322 results about "Swarm intelligence" patented technology

The invention provides a sequential network traffic prediction method and system based on swarm intelligence parameter optimization, and relates to the technical field of network traffic prediction. The method comprises the following steps: acquiring indexes such as throughput packet loss rate and round-trip delay of a target link by using a network probe, and performing deletion filling normalization and multi-scale decomposition to obtain a standardized traffic sequence; calculating information entropy, constructing a traffic complexity feature vector, and dividing a training set and a verification set; constructing a hybrid depth prediction model composed of a one-dimensional convolutional network and a gating cycle unit, and establishing a hyper-parameter search space; using particle swarm optimization and entropy-driven inertia weight adjustment and mutation probability mapping to reconstruct a speed and position updating strategy, and iteratively outputting a global optimal hyper-parameter; and generating a benchmark prediction result according to full-amount training, extracting a residual error, training a nonlinear residual error compensation model to carry out superposition correction and reverse normalization, obtaining a final flow prediction result, and improving prediction precision and generalization ability.

The invention relates to the field of emergency management, in particular to an emergency cooperative scheduling strategy generation method based on swarm intelligence. The method comprises the following steps: acquiring multi-source data of each agent, preprocessing the multi-source data, and feeding back the preprocessed multi-source data to the corresponding agent; the intelligent agent generates a preliminary scheduling strategy according to the received multi-source data, and updates and maintains a strategy distribution snapshot of an edge node in the preliminary scheduling strategy; and obtaining an evolution path of the secondary disaster, inputting the evolution path of the secondary disaster, the preprocessed multi-source data and the strategy distribution snapshot of the edge node into the federal depth Q network model, and generating a collaborative scheduling strategy. In this way, the technical problems that structural obstacles exist in data integration and sharing facing emergency scenes, allocation and scheduling of computing resources are difficult to meet dynamic and high-timeliness requirements of emergency responses, and the overall toughness and cooperative capacity of a system are insufficient are solved.

The invention discloses a multi-agent collaborative logistics distribution and scheduling system based on swarm intelligence emergence optimization and a method thereof, and relates to the technical field of swarm intelligence, multi-agent systems, intelligent logistics and distributed optimization, in particular to a multi-agent collaborative logistics distribution and scheduling system based on swarm intelligence emergence optimization and a method thereof. The system adopts a completely distributed architecture and is composed of a plurality of agents for autonomous decision making, each agent comprises a sensing module, a decision making module, a communication module and an execution module, cooperation is achieved through local sensing and neighborhood communication, and a central controller is not needed. The system performs path optimization and obstacle avoidance by using a coupling mechanism of a pheromone field and a potential field function, and supports multi-scale collaboration, distributed consensus decision and self-organization capability. The method comprises the following steps: acquiring local information by an intelligent agent, planning a path based on a pheromone field and a potential field, and realizing task allocation and conflict resolution through interaction. According to the system, the energy consumption can be effectively reduced by 28%, the efficiency is improved by 5%, and the system performance exceeds the total sum of intelligent agents by 40-50%.

The invention provides an energy storage electrical intelligent system of a self-adaptive control strategy, and relates to the technical field of electric power grids. According to the invention, multi-source operation data of a power grid, a load, new energy and an energy storage system are collected in real time through the sensing layer, the decision-making layer realizes accurate synchronization and updating of the system operation state by using a digital twin model, and distributed optimization of swarm intelligence and extreme scene testing of confrontation deduction are fused. Dynamically generating and screening out an optimal control instruction which shows robustness under various working conditions; and finally, the execution layer accurately controls the energy storage system to form a sensing-decision-execution-feedback adaptive closed loop, so that the control strategy of the energy storage system can be automatically and accurately adjusted along with the fluctuation of the running state of the power grid, the stiffness defect of a fixed strategy is overcome, the capacity of the power grid for dealing with source load fluctuation and sudden faults is enhanced, and the energy storage system is ensured to be more stable. The self-adaptive matching of the energy storage system control strategy and the power grid operation state is realized, and the dynamic stability and the operation safety of the power grid are improved.

The invention relates to the technical field of automobile dynamics control, in particular to an ambulance suspension intelligent agent based on deep reinforcement learning and an optimization method thereof, and the optimization method comprises the steps: S1, initializing an evaluation network and a control strategy network; s2, adopting a swarm intelligence algorithm to initialize a population; s3, the number M of evolution generations of the controller and the time step T of each generation are set, in each time step, the initial fitness of the controller is set to be 0, and the fitness of the controller is updated according to the reward value and the auxiliary reward of the current time step; s4, after each intergeneration is finished, updating the population according to the fitness by adopting a swarm intelligence algorithm, and training the evaluation network and the control strategy network to update network parameters; and S5, after M generations of evolution are completed, screening out the controller with the highest fitness from the controllers, and setting the network parameters corresponding to the controller in the control strategy network. The invention is at least beneficial to improving the adaptability of the ambulance to different working conditions.

The invention relates to a swarm intelligence-driven cascade reservoir autonomous negotiation scheduling method. The method comprises the following steps: firstly, generating a scheduling basic data set; respectively packaging each reservoir node of the cascade reservoir group into an independent reservoir unit body; each reservoir unit carries out parallel computing and distributed negotiation through a group fusion negotiation strategy based on interaction data of a local scheduling basic data set and a neighborhood reservoir unit, and a preliminary scheduling scheme is generated; the group fusion negotiation strategy is based on the function types of the reservoir units, adopts a distributed negotiation mode of a contract network protocol or a bidding mechanism, takes the minimum transaction cost among the reservoir units as a core objective function, and combines flood control, power generation and ecological multi-objective weight coefficients to determine a preliminary scheduling scheme; and carrying out digital twinborn simulation verification and fine tuning to obtain a final scheme. In case of exception, preferential intra-group coordination is realized, and in case of invalidation, cross-group linkage is realized. The method improves the scheduling efficiency, guarantees the multi-target balance of flood control, power generation and the like, and enhances the anti-risk capability.

The invention discloses a power transmission and transformation project economic evaluation method, system, equipment and medium fusing adaptive fuzzy entropy weighting and a multi-target grey wolf optimization algorithm, and belongs to the technical field of power system economic analysis, and the method comprises the steps: constructing an economic index system, building a fuzzy membership matrix, and calculating an index weight through combining fuzzy entropy and information entropy; a comprehensive weight is generated by adopting a self-adaptive fusion mechanism, then a multi-target weighted evaluation model is constructed, and finally multi-target search is performed by utilizing a swarm intelligence optimization algorithm. According to the invention, by constructing a self-adaptive weighting mechanism fusing the fuzzy entropy and the information entropy and combining the global search capability of the multi-target grey wolf optimization algorithm, multi-index weight dynamic optimization and multi-target cooperative solution in the economic evaluation of the power transmission and transformation project are realized; the method effectively overcomes the limitation of a traditional method in the aspects of weight distribution subjectivity, insufficient index coupling processing and multi-target balance, and forms a closed-loop evaluation system from index processing to intelligent decision making.

The invention discloses a business processing method and device based on an ant colony algorithm, electronic equipment and a medium. The method comprises the following steps: acquiring a business service request, and analyzing the business service request to obtain a business task; determining each agent matched with the business task; wherein the intelligent agents are used for cooperative processing of business tasks; planning the cooperation path of each agent based on an ant colony algorithm to obtain a target path; and according to the cooperation sequence of the intelligent agents in the target path, executing the business task by using the intelligent agents in sequence. According to the technical scheme, efficient collaboration between agents is achieved through the improved ant colony algorithm. According to the system, a multi-dimensional pheromone matrix is adopted to record and transmit collaborative experience among departments, a knowledge verification mechanism based on swarm intelligence is established, and dynamic optimization and rapid convergence of a cross-department business process are realized.

The invention relates to the technical field of unmanned aerial vehicle path planning, and discloses a multi-unmanned aerial vehicle three-dimensional group intelligent dynamic path planning method fusing multi-source environment perception, which comprises an intelligent dynamic path planning system and comprises the following operation steps: S1, collecting and preprocessing multi-source environment information; s2, performing multi-source information fusion and three-dimensional environment modeling; s3, initializing an improved swarm intelligence algorithm and optimizing a path; s4, multi-machine collaboration and dynamic path adjustment; and S5, smoothly outputting the path. According to the multi-unmanned aerial vehicle three-dimensional group intelligent dynamic path planning method fused with multi-source environment perception, through multi-source data fusion and accurate three-dimensional environment modeling, environment information such as the terrain of an operation area can be comprehensively mastered in real time, so that an unmanned aerial vehicle group can still plan a feasible path in a complex and changeable scene, and the working efficiency is improved. By improving a swarm intelligence algorithm and a multi-aircraft cooperation mechanism, multi-aircraft conflicts are effectively avoided, and the operation efficiency and cooperation safety of the unmanned aerial vehicle group are remarkably improved.

The invention discloses an automatic design and optimization system for a hydraulic speed control loop, which takes a large language model intelligent body as a core, realizes automatic design and optimization of the hydraulic speed control loop through semantic comprehension, knowledge retrieval and parameter optimization, and specifically comprises an LLM intelligent body, a data processing module and a data processing module, the analysis module is used for analyzing natural language input containing design requirements and performance targets of a user, generating a loop structure in combination with a local knowledge base and calling an optimization algorithm; the local knowledge base comprises a basic hydraulic loop, a key empirical relationship and a typical structure template which are artificially extracted; and the simulation and optimization module is used for executing a swarm intelligence optimization algorithm to optimize and adjust parameters of the loop structure. The invention constructs a hydraulic speed control loop automatic design and optimization system with semantic understanding, automatic generation and adaptive optimization capabilities, and aims to realize full-process intelligent design from user demand input to loop structure generation and performance optimization.

The invention discloses a low-voltage transformer area electric energy meter time synchronization method and system based on swarm intelligence, and relates to the technical field of intelligent power grid and power distribution automation. The method comprises the steps that a transformer area acquisition terminal issues reference time, and each electric energy meter collects neighborhood information through neighbor electric energy meter bidirectional message exchange; jointly estimating the clock skew and the drift rate by adopting a consistency algorithm; introducing a time-varying weight calculated according to SNR, a message success rate and historical stability to suppress the influence of an inferior link and an abnormal node; the virtual synchronization time is output through software compensation on the service side; and adjusting the synchronization period interval and the convergence step length in a linkage manner according to a double-threshold self-adaptive rule. According to the scheme, deviation and drift rate rapid convergence and stable noise suppression are realized in a time-varying and easy packet loss environment, communication energy consumption is reduced, time jump caused by hardware callback is avoided, and the method has the advantages of high precision, strong robustness and large-scale deployment.

The invention discloses a full-working-condition simulation test method and device for a heat dissipation system of an engineering vehicle, and relates to the technical field of engineering testing. The method comprises the following steps: constructing a digital twinborn body by using a digital twinborn technology according to an engineering vehicle heat dissipation system entity of a target vehicle; constructing a dynamic response agent model and a control strategy generation model by using an artificial intelligence algorithm based on the digital twinborn body, and generating an intelligent test working condition sequence; based on the dynamic response agent model and the control strategy generation model, a swarm intelligence optimization algorithm is used for design optimization of the engineering vehicle cooling system, and a design parameter scheme set and a control strategy set thereof are generated; according to the intelligent test working condition sequence, the design parameter scheme set and the control strategy set, full-working-condition simulation test is carried out, a full-working-condition simulation test result is obtained, and verification is carried out after virtual-real combination. The problems of poor test comprehensiveness, high cost and long period in the prior art are solved.

The invention provides a whole-process production scheduling method considering processing and assembling, which comprises the following steps: constructing a two-stage flexible flow shop scheduling model, scheduling processing tasks of all parts of a plurality of products on a parallel machine in the first stage, and scheduling assembling of the product parts and processing tasks of semi-finished products in the second stage; minimizing the maximum completion time and the total energy consumption of the machine is taken as a double-optimization target; a multi-target swarm intelligence algorithm is adopted to solve the model, population individuals represent a scheduling scheme through two-segment coding, the first segment of coding defines a process execution sequence, and the second segment of coding defines a machine selection result; in an iteration process, alternately executing a Thompson sampling strategy and a dedirectional sampling and generating strategy according to a preset probability, adaptively selecting a bottom layer optimization operator to realize global search, and constructing a guide solution set to realize local mining; and outputting a non-dominated solution set after iteration is ended, and obtaining a corresponding whole-process scheduling scheme after decoding.

The invention relates to the field of power system operation, and discloses a partition power grid new energy consumption capability evaluation method considering power-carbon collaborative optimization, and the method comprises the following steps: S1, carrying out the modeling of power grid time sequence data and topological information based on a time sequence channel decoupling lightweight graph convolutional network, and obtaining a power grid dynamic partitioning result; s2, on the basis of a semantic perception feature enhancement network, calculating a partitioned power grid security domain on the basis of the partitioning result; and S3, under the constraint of the security domain, carrying out power-carbon collaborative optimization scheduling by using a colistia colony intelligent optimization algorithm. According to the method, a lightweight graph convolutional network is constructed based on a space-time decoupling principle of power grid topology and new energy output, and node electrical association strength is dynamically weighted based on a graph attention mechanism; through a time sequence channel separation method, adaptive optimization of a minute-level power grid partition structure is realized, and the mismatch problem of a fixed partition mode under source load fluctuation is solved.

The invention discloses a four-direction shuttle vehicle collaborative scheduling method and system based on swarm intelligence, and the method comprises the following steps: obtaining a task set of a warehouse management system, and building a topological graph model; acquiring running state information of the four-way shuttle vehicle, and associating the running state information with the topological graph model; mapping the associated operation state to a scheduling scheme space, executing multilayer wave propagation, and generating a plurality of candidate scheduling schemes; a conflict regulation and control rule is introduced in the water wave refraction process, refraction execution objects are determined according to the attribute parameters when conflicts occur in different task paths, and an alternative path combination is generated; constructing a composite fitness function, and evaluating the candidate scheduling scheme by taking task completion time, mobile energy consumption and battery health degree attenuation cost as optimization indexes to obtain a fitness evaluation result; and selecting an optimal scheduling scheme based on a fitness evaluation result. According to the invention, multi-vehicle cooperative scheduling is realized through the improved water wave optimization algorithm, and the operation efficiency and reliability of the warehousing system are significantly improved.

The invention discloses an engine main bearing resonance parameter determination method and device, equipment and a medium, and relates to the technical field of mechanical state monitoring, and the method comprises the steps: obtaining a current working condition parameter of a target engine, and detecting whether the current working condition parameter meets a state threshold condition in a corresponding cruise state or not; if yes, acquiring corresponding equipment characteristic parameters, acquisition configuration parameters and original vibration data, determining fault characteristic frequency of each element of the main bearing of the target engine, acquiring harmonic amplitude of each order corresponding to the fault characteristic frequency, and constructing a target function; performing global optimization on the target function by using a preset swarm intelligence optimization algorithm according to the target constraint condition to obtain a first resonance parameter; when it is monitored that the impact signal performance index extracted based on the first resonance parameter is lower than a preset threshold value, the first resonance parameter serves as a search starting point, local optimization is conducted on the target function, and a second resonance parameter is output. And the most suitable resonance parameter is automatically selected in the actual operation process.

The invention discloses a data burying point and analysis method and system for cross-platform dynamic configuration, and relates to the technical field of data burying point, a server determines a candidate parameter set of burying point configuration based on an event model, performs optimization through a swarm intelligence algorithm, generates dynamic burying point configuration including a target control topological neighborhood feature vector, and transmits the dynamic burying point configuration to a server; issuing to a terminal; the terminal calculates the geometric structure similarity between view tree nodes and topological neighborhood feature vectors, and binds the nodes exceeding a threshold value as a buried point trigger source; when a burying point trigger source is activated, obtaining an operation sequence of a current context and sampling strategy generation event data, injecting a logic precursor identifier and a statistical weight factor, and sending the data to a server through local caching and batch reporting; and the server performs logic causal rearrangement, constructs a statistical analysis model to identify a statistical weight factor, executes inverse probability weighted calculation and outputs an unbiased analysis result, so that the problem of burying point failure caused by version iteration is solved, and the robustness and adaptability of burying point configuration are improved.

The invention relates to the technical field of intelligent group collaboration, and discloses a cloud dynamic load-driven group intelligent collaboration processing system and method, and the method comprises the steps: carrying out the feature extraction, coupling degree matrix construction, spectral clustering initialization, load sensing clustering, and high coupling node optimization operation based on the network topology and task demands of an intelligent agent. Dynamically dividing intelligent agents into cooperative subgroups, and outputting a subgroup division structure and a resource capability matrix on the premise of ensuring load balance and minimizing communication overhead; and according to the task resource demand and the subgroup capability matrix, constructing a multi-objective optimization model. According to the method, efficient self-adaptive processing in a dynamic environment is realized through deep fusion of cloud computing elastic resources and a swarm intelligence collaboration mechanism, topology mutation and resource fluctuation caused by frequent joining / quitting of the agents can be autonomously dealt with, the delay sensitivity of multi-agent interaction is reduced through optimization of communication efficiency, and the service life of the multi-agent interaction is prolonged. And real-time cooperative computing of large-scale groups on a cloud platform is supported.

The embodiment of the invention provides a net power prediction method and device, equipment, a medium and a program product, and particularly relates to the technical field of electric power. The method comprises the following steps: optimizing parameters of a signal decomposition model by adopting a swarm intelligence optimization algorithm, and determining a target parameter combination; based on the determined target parameter combination, performing variational mode decomposition on the net power historical sequence data to obtain a plurality of mode components; extracting high-frequency mutation features and low-frequency trend features for the plurality of modal components to obtain modal component feature vectors corresponding to the modal components respectively; performing net power prediction based on the modal component feature vectors in combination with the bidirectional time sequence modeling model to obtain prediction results corresponding to the modal components; and generating a final net power prediction result based on the prediction result corresponding to each modal component. The method is used for achieving the effect of improving the net power prediction precision and real-time performance in a complex scene.

The invention belongs to the technical field of water resource optimal scheduling, and discloses a reservoir optimal scheduling method based on hybrid swarm intelligent optimization, which comprises the following steps: S1, collecting data required by reservoir historical inflow, a reservoir capacity curve, a water supply demand and a scheduling constraint condition; s2, setting a constraint condition and a scheduling target, and establishing a reservoir scheduling optimization model; s3, constructing a candidate solution group on the basis of combining reservoir scheduling decision variables, performing initial fitness calculation by utilizing an objective function of the reservoir scheduling optimization model, introducing a hybrid group intelligent optimization algorithm, performing multi-objective optimization scheduling calculation on the reservoir scheduling optimization model, and performing iterative updating; s4, completing all set iterations, and outputting a reservoir optimization scheduling scheme meeting constraint conditions; according to the method, the premature convergence problem of a traditional swarm intelligence optimization algorithm is effectively avoided, the convergence speed and the solution stability are improved, and the method is suitable for optimization solution of single-library and multi-library systems in single-target or multi-target scheduling problems of water supply, flood control, power generation and the like.

The invention discloses a financial credit data verification system with zero knowledge proof, and relates to the technical field of financial science and technology. According to the system, a ZKP multi-source credit data acquisition module acquires multi-dimensional credit data of a borrower, and a data available and invisible mechanism is adopted to protect privacy; the credit data entropy analysis module quantifies data uncertainty based on a clustering algorithm, dynamically generates a threshold value in combination with a historical entropy value, and quickly screens abnormal data; a ZKP enhanced feature extraction module captures a dynamic change rate index and zero knowledge proof features; the deep verification model evaluation module utilizes a deep belief network and a federated learning framework to realize high-precision anomaly recognition on the premise of protecting privacy; the verification strategy regulation and control module generates a parameter regulation and control strategy through a swarm intelligence optimization algorithm; the feedback optimization module dynamically adjusts parameters through a closed-loop feedback mechanism, and improves the efficiency, precision and safety of financial credit data verification.

The invention belongs to the technical field of artificial intelligence and medical rehabilitation, particularly relates to an intelligent training optimization system for orthopedic rehabilitation, and aims to solve the problems of insufficient individuation, feedback lag, subjective evaluation and the like in traditional rehabilitation training. The system collects motion and physiological data through a wearable sensing unit, and generates and adjusts a training scheme in combination with a self-adaptive optimization algorithm driven by cloud individualized modeling, dynamic risk assessment and reinforcement learning; real-time motion correction is achieved through multi-modal feedback, doctor-patient cooperation and group intelligent analysis are supported through a clinical management platform, and rehabilitation safety, effectiveness and accessibility are improved.

The invention provides an AGI group optimization method based on a common star map, which solves the problem that the optimization process of a single model is lack of multi-view verification and counterbalance, and the like, and carries out real-time acquisition and mathematical aggregation on decision coordinates of a plurality of AGI mental entities in a shared vector space defined by a formalized philosophy axiom, so as to improve the optimization accuracy of the AGI group. Generating a dynamically evolved group consensus field domain; furthermore, incremental learning fine tuning guided by non-forced traction vectors is performed on deviated individuals based on the field domain, and directional scene generation and exploratory training are performed on a group cognitive blind area identified through spatial density analysis, so that a group cognitive blind area field domain is constructed on the premise of enabling the individuals to be in equal symbiotic with the group. And the AGI group intelligent ecosystem can continuously converge to a value origin, collaboratively expand a cognitive boundary and has a self-perfection capability. The method has the advantages of high inclusiveness, good safety and the like.

The utility model discloses an assembly type wallboard structure based on a swarm intelligence algorithm, and particularly relates to the technical field of assembly type wallboard structures, the assembly type wallboard structure comprises a foundation layer, a waterproof layer, a filling layer, a heat preservation layer and an installation clamping groove, the waterproof layer is installed on the foundation layer, the filling layer is installed on the side face of the waterproof layer, and the heat preservation layer is installed in the installation clamping groove. A heat preservation layer is mounted on the side, away from the waterproof layer, of the filling layer, a mounting clamping groove is formed in the upper portion of the heat preservation layer, the foundation layer comprises a reinforcing steel bar filling plate, a damp-proof plate and a separation layer, the damp-proof plate is mounted on the reinforcing steel bar filling plate, and the separation layer is mounted on the damp-proof plate; according to the fabricated wallboard structure based on the swarm intelligence algorithm, the construction site can be rapidly analyzed through the swarm intelligence algorithm, the installation route of the fabricated wallboard structure is analyzed, and construction workers only need to conduct construction according to the route of the swarm intelligence algorithm, so that the construction efficiency can be guaranteed.

This invention discloses an adaptive control method, training method, and apparatus for swarm intelligence agents, relating to the fields of artificial intelligence and computer science. The method includes: constructing joint intelligence agents for each joint of a robot and configuring connection relationships; constructing a central intelligence agent to process input information; setting a mechanism for parameter sharing and synchronous updating for each joint intelligence agent and the central intelligence agent; the central intelligence agent outputting signals to control each joint intelligence agent; acquiring real motion data and evaluation data; and training and optimizing each joint intelligence agent and the central intelligence agent based on the real motion data and evaluation data through imitation learning and reinforcement learning before controlling the robot. This invention solves the problems of existing technologies' inability to achieve multi-task, multi-scenario robot control, and poor generalization and flexibility, by constructing intelligence agents for each joint of the robot and configuring connection relationships, and by constructing a central intelligence agent to process diverse input information.

The invention discloses an optical storage and charging dynamic energy management method based on swarm intelligence optimization. The method comprises the following steps: step 1, collecting and standardizing original multi-source optical storage and charging data; 2, feature extraction and jump connection are carried out through a ResNet network; 3, inputting the optical storage and charging feature vector into an improved GATv2 model to obtain an energy flow prediction optimization model; 4, globally optimizing the load balance of the energy flow prediction optimization model by adopting a differential evolution algorithm; 5, monitoring the energy loss between the optical storage and charging devices and compensating the energy loss; 6, adjusting an energy scheduling strategy and carrying out feedback processing; 7, generating a Hash value through Hash processing, and storing the Hash value to the block chain; and 8, generating an optical storage and charging equipment scheduling log based on the block chain record. According to the invention, the improved GATv2 model and the differential evolution algorithm are combined, so that the energy efficiency, the load balance and the safety of the optical storage and charging system are improved.

The application discloses a kind of deep reinforcement learning method and system for group wisdom flag capture game, solve the problem of group wisdom path planning and flag capture under the condition of external competition, internal cooperation of imperfect information.Specifically, first, the picture features are extracted based on the split channels of convolutional neural network;Then, based on the graph attention network, the competitive relationship between agents under the condition of imperfect information is quantitatively determined according to the observed information and the received teammate observation information, so that the agent fully considers the state of other agents when making decisions;Finally, according to the attention value of different agents on the field, the multi-agent double duel deep Q network is assisted to realize the path planning and autonomous navigation of multi-agent in a two-dimensional maze environment, optimize the group wisdom flag capture strategy, to realize fast and accurate two-to-two flag capture.

The present application relates to the technical field of agricultural remote sensing and machine learning, and particularly relates to a leaf area index estimation method based on improved XGBoost. The method comprises the following steps: acquiring unmanned aerial vehicle multi-spectral images and sample leaf area index measured values, and constructing a vegetation index map sample data set after preprocessing; performing feature extraction and fusion on the vegetation index map by using a deep learning network; constructing an improved beaver optimization algorithm, generating an initial population by using a two-stage initialization strategy, updating the position of the architect subpopulation by using an elite directional felling strategy, recombining individuals and the global optimal solution by using a vertical and horizontal cross strategy; optimizing the XGBoost hyperparameters by using the improved beaver optimization algorithm, and establishing a leaf area index estimation model. The leaf area index estimation method based on improved XGBoost combines deep learning feature extraction, improved swarm intelligence optimization algorithm and integrated learning regression modeling, and is helpful to improve the prediction accuracy and stability of the leaf area index estimation model.

This invention discloses a brain-inspired bio-inspired asynchronous event-driven sparse computation method for massive video swarm intelligence, belonging to the field of brain-inspired computing technology. Addressing the problems of resource overload, low computational efficiency, and insufficient system adaptability in city-level video swarm intelligence sensing, it constructs an edge-cloud collaborative asynchronous event-driven architecture: the edge triggers effective events based on a bio-inspired mechanism to generate and transmit sparse video data; the edge uses an SNN-ANN dual-stream architecture to asynchronously extract semantic features; the intermediate layer only triggers spatiotemporal fusion and trajectory stitching for cross-domain events; and the cloud completes global situation aggregation and dynamically adjusts the trigger thresholds of each layer according to system resource load. This invention enables sparse computation with no-event sleep and event-awakening capabilities, significantly reducing data transmission and computational overhead, improving system energy efficiency and stability, and can be widely applied to massive video swarm intelligence sensing scenarios such as smart transportation, security monitoring, and city brains.

The invention discloses a teenager long-distance running strategy method fusing deep learning and an improved swarm intelligence optimization algorithm, and the method comprises the following steps: collecting multi-dimensional time sequence features in the historical training and competition process of athletes, and constructing and training a CNN-LSTM-Attention prediction model based on the multi-dimensional time sequence features; establishing an integral form long-distance running strategy optimization model framework with the goal of minimizing the game completion time; dividing the long-distance running process into a plurality of continuous time sequence windows, calling a CNN-LSTM-Attention model at the starting moment of each window to generate a state prediction result as a dynamic constraint, and constructing a state transition equation; and based on the state transition equation, solving the optimal speed under the current time sequence window through an improved dung beetle optimization algorithm, rolling to the next window after execution, and carrying out iterative execution until the optimal speeds under all time sequence windows are output.