Spectrum-based fault localization (SBFL) generates a ranked list of suspicious elements by using the program execution spectrum, but the excessive number of elements ranked in parallel results in low localization accu...Spectrum-based fault localization (SBFL) generates a ranked list of suspicious elements by using the program execution spectrum, but the excessive number of elements ranked in parallel results in low localization accuracy. Most researchers consider intra-class dependencies to improve localization accuracy. However, some studies show that inter-class method call type faults account for more than 20%, which means such methods still have certain limitations. To solve the above problems, this paper proposes a two-phase software fault localization based on relational graph convolutional neural networks (Two-RGCNFL). Firstly, in Phase 1, the method call dependence graph (MCDG) of the program is constructed, the intra-class and inter-class dependencies in MCDG are extracted by using the relational graph convolutional neural network, and the classifier is used to identify the faulty methods. Then, the GraphSMOTE algorithm is improved to alleviate the impact of class imbalance on classification accuracy. Aiming at the problem of parallel ranking of element suspicious values in traditional SBFL technology, in Phase 2, Doc2Vec is used to learn static features, while spectrum information serves as dynamic features. A RankNet model based on siamese multi-layer perceptron is constructed to score and rank statements in the faulty method. This work conducts experiments on 5 real projects of Defects4J benchmark. Experimental results show that, compared with the traditional SBFL technique and two baseline methods, our approach improves the Top-1 accuracy by 262.86%, 29.59% and 53.01%, respectively, which verifies the effectiveness of Two-RGCNFL. Furthermore, this work verifies the importance of inter-class dependencies through ablation experiments.展开更多
The proposed hybrid optimization algorithm integrates particle swarm optimizatio(PSO)with Ant Colony Optimization(ACO)to improve a number of pitfalls within PSO methods traditionally considered and/or applied to indus...The proposed hybrid optimization algorithm integrates particle swarm optimizatio(PSO)with Ant Colony Optimization(ACO)to improve a number of pitfalls within PSO methods traditionally considered and/or applied to industrial robots.Particle Swarm Optimization may frequently suffer from local optima and inaccuracies in identifying the geometric parameters,which are necessary for applications requiring high-accuracy performances.The proposed approach integrates pheromone-based learning of ACO with the D-H method of developing an error model;hence,the global search effectiveness together with the convergence accuracy is further improved.Comparison studies of the hybrid PSO-ACO algorithm show higher precision and effectiveness in the optimization of geometric error parameters compared to the traditional methods.This is a remarkable reduction of localization errors,thus yielding accuracy and reliability in industrial robotic systems,as the results show.This approach improves performance in those applications that demand high geometric calibration by reducing the geometric error.The paper provides an overview of input for developing robotics and automation,giving importance to precision in industrial engineering.The proposed hybrid methodology is a good way to enhance the working accuracy and effectiveness of industrial robots and shall enable their wide application to complex tasks that require a high degree of accuracy.展开更多
Ecological monitoring vehicles are equipped with a range of sensors and monitoring devices designed to gather data on ecological and environmental factors.These vehicles are crucial in various fields,including environ...Ecological monitoring vehicles are equipped with a range of sensors and monitoring devices designed to gather data on ecological and environmental factors.These vehicles are crucial in various fields,including environmental science research,ecological and environmental monitoring projects,disaster response,and emergency management.A key method employed in these vehicles for achieving high-precision positioning is LiDAR(lightlaser detection and ranging)-Visual Simultaneous Localization and Mapping(SLAM).However,maintaining highprecision localization in complex scenarios,such as degraded environments or when dynamic objects are present,remains a significant challenge.To address this issue,we integrate both semantic and texture information from LiDAR and cameras to enhance the robustness and efficiency of data registration.Specifically,semantic information simplifies the modeling of scene elements,reducing the reliance on dense point clouds,which can be less efficient.Meanwhile,visual texture information complements LiDAR-Visual localization by providing additional contextual details.By incorporating semantic and texture details frompaired images and point clouds,we significantly improve the quality of data association,thereby increasing the success rate of localization.This approach not only enhances the operational capabilities of ecological monitoring vehicles in complex environments but also contributes to improving the overall efficiency and effectiveness of ecological monitoring and environmental protection efforts.展开更多
This work presents a method for the three-dimensional localization of individual shallow NV center in diamond,leveraging the near-field quenching effect of a gold tip.Our experimental setup involves the use of an atom...This work presents a method for the three-dimensional localization of individual shallow NV center in diamond,leveraging the near-field quenching effect of a gold tip.Our experimental setup involves the use of an atomic force microscope to precisely move the gold tip close to the NV center,while simultaneously employing a home-made confocal microscope to monitor the fluorescence of the NV center.This approach allows for lateral super-resolution,achieving a full width at half maximum(FWHM)of 38.0 nm and a location uncertainty of 0.7 nm.Additionally,we show the potential of this method for determining the depth of the NV centers.We also attempt to determine the depth of the NV centers in combination with finite-difference time-domain(FDTD)simulations.Compared to other depth determination methods,this approach allows for simultaneous lateral and longitudinal localization of individual NV centers,and holds promise for facilitating manipulation of the local environment surrounding the NV center.展开更多
This paper investigates the mechanisms underlying the localization of Buddhism among the Kalmyks during Tsarist rule.It identifies and analyzes three interconnected processes:(1)the evolving framework of Tsarist polic...This paper investigates the mechanisms underlying the localization of Buddhism among the Kalmyks during Tsarist rule.It identifies and analyzes three interconnected processes:(1)the evolving framework of Tsarist policies aimed at administrative integration and religious regulation;(2)Kalmyk adaptive strategies,particularly the development of unique institutional responses(Supreme Lama election,Chief Bagshi,Dayanqi,and Temple Adherent systems)to navigate state constraints;and(3)spontaneous processes of cultural hybridity are manifested in material culture(e.g.,the Khoshut temple)and religious narratives(e.g.,Ulyanov’s reinvention of prophecies in Prophecies of Buddha).Utilizing the concept of“conjuncture practice”to frame these interactions,the study demonstrates how localization operated through a combination of regulatory pressure,community-level adaptation,and cultural synthesis,ultimately forging a distinct Kalmyk Buddhist expression within the imperial context.展开更多
Taking the Hotel Indigo Shanghai on the Bund as an example,this paper explores the localization of international high-end boutique hotels in China by using the methods of literature research and case study.The results...Taking the Hotel Indigo Shanghai on the Bund as an example,this paper explores the localization of international high-end boutique hotels in China by using the methods of literature research and case study.The results show that the localization of international high-end boutique hotels is embodied in brand building,spatial layout,service design and cultural activity planning,and that the perfect integration of international brand concept and local culture is an important factor for its success in the Chinese market.The research aims to provide reference for promoting the in-depth development and integration of international high-end boutique hotels in the Chinese market and the localization process of state-owned high-end boutique hotels in the future host country.展开更多
The utilization of nanostructures with diverse geometric shapes is essential for manipulating the energy of electromagnetic(EM) fields and achieving various applications in optics, such as nanofocusing. The plasmonic ...The utilization of nanostructures with diverse geometric shapes is essential for manipulating the energy of electromagnetic(EM) fields and achieving various applications in optics, such as nanofocusing. The plasmonic cone structure is highly representative in the field of nanofocusing applications, effectively guiding EM field energy to the tip of the cone and resulting in high local electric field and temperature effects. In certain chemical catalytic applications, an elevated temperature and a larger surface area may be required to enhance catalysis reactions. Here, we propose a hollow gold nanocone structure that can achieve higher temperature both at the tip and within its hollow region under the excitation of an EM field.Through rigorous finite element method(FEM) simulations, we investigated the EM field and temperature distribution of the hollow cone at various cone angles and identified those angles that yield higher local temperatures. Additionally, the analysis of the scattering cross section of hollow cones reveals that the presence of electric dipole component of the EM field corresponds to Fabry–Perot-like(FP-like) resonance in short wavelengths(600 nm–1200 nm), which predominantly contributes to the temperature localization. These findings provide novel insights into utilizing conical nanostructures for applications such as catalysis.展开更多
Traditional Global Positioning System(GPS)technology,with its high power consumption and limited perfor-mance in obstructed environments,is unsuitable for many Internet of Things(IoT)applications.This paper explores L...Traditional Global Positioning System(GPS)technology,with its high power consumption and limited perfor-mance in obstructed environments,is unsuitable for many Internet of Things(IoT)applications.This paper explores LoRa as an alternative localization technology,leveraging its low power consumption,robust indoor penetration,and extensive coverage area,which render it highly suitable for diverse IoT settings.We comprehensively review several LoRa-based localization techniques,including time of arrival(ToA),time difference of arrival(TDoA),round trip time(RTT),received signal strength indicator(RSSI),and fingerprinting methods.Through this review,we evaluate the strengths and limitations of each technique and investigate hybrid models to potentially improve positioning accuracy.Case studies in smart cities,agriculture,and logistics exemplify the versatility of LoRa for indoor and outdoor applications.Our findings demonstrate that LoRa technology not only overcomes the limitations of GPS regarding power consumption and coverage but also enhances the scalability and efficiency of IoT deployments in complex environments.展开更多
A kind of slow deformation wave is produced in the crust under the action of internal and external factors,which plays an important role in the formation and occurrence of earthquakes.In this paper,uniaxial compressio...A kind of slow deformation wave is produced in the crust under the action of internal and external factors,which plays an important role in the formation and occurrence of earthquakes.In this paper,uniaxial compression tests are carried out on red sandstone samples with uniform texture.Displacement controlled loading methods are adopted,and the loading rates are 0.1 mm/min,0.5 mm/min and 1.0 mm/min,respectively.The micro-characterization method of speckle photography and DIC processing technology are adopted.The transfer characteristics of slow deformation and strain localization of red sandstone specimens during loading and deformation are discussed.The results show that the boundary advance velocity is proportional to the slow deformation transfer velocity with the change of position,so it can be considered that the slow deformation transfer velocity is equal to the particle motion transfer velocity.The formation and development of sample strain localization may be determined by the flow channel,nucleation and Luders zone evolution.The formation of the Luders band is related to the maximum value of the flow channel,and as deformation increases,the Luders band merges and develops with the maximum value of the nearby flow channel.By applying different loading rates,the influence of loading rate on the average transfer velocity of slow deformation was obtained;the slow deformation wave during seismic migration has similar characteristics to the deformation transfer in the experiment,therefore the research results have reference significance for further studies on the evolution characteristics of slow deformation waves and seismic migration.展开更多
The mobile sound source localization system is a technology that can track and locate mobile sound sources in real time and has broad application prospects in many fields.This article first provides an overview of the...The mobile sound source localization system is a technology that can track and locate mobile sound sources in real time and has broad application prospects in many fields.This article first provides an overview of the mobile sound source localization system,introducing its concept and composition,as well as its design and application significance.It elaborates on the importance of the mobile sound source localization system from multiple aspects,such as safety,production,and daily life,and deeply explores its design and application strategies.The problems faced by the mobile sound source localization system and its future development direction were pointed out.展开更多
Deconvolution methods are commonly used to improve the performance of phased array beamforming for sound source localization. However, for coherent sources localization, existing deconvolution methods are either highl...Deconvolution methods are commonly used to improve the performance of phased array beamforming for sound source localization. However, for coherent sources localization, existing deconvolution methods are either highly computationally demanding or sensitive to parameters.A deconvolution method, based on modifications of Clean based on Source Coherence(CLEAN-SC), is proposed for coherent sources localization. This method is called Coherence CLEAN-SC(C–CLEAN-SC). C–CLEAN-SC is able to locate coherent and incoherent sources in simulation and experimental cases. It has a high computational efficiency and does not require pre-set parameters.展开更多
Multiple quadrotors target encirclement is widely used in the intelligent field,as it can effectively monitor and control target behavior.However,it faces the danger of collision,as well as difficulties in localizatio...Multiple quadrotors target encirclement is widely used in the intelligent field,as it can effectively monitor and control target behavior.However,it faces the danger of collision,as well as difficulties in localization and tracking.Therefore,we propose a complete target encirclement method.Firstly,based on Hooke's law,a collision avoidance controller is designed to maintain a safe flying distance among quadrotors.Then,based on the consensus theory,a formation tracking controller is designed to meet the requirements of formation transformation and encirclement tasks,and a stability proof based on Lyapunov was provided.Besides,the target detection is designed based on YOLOv5s,and the target location model is constructed based on the principle of pinhole projection and triangle similarity.Finally,we conducted experiments on the built platform,with 3 reconnaissance quadrotors detecting and localization 3 target vehicles and 7 hunter quadrotors tracking them.The results show that the minimum average error for localization targets with reconnaissance quadrotors can reach 0.1354 m,while the minimum average error for tracking with hunter quadrotors is only 0.2960 m.No quadrotors collision occurred in the whole formation transformation and tracking experiment.In addition,compared with the advanced methods,the proposed method has better performance.展开更多
Indoor visual localization relies heavily on image retrieval to ascertain location information.However,the widespread presence and high consistency of floor patterns across different images of-ten lead to the extracti...Indoor visual localization relies heavily on image retrieval to ascertain location information.However,the widespread presence and high consistency of floor patterns across different images of-ten lead to the extraction of numerous repetitive features,thereby reducing the accuracy of image retrieval.This article proposes an indoor visual localization method based on semantic segmentation and adaptive weight fusion to address the issue of ground texture interference with retrieval results.During the positioning process,an indoor semantic segmentation model is established.Semantic segmentation technology is applied to accurately delineate the ground portion of the images.Fea-ture extraction is performed on both the original database and the ground-segmented database.The vector of locally aggregated descriptors(VLAD)algorithm is then used to convert image features into a fixed-length feature representation,which improves the efficiency of image retrieval.Simul-taneously,a method for adaptive weight optimization in similarity calculation is proposed,using a-daptive weights to compute similarity for different regional features,thereby improving the accuracy of image retrieval.The experimental results indicate that this method significantly reduces ground interference and effectively utilizes ground information,thereby improving the accuracy of image retrieval.展开更多
A lightweight composite resonator,consisting of a soft material acoustic black hole(SABH)and multiple vibration absorbers,is embedded in a plate to achieve localization and absorption of low-frequency vibration energy...A lightweight composite resonator,consisting of a soft material acoustic black hole(SABH)and multiple vibration absorbers,is embedded in a plate to achieve localization and absorption of low-frequency vibration energy.The combination of local and global admissible functions for displacement enhances the accuracy of the Ritz method in predicting vibration localization characteristics within the SABH domain.Utilizing soft materials for the SABH can reduce the mass and frequency of the composite resonator.Due to the lack of orthogonality between global vibration modes and localized modes,the low-frequency localized modes induced by the SABH are used to shape the initial global modes,thereby concentrating the global vibration of the plate in the SABH region.Consequently,the absorbers of the composite resonator only need to be a small fraction of the mass of the local SABH to achieve substantial vibration control of the host plate.This vibration localization strategy can significantly reduce the vibration amplitude of the host plate and enhance the effectiveness of lightweight absorbers in vibration reduction.展开更多
Image tampering detection and localization have emerged as a critical domain in combating the pervasive issue of image manipulation due to the advancement of the large-scale availability of sophisticated image editing...Image tampering detection and localization have emerged as a critical domain in combating the pervasive issue of image manipulation due to the advancement of the large-scale availability of sophisticated image editing tools.The manual forgery localization is often reliant on forensic expertise.In recent times,machine learning(ML)and deep learning(DL)have shown promising results in automating image forgery localization.However,the ML-based method relies on hand-crafted features.Conversely,the DL method automatically extracts shallow spatial features to enhance the accuracy.However,DL-based methods lack the global co-relation of the features due to this performance degradation noticed in several applications.In the proposed study,we designed FLTNet(forgery localization transformer network)with a CNN(convolution neural network)encoder and transformer-based attention.The encoder extracts local high-dimensional features,and the transformer provides the global co-relation of the features.In the decoder,we have exclusively utilized a CNN to upsample the features that generate tampered mask images.Moreover,we evaluated visual and quantitative performance on three standard datasets and comparison with six state-of-the-art methods.The IoU values of the proposed method on CASIA V1,CASIA V2,and CoMoFoD datasets are 0.77,0.82,and 0.84,respectively.In addition,the F1-scores of these three datasets are 0.80,0.84,and 0.86,respectively.Furthermore,the visual results of the proposed method are clean and contain rich information,which can be used for real-time forgery detection.The code used in the study can be accessed through URL:https://github.com/ajit2k5/Forgery-Localization(accessed on 21 January 2025).展开更多
In existing image manipulation localization methods,the receptive field of standard convolution is limited,and during feature transfer,it is easy to lose high-frequency information about traces of manipulation.In addi...In existing image manipulation localization methods,the receptive field of standard convolution is limited,and during feature transfer,it is easy to lose high-frequency information about traces of manipulation.In addition,during feature fusion,the use of fixed sampling kernels makes it difficult to focus on local changes in features,leading to limited localization accuracy.This paper proposes an image manipulation localization method based on dual-branch hybrid convolution.First,a dual-branch hybrid convolution module is designed to expand the receptive field of the model to enhance the feature extraction ability of contextual semantic information,while also enabling the model to focus more on the high-frequency detail features of manipulation traces while localizing the manipulated area.Second,a multiscale content-aware feature fusion module is used to dynamically generate adaptive sampling kernels for each position in the feature map,enabling the model to focus more on the details of local features while locating the manipulated area.Experimental results on multiple datasets show that this method not only effectively improves the accuracy of image manipulation localization but also enhances the robustness of the model.展开更多
Aiming at the problem that the traditional SRP-PHAT sound source localization method performs intensive search in a 360-degree space,resulting in high computational complexity and difficulty in meeting real-time requi...Aiming at the problem that the traditional SRP-PHAT sound source localization method performs intensive search in a 360-degree space,resulting in high computational complexity and difficulty in meeting real-time requirements,an innovative high-precision sound source localization method is proposed.This method combines the selective SRP-PHAT algorithm with real-time visual analysis.Its core innovations include using face detection to dynamically determine the scanning angle range to achieve visually guided selective scanning,distinguishing face sound sources from background noise through a sound source classification mechanism,and implementing intelligent background orientation selection to ensure comprehensive monitoring of environmental noise.Experimental results show that the method achieves a positioning accuracy of±5 degrees and a processing speed of more than 10FPS in complex real environments,and its performance is significantly better than the traditional full-angle scanning method.展开更多
BACKGROUND Small-bowel capsule endoscopy(SBCE)is widely used to evaluate obscure gastrointestinal bleeding;however,its interpretation is time-consuming and reader-dependent.Although artificial intelligence(AI)has emer...BACKGROUND Small-bowel capsule endoscopy(SBCE)is widely used to evaluate obscure gastrointestinal bleeding;however,its interpretation is time-consuming and reader-dependent.Although artificial intelligence(AI)has emerged to address these limitations,few models simultaneously perform small-bowel(SB)loca lization and abnormality detection.AIMTo develop an AI model that automatically distinguishes the SB from the stomach and colon and diagnoses SBabnormalities.METHODSWe developed an AI model using 87005 CE images (11925, 33781, and 41299 from the stomach, SB, and colon,respectively) for SB localization and 28405 SBCE images (1337 erosions/ulcers, 126 angiodysplasia, 494 bleeding,and 26448 normal) for abnormality detection. The diagnostic performances of AI-assisted reading and conventionalreading were compared using 32 SBCE videos in patients with suspicious SB bleeding.RESULTSRegarding organ localization, the AI model achieved an area under the receiver operating characteristic curve(AUC) and accuracy exceeding 0.99 and 97%, respectively. For SB abnormality detection, the performance was asfollows: Erosion/ulcer: 99.4% accuracy (AUC, 0.98);angiodysplasia: 99.8% accuracy (AUC, 0.99);bleeding: 99.9%accuracy (AUC, 0.99);normal: 99.3% accuracy (AUC, 0.98). In external validation, AI-assisted reading (8.7 minutes)was significantly faster than conventional reading (53.9 minutes;P < 0.001). The SB localization accuracies (88.6% vs72.7%, P = 0.07) and SB abnormality detection rates (77.3% vs 77.3%, P = 1.00) of the conventional reading and AIassistedreading were comparable.CONCLUSIONOur AI model decreased SBCE reading time and achieved performance comparable to that of experiencedendoscopists, suggesting that AI integration into SBCE reading enables efficient and reliable SB abnormalitydetection.展开更多
Existing image manipulation localization(IML)techniques require large,densely annotated sets of forged images.This requirement greatly increases labeling costs and limits a model’s ability to handle manipulation type...Existing image manipulation localization(IML)techniques require large,densely annotated sets of forged images.This requirement greatly increases labeling costs and limits a model’s ability to handle manipulation types that are novel or absent from the training data.To address these issues,we present CLIP-IML,an IML framework that leverages contrastive language-image pre-training(CLIP).A lightweight feature-reconstruction module transforms CLIP token sequences into spatial tensors,after which a compact feature-pyramid network and a multi-scale fusion decoder work together to capture information from fine to coarse levels.We evaluated CLIP-IML on ten public datasets that cover copy-move,splicing,removal,and artificial intelligence(AI)-generated forgeries.The framework raises the average F1-score by 7.85%relative to the strongest recent baselines and secures either the first-or second-place performance on every dataset.Ablation studies show that CLIP pre-training,higher resolution inputs,and the multi-scale decoder each make complementary contributions.Under six common post-processing perturbations,as well as the compression pipelines used by Facebook,Weibo,and WeChat,the performance decline never exceeds 2.2%,confirming strong practical robustness.Moreover,CLIP-IML requires only a few thousand annotated images for training,which markedly reduces data-collection and labeling effort compared with previous methods.All of these results indicate that CLIP-IML is highly generalizable for image tampering localization across a wide range of tampering scenarios.展开更多
Spherical objects are widely used in target localization applications,and the existing sphere localization methods with cameras or total stations both have some limitations.A new high-precision sphere localization met...Spherical objects are widely used in target localization applications,and the existing sphere localization methods with cameras or total stations both have some limitations.A new high-precision sphere localization method with a theodolite is proposed in this paper.From the view point of the theodolite,the contour points of a sphere with a known radius are measured as latitude-longitude coordinates.It is observed that the center of the target sphere is located on a cylindrical surface constructed with the latitude-longitude coordinates,and therefore the latitude-longitude coordinates of at least three contour points can be used to construct a set of ternary quadratic equations.The Gröbner basis method is used to compute at most four real solutions of the sphere center coordinates.To distinguish the only meaningful solution from the other possible real solutions,a pre-processing of the measured longitude values is also proposed.The factors affecting the positioning accuracy of the sphere center are evaluated in simulation experiments,which are used to obtain an empirical estimation model of the positioning error.Real data experiments are also performed and the results show that the proposed method can achieve high localization precision.展开更多
基金funded by the Youth Fund of the National Natural Science Foundation of China(Grant No.42261070).
文摘Spectrum-based fault localization (SBFL) generates a ranked list of suspicious elements by using the program execution spectrum, but the excessive number of elements ranked in parallel results in low localization accuracy. Most researchers consider intra-class dependencies to improve localization accuracy. However, some studies show that inter-class method call type faults account for more than 20%, which means such methods still have certain limitations. To solve the above problems, this paper proposes a two-phase software fault localization based on relational graph convolutional neural networks (Two-RGCNFL). Firstly, in Phase 1, the method call dependence graph (MCDG) of the program is constructed, the intra-class and inter-class dependencies in MCDG are extracted by using the relational graph convolutional neural network, and the classifier is used to identify the faulty methods. Then, the GraphSMOTE algorithm is improved to alleviate the impact of class imbalance on classification accuracy. Aiming at the problem of parallel ranking of element suspicious values in traditional SBFL technology, in Phase 2, Doc2Vec is used to learn static features, while spectrum information serves as dynamic features. A RankNet model based on siamese multi-layer perceptron is constructed to score and rank statements in the faulty method. This work conducts experiments on 5 real projects of Defects4J benchmark. Experimental results show that, compared with the traditional SBFL technique and two baseline methods, our approach improves the Top-1 accuracy by 262.86%, 29.59% and 53.01%, respectively, which verifies the effectiveness of Two-RGCNFL. Furthermore, this work verifies the importance of inter-class dependencies through ablation experiments.
文摘The proposed hybrid optimization algorithm integrates particle swarm optimizatio(PSO)with Ant Colony Optimization(ACO)to improve a number of pitfalls within PSO methods traditionally considered and/or applied to industrial robots.Particle Swarm Optimization may frequently suffer from local optima and inaccuracies in identifying the geometric parameters,which are necessary for applications requiring high-accuracy performances.The proposed approach integrates pheromone-based learning of ACO with the D-H method of developing an error model;hence,the global search effectiveness together with the convergence accuracy is further improved.Comparison studies of the hybrid PSO-ACO algorithm show higher precision and effectiveness in the optimization of geometric error parameters compared to the traditional methods.This is a remarkable reduction of localization errors,thus yielding accuracy and reliability in industrial robotic systems,as the results show.This approach improves performance in those applications that demand high geometric calibration by reducing the geometric error.The paper provides an overview of input for developing robotics and automation,giving importance to precision in industrial engineering.The proposed hybrid methodology is a good way to enhance the working accuracy and effectiveness of industrial robots and shall enable their wide application to complex tasks that require a high degree of accuracy.
基金supported by the project“GEF9874:Strengthening Coordinated Approaches to Reduce Invasive Alien Species(lAS)Threats to Globally Significant Agrobiodiversity and Agroecosystems in China”funding from the Excellent Talent Training Funding Project in Dongcheng District,Beijing,with project number 2024-dchrcpyzz-9.
文摘Ecological monitoring vehicles are equipped with a range of sensors and monitoring devices designed to gather data on ecological and environmental factors.These vehicles are crucial in various fields,including environmental science research,ecological and environmental monitoring projects,disaster response,and emergency management.A key method employed in these vehicles for achieving high-precision positioning is LiDAR(lightlaser detection and ranging)-Visual Simultaneous Localization and Mapping(SLAM).However,maintaining highprecision localization in complex scenarios,such as degraded environments or when dynamic objects are present,remains a significant challenge.To address this issue,we integrate both semantic and texture information from LiDAR and cameras to enhance the robustness and efficiency of data registration.Specifically,semantic information simplifies the modeling of scene elements,reducing the reliance on dense point clouds,which can be less efficient.Meanwhile,visual texture information complements LiDAR-Visual localization by providing additional contextual details.By incorporating semantic and texture details frompaired images and point clouds,we significantly improve the quality of data association,thereby increasing the success rate of localization.This approach not only enhances the operational capabilities of ecological monitoring vehicles in complex environments but also contributes to improving the overall efficiency and effectiveness of ecological monitoring and environmental protection efforts.
基金supported by the National Natural Science Foundation of China(T2325023,92265204,12104447)the National Key R&D Program of China(2023YFF0718400)+1 种基金the Innovation Program for Quantum Science and Technology(2021ZD0302200)the Fundamental Research Funds for the Central Universities。
文摘This work presents a method for the three-dimensional localization of individual shallow NV center in diamond,leveraging the near-field quenching effect of a gold tip.Our experimental setup involves the use of an atomic force microscope to precisely move the gold tip close to the NV center,while simultaneously employing a home-made confocal microscope to monitor the fluorescence of the NV center.This approach allows for lateral super-resolution,achieving a full width at half maximum(FWHM)of 38.0 nm and a location uncertainty of 0.7 nm.Additionally,we show the potential of this method for determining the depth of the NV centers.We also attempt to determine the depth of the NV centers in combination with finite-difference time-domain(FDTD)simulations.Compared to other depth determination methods,this approach allows for simultaneous lateral and longitudinal localization of individual NV centers,and holds promise for facilitating manipulation of the local environment surrounding the NV center.
文摘This paper investigates the mechanisms underlying the localization of Buddhism among the Kalmyks during Tsarist rule.It identifies and analyzes three interconnected processes:(1)the evolving framework of Tsarist policies aimed at administrative integration and religious regulation;(2)Kalmyk adaptive strategies,particularly the development of unique institutional responses(Supreme Lama election,Chief Bagshi,Dayanqi,and Temple Adherent systems)to navigate state constraints;and(3)spontaneous processes of cultural hybridity are manifested in material culture(e.g.,the Khoshut temple)and religious narratives(e.g.,Ulyanov’s reinvention of prophecies in Prophecies of Buddha).Utilizing the concept of“conjuncture practice”to frame these interactions,the study demonstrates how localization operated through a combination of regulatory pressure,community-level adaptation,and cultural synthesis,ultimately forging a distinct Kalmyk Buddhist expression within the imperial context.
基金Sponsored by application research project of social sciences of Jiangsu Province(24SZC-117).
文摘Taking the Hotel Indigo Shanghai on the Bund as an example,this paper explores the localization of international high-end boutique hotels in China by using the methods of literature research and case study.The results show that the localization of international high-end boutique hotels is embodied in brand building,spatial layout,service design and cultural activity planning,and that the perfect integration of international brand concept and local culture is an important factor for its success in the Chinese market.The research aims to provide reference for promoting the in-depth development and integration of international high-end boutique hotels in the Chinese market and the localization process of state-owned high-end boutique hotels in the future host country.
基金Project supported by the Science and Technology Department of Gansu Province, China (Grant No. 24RCKB011)the National Natural Science Foundation of China (Grant No. 12325511)。
文摘The utilization of nanostructures with diverse geometric shapes is essential for manipulating the energy of electromagnetic(EM) fields and achieving various applications in optics, such as nanofocusing. The plasmonic cone structure is highly representative in the field of nanofocusing applications, effectively guiding EM field energy to the tip of the cone and resulting in high local electric field and temperature effects. In certain chemical catalytic applications, an elevated temperature and a larger surface area may be required to enhance catalysis reactions. Here, we propose a hollow gold nanocone structure that can achieve higher temperature both at the tip and within its hollow region under the excitation of an EM field.Through rigorous finite element method(FEM) simulations, we investigated the EM field and temperature distribution of the hollow cone at various cone angles and identified those angles that yield higher local temperatures. Additionally, the analysis of the scattering cross section of hollow cones reveals that the presence of electric dipole component of the EM field corresponds to Fabry–Perot-like(FP-like) resonance in short wavelengths(600 nm–1200 nm), which predominantly contributes to the temperature localization. These findings provide novel insights into utilizing conical nanostructures for applications such as catalysis.
基金supported by the Natural Science Foundation of Zhejiang Province under grant no.LGF22F010006the Humanities and Social Science Research Project of Ministry of Education of China under grant no.22YJAZH016.
文摘Traditional Global Positioning System(GPS)technology,with its high power consumption and limited perfor-mance in obstructed environments,is unsuitable for many Internet of Things(IoT)applications.This paper explores LoRa as an alternative localization technology,leveraging its low power consumption,robust indoor penetration,and extensive coverage area,which render it highly suitable for diverse IoT settings.We comprehensively review several LoRa-based localization techniques,including time of arrival(ToA),time difference of arrival(TDoA),round trip time(RTT),received signal strength indicator(RSSI),and fingerprinting methods.Through this review,we evaluate the strengths and limitations of each technique and investigate hybrid models to potentially improve positioning accuracy.Case studies in smart cities,agriculture,and logistics exemplify the versatility of LoRa for indoor and outdoor applications.Our findings demonstrate that LoRa technology not only overcomes the limitations of GPS regarding power consumption and coverage but also enhances the scalability and efficiency of IoT deployments in complex environments.
基金Postdoctoral Science Fund(043201027)National Natural Science Key Foundation of China(41831290)National Natural Science Foundation of China(52079068).
文摘A kind of slow deformation wave is produced in the crust under the action of internal and external factors,which plays an important role in the formation and occurrence of earthquakes.In this paper,uniaxial compression tests are carried out on red sandstone samples with uniform texture.Displacement controlled loading methods are adopted,and the loading rates are 0.1 mm/min,0.5 mm/min and 1.0 mm/min,respectively.The micro-characterization method of speckle photography and DIC processing technology are adopted.The transfer characteristics of slow deformation and strain localization of red sandstone specimens during loading and deformation are discussed.The results show that the boundary advance velocity is proportional to the slow deformation transfer velocity with the change of position,so it can be considered that the slow deformation transfer velocity is equal to the particle motion transfer velocity.The formation and development of sample strain localization may be determined by the flow channel,nucleation and Luders zone evolution.The formation of the Luders band is related to the maximum value of the flow channel,and as deformation increases,the Luders band merges and develops with the maximum value of the nearby flow channel.By applying different loading rates,the influence of loading rate on the average transfer velocity of slow deformation was obtained;the slow deformation wave during seismic migration has similar characteristics to the deformation transfer in the experiment,therefore the research results have reference significance for further studies on the evolution characteristics of slow deformation waves and seismic migration.
基金supported by the National Natural Science Foundation of China(U2013602).
文摘The mobile sound source localization system is a technology that can track and locate mobile sound sources in real time and has broad application prospects in many fields.This article first provides an overview of the mobile sound source localization system,introducing its concept and composition,as well as its design and application significance.It elaborates on the importance of the mobile sound source localization system from multiple aspects,such as safety,production,and daily life,and deeply explores its design and application strategies.The problems faced by the mobile sound source localization system and its future development direction were pointed out.
基金supported by the National Science and Technology Major Project of China (No. 2017-II-003–0015)。
文摘Deconvolution methods are commonly used to improve the performance of phased array beamforming for sound source localization. However, for coherent sources localization, existing deconvolution methods are either highly computationally demanding or sensitive to parameters.A deconvolution method, based on modifications of Clean based on Source Coherence(CLEAN-SC), is proposed for coherent sources localization. This method is called Coherence CLEAN-SC(C–CLEAN-SC). C–CLEAN-SC is able to locate coherent and incoherent sources in simulation and experimental cases. It has a high computational efficiency and does not require pre-set parameters.
基金the National Natural Science Foundation of China(Grant Nos.62303348 and 62173242)the Aeronautical Science Foundation of China(Grant No.2024M071048002)the National Science Fund for Distinguished Young Scholars(Grant No.62225308)to provide fund for conducting experiments.
文摘Multiple quadrotors target encirclement is widely used in the intelligent field,as it can effectively monitor and control target behavior.However,it faces the danger of collision,as well as difficulties in localization and tracking.Therefore,we propose a complete target encirclement method.Firstly,based on Hooke's law,a collision avoidance controller is designed to maintain a safe flying distance among quadrotors.Then,based on the consensus theory,a formation tracking controller is designed to meet the requirements of formation transformation and encirclement tasks,and a stability proof based on Lyapunov was provided.Besides,the target detection is designed based on YOLOv5s,and the target location model is constructed based on the principle of pinhole projection and triangle similarity.Finally,we conducted experiments on the built platform,with 3 reconnaissance quadrotors detecting and localization 3 target vehicles and 7 hunter quadrotors tracking them.The results show that the minimum average error for localization targets with reconnaissance quadrotors can reach 0.1354 m,while the minimum average error for tracking with hunter quadrotors is only 0.2960 m.No quadrotors collision occurred in the whole formation transformation and tracking experiment.In addition,compared with the advanced methods,the proposed method has better performance.
基金Supported by the National Natural Science Foundation of China(No.61971162,61771186)the Natural Science Foundation of Heilongjiang Province(No.PL2024F025)+2 种基金the Open Research Fund of National Mobile Communications Research Laboratory Southeast University(No.2023D07)the Outstanding Youth Program of Natural Science Foundation of Heilongjiang Province(No.YQ2020F012)the Funda-mental Scientific Research Funds of Heilongjiang Province(No.2022-KYYWF-1050).
文摘Indoor visual localization relies heavily on image retrieval to ascertain location information.However,the widespread presence and high consistency of floor patterns across different images of-ten lead to the extraction of numerous repetitive features,thereby reducing the accuracy of image retrieval.This article proposes an indoor visual localization method based on semantic segmentation and adaptive weight fusion to address the issue of ground texture interference with retrieval results.During the positioning process,an indoor semantic segmentation model is established.Semantic segmentation technology is applied to accurately delineate the ground portion of the images.Fea-ture extraction is performed on both the original database and the ground-segmented database.The vector of locally aggregated descriptors(VLAD)algorithm is then used to convert image features into a fixed-length feature representation,which improves the efficiency of image retrieval.Simul-taneously,a method for adaptive weight optimization in similarity calculation is proposed,using a-daptive weights to compute similarity for different regional features,thereby improving the accuracy of image retrieval.The experimental results indicate that this method significantly reduces ground interference and effectively utilizes ground information,thereby improving the accuracy of image retrieval.
基金supported by the National Natural Science Foundation of China(Grant Nos.12302006,12132002,and 62188101).
文摘A lightweight composite resonator,consisting of a soft material acoustic black hole(SABH)and multiple vibration absorbers,is embedded in a plate to achieve localization and absorption of low-frequency vibration energy.The combination of local and global admissible functions for displacement enhances the accuracy of the Ritz method in predicting vibration localization characteristics within the SABH domain.Utilizing soft materials for the SABH can reduce the mass and frequency of the composite resonator.Due to the lack of orthogonality between global vibration modes and localized modes,the low-frequency localized modes induced by the SABH are used to shape the initial global modes,thereby concentrating the global vibration of the plate in the SABH region.Consequently,the absorbers of the composite resonator only need to be a small fraction of the mass of the local SABH to achieve substantial vibration control of the host plate.This vibration localization strategy can significantly reduce the vibration amplitude of the host plate and enhance the effectiveness of lightweight absorbers in vibration reduction.
文摘Image tampering detection and localization have emerged as a critical domain in combating the pervasive issue of image manipulation due to the advancement of the large-scale availability of sophisticated image editing tools.The manual forgery localization is often reliant on forensic expertise.In recent times,machine learning(ML)and deep learning(DL)have shown promising results in automating image forgery localization.However,the ML-based method relies on hand-crafted features.Conversely,the DL method automatically extracts shallow spatial features to enhance the accuracy.However,DL-based methods lack the global co-relation of the features due to this performance degradation noticed in several applications.In the proposed study,we designed FLTNet(forgery localization transformer network)with a CNN(convolution neural network)encoder and transformer-based attention.The encoder extracts local high-dimensional features,and the transformer provides the global co-relation of the features.In the decoder,we have exclusively utilized a CNN to upsample the features that generate tampered mask images.Moreover,we evaluated visual and quantitative performance on three standard datasets and comparison with six state-of-the-art methods.The IoU values of the proposed method on CASIA V1,CASIA V2,and CoMoFoD datasets are 0.77,0.82,and 0.84,respectively.In addition,the F1-scores of these three datasets are 0.80,0.84,and 0.86,respectively.Furthermore,the visual results of the proposed method are clean and contain rich information,which can be used for real-time forgery detection.The code used in the study can be accessed through URL:https://github.com/ajit2k5/Forgery-Localization(accessed on 21 January 2025).
基金National Natural Science Foundation of China(61703363)Shanxi Provincial Basic Research Program(202403021221206)+2 种基金Key Project of Shanxi Provincial Strategic Research on Science and Technology(202304031401011)Funding Project for Scientific Research Innovation Team on Data Mining and Industrial Intelligence Applications(YCXYTD-202402)Yuncheng University Research Project(YQ-2020021)。
文摘In existing image manipulation localization methods,the receptive field of standard convolution is limited,and during feature transfer,it is easy to lose high-frequency information about traces of manipulation.In addition,during feature fusion,the use of fixed sampling kernels makes it difficult to focus on local changes in features,leading to limited localization accuracy.This paper proposes an image manipulation localization method based on dual-branch hybrid convolution.First,a dual-branch hybrid convolution module is designed to expand the receptive field of the model to enhance the feature extraction ability of contextual semantic information,while also enabling the model to focus more on the high-frequency detail features of manipulation traces while localizing the manipulated area.Second,a multiscale content-aware feature fusion module is used to dynamically generate adaptive sampling kernels for each position in the feature map,enabling the model to focus more on the details of local features while locating the manipulated area.Experimental results on multiple datasets show that this method not only effectively improves the accuracy of image manipulation localization but also enhances the robustness of the model.
基金the research result of the 2024 Guangxi Higher Education Undergraduate Teaching Reform Project“OBE-Guided,Digitally Empowered‘Hadoop Big Data Development Technology’Course Ideological and Political Construction Innovation Exploration and Practice”(Project No.:2024JGA396).
文摘Aiming at the problem that the traditional SRP-PHAT sound source localization method performs intensive search in a 360-degree space,resulting in high computational complexity and difficulty in meeting real-time requirements,an innovative high-precision sound source localization method is proposed.This method combines the selective SRP-PHAT algorithm with real-time visual analysis.Its core innovations include using face detection to dynamically determine the scanning angle range to achieve visually guided selective scanning,distinguishing face sound sources from background noise through a sound source classification mechanism,and implementing intelligent background orientation selection to ensure comprehensive monitoring of environmental noise.Experimental results show that the method achieves a positioning accuracy of±5 degrees and a processing speed of more than 10FPS in complex real environments,and its performance is significantly better than the traditional full-angle scanning method.
基金Supported by The Bio and Medical Technology Development Program of the National Research Foundation,No.NRF-2022R1C1C1010643.
文摘BACKGROUND Small-bowel capsule endoscopy(SBCE)is widely used to evaluate obscure gastrointestinal bleeding;however,its interpretation is time-consuming and reader-dependent.Although artificial intelligence(AI)has emerged to address these limitations,few models simultaneously perform small-bowel(SB)loca lization and abnormality detection.AIMTo develop an AI model that automatically distinguishes the SB from the stomach and colon and diagnoses SBabnormalities.METHODSWe developed an AI model using 87005 CE images (11925, 33781, and 41299 from the stomach, SB, and colon,respectively) for SB localization and 28405 SBCE images (1337 erosions/ulcers, 126 angiodysplasia, 494 bleeding,and 26448 normal) for abnormality detection. The diagnostic performances of AI-assisted reading and conventionalreading were compared using 32 SBCE videos in patients with suspicious SB bleeding.RESULTSRegarding organ localization, the AI model achieved an area under the receiver operating characteristic curve(AUC) and accuracy exceeding 0.99 and 97%, respectively. For SB abnormality detection, the performance was asfollows: Erosion/ulcer: 99.4% accuracy (AUC, 0.98);angiodysplasia: 99.8% accuracy (AUC, 0.99);bleeding: 99.9%accuracy (AUC, 0.99);normal: 99.3% accuracy (AUC, 0.98). In external validation, AI-assisted reading (8.7 minutes)was significantly faster than conventional reading (53.9 minutes;P < 0.001). The SB localization accuracies (88.6% vs72.7%, P = 0.07) and SB abnormality detection rates (77.3% vs 77.3%, P = 1.00) of the conventional reading and AIassistedreading were comparable.CONCLUSIONOur AI model decreased SBCE reading time and achieved performance comparable to that of experiencedendoscopists, suggesting that AI integration into SBCE reading enables efficient and reliable SB abnormalitydetection.
基金supported by the Natural Science Foundation of Xinjiang Uygur Autonomous Region under Grant No.2023D01C21the National Natural Science Foundation of China under Grant No.62362063.
文摘Existing image manipulation localization(IML)techniques require large,densely annotated sets of forged images.This requirement greatly increases labeling costs and limits a model’s ability to handle manipulation types that are novel or absent from the training data.To address these issues,we present CLIP-IML,an IML framework that leverages contrastive language-image pre-training(CLIP).A lightweight feature-reconstruction module transforms CLIP token sequences into spatial tensors,after which a compact feature-pyramid network and a multi-scale fusion decoder work together to capture information from fine to coarse levels.We evaluated CLIP-IML on ten public datasets that cover copy-move,splicing,removal,and artificial intelligence(AI)-generated forgeries.The framework raises the average F1-score by 7.85%relative to the strongest recent baselines and secures either the first-or second-place performance on every dataset.Ablation studies show that CLIP pre-training,higher resolution inputs,and the multi-scale decoder each make complementary contributions.Under six common post-processing perturbations,as well as the compression pipelines used by Facebook,Weibo,and WeChat,the performance decline never exceeds 2.2%,confirming strong practical robustness.Moreover,CLIP-IML requires only a few thousand annotated images for training,which markedly reduces data-collection and labeling effort compared with previous methods.All of these results indicate that CLIP-IML is highly generalizable for image tampering localization across a wide range of tampering scenarios.
基金supported in part by the National Natural Science Foundation of China under Grants 61703373,61873246,U1504604in part by the Key research project of Henan Province Universities under Grant 19A413014.
文摘Spherical objects are widely used in target localization applications,and the existing sphere localization methods with cameras or total stations both have some limitations.A new high-precision sphere localization method with a theodolite is proposed in this paper.From the view point of the theodolite,the contour points of a sphere with a known radius are measured as latitude-longitude coordinates.It is observed that the center of the target sphere is located on a cylindrical surface constructed with the latitude-longitude coordinates,and therefore the latitude-longitude coordinates of at least three contour points can be used to construct a set of ternary quadratic equations.The Gröbner basis method is used to compute at most four real solutions of the sphere center coordinates.To distinguish the only meaningful solution from the other possible real solutions,a pre-processing of the measured longitude values is also proposed.The factors affecting the positioning accuracy of the sphere center are evaluated in simulation experiments,which are used to obtain an empirical estimation model of the positioning error.Real data experiments are also performed and the results show that the proposed method can achieve high localization precision.
