47 results about "Swarm behavior" patented technology

The invention provides a mobile phone big data-based floating population classification identification analysis method. According to the method, the limitation of conventional survey is broken through; objective time-space information is extracted from a behavior track by utilizing big data to perform analysis mining; the limitation of low sampling rate is broken through and multi-time full information extraction of different dimensions can be performed; population mobility is observed and identified in space and time to distinguish floating population groups; and floating population is classified into long-term floating population, short-term floating population and short-time immigration population by considering different categories of the floating population from the perspective of users based on behavior characteristics and staying durations of the groups, so that the application of data can generate values in different fields.

The invention discloses a crowd behavior model analysis and abnormal behavior detection method under a geographical environment. The method comprises the following steps that: video monitoring signals can be captured, and crowd movement regions in a monitoring scene are set, and video monitoring crowd images are obtained, and geographic spatial mapping processing is performed on the crowd movement regions; measurable crowd movement fields are calculated through using an optical flow method under geographic reference, and the crowd movement fields are converted and mapped to polar coordinate reference; according to the distribution situation of the crowd movement fields under the polar coordinate reference, statistical analysis is performed on the crowd movement fields at each main direction of the polar coordinate reference, and then, crowd movement models and crowd movement trends under the geographical environment can be judged, and crowd movement rate at each main direction can be estimated; and based on the analysis results of the crowd movement models, movement trends and movement rate, detection on crowd abnormal behaviors such as movement rate mutation, movement trend mutation, reverse walking, sudden aggregation and sudden scatter is performed. The crowd behavior model analysis and abnormal behavior detection method of the invention can be widely used in areas where crowds are prone to aggregation.

The invention discloses a crowd evacuation path planning method based on an artificial fish swarm algorithm. The crowd evacuation path planning method includes the steps: building an artificial fish swarm model and initializing relevant parameters; calculating the distance between each grid and a danger source and the crowdedness degree of each grid, and updating artificial fish positions if open exit evacuation is performed; calculating the distance between each grid and an exit and the crowdedness degree of each exit zone, and updating the artificial fish positions if fixed exit evacuation is performed; generating the optimal path of crowd evacuation simulated by individual artificial fishes. The crowd evacuation path planning method has the advantages that swarm adaptive path planning can be realized, a parameter setting panel is designed by the aid of a visual interface, evacuation behaviors under different situations are simulated, generated movement more conforms to swarm movement in a real world, so that unpredictable swarm behaviors are generated, and movement authenticity is improved.

The invention discloses an adaptive abnormal crowd behavior analysis method, which is used for analyzing crowd behaviors in a video image. The method comprises the following steps of performing streak line calculation on the video image; calculating a streak line flow; detecting abnormal behaviors; performing foreground detection on the video image of abnormal crowd behaviors; performing adaptive crowd density estimation comprising pixel-counting-based density estimation and texture-analysis-based density estimation, and finally dividing estimated density into four density levels, i.e. a low density level, a medium density level, a high density level and an ultrahigh density level, thereby finishing grading the abnormal crowd behaviors. According to the method, the concepts of streak line and streak line flow are introduced to analyze whether a crowd in the video image is abnormal or not; the method has the advantage of detection accuracy; the densities of crowds involved in the abnormal crowd behaviors in different density scenarios are estimated in an adaptive way, and the detected abnormal crowd behaviors are graded by using density estimation results as main characteristics; the method is used for accurately grading the abnormal behaviors (such as mass brawl) in crowded public places, and giving alarms.

The invention discloses a robot path planning method. A direction operator is introduced on the basis of an artificial fish swarm algorithm to improve the accuracy and the success rate of fish swarm behaviors such as clustering, tailgating and even foraging, and an immunological memory operation is added to improve the global searching capability of the algorithm and reduce the probability of local extreme values. Simulation experiments in two typical grid map environments show that compared with a fast genetic algorithm and an artificial fish swarm algorithm, the immunological-directional artificial fish swarm algorithm has the advantages of better result stability, shorter calculation time and feasible solution closer to the optimal path.

The invention provides an abnormal behavior detection method based on a large-scale WiFi activity track. The method comprises the following steps: on the basis of a collected MAC record, finding MACs with normal individual behaviors by using a frequent track mining algorithm, extracting the activity feature attributes of these MACs with normal individual behaviors to serve as the input of an SVDD algorithm, establishing a plurality of abnormal behavior detection models to filter a large number of MACs satisfying group behavior rules, thereby not only greatly shortening the time necessary for processing large-scale data, but also ensuring the stability of the abnormal behavior detection method, the feature of serious unbalance of positive and negative samples in the application environment can be well overcome, and accordingly time consistency and space consistency detection is carried out on a single MAC different from the group behavior rules to lock the MAC with abnormal activity more accurately. By adoption of the abnormal behavior detection method provided by the invention, the moving track of a moving object in the public security field can be monitored in real time, abnormal behaviors can be identified accurately in real time, auxiliary judgment is provided for the happening security events, and early warning is provided for the possible security events.

The invention discloses a bionic swarm intelligence-based real-time positioning navigation and motion control method for a moving vehicle and is used for solving the technical problem of lower reliability of the existing real-time positioning navigation and motion control method for the moving vehicle. The technical scheme is that the method comprises the steps of firstly selecting the vehicle and information nodes of known coordinates in a complex road as the positioning reference nodes, converting the equation set positioning and solving problem into the extreme value optimizing problem, and adopting a bionic swarm algorithm to solve the positioning coordinates. For the control on driving among multiple vehicles, a bionic swarm motion model is established to control the motion among the vehicles by establishing the bionic swarm behaviors, and the controllability on the real-time positioning and navigation and the motion control for the moving vehicle is improved. The real-time positioning navigation and motion control system for the moving vehicle is formed by a vehicle-mounted terminal module, a road information node module and a road traffic control center module. The three modules cooperatively work to realize the real-time positioning navigation and motion control on the moving vehicle.

Apparatus, systems, and methods may operate to present a wagering game upon which monetary value may be wagered; to present an initial image including a subset of a swarm in space representing a portion of the wagering game; and to determine the actual outcome of the wagering game based on player input indications, swarm behavior modeling, and a selected statistical game outcome. An updated image may then be generated and presented, derived from the initial image and the actual outcome.

The invention discloses a complex chemical process modeling method of a DNA genetic algorithm based on a swarm behavior. The method includes the following steps of firstly, obtaining input sampling data and output sampling data in the chemical process through experiments, and using the sum of an error absolute value of estimated output of a model and an error absolute value of practical sampling output in the chemical process as a fitness function aiming at the input sampling data in the same chemical process; secondly, setting control parameters of the algorithm; thirdly, conducting estimation on unknown parameters in a chemical process model by running the algorithm, obtaining estimated values of the unknown parameters in the model through a minimum objective function value, putting the estimated values of the unknown parameters in the model into the chemical process model, and obtaining an optimal chemical process model. According to the complex chemical process modeling method of the DNA genetic algorithm based on the swarm behavior, by the adopting of the DNA genetic algorithm based on a swarm honey gathering behavior and a swarm breeding behavior, the established chemical process model is made to have high fitting precision, and has the advantages of being high in convergence rate and rich in population diversity.

The invention discloses a method for identifying key proteins with an AFSO (artificial fish school optimization) algorithm. The method comprises steps as follows: a protein-protein interaction networkis converted into an undirected graph, a purified protein-protein interaction network is constructed, RNA gene expression values corresponding to proteins, GO comment information and degrees of proteins in known compounds are obtained, edges and nodes of the purified protein-protein interaction network are treated, known key proteins are selected as initial artificial fishes, the artificial fishes execute foraging behavior, random behavior, following behavior and swarm behavior, and the key proteins are produced. According to the method, the key proteins can be identified accurately; a simulation experiment result indicates that performance of indexes such as sensitiveness, specificity, a positive predictive value, a negative predictive value and the like is better; compared with other methods for identifying the key proteins, the method has the advantages that optimizing characteristics of artificial fish schools are combined with topological characteristics of the protein-protein interaction network to realize the key protein identification process, and the accuracy rate of the key protein identification is increased.

A cloud application management infrastructure models biological swarm behaviors to assign application resources to physical processing resources in a decentralized manner. A balanced and highly automated management of cloud infrastructure has a predictable and reliable response to changing resource loads by using a limited local rule set to define how application instances interact with available resources. Digital pheromone signals at physical resources are applied locally by a swarm module to determine if the physical resources provide an acceptable environment for an application and, if not, the application swarms to other environments until a suitable environment is found.

The invention relates to a neural network-based method for swarm robots to realize cooperative foraging through using pheromone-based communication. The method includes the following steps that: a neural network model is established; a pheromone volatilization model is designed; and a system overall behavior framework model is established. According to the method of the invention, the pheromone volatilization model of swarm robot cooperative foraging behaviors is put forward and is defined as Ii(t), that is, the external input of an i-th neuron at a time t, and in the formula, an attracting pheromone Pa has a large positive value, a repulsion pheromone Po and a repulsion pheromone Pe have small negative values; when a foraging robot finds food and transports the food back to a nest, the foraging robot releases the attracting pheromone Pa; when the robot avoids an obstacle, the robot releases the repulsion pheromone Po; when the robot searches for food randomly in a working environment,the robot releases the repulsion pheromone Pe; the neural network updates output at any time according to the change of the Ii(t); and the evolution of the neural network enables the swarm robots tocommunicate locally, and witness self-organized group behaviors during an interaction process.

The invention discloses a circulating water culturing water quality intelligent early warning device and method based on fish shoal behavior spatio-temporal characteristics. The device comprises a circulating water culture pond, a circulating water treatment system, a depth camera, an alarm, mobile equipment, a display and a server. The device mainly utilizes a computer vision technology and an image processing technology to construct a motion influence diagram capable of reflecting water quality change characteristics, and performs water quality abnormity early warning in time under the condition of not influencing normal growth and development of fishes through quantitative analysis of spatiotemporal characteristics of fish shoal behaviors. The device is simple in structure, the method is accurate, simple and convenient, the intelligent water quality early warning device and method can effectively solve the problems that existing common water quality detection equipment is not high in accuracy and low in reliability, it is guaranteed that the water quality of the aquaculture water body is within the adaptive range in a non-invasive mode, and fish aquaculture welfare is facilitated.

Provided is a method for providing a safe operation of subsystems within a safety critical system (SCS), wherein a malfunctioning subsystem of the SCS sends a malfunction signal to the other subsystems of the SCS including a one-time cryptographic key unique to the malfunctioning subsystem, which is then decrypted by the other subsystems and collective safety management is initiated when the cryptographic key is valid. Also provided are traffic control systems, autonomous driving systems or automotive driver assistance systems. A swarm-like behavior of the subsystems collectively reacting to emergency situations is combined with a one-time cryptographic authentication and/or authorization procedure preventing repeated manipulation of the system by the same perpetrator.

The invention discloses a method for judging swarming behavior of bees by utilizing temperature change. The method comprises the following steps: as the activity of bees in a honeycomb before swarming causes the rise of temperature of a swarm, a sensitive temperature point, namely a swarming early-warning temperature threshold, is set by utilizing the temperature rise characteristic in the design, wherein the temperature change in the honeycomb corresponding to the temperature change is most sensitive; in a plurality of honeycombs of a beehive structure, two wireless temperature sensor monitoring nodes are set corresponding to each honeycomb, so as to realize the accurate temperature detection; swarming early-warning temperature threshold is acquired by adopting honeycomb temperature change algorithm through utilizing a K-means method for clustering analysis, the temperature threshold acquired by a wireless sensing network is compared with the swarming early-warning temperature threshold, if the temperature value is greater than the swarming early-warning temperature threshold, that swarming behavior occurs in the honeycomb can be judged.

The invention relates to a bee swarming early-warning method. The bee swarming early-warning method comprises the steps that a temperature probe of a temperature sensor is arranged at the front portion of a honeycomb in a beehive; a swarming early-warning temperature threshold is set, the temperature value acquired by the temperature probe is compared with the swarming early-warning temperature threshold, it is judged that a swarming behavior occurs in the honeycomb and alarm information is sent to a bee keeper if the temperature value acquired by the temperature probe is greater than the swarming early-warning temperature threshold. According to the bee swarming early-warning method, the temperature probe is arranged in the area in which temperature change is the earliest and most sensitive in a front swarming honeycomb, namely the front portion of the honeycomb, occurrence of swarming can be early warned 15 minutes earlier, and bee-keeping production loss caused by swarming is effectively avoided.

The invention belongs to the field of group behavior management and control, and discloses a special group gathering behavior early detection and gathering place prediction method and system. The effective active members of the group are defined by using a gathering behavior detection algorithm based on the average sliding distance between the effective active members, and the interference of thenoise member on gathering behavior detection can be eliminated; as for the special group having the gathering behavior, the gathering tendency of the group is detected in the early stage of the groupactivity and early warning is given; and the potential gathering members are selected through screening by using a gathering place prediction algorithm based on the potential gathering member moving trace least square fitting straight line so as to perform gathering place prediction. Rapid judgment of the special group gathering behavior can be realized by only using the historical moving trace data of the group members without depending on the video monitoring system, early warning is given to the group having the gathering behavior in time and the gathering place can be accurately predicted.

The invention belongs to the technical field of ocean wave height prediction, and discloses an ocean wave height prediction method and system, computer equipment, a storage medium, and a terminal. The method comprises the following steps: selecting a feature with a high correlation coefficient as an input feature for predicting an ocean wave height; establishing a chaos model according to particle swarm behavior characteristics to solve the problem of premature convergence of particle swarms, wherein the CDW performs optimization in an initialization stage for a BP model, and in a CPSO-BP model, a chaotic particle swarm optimization (CPSO) algorithm searches optimal particles in a solution space to optimize initial weights and threshold values of a BP network; using parameters optimized by the CPSO algorithm as initial weights and threshold values of an ELM network to be transmitted to an ELM network; carrying out wave height prediction in the ocean early warning field by using a CPSO-BP model or a CPSO-ELM model. The deep learning method is used for wave height prediction, and the method has the advantages of high accuracy, low cost and high operation speed.

The invention discloses an unmanned aerial vehicle swarm countering method based on swarm behavior characteristics. According to the method, radar and infrared information and visible light images of an unmanned aerial vehicle swarm are collected through detection and recognition equipment arranged on a mobile carrier; the spatial position of the unmanned aerial vehicle is predicted by using a multi-source information fusion method, and swarm orientation and member position detection is realized; the formation and the motion trail of the unmanned aerial vehicle swarm are analyzed by using the swarm behavior characteristics, and recognizing a swarm countering key node; generating a navigation deception signal for the key unmanned aerial vehicle, transmitting an error signal to the whole swarm through the distributed interactive network, forcing the unmanned aerial vehicle swarm to deviate from an original flight path, and achieving the countering of the unmanned aerial vehicle swarm. According to the invention, through application of behavior characteristics of the unmanned aerial vehicle swarm, a problem of insufficient capability of countering the unmanned aerial vehicle swarm is solved, threats of omnidirectional defense penetration of the unmanned aerial vehicle swarm to important economic facilities are solved, and countering of the unmanned aerial vehicle swarm is effectively realized.

The invention discloses a method and equipment for determining the occurrence place of group behaviors, which are used for determining the occurrence place of the group behaviors in time and can be used for intelligently evacuating aggregated groups in time. The method comprises the steps that a monitored environment area is divided into grid areas corresponding to different environment attributes, and each grid area is divided into at least one fine grid; processing the sampling data of the terminal in the fine grid area based on an edge data center, determining a terminal behavior parameterwarning value corresponding to the fine grid, and determining a terminal behavior parameter in the fine grid area; and according to the determined terminal behavior parameter alert value correspondingto the fine grid and the terminal behavior parameters in the fine grid area, determining whether the fine grid has a user group aggregation behavior or not.

The invention discloses a behavior trajectory sequence multi-feature simulation method based on quantum walk. The method comprises the following steps: (1) generating a complete set feature sequence; (2) screening a feature sequence; (3) constructing a feature sequence mapping mechanism; (4) executing the experimental verification. According to the method, on the basis of conversion combination characteristics between individual behaviors and group behaviors, the feature structures of similar individuals are simulated from the perspective of multi-scale analysis by utilizing quantum migration, and behavior tracks are simulated.

The invention discloses a multi-tenant-based safe configuration method of a virtual machine in a cloud data center. The method comprises the following steps: collecting idle resource in the cloud data center; collecting recourse usage requests of user equipment; safely allocating the virtual machine resources which all users apply for by employing an artificial fish swarm algorithm; initializing parameters of the artificial fish swarm algorithm; calculating the optimal fish position and the optimal value and recording the same in a bulletin board; for each artificial fish, choosing and executing the optimal behavior among a swarming behavior, a following behavior and a preying behavior; calculating the new position and fitness function value of each artificial fish, and then updating the bulletin board; judging whether the algorithm termination condition is met or not, if not, returning to the second step, and if so, then entering the next step; taking the obtained optimal fitness function value as the optimal artificial fish position; and repeating the second to sixth steps for Ng times to obtain the optimal safe allocation result of the virtual machine resources. The invention can significantly improve the quality of service of users and reduces the resource waste of the cloud data center.

The invention provides a big data fusion processing method and system, and the method comprises the steps: extracting the behavior data of each target user in a target user group, recognizing a specific behavior from the behavior data of a single target user, and determining the individual behavior characteristics of each target user, and fusing the individual behavior characteristics of the target users to obtain group behavior characteristics of the whole target user group, and classifying the target user group according to the group behavior characteristics. Therefore, the determined group behavior characteristics can more accurately reflect the influence of individual behaviors on the whole group, so that the characteristics of the whole user group are more accurately reflected, and the user group classification action based on the group behavior characteristics is more accurate.