)in the printing field on 3D objects,as well as the impact of four standard light sources(D65,D50,A,and TL84)on 3D color difference evaluations,50 glossy spheres with a diameter of 2cm based on the Sailner J4003D color printing device were created.These spheres were centered around the five recommended colors(gray,red,yellow,green,and blue)by CIE.Color difference was calculated according to the four formulas,and 111 pairs of experimental samples meeting the CIELAB gray scale color difference requirements(1.0-14.0)were selected.Ten observers,aged between 22 and 27 with normal color vision,were participated in this study,using the gray scale method from psychophysical experiments to conduct color difference evaluations under the four light sources,with repeated experiments for each observer.The results indicated that the overall effect of the D65 light source on 3D objects color difference was minimal.In contrast,D50 and A light sources had a significant impact within the small color difference range,while the TL84 light source influenced both large and small color difference considerably.Among the four color difference formulas,CIEDE2000 demonstrated the best predictive performance for color difference in 3D objects,followed by CMC(1:1),CIE94,and CIELAB.展开更多
Accurate segmentation of camouflage objects in aerial imagery is vital for improving the efficiency of UAV-based reconnaissance and rescue missions.However,camouflage object segmentation is increasingly challenging du...Accurate segmentation of camouflage objects in aerial imagery is vital for improving the efficiency of UAV-based reconnaissance and rescue missions.However,camouflage object segmentation is increasingly challenging due to advances in both camouflage materials and biological mimicry.Although multispectral-RGB based technology shows promise,conventional dual-aperture multispectral-RGB imaging systems are constrained by imprecise and time-consuming registration and fusion across different modalities,limiting their performance.Here,we propose the Reconstructed Multispectral-RGB Fusion Network(RMRF-Net),which reconstructs RGB images into multispectral ones,enabling efficient multimodal segmentation using only an RGB camera.Specifically,RMRF-Net employs a divergentsimilarity feature correction strategy to minimize reconstruction errors and includes an efficient boundary-aware decoder to enhance object contours.Notably,we establish the first real-world aerial multispectral-RGB semantic segmentation of camouflage objects dataset,including 11 object categories.Experimental results demonstrate that RMRF-Net outperforms existing methods,achieving 17.38 FPS on the NVIDIA Jetson AGX Orin,with only a 0.96%drop in mIoU compared to the RTX 3090,showing its practical applicability in multimodal remote sensing.展开更多
基金Projects(U22B2084,52275483,52075142)supported by the National Natural Science Foundation of ChinaProject(2023ZY01050)supported by the Ministry of Industry and Information Technology High Quality Development,China。
文摘The gears of new energy vehicles are required to withstand higher rotational speeds and greater loads,which puts forward higher precision essentials for gear manufacturing.However,machining process parameters can cause changes in cutting force/heat,resulting in affecting gear machining precision.Therefore,this paper studies the effect of different process parameters on gear machining precision.A multi-objective optimization model is established for the relationship between process parameters and tooth surface deviations,tooth profile deviations,and tooth lead deviations through the cutting speed,feed rate,and cutting depth of the worm wheel gear grinding machine.The response surface method(RSM)is used for experimental design,and the corresponding experimental results and optimal process parameters are obtained.Subsequently,gray relational analysis-principal component analysis(GRA-PCA),particle swarm optimization(PSO),and genetic algorithm-particle swarm optimization(GA-PSO)methods are used to analyze the experimental results and obtain different optimal process parameters.The results show that optimal process parameters obtained by the GRA-PCA,PSO,and GA-PSO methods improve the gear machining precision.Moreover,the gear machining precision obtained by GA-PSO is superior to other methods.
文摘To assist readers to have a comprehensive understanding, the classical and intelligent methods roundly based on precursory research achievements are summarized in this paper. First, basic conception and description about multi-objective (MO) optimization are introduced. Then some definitions and related terminologies are given. Furthermore several MO optimization methods including classical and current intelligent methods are discussed one by one succinctly. Finally evaluations on advantages and disadvantages about these methods are made at the end of the paper.
基金Projects(61001188,1161140319)supported by the National Natural Science Foundation of ChinaProject(2012ZX03001034)supported by the National Science and Technology Major ProjectProject(YETP1202)supported by Beijing Higher Education Young Elite Teacher Project,China
文摘Objective speech quality is difficult to be measured without the input reference speech.Mapping methods using data mining are investigated and designed to improve the output-based speech quality assessment algorithm.The degraded speech is firstly separated into three classes(unvoiced,voiced and silence),and then the consistency measurement between the degraded speech signal and the pre-trained reference model for each class is calculated and mapped to an objective speech quality score using data mining.Fuzzy Gaussian mixture model(GMM)is used to generate the artificial reference model trained on perceptual linear predictive(PLP)features.The mean opinion score(MOS)mapping methods including multivariate non-linear regression(MNLR),fuzzy neural network(FNN)and support vector regression(SVR)are designed and compared with the standard ITU-T P.563 method.Experimental results show that the assessment methods with data mining perform better than ITU-T P.563.Moreover,FNN and SVR are more efficient than MNLR,and FNN performs best with 14.50% increase in the correlation coefficient and 32.76% decrease in the root-mean-square MOS error.
基金Project(61102039)supported by the National Natural Science Foundation of ChinaProject(2014AA052600)supported by National Hi-tech Research and Development Plan,China
文摘With the development of automation in smart grids,network reconfiguration is becoming a feasible approach for improving the operation of distribution systems.A novel reconfiguration strategy was presented to get the optimal configuration of improving economy of the system,and then identifying the important nodes.In this strategy,the objectives increase the node importance degree and decrease the active power loss subjected to operational constraints.A compound objective function with weight coefficients is formulated to balance the conflict of the objectives.Then a novel quantum particle swarm optimization based on loop switches hierarchical encoded was employed to address the compound objective reconfiguration problem.Its main contribution is the presentation of the hierarchical encoded scheme which is used to generate the population swarm particles of representing only radial connected solutions.Because the candidate solutions are feasible,the search efficiency would improve dramatically during the optimization process without tedious topology verification.To validate the proposed strategy,simulations are carried out on the test systems.The results are compared with other techniques in order to evaluate the performance of the proposed method.
文摘The decomposition based approach decomposes a multi-objective problem into a series of single objective subproblems, which are optimized along contours towards the ideal point. But non-dominated solutions cannot spread uniformly, since the Pareto front shows different features, such as concave and convex. To improve the distribution uniformity of non-dominated solutions, a bidirectional decomposition based approach that constructs two search directions is proposed to provide a uniform distribution no matter what features problems have. Since two populations along two search directions show differently on diversity and convergence, an adaptive neighborhood selection approach is presented to choose suitable parents for the offspring generation. In order to avoid the problem of the shrinking search region caused by the close distance of the ideal and nadir points, a reference point update approach is presented. The performance of the proposed algorithm is validated with four state-of-the-art algorithms. Experimental results demonstrate the superiority of the proposed algorithm on all considered test problems.
基金Supported by the Major Program of the National Science Foundation of China(41590851)the Beijing Municipal Science and Technology Commission(Z181100002918003)。
文摘China’s first Mars exploration mission is scheduled to be launched in 2020.It aims not only to conduct global and comprehensive exploration of Mars by use of an orbiter but also to carry out in situ observation of key sites on Mars with a rover.This mission focuses on the following studies:topography,geomorphology,geological structure,soil characteristics,water-ice distribution,material composition,atmosphere and ionosphere,surface climate,environmental characteristics,Mars internal structure,and Martian magnetic field.It is comprised of an orbiter,a lander,and a rover equipped with 13 scientific payloads.This article will give an introduction to the mission including mission plan,scientific objectives,scientific payloads,and its recent development progress.
文摘Risk management of projects is about the real time ev aluation and making of decisions proactively in order to maximize the probabilit y of achieving or surpassing the targets set for project objectives. Project objective generally includes three elements: time, cost, quality. Risk occurrin g in the projects will affect these three factors to some various degrees in the end. There are different emphases in each stage and integrated balanced goals b etween the three factors. A large complex engineering project generally consists of several stages each of which has variable objective combinations leading to variable important risks. In order to achieve strategic goals on the schedule under the restriction of lim ited resources, the paper gives the analysis of the so-called risk identificati on-assessment process on the basis of objective orientation. In this paper the set of involved mostly hazards is presented in terms of given objective weight v ector, and so is the model of risk ranking .By reducing the range of risk factor s step by step, risk manager could pay more attention to important ventures and effectively control of them. According to different objective combination at different stages, primary risk f actor sets at different stages are given. With the probability and their various effects to project objectives, evaluation of these sets is made aiming to r educing of the scope of risks and providing decision maker with a better decisio ns support. Successful projects are those, which focus on the relevant business objectives t hroughout the whole process and seek to information integration across project l ife cycle. This paper also introduces the idea of real time process of risk iden tification-assessment and presents a flow chart as a demonstration.
文摘Multi-modality sensor fusion has emerged as a prevailing trend in 3D object detection tasks.However,existing research predominantly emphasizes the efficient fusion of data from diverse sensors,overlooking the potential severe consequences of calibration failures.In this paper,we present an innovative analysis and prediction of scenarios that could lead to fusion algorithm failures,along with introducing remedial measures to enhance model robustness.Specifically,leveraging our predicted outcomes,we proactively generate similar hazardous scenarios during the model training phase to facilitate generalization capabilities.Subsequently,we introduce a query mechanism during data fusion to identify the appropriate fusion target in the event of miscalibration.Evaluation on the nuScenes dataset demonstrates that our approach can mitigate model instability by up to 90%,and our framework can be seamlessly adapted to other fusion algorithms.
基金supported by the National Natural Science Foundation of China(42476084,62203456,42276199)the Stable Support Project of National Key Laboratory(WDZC 20245250302)the National Key R&D Program of China(2024YFC2813502,2024YFC2813302)。
文摘Bird's-eye-view(BEV)perception is a core technology for autonomous driving systems.However,existing solutions face the dilemma of high costs associated with multimodal methods and limited performance of vision-only approaches.To address this issue,this paper proposes a framework named“a lightweight pure visual BEV perception method based on dual distillation of spatial-temporal knowledge”.This framework innovatively designs a lightweight vision-only student model based on Res Net,which leverages a dual distillation mechanism to learn from a powerful teacher model that integrates temporal information from both image and light detection and ranging(LiDAR)modalities.Specifically,we distill efficient multi-modal feature extraction and spatial fusion capabilities from the BEVFusion model,and distill advanced temporal information fusion and spatiotemporal attention mechanisms from the BEVFormer model.This dual distillation strategy enables the student model to achieve perception performance close to that of multi-modal models without relying on Li DAR.Experimental results on the nu Scenes dataset demonstrate that the proposed model significantly outperforms classical vision-only algorithms,achieves comparable performance to current state-of-the-art vision-only methods on the nu Scenes detection leaderboard in terms of both mean average precision(mAP)and the nu Scenes detection score(NDS)metrics,and exhibits notable advantages in inference computational efficiency.Although the proposed dual-teacher paradigm incurs higher offline training costs compared to single-model approaches,it yields a streamlined and highly efficient student model suitable for resource-constrained real-time deployment.This provides an effective pathway toward low-cost,high-performance autonomous driving perception systems.
文摘Cucumber is one of the most important vegetables and economic crops in the world.The occurrence of fungal diseases in cucumbers seriously threatens the safety of cucumber production,with powdery mildew being one of the most common fungal diseases.With the rapid development of computer technology,more and more deep learning algorithms are being applied to identify powdery mildew fungus.However,existing algorithms suffer from low accuracy in recognizing small and occluded targets,as well as insufficient localization precision.To address this issue,the parallelized patch-aware attention(PPA)module was firstly introduced into the backbone network of YOLO v8s.By employing a parallel multi-branch structure and attention mechanism,it effectively captured multi-scale features of small targets,preserved critical information during multiple downsampling processes,and enhanced the performance of small target detection.Additionally,the global-to-local spatial aggregation(GLSA)module was introduced into the neck,which combined global contextual information with local detail features,significantly improving the model’s feature representation capability.This module enhanced the detection performance for small targets and complex scenes by better capturing multi-scale features.Experimental results showed that PG-YOLO v8s significantly improved powdery mildew fungus detection performance compared with YOLO v8s.The network achieved high precision in detecting powdery mildew fungus,with notable improvements in the detection accuracy of small and occluded targets.The research result can provide a high-throughput method for detecting powdery mildew fungus,enabling precise early detection and guiding early intelligent decision-making in cucumber production.This approach can help to improve disease control efficiency,ensure cucumber yield and quality,and it was of great significance for the sustainable development of agricultural production.
文摘To address the challenges of low detection accuracy caused by the diverse species,significant size variations,and complex growth environments of wheat pests in natural settings,a PSA-YOLO11n algorithm is proposed to enhance detection precision.Building upon the YOLO11n framework,the proposed improvements include three key components:1)SimCSPSPPF in Backbone:An improved Spatial Pyramid Pooling-Fast(SPPF)module,SimCSPSPPF,is integrated into the Backbone to reduce the number of channels in the hidden layers,thereby accelerating model training.2)PEC in Neck:The standard convolution layers in the Neck are replaced with Perception Enhancement Convolutions(PEC)to improve multi-scale feature extraction capabilities,enhancing detection speed.3)AWIoU Loss Function:The regression loss function is replaced with Adequate Wise IoU(AWIoU),addressing issues of bounding box distortion caused by the diversity in pest species and size variations,thereby improving the precision of bounding box localization.Experimental evaluations on the IP102 dataset demonstrate that PSA-YOLO11n achieves a mean Average Precision(mAP)of 89.10%,surpassing YOLO11n by 0.8%.Comparisons with other mainstream algorithms,including Faster R-CNN,RetinaNet,YOLOv5s,YOLOv8n,YOLOv10n,and YOLO11n,confirm that PSA-YOLO11n outperforms all baselines in terms of detection performance.These results highlight the algorithm’s capability to significantly improve the detection accuracy of multi-scale wheat pests in natural environments,providing an effective solution for pest management in wheat production.
基金National Natural Science Foundation of China(12103020,12363009)Natural Science Foundation of Jiangxi Province(20224BAB211011)+1 种基金Open Project Program of State Key Laboratory of Lunar and Planetary Sciences(Macao University of Science and Technology)(Macao FDCT grant No.002/2024/SKL)Youth Talent Project of Science and Technology Plan of Ganzhou(2022CXRC9191,2023CYZ26970)。
文摘Lunar impact crater detection is crucial for lunar surface studies and spacecraft landing missions,yet deep learning still struggles with accurately detecting small craters,especially when relying on incomplete catalogs.In this work,we integrate Digital Elevation Model(DEM)data to construct a high-quality dataset enriched with slope information,enabling a detailed analysis of crater features and effectively improving detection performance in complex terrains and low-contrast areas.Based on this foundation,we propose a novel two-stage detection network,MSFNet,which leverages multi-scale adaptive feature fusion and multisize ROI pooling to enhance the recognition of craters across various scales.Experimental results demonstrate that MSFNet achieves an F1 score of 74.8%on Test Region1 and a recall rate of 87%for craters with diameters larger than 2 km.Moreover,it shows exceptional performance in detecting sub-kilometer craters by successfully identifying a large number of high-confidence,previously unlabeled targets with a low false detection rate confirmed through manual review.This approach offers an efficient and reliable deep learning solution for lunar impact crater detection.
文摘Objective Autism spectrum disorder(ASD)is a neurodevelopmental condition characterized by difficulties with communication and social interaction,restricted and repetitive behaviors.Previous studies have indicated that individuals with ASD exhibit early and lifelong attention deficits,which are closely related to the core symptoms of ASD.Basic visual attention processes may provide a critical foundation for their social communication and interaction abilities.Therefore,this study explores the behavior of children with ASD in capturing attention to changes in topological properties.Methods Our study recruited twenty-seven ASD children diagnosed by professional clinicians according to DSM-5 and twenty-eight typically developing(TD)age-matched controls.In an attention capture task,we recorded the saccadic behaviors of children with ASD and TD in response to topological change(TC)and non-topological change(nTC)stimuli.Saccadic reaction time(SRT),visual search time(VS),and first fixation dwell time(FFDT)were used as indicators of attentional bias.Pearson correlation tests between the clinical assessment scales and attentional bias were conducted.Results This study found that TD children had significantly faster SRT(P<0.05)and VS(P<0.05)for the TC stimuli compared to the nTC stimuli,while the children with ASD did not exhibit significant differences in either measure(P>0.05).Additionally,ASD children demonstrated significantly less attention towards the TC targets(measured by FFDT),in comparison to TD children(P<0.05).Furthermore,ASD children exhibited a significant negative linear correlation between their attentional bias(measured by VS)and their scores on the compulsive subscale(P<0.05).Conclusion The results suggest that children with ASD have difficulty shifting their attention to objects with topological changes during change detection.This atypical attention may affect the child’s cognitive and behavioral development,thereby impacting their social communication and interaction.In sum,our findings indicate that difficulties in attentional capture by TC may be a key feature of ASD.
文摘The subcortical visual pathway is generally thought to be involved in dangerous information processing,such as fear processing and defensive behavior.A recent study,published in Human Brain Mapping,shows a new function of the subcortical pathway involved in the fast processing of non-emotional object perception.Rapid object processing is a critical function of visual system.Topological perception theory proposes that the initial perception of objects begins with the extraction of topological property(TP).However,the mechanism of rapid TP processing remains unclear.The researchers investigated the subcortical mechanism of TP processing with transcranial magnetic stimulation(TMS).They find that a subcortical magnocellular pathway is responsible for the early processing of TP,and this subcortical processing of TP accelerates object recognition.Based on their findings,we propose a novel training approach called subcortical magnocellular pathway training(SMPT),aimed at improving the efficiency of the subcortical M pathway to restore visual and attentional functions in disorders associated with subcortical pathway dysfunction.
文摘To investigate the applicability of four commonly used color difference formulas(CIELAB,CIE94,CMC(1:1),and CIEDE2000)in the printing field on 3D objects,as well as the impact of four standard light sources(D65,D50,A,and TL84)on 3D color difference evaluations,50 glossy spheres with a diameter of 2cm based on the Sailner J4003D color printing device were created.These spheres were centered around the five recommended colors(gray,red,yellow,green,and blue)by CIE.Color difference was calculated according to the four formulas,and 111 pairs of experimental samples meeting the CIELAB gray scale color difference requirements(1.0-14.0)were selected.Ten observers,aged between 22 and 27 with normal color vision,were participated in this study,using the gray scale method from psychophysical experiments to conduct color difference evaluations under the four light sources,with repeated experiments for each observer.The results indicated that the overall effect of the D65 light source on 3D objects color difference was minimal.In contrast,D50 and A light sources had a significant impact within the small color difference range,while the TL84 light source influenced both large and small color difference considerably.Among the four color difference formulas,CIEDE2000 demonstrated the best predictive performance for color difference in 3D objects,followed by CMC(1:1),CIE94,and CIELAB.
基金National Natural Science Foundation of China(Grant Nos.62005049 and 62072110)Natural Science Foundation of Fujian Province(Grant No.2020J01451).
文摘Accurate segmentation of camouflage objects in aerial imagery is vital for improving the efficiency of UAV-based reconnaissance and rescue missions.However,camouflage object segmentation is increasingly challenging due to advances in both camouflage materials and biological mimicry.Although multispectral-RGB based technology shows promise,conventional dual-aperture multispectral-RGB imaging systems are constrained by imprecise and time-consuming registration and fusion across different modalities,limiting their performance.Here,we propose the Reconstructed Multispectral-RGB Fusion Network(RMRF-Net),which reconstructs RGB images into multispectral ones,enabling efficient multimodal segmentation using only an RGB camera.Specifically,RMRF-Net employs a divergentsimilarity feature correction strategy to minimize reconstruction errors and includes an efficient boundary-aware decoder to enhance object contours.Notably,we establish the first real-world aerial multispectral-RGB semantic segmentation of camouflage objects dataset,including 11 object categories.Experimental results demonstrate that RMRF-Net outperforms existing methods,achieving 17.38 FPS on the NVIDIA Jetson AGX Orin,with only a 0.96%drop in mIoU compared to the RTX 3090,showing its practical applicability in multimodal remote sensing.
