Impact craters are important for understanding the evolution of lunar geologic and surface erosion rates,among other functions.However,the morphological characteristics of these micro impact craters are not obvious an...Impact craters are important for understanding the evolution of lunar geologic and surface erosion rates,among other functions.However,the morphological characteristics of these micro impact craters are not obvious and they are numerous,resulting in low detection accuracy by deep learning models.Therefore,we proposed a new multi-scale fusion crater detection algorithm(MSF-CDA)based on the YOLO11 to improve the accuracy of lunar impact crater detection,especially for small craters with a diameter of<1 km.Using the images taken by the LROC(Lunar Reconnaissance Orbiter Camera)at the Chang’e-4(CE-4)landing area,we constructed three separate datasets for craters with diameters of 0-70 m,70-140 m,and>140 m.We then trained three submodels separately with these three datasets.Additionally,we designed a slicing-amplifying-slicing strategy to enhance the ability to extract features from small craters.To handle redundant predictions,we proposed a new Non-Maximum Suppression with Area Filtering method to fuse the results in overlapping targets within the multi-scale submodels.Finally,our new MSF-CDA method achieved high detection performance,with the Precision,Recall,and F1 score having values of 0.991,0.987,and 0.989,respectively,perfectly addressing the problems induced by the lesser features and sample imbalance of small craters.Our MSF-CDA can provide strong data support for more in-depth study of the geological evolution of the lunar surface and finer geological age estimations.This strategy can also be used to detect other small objects with lesser features and sample imbalance problems.We detected approximately 500,000 impact craters in an area of approximately 214 km2 around the CE-4 landing area.By statistically analyzing the new data,we updated the distribution function of the number and diameter of impact craters.Finally,we identified the most suitable lighting conditions for detecting impact crater targets by analyzing the effect of different lighting conditions on the detection accuracy.展开更多
As the number and complexity of sensors in autonomous vehicles continue to rise,multimodal fusionbased object detection algorithms are increasingly being used to detect 3D environmental information,significantly advan...As the number and complexity of sensors in autonomous vehicles continue to rise,multimodal fusionbased object detection algorithms are increasingly being used to detect 3D environmental information,significantly advancing the development of perception technology in autonomous driving.To further promote the development of fusion algorithms and improve detection performance,this paper discusses the advantages and recent advancements of multimodal fusion-based object detection algorithms.Starting fromsingle-modal sensor detection,the paper provides a detailed overview of typical sensors used in autonomous driving and introduces object detection methods based on images and point clouds.For image-based detection methods,they are categorized into monocular detection and binocular detection based on different input types.For point cloud-based detection methods,they are classified into projection-based,voxel-based,point cluster-based,pillar-based,and graph structure-based approaches based on the technical pathways for processing point cloud features.Additionally,multimodal fusion algorithms are divided into Camera-LiDAR fusion,Camera-Radar fusion,Camera-LiDAR-Radar fusion,and other sensor fusion methods based on the types of sensors involved.Furthermore,the paper identifies five key future research directions in this field,aiming to provide insights for researchers engaged in multimodal fusion-based object detection algorithms and to encourage broader attention to the research and application of multimodal fusion-based object detection.展开更多
A memetic algorithm （MA） for a multi-mode resourceconstrained project scheduling problem （MRCPSP） is proposed. We use a new fitness function and two very effective local search procedures in the proposed MA. The f...A memetic algorithm （MA） for a multi-mode resourceconstrained project scheduling problem （MRCPSP） is proposed. We use a new fitness function and two very effective local search procedures in the proposed MA. The fitness function makes use of a mechanism called ＂strategic oscillation＂ to make the search process have a higher probability to visit solutions around a ＂feasible boundary＂. One of the local search procedures aims at improving the lower bound of project makespan to be less than a known upper bound, and another aims at improving a solution of an MRCPSP instance accepting infeasible solutions based on the new fitness function in the search process. A detailed computational experiment is set up using instances from the problem instance library PSPLIB. Computational results show that the proposed MA is very competitive with the state-of-the-art algorithms. The MA obtains improved solutions for one instance of set J30.展开更多
To address the challenge of missing modal information in entity alignment and to mitigate information loss or bias arising frommodal heterogeneity during fusion,while also capturing shared information acrossmodalities...To address the challenge of missing modal information in entity alignment and to mitigate information loss or bias arising frommodal heterogeneity during fusion,while also capturing shared information acrossmodalities,this paper proposes a Multi-modal Pre-synergistic Entity Alignmentmodel based on Cross-modalMutual Information Strategy Optimization(MPSEA).The model first employs independent encoders to process multi-modal features,including text,images,and numerical values.Next,a multi-modal pre-synergistic fusion mechanism integrates graph structural and visual modal features into the textual modality as preparatory information.This pre-fusion strategy enables unified perception of heterogeneous modalities at the model’s initial stage,reducing discrepancies during the fusion process.Finally,using cross-modal deep perception reinforcement learning,the model achieves adaptive multilevel feature fusion between modalities,supporting learningmore effective alignment strategies.Extensive experiments on multiple public datasets show that the MPSEA method achieves gains of up to 7% in Hits@1 and 8.2% in MRR on the FBDB15K dataset,and up to 9.1% in Hits@1 and 7.7% in MRR on the FBYG15K dataset,compared to existing state-of-the-art methods.These results confirm the effectiveness of the proposed model.展开更多
Multi-modal Named Entity Recognition(MNER)aims to better identify meaningful textual entities by integrating information from images.Previous work has focused on extracting visual semantics at a fine-grained level,or ...Multi-modal Named Entity Recognition(MNER)aims to better identify meaningful textual entities by integrating information from images.Previous work has focused on extracting visual semantics at a fine-grained level,or obtaining entity related external knowledge from knowledge bases or Large Language Models(LLMs).However,these approaches ignore the poor semantic correlation between visual and textual modalities in MNER datasets and do not explore different multi-modal fusion approaches.In this paper,we present MMAVK,a multi-modal named entity recognition model with auxiliary visual knowledge and word-level fusion,which aims to leverage the Multi-modal Large Language Model(MLLM)as an implicit knowledge base.It also extracts vision-based auxiliary knowledge from the image formore accurate and effective recognition.Specifically,we propose vision-based auxiliary knowledge generation,which guides the MLLM to extract external knowledge exclusively derived from images to aid entity recognition by designing target-specific prompts,thus avoiding redundant recognition and cognitive confusion caused by the simultaneous processing of image-text pairs.Furthermore,we employ a word-level multi-modal fusion mechanism to fuse the extracted external knowledge with each word-embedding embedded from the transformerbased encoder.Extensive experimental results demonstrate that MMAVK outperforms or equals the state-of-the-art methods on the two classical MNER datasets,even when the largemodels employed have significantly fewer parameters than other baselines.展开更多
In the deployment of wireless networks in two-dimensional outdoor campus spaces,aiming at the problem of efficient coverage of the monitoring area by limited number of access points(APs),this paper proposes a deployme...In the deployment of wireless networks in two-dimensional outdoor campus spaces,aiming at the problem of efficient coverage of the monitoring area by limited number of access points(APs),this paper proposes a deployment method of multi-objective optimization with virtual force fusion bat algorithm(VFBA)using the classical four-node regular distribution as an entry point.The introduction of Lévy flight strategy for bat position updating helps to maintain the population diversity,reduce the premature maturity problem caused by population convergence,avoid the over aggregation of individuals in the local optimal region,and enhance the superiority in global search;the virtual force algorithm simulates the attraction and repulsion between individuals,which enables individual bats to precisely locate the optimal solution within the search space.At the same time,the fusion effect of virtual force prompts the bat individuals to move faster to the potential optimal solution.To validate the effectiveness of the fusion algorithm,the benchmark test function is selected for simulation testing.Finally,the simulation result verifies that the VFBA achieves superior coverage and effectively reduces node redundancy compared to the other three regular layout methods.The VFBA also shows better coverage results when compared to other optimization algorithms.展开更多
The traditional A^(*)algorithm exhibits a low efficiency in the path planning of unmanned surface vehicles(USVs).In addition,the path planned presents numerous redundant inflection waypoints,and the security is low,wh...The traditional A^(*)algorithm exhibits a low efficiency in the path planning of unmanned surface vehicles(USVs).In addition,the path planned presents numerous redundant inflection waypoints,and the security is low,which is not conducive to the control of USV and also affects navigation safety.In this paper,these problems were addressed through the following improvements.First,the path search angle and security were comprehensively considered,and a security expansion strategy of nodes based on the 5×5 neighborhood was proposed.The A^(*)algorithm search neighborhood was expanded from 3×3 to 5×5,and safe nodes were screened out for extension via the node security expansion strategy.This algorithm can also optimize path search angles while improving path security.Second,the distance from the current node to the target node was introduced into the heuristic function.The efficiency of the A^(*)algorithm was improved,and the path was smoothed using the Floyd algorithm.For the dynamic adjustment of the weight to improve the efficiency of DWA,the distance from the USV to the target point was introduced into the evaluation function of the dynamic-window approach(DWA)algorithm.Finally,combined with the local target point selection strategy,the optimized DWA algorithm was performed for local path planning.The experimental results show the smooth and safe path planned by the fusion algorithm,which can successfully avoid dynamic obstacles and is effective and feasible in path planning for USVs.展开更多
Wireless sensor network deployment optimization is a classic NP-hard problem and a popular topic in academic research.However,the current research on wireless sensor network deployment problems uses overly simplistic ...Wireless sensor network deployment optimization is a classic NP-hard problem and a popular topic in academic research.However,the current research on wireless sensor network deployment problems uses overly simplistic models,and there is a significant gap between the research results and actual wireless sensor networks.Some scholars have now modeled data fusion networks to make them more suitable for practical applications.This paper will explore the deployment problem of a stochastic data fusion wireless sensor network(SDFWSN),a model that reflects the randomness of environmental monitoring and uses data fusion techniques widely used in actual sensor networks for information collection.The deployment problem of SDFWSN is modeled as a multi-objective optimization problem.The network life cycle,spatiotemporal coverage,detection rate,and false alarm rate of SDFWSN are used as optimization objectives to optimize the deployment of network nodes.This paper proposes an enhanced multi-objective mongoose optimization algorithm(EMODMOA)to solve the deployment problem of SDFWSN.First,to overcome the shortcomings of the DMOA algorithm,such as its low convergence and tendency to get stuck in a local optimum,an encircling and hunting strategy is introduced into the original algorithm to propose the EDMOA algorithm.The EDMOA algorithm is designed as the EMODMOA algorithm by selecting reference points using the K-Nearest Neighbor(KNN)algorithm.To verify the effectiveness of the proposed algorithm,the EMODMOA algorithm was tested at CEC 2020 and achieved good results.In the SDFWSN deployment problem,the algorithm was compared with the Non-dominated Sorting Genetic Algorithm II(NSGAII),Multiple Objective Particle Swarm Optimization(MOPSO),Multi-Objective Evolutionary Algorithm based on Decomposition(MOEA/D),and Multi-Objective Grey Wolf Optimizer(MOGWO).By comparing and analyzing the performance evaluation metrics and optimization results of the objective functions of the multi-objective algorithms,the algorithm outperforms the other algorithms in the SDFWSN deployment results.To better demonstrate the superiority of the algorithm,simulations of diverse test cases were also performed,and good results were obtained.展开更多
Fault diagnosis of rolling bearings is crucial for ensuring the stable operation of mechanical equipment and production safety in industrial environments.However,due to the nonlinearity and non-stationarity of collect...Fault diagnosis of rolling bearings is crucial for ensuring the stable operation of mechanical equipment and production safety in industrial environments.However,due to the nonlinearity and non-stationarity of collected vibration signals,single-modal methods struggle to capture fault features fully.This paper proposes a rolling bearing fault diagnosis method based on multi-modal information fusion.The method first employs the Hippopotamus Optimization Algorithm(HO)to optimize the number of modes in Variational Mode Decomposition(VMD)to achieve optimal modal decomposition performance.It combines Convolutional Neural Networks(CNN)and Gated Recurrent Units(GRU)to extract temporal features from one-dimensional time-series signals.Meanwhile,the Markovian Transition Field(MTF)is used to transform one-dimensional signals into two-dimensional images for spatial feature mining.Through visualization techniques,the effectiveness of generated images from different parameter combinations is compared to determine the optimal parameter configuration.A multi-modal network(GSTCN)is constructed by integrating Swin-Transformer and the Convolutional Block Attention Module(CBAM),where the attention module is utilized to enhance fault features.Finally,the fault features extracted from different modalities are deeply fused and fed into a fully connected layer to complete fault classification.Experimental results show that the GSTCN model achieves an average diagnostic accuracy of 99.5%across three datasets,significantly outperforming existing comparison methods.This demonstrates that the proposed model has high diagnostic precision and good generalization ability,providing an efficient and reliable solution for rolling bearing fault diagnosis.展开更多
To address the difficulties in fusing multi-mode sensor data for complex industrial machinery, an adaptive deep coupling convolutional auto-encoder (ADCCAE) fusion method was proposed. First, the multi-mode features e...To address the difficulties in fusing multi-mode sensor data for complex industrial machinery, an adaptive deep coupling convolutional auto-encoder (ADCCAE) fusion method was proposed. First, the multi-mode features extracted synchronously by the CCAE were stacked and fed to the multi-channel convolution layers for fusion. Then, the fused data was passed to all connection layers for compression and fed to the Softmax module for classification. Finally, the coupling loss function coefficients and the network parameters were optimized through an adaptive approach using the gray wolf optimization (GWO) algorithm. Experimental comparisons showed that the proposed ADCCAE fusion model was superior to existing models for multi-mode data fusion.展开更多
At present,most experimental teaching systems lack guidance of an operator,and thus users often do not know what to do during an experiment.The user load is therefore increased,and the learning efficiency of the stude...At present,most experimental teaching systems lack guidance of an operator,and thus users often do not know what to do during an experiment.The user load is therefore increased,and the learning efficiency of the students is decreased.To solve the problem of insufficient system interactivity and guidance,an experimental navigation system based on multi-mode fusion is proposed in this paper.The system first obtains user information by sensing the hardware devices,intelligently perceives the user intention and progress of the experiment according to the information acquired,and finally carries out a multi-modal intelligent navigation process for users.As an innovative aspect of this study,an intelligent multi-mode navigation system is used to guide users in conducting experiments,thereby reducing the user load and enabling the users to effectively complete their experiments.The results prove that this system can guide users in completing their experiments,and can effectively reduce the user load during the interaction process and improve the efficiency.展开更多
To establish a parallel fusion approach of processing high dimensional information, the model and criterion of multisensor fuzzy stochastic data fusion were presented. In order to design genetic algorithm fusion, the ...To establish a parallel fusion approach of processing high dimensional information, the model and criterion of multisensor fuzzy stochastic data fusion were presented. In order to design genetic algorithm fusion, the fusion parameter coding, initial population and fitness function establishing, and fuzzy logic controller designing for genetic operations and probability choosing were completed. The discussion on the highly dimensional fusion was given. For a moving target with the division of 1 64 (velocity) and 1 75 (acceleration), the precision of fusion is 0 94 and 0 98 respectively. The fusion approach can improve the reliability and decision precision effectively.展开更多
To aim at the multimode character of the data from the airplane detecting system, the paper combines Dempster- Shafer evidence theory and subjective Bayesian algorithm and makes to propose a mixed structure multimode ...To aim at the multimode character of the data from the airplane detecting system, the paper combines Dempster- Shafer evidence theory and subjective Bayesian algorithm and makes to propose a mixed structure multimode data fusion algorithm. The algorithm adopts a prorated algorithm relate to the incertitude evaluation to convert the probability evaluation into the precognition probability in an identity frame, and ensures the adaptability of different data from different source to the mixed system. To guarantee real time fusion, a combination of time domain fusion and space domain fusion is established, this not only assure the fusion of data chain in different time of the same sensor, but also the data fusion from different sensors distributed in different platforms and the data fusion among different modes. The feasibility and practicability are approved through computer simulation.展开更多
Multi-modal fusion technology gradually become a fundamental task in many fields,such as autonomous driving,smart healthcare,sentiment analysis,and human-computer interaction.It is rapidly becoming the dominant resear...Multi-modal fusion technology gradually become a fundamental task in many fields,such as autonomous driving,smart healthcare,sentiment analysis,and human-computer interaction.It is rapidly becoming the dominant research due to its powerful perception and judgment capabilities.Under complex scenes,multi-modal fusion technology utilizes the complementary characteristics of multiple data streams to fuse different data types and achieve more accurate predictions.However,achieving outstanding performance is challenging because of equipment performance limitations,missing information,and data noise.This paper comprehensively reviews existing methods based onmulti-modal fusion techniques and completes a detailed and in-depth analysis.According to the data fusion stage,multi-modal fusion has four primary methods:early fusion,deep fusion,late fusion,and hybrid fusion.The paper surveys the three majormulti-modal fusion technologies that can significantly enhance the effect of data fusion and further explore the applications of multi-modal fusion technology in various fields.Finally,it discusses the challenges and explores potential research opportunities.Multi-modal tasks still need intensive study because of data heterogeneity and quality.Preserving complementary information and eliminating redundant information between modalities is critical in multi-modal technology.Invalid data fusion methods may introduce extra noise and lead to worse results.This paper provides a comprehensive and detailed summary in response to these challenges.展开更多
Power Shell has been widely deployed in fileless malware and advanced persistent threat(APT)attacks due to its high stealthiness and live-off-theland technique.However,existing works mainly focus on deobfuscation and ...Power Shell has been widely deployed in fileless malware and advanced persistent threat(APT)attacks due to its high stealthiness and live-off-theland technique.However,existing works mainly focus on deobfuscation and malicious detection,lacking the malicious Power Shell families classification and behavior analysis.Moreover,the state-of-the-art methods fail to capture fine-grained features and semantic relationships,resulting in low robustness and accuracy.To this end,we propose Power Detector,a novel malicious Power Shell script detector based on multimodal semantic fusion and deep learning.Specifically,we design four feature extraction methods to extract key features from character,token,abstract syntax tree(AST),and semantic knowledge graph.Then,we intelligently design four embeddings(i.e.,Char2Vec,Token2Vec,AST2Vec,and Rela2Vec) and construct a multi-modal fusion algorithm to concatenate feature vectors from different views.Finally,we propose a combined model based on transformer and CNN-Bi LSTM to implement Power Shell family detection.Our experiments with five types of Power Shell attacks show that PowerDetector can accurately detect various obfuscated and stealth PowerShell scripts,with a 0.9402 precision,a 0.9358 recall,and a 0.9374 F1-score.Furthermore,through singlemodal and multi-modal comparison experiments,we demonstrate that PowerDetector’s multi-modal embedding and deep learning model can achieve better accuracy and even identify more unknown attacks.展开更多
This paper presents a two-phase genetic algorithm (TPGA) based on the multi- parent genetic algorithm (MPGA). Through analysis we find MPGA will lead the population' s evol vement to diversity or convergence accor...This paper presents a two-phase genetic algorithm (TPGA) based on the multi- parent genetic algorithm (MPGA). Through analysis we find MPGA will lead the population' s evol vement to diversity or convergence according to the population size and the crossover size, so we make it run in different forms during the global and local optimization phases and then forms TPGA. The experiment results show that TPGA is very efficient for the optimization of low-dimension multi-modal functions, usually we can obtain all the global optimal solutions.展开更多
In this paper, a new algorithm for solving multi-modal function optimization problems-two-level subspace evolutionary algorithm is proposed. In the first level, the improved GT algorithm is used to do global recombina...In this paper, a new algorithm for solving multi-modal function optimization problems-two-level subspace evolutionary algorithm is proposed. In the first level, the improved GT algorithm is used to do global recombination search so that the whole population can be separated into several niches according to the position of solutions; then, in the second level, the niche evolutionary strategy is used for local search in the subspaces gotten in the first level till solutions of the problem are found. The new algorithm has been tested on some hard problems and some good results are obtained.展开更多
Current works of environmental perception for connected autonomous electrified vehicles(CAEVs)mainly focus on the object detection task in good weather and illumination conditions,they often perform poorly in adverse ...Current works of environmental perception for connected autonomous electrified vehicles(CAEVs)mainly focus on the object detection task in good weather and illumination conditions,they often perform poorly in adverse scenarios and have a vague scene parsing ability.This paper aims to develop an end-to-end sharpening mixture of experts(SMoE)fusion framework to improve the robustness and accuracy of the perception systems for CAEVs in complex illumination and weather conditions.Three original contributions make our work distinctive from the existing relevant literature.The Complex KITTI dataset is introduced which consists of 7481 pairs of modified KITTI RGB images and the generated LiDAR dense depth maps,and this dataset is fine annotated in instance-level with the proposed semi-automatic annotation method.The SMoE fusion approach is devised to adaptively learn the robust kernels from complementary modalities.Comprehensive comparative experiments are implemented,and the results show that the proposed SMoE framework yield significant improvements over the other fusion techniques in adverse environmental conditions.This research proposes a SMoE fusion framework to improve the scene parsing ability of the perception systems for CAEVs in adverse conditions.展开更多
Laser cleaning is a highly nonlinear physical process for solving poor single-modal(e.g., acoustic or vision)detection performance and low inter-information utilization. In this study, a multi-modal feature fusion net...Laser cleaning is a highly nonlinear physical process for solving poor single-modal(e.g., acoustic or vision)detection performance and low inter-information utilization. In this study, a multi-modal feature fusion network model was constructed based on a laser paint removal experiment. The alignment of heterogeneous data under different modals was solved by combining the piecewise aggregate approximation and gramian angular field. Moreover, the attention mechanism was introduced to optimize the dual-path network and dense connection network, enabling the sampling characteristics to be extracted and integrated. Consequently, the multi-modal discriminant detection of laser paint removal was realized. According to the experimental results, the verification accuracy of the constructed model on the experimental dataset was 99.17%, which is 5.77% higher than the optimal single-modal detection results of the laser paint removal. The feature extraction network was optimized by the attention mechanism, and the model accuracy was increased by 3.3%. Results verify the improved classification performance of the constructed multi-modal feature fusion model in detecting laser paint removal, the effective integration of acoustic data and visual image data, and the accurate detection of laser paint removal.展开更多
To Meet the requirements of multi-sensor data fusion in diagnosis for complex equipment systems,a novel, fuzzy similarity-based data fusion algorithm is given. Based on fuzzy set theory, it calculates the fuzzy simila...To Meet the requirements of multi-sensor data fusion in diagnosis for complex equipment systems,a novel, fuzzy similarity-based data fusion algorithm is given. Based on fuzzy set theory, it calculates the fuzzy similarity among a certain sensor's measurement values and the multiple sensor's objective prediction values to determine the importance weigh of each sensor,and realizes the multi-sensor diagnosis parameter data fusion.According to the principle, its application software is also designed. The applied example proves that the algorithm can give priority to the high-stability and high -reliability sensors and it is laconic ,feasible and efficient to real-time circumstance measure and data processing in engine diagnosis.展开更多
基金the National Key Research and Development Program of China (Grant No.2022YFF0711400)the National Space Science Data Center Youth Open Project (Grant No. NSSDC2302001)
文摘Impact craters are important for understanding the evolution of lunar geologic and surface erosion rates,among other functions.However,the morphological characteristics of these micro impact craters are not obvious and they are numerous,resulting in low detection accuracy by deep learning models.Therefore,we proposed a new multi-scale fusion crater detection algorithm(MSF-CDA)based on the YOLO11 to improve the accuracy of lunar impact crater detection,especially for small craters with a diameter of<1 km.Using the images taken by the LROC(Lunar Reconnaissance Orbiter Camera)at the Chang’e-4(CE-4)landing area,we constructed three separate datasets for craters with diameters of 0-70 m,70-140 m,and>140 m.We then trained three submodels separately with these three datasets.Additionally,we designed a slicing-amplifying-slicing strategy to enhance the ability to extract features from small craters.To handle redundant predictions,we proposed a new Non-Maximum Suppression with Area Filtering method to fuse the results in overlapping targets within the multi-scale submodels.Finally,our new MSF-CDA method achieved high detection performance,with the Precision,Recall,and F1 score having values of 0.991,0.987,and 0.989,respectively,perfectly addressing the problems induced by the lesser features and sample imbalance of small craters.Our MSF-CDA can provide strong data support for more in-depth study of the geological evolution of the lunar surface and finer geological age estimations.This strategy can also be used to detect other small objects with lesser features and sample imbalance problems.We detected approximately 500,000 impact craters in an area of approximately 214 km2 around the CE-4 landing area.By statistically analyzing the new data,we updated the distribution function of the number and diameter of impact craters.Finally,we identified the most suitable lighting conditions for detecting impact crater targets by analyzing the effect of different lighting conditions on the detection accuracy.
基金funded by the Yangtze River Delta Science and Technology Innovation Community Joint Research Project(2023CSJGG1600)the Natural Science Foundation of Anhui Province(2208085MF173)Wuhu“ChiZhu Light”Major Science and Technology Project(2023ZD01,2023ZD03).
文摘As the number and complexity of sensors in autonomous vehicles continue to rise,multimodal fusionbased object detection algorithms are increasingly being used to detect 3D environmental information,significantly advancing the development of perception technology in autonomous driving.To further promote the development of fusion algorithms and improve detection performance,this paper discusses the advantages and recent advancements of multimodal fusion-based object detection algorithms.Starting fromsingle-modal sensor detection,the paper provides a detailed overview of typical sensors used in autonomous driving and introduces object detection methods based on images and point clouds.For image-based detection methods,they are categorized into monocular detection and binocular detection based on different input types.For point cloud-based detection methods,they are classified into projection-based,voxel-based,point cluster-based,pillar-based,and graph structure-based approaches based on the technical pathways for processing point cloud features.Additionally,multimodal fusion algorithms are divided into Camera-LiDAR fusion,Camera-Radar fusion,Camera-LiDAR-Radar fusion,and other sensor fusion methods based on the types of sensors involved.Furthermore,the paper identifies five key future research directions in this field,aiming to provide insights for researchers engaged in multimodal fusion-based object detection algorithms and to encourage broader attention to the research and application of multimodal fusion-based object detection.
基金supported by the National Natural Science Foundation of China(71171038)
文摘A memetic algorithm （MA） for a multi-mode resourceconstrained project scheduling problem （MRCPSP） is proposed. We use a new fitness function and two very effective local search procedures in the proposed MA. The fitness function makes use of a mechanism called ＂strategic oscillation＂ to make the search process have a higher probability to visit solutions around a ＂feasible boundary＂. One of the local search procedures aims at improving the lower bound of project makespan to be less than a known upper bound, and another aims at improving a solution of an MRCPSP instance accepting infeasible solutions based on the new fitness function in the search process. A detailed computational experiment is set up using instances from the problem instance library PSPLIB. Computational results show that the proposed MA is very competitive with the state-of-the-art algorithms. The MA obtains improved solutions for one instance of set J30.
基金partially supported by the National Natural Science Foundation of China under Grants 62471493 and 62402257(for conceptualization and investigation)partially supported by the Natural Science Foundation of Shandong Province,China under Grants ZR2023LZH017,ZR2024MF066,and 2023QF025(for formal analysis and validation)+1 种基金partially supported by the Open Foundation of Key Laboratory of Computing Power Network and Information Security,Ministry of Education,Qilu University of Technology(Shandong Academy of Sciences)under Grant 2023ZD010(for methodology and model design)partially supported by the Russian Science Foundation(RSF)Project under Grant 22-71-10095-P(for validation and results verification).
文摘To address the challenge of missing modal information in entity alignment and to mitigate information loss or bias arising frommodal heterogeneity during fusion,while also capturing shared information acrossmodalities,this paper proposes a Multi-modal Pre-synergistic Entity Alignmentmodel based on Cross-modalMutual Information Strategy Optimization(MPSEA).The model first employs independent encoders to process multi-modal features,including text,images,and numerical values.Next,a multi-modal pre-synergistic fusion mechanism integrates graph structural and visual modal features into the textual modality as preparatory information.This pre-fusion strategy enables unified perception of heterogeneous modalities at the model’s initial stage,reducing discrepancies during the fusion process.Finally,using cross-modal deep perception reinforcement learning,the model achieves adaptive multilevel feature fusion between modalities,supporting learningmore effective alignment strategies.Extensive experiments on multiple public datasets show that the MPSEA method achieves gains of up to 7% in Hits@1 and 8.2% in MRR on the FBDB15K dataset,and up to 9.1% in Hits@1 and 7.7% in MRR on the FBYG15K dataset,compared to existing state-of-the-art methods.These results confirm the effectiveness of the proposed model.
基金funded by Research Project,grant number BHQ090003000X03.
文摘Multi-modal Named Entity Recognition(MNER)aims to better identify meaningful textual entities by integrating information from images.Previous work has focused on extracting visual semantics at a fine-grained level,or obtaining entity related external knowledge from knowledge bases or Large Language Models(LLMs).However,these approaches ignore the poor semantic correlation between visual and textual modalities in MNER datasets and do not explore different multi-modal fusion approaches.In this paper,we present MMAVK,a multi-modal named entity recognition model with auxiliary visual knowledge and word-level fusion,which aims to leverage the Multi-modal Large Language Model(MLLM)as an implicit knowledge base.It also extracts vision-based auxiliary knowledge from the image formore accurate and effective recognition.Specifically,we propose vision-based auxiliary knowledge generation,which guides the MLLM to extract external knowledge exclusively derived from images to aid entity recognition by designing target-specific prompts,thus avoiding redundant recognition and cognitive confusion caused by the simultaneous processing of image-text pairs.Furthermore,we employ a word-level multi-modal fusion mechanism to fuse the extracted external knowledge with each word-embedding embedded from the transformerbased encoder.Extensive experimental results demonstrate that MMAVK outperforms or equals the state-of-the-art methods on the two classical MNER datasets,even when the largemodels employed have significantly fewer parameters than other baselines.
基金supported in part by the National Natural Science Foundation of China under Grant No.62271453in part by the National Natural Science Foundation of China No.62101512+2 种基金in part by the Central Support for Local Projects under Grant No.YDZJSX2024D031in part by Project supported by the Shanxi Provincial Foundation for Leaders of Disciplines in Science,China under Grant No.2024Q022in part by Shanxi Province Patent Conversion Special Plan Funding Projects under Grant No.202405004。
文摘In the deployment of wireless networks in two-dimensional outdoor campus spaces,aiming at the problem of efficient coverage of the monitoring area by limited number of access points(APs),this paper proposes a deployment method of multi-objective optimization with virtual force fusion bat algorithm(VFBA)using the classical four-node regular distribution as an entry point.The introduction of Lévy flight strategy for bat position updating helps to maintain the population diversity,reduce the premature maturity problem caused by population convergence,avoid the over aggregation of individuals in the local optimal region,and enhance the superiority in global search;the virtual force algorithm simulates the attraction and repulsion between individuals,which enables individual bats to precisely locate the optimal solution within the search space.At the same time,the fusion effect of virtual force prompts the bat individuals to move faster to the potential optimal solution.To validate the effectiveness of the fusion algorithm,the benchmark test function is selected for simulation testing.Finally,the simulation result verifies that the VFBA achieves superior coverage and effectively reduces node redundancy compared to the other three regular layout methods.The VFBA also shows better coverage results when compared to other optimization algorithms.
基金Supported by the EDD of China(No.80912020104)the Science and Technology Commission of Shanghai Municipality(No.22ZR1427700 and No.23692106900).
文摘The traditional A^(*)algorithm exhibits a low efficiency in the path planning of unmanned surface vehicles(USVs).In addition,the path planned presents numerous redundant inflection waypoints,and the security is low,which is not conducive to the control of USV and also affects navigation safety.In this paper,these problems were addressed through the following improvements.First,the path search angle and security were comprehensively considered,and a security expansion strategy of nodes based on the 5×5 neighborhood was proposed.The A^(*)algorithm search neighborhood was expanded from 3×3 to 5×5,and safe nodes were screened out for extension via the node security expansion strategy.This algorithm can also optimize path search angles while improving path security.Second,the distance from the current node to the target node was introduced into the heuristic function.The efficiency of the A^(*)algorithm was improved,and the path was smoothed using the Floyd algorithm.For the dynamic adjustment of the weight to improve the efficiency of DWA,the distance from the USV to the target point was introduced into the evaluation function of the dynamic-window approach(DWA)algorithm.Finally,combined with the local target point selection strategy,the optimized DWA algorithm was performed for local path planning.The experimental results show the smooth and safe path planned by the fusion algorithm,which can successfully avoid dynamic obstacles and is effective and feasible in path planning for USVs.
基金supported by the National Natural Science Foundation of China under Grant Nos.U21A20464,62066005Innovation Project of Guangxi Graduate Education under Grant No.YCSW2024313.
文摘Wireless sensor network deployment optimization is a classic NP-hard problem and a popular topic in academic research.However,the current research on wireless sensor network deployment problems uses overly simplistic models,and there is a significant gap between the research results and actual wireless sensor networks.Some scholars have now modeled data fusion networks to make them more suitable for practical applications.This paper will explore the deployment problem of a stochastic data fusion wireless sensor network(SDFWSN),a model that reflects the randomness of environmental monitoring and uses data fusion techniques widely used in actual sensor networks for information collection.The deployment problem of SDFWSN is modeled as a multi-objective optimization problem.The network life cycle,spatiotemporal coverage,detection rate,and false alarm rate of SDFWSN are used as optimization objectives to optimize the deployment of network nodes.This paper proposes an enhanced multi-objective mongoose optimization algorithm(EMODMOA)to solve the deployment problem of SDFWSN.First,to overcome the shortcomings of the DMOA algorithm,such as its low convergence and tendency to get stuck in a local optimum,an encircling and hunting strategy is introduced into the original algorithm to propose the EDMOA algorithm.The EDMOA algorithm is designed as the EMODMOA algorithm by selecting reference points using the K-Nearest Neighbor(KNN)algorithm.To verify the effectiveness of the proposed algorithm,the EMODMOA algorithm was tested at CEC 2020 and achieved good results.In the SDFWSN deployment problem,the algorithm was compared with the Non-dominated Sorting Genetic Algorithm II(NSGAII),Multiple Objective Particle Swarm Optimization(MOPSO),Multi-Objective Evolutionary Algorithm based on Decomposition(MOEA/D),and Multi-Objective Grey Wolf Optimizer(MOGWO).By comparing and analyzing the performance evaluation metrics and optimization results of the objective functions of the multi-objective algorithms,the algorithm outperforms the other algorithms in the SDFWSN deployment results.To better demonstrate the superiority of the algorithm,simulations of diverse test cases were also performed,and good results were obtained.
基金funded by the Jilin Provincial Department of Science and Technology,grant number 20230101208JC.
文摘Fault diagnosis of rolling bearings is crucial for ensuring the stable operation of mechanical equipment and production safety in industrial environments.However,due to the nonlinearity and non-stationarity of collected vibration signals,single-modal methods struggle to capture fault features fully.This paper proposes a rolling bearing fault diagnosis method based on multi-modal information fusion.The method first employs the Hippopotamus Optimization Algorithm(HO)to optimize the number of modes in Variational Mode Decomposition(VMD)to achieve optimal modal decomposition performance.It combines Convolutional Neural Networks(CNN)and Gated Recurrent Units(GRU)to extract temporal features from one-dimensional time-series signals.Meanwhile,the Markovian Transition Field(MTF)is used to transform one-dimensional signals into two-dimensional images for spatial feature mining.Through visualization techniques,the effectiveness of generated images from different parameter combinations is compared to determine the optimal parameter configuration.A multi-modal network(GSTCN)is constructed by integrating Swin-Transformer and the Convolutional Block Attention Module(CBAM),where the attention module is utilized to enhance fault features.Finally,the fault features extracted from different modalities are deeply fused and fed into a fully connected layer to complete fault classification.Experimental results show that the GSTCN model achieves an average diagnostic accuracy of 99.5%across three datasets,significantly outperforming existing comparison methods.This demonstrates that the proposed model has high diagnostic precision and good generalization ability,providing an efficient and reliable solution for rolling bearing fault diagnosis.
文摘To address the difficulties in fusing multi-mode sensor data for complex industrial machinery, an adaptive deep coupling convolutional auto-encoder (ADCCAE) fusion method was proposed. First, the multi-mode features extracted synchronously by the CCAE were stacked and fed to the multi-channel convolution layers for fusion. Then, the fused data was passed to all connection layers for compression and fed to the Softmax module for classification. Finally, the coupling loss function coefficients and the network parameters were optimized through an adaptive approach using the gray wolf optimization (GWO) algorithm. Experimental comparisons showed that the proposed ADCCAE fusion model was superior to existing models for multi-mode data fusion.
基金the the National Key R&D Program of China(No.2018YFB1004901)the Independent Innovation Team Project of Jinan City(No.2019GXRC013).
文摘At present,most experimental teaching systems lack guidance of an operator,and thus users often do not know what to do during an experiment.The user load is therefore increased,and the learning efficiency of the students is decreased.To solve the problem of insufficient system interactivity and guidance,an experimental navigation system based on multi-mode fusion is proposed in this paper.The system first obtains user information by sensing the hardware devices,intelligently perceives the user intention and progress of the experiment according to the information acquired,and finally carries out a multi-modal intelligent navigation process for users.As an innovative aspect of this study,an intelligent multi-mode navigation system is used to guide users in conducting experiments,thereby reducing the user load and enabling the users to effectively complete their experiments.The results prove that this system can guide users in completing their experiments,and can effectively reduce the user load during the interaction process and improve the efficiency.
文摘To establish a parallel fusion approach of processing high dimensional information, the model and criterion of multisensor fuzzy stochastic data fusion were presented. In order to design genetic algorithm fusion, the fusion parameter coding, initial population and fitness function establishing, and fuzzy logic controller designing for genetic operations and probability choosing were completed. The discussion on the highly dimensional fusion was given. For a moving target with the division of 1 64 (velocity) and 1 75 (acceleration), the precision of fusion is 0 94 and 0 98 respectively. The fusion approach can improve the reliability and decision precision effectively.
文摘To aim at the multimode character of the data from the airplane detecting system, the paper combines Dempster- Shafer evidence theory and subjective Bayesian algorithm and makes to propose a mixed structure multimode data fusion algorithm. The algorithm adopts a prorated algorithm relate to the incertitude evaluation to convert the probability evaluation into the precognition probability in an identity frame, and ensures the adaptability of different data from different source to the mixed system. To guarantee real time fusion, a combination of time domain fusion and space domain fusion is established, this not only assure the fusion of data chain in different time of the same sensor, but also the data fusion from different sensors distributed in different platforms and the data fusion among different modes. The feasibility and practicability are approved through computer simulation.
基金supported by the Natural Science Foundation of Liaoning Province(Grant No.2023-MSBA-070)the National Natural Science Foundation of China(Grant No.62302086).
文摘Multi-modal fusion technology gradually become a fundamental task in many fields,such as autonomous driving,smart healthcare,sentiment analysis,and human-computer interaction.It is rapidly becoming the dominant research due to its powerful perception and judgment capabilities.Under complex scenes,multi-modal fusion technology utilizes the complementary characteristics of multiple data streams to fuse different data types and achieve more accurate predictions.However,achieving outstanding performance is challenging because of equipment performance limitations,missing information,and data noise.This paper comprehensively reviews existing methods based onmulti-modal fusion techniques and completes a detailed and in-depth analysis.According to the data fusion stage,multi-modal fusion has four primary methods:early fusion,deep fusion,late fusion,and hybrid fusion.The paper surveys the three majormulti-modal fusion technologies that can significantly enhance the effect of data fusion and further explore the applications of multi-modal fusion technology in various fields.Finally,it discusses the challenges and explores potential research opportunities.Multi-modal tasks still need intensive study because of data heterogeneity and quality.Preserving complementary information and eliminating redundant information between modalities is critical in multi-modal technology.Invalid data fusion methods may introduce extra noise and lead to worse results.This paper provides a comprehensive and detailed summary in response to these challenges.
基金This work was supported by National Natural Science Foundation of China(No.62172308,No.U1626107,No.61972297,No.62172144,and No.62062019).
文摘Power Shell has been widely deployed in fileless malware and advanced persistent threat(APT)attacks due to its high stealthiness and live-off-theland technique.However,existing works mainly focus on deobfuscation and malicious detection,lacking the malicious Power Shell families classification and behavior analysis.Moreover,the state-of-the-art methods fail to capture fine-grained features and semantic relationships,resulting in low robustness and accuracy.To this end,we propose Power Detector,a novel malicious Power Shell script detector based on multimodal semantic fusion and deep learning.Specifically,we design four feature extraction methods to extract key features from character,token,abstract syntax tree(AST),and semantic knowledge graph.Then,we intelligently design four embeddings(i.e.,Char2Vec,Token2Vec,AST2Vec,and Rela2Vec) and construct a multi-modal fusion algorithm to concatenate feature vectors from different views.Finally,we propose a combined model based on transformer and CNN-Bi LSTM to implement Power Shell family detection.Our experiments with five types of Power Shell attacks show that PowerDetector can accurately detect various obfuscated and stealth PowerShell scripts,with a 0.9402 precision,a 0.9358 recall,and a 0.9374 F1-score.Furthermore,through singlemodal and multi-modal comparison experiments,we demonstrate that PowerDetector’s multi-modal embedding and deep learning model can achieve better accuracy and even identify more unknown attacks.
基金Supported by the National Natural Science Foundation of China (70071042,60073043,60133010)
文摘This paper presents a two-phase genetic algorithm (TPGA) based on the multi- parent genetic algorithm (MPGA). Through analysis we find MPGA will lead the population' s evol vement to diversity or convergence according to the population size and the crossover size, so we make it run in different forms during the global and local optimization phases and then forms TPGA. The experiment results show that TPGA is very efficient for the optimization of low-dimension multi-modal functions, usually we can obtain all the global optimal solutions.
基金Supported by the National Natural Science Foundation of China (70071042,60073043,60133010)
文摘In this paper, a new algorithm for solving multi-modal function optimization problems-two-level subspace evolutionary algorithm is proposed. In the first level, the improved GT algorithm is used to do global recombination search so that the whole population can be separated into several niches according to the position of solutions; then, in the second level, the niche evolutionary strategy is used for local search in the subspaces gotten in the first level till solutions of the problem are found. The new algorithm has been tested on some hard problems and some good results are obtained.
基金Supported by National Natural Science Foundation of China(Grant Nos.51975118,52025121,51975103,51905095)National Natural Science Foundation of Jiangsu Province(Grant No.BK20180401).
文摘Current works of environmental perception for connected autonomous electrified vehicles(CAEVs)mainly focus on the object detection task in good weather and illumination conditions,they often perform poorly in adverse scenarios and have a vague scene parsing ability.This paper aims to develop an end-to-end sharpening mixture of experts(SMoE)fusion framework to improve the robustness and accuracy of the perception systems for CAEVs in complex illumination and weather conditions.Three original contributions make our work distinctive from the existing relevant literature.The Complex KITTI dataset is introduced which consists of 7481 pairs of modified KITTI RGB images and the generated LiDAR dense depth maps,and this dataset is fine annotated in instance-level with the proposed semi-automatic annotation method.The SMoE fusion approach is devised to adaptively learn the robust kernels from complementary modalities.Comprehensive comparative experiments are implemented,and the results show that the proposed SMoE framework yield significant improvements over the other fusion techniques in adverse environmental conditions.This research proposes a SMoE fusion framework to improve the scene parsing ability of the perception systems for CAEVs in adverse conditions.
基金Project(51875491) supported by the National Natural Science Foundation of ChinaProject(2021T3069) supported by the Fujian Science and Technology Plan STS Project,China。
文摘Laser cleaning is a highly nonlinear physical process for solving poor single-modal(e.g., acoustic or vision)detection performance and low inter-information utilization. In this study, a multi-modal feature fusion network model was constructed based on a laser paint removal experiment. The alignment of heterogeneous data under different modals was solved by combining the piecewise aggregate approximation and gramian angular field. Moreover, the attention mechanism was introduced to optimize the dual-path network and dense connection network, enabling the sampling characteristics to be extracted and integrated. Consequently, the multi-modal discriminant detection of laser paint removal was realized. According to the experimental results, the verification accuracy of the constructed model on the experimental dataset was 99.17%, which is 5.77% higher than the optimal single-modal detection results of the laser paint removal. The feature extraction network was optimized by the attention mechanism, and the model accuracy was increased by 3.3%. Results verify the improved classification performance of the constructed multi-modal feature fusion model in detecting laser paint removal, the effective integration of acoustic data and visual image data, and the accurate detection of laser paint removal.
文摘To Meet the requirements of multi-sensor data fusion in diagnosis for complex equipment systems,a novel, fuzzy similarity-based data fusion algorithm is given. Based on fuzzy set theory, it calculates the fuzzy similarity among a certain sensor's measurement values and the multiple sensor's objective prediction values to determine the importance weigh of each sensor,and realizes the multi-sensor diagnosis parameter data fusion.According to the principle, its application software is also designed. The applied example proves that the algorithm can give priority to the high-stability and high -reliability sensors and it is laconic ,feasible and efficient to real-time circumstance measure and data processing in engine diagnosis.
