Country public space collaboration evaluation method and system based on continuous track electroencephalogram

Abstract

The invention discloses a rural public space collaboration evaluation method and system based on continuous track electroencephalogram, and relates to the technical field of human settlement environment space quality measurement, and the method comprises the steps: receiving related data of a rural public space, carrying out the preprocessing of the related data of the rural public space, and obtaining the processed related data of the rural public space, the related data of the rural public space comprises walking sightseeing real-time electroencephalogram data, continuous GPS track data and environment basic geographic space data; based on the processed rural public space related data, extracting a walking brain perception cooperation index, inputting the walking brain perception cooperation index into a pre-established Gaussian process regression model based on a perception cooperation attenuation kernel function, and outputting to obtain a distribution result of the rural public space cooperation degree; and obtaining hierarchical vector transfer data and weight data of the environmental elements, projecting the hierarchical vector transfer data and the weight data of the environmental elements to the rural public space grid units, and performing superposition in combination with the distribution result of the rural public space collaboration degree to obtain a rural public space environmental element weighted collaboration degree distribution result. And clustering to obtain a village advantage collaboration space and a disadvantaged collaboration space.

Description

Technical Field

[0001] This invention relates to the field of human settlement environment spatial quality measurement technology, specifically a method and system for evaluating the collaborativeness of rural public spaces based on continuous trajectory EEG. Background Technology

[0002] Rural public spaces refer to open areas accessible to rural residents, primarily consisting of hard-surface spaces, and serve as an important carrier of rural life. The synergy of rural public spaces refers to the systemic characteristics that maximize spatial efficiency by analyzing the dynamic adaptation relationship between residents' neural perception and physical space through trajectory EEG data analysis. Its core lies in breaking down the disconnect between people and space, achieving value co-creation and collaborative development. In the process of rural renewal and governance, the design of rural public spaces is highly relevant to environmental quality, integrating the construction logic of physical and perceived spaces, carrying the connotations of life, and responding to the demands of the times. Therefore, scientifically integrating the "perception-behavior-environment" information of rural public spaces, conducting measurements of walking brain perception synergy and geospatial weighted clustering visualization, and providing targeted guidance for the design and renovation of rural public space environments, thereby promoting the upgrading of humanized and warm spatial quality, has become an important path to achieving refined rural governance.

[0003] Continuous trajectory EEG is a cross-modal data integration concept, referring to a spatiotemporally coupled dataset of "neural response-geographic location" formed by synchronously acquiring, processing, and matching continuous EEG signals and movement trajectories. EEG signals reflect the neurophysiological state of the brain, capturing brain activation, approach-avoidance perceptual responses, and fluctuations; while movement trajectories reflect changes in location and movement paths in geographic space. Based on the integrated data analysis of EEG signals and movement trajectories, real-time measurement of continuous walking paths and corresponding brain perception data in the spatial environment, combined with spatial synergy fusion prediction of environmental elements and weighted spatial overlay generation, is beneficial for improving the accuracy and decision-making efficiency of synergy analysis in rural public spaces.

[0004] Currently, the perception evaluation data for relevant rural public spaces mainly comes from subjective reports of environmental images. This data has low temporal resolution, making it prone to bias and distortion. Furthermore, existing methods struggle to effectively capture the trajectory location and temporal changes of instantaneous environmental perception data. Specifically, the geographic pixel scale of the perception space is large, and the spatial grid resolution is low, limiting the reliability and accuracy of perception space distribution predictions. In addition, the lack of synergistic integration analysis of rural environmental material elements and perception space results in low integration of rural public space quality measurements, thus limiting their application in urban renewal and governance. Summary of the Invention

[0005] To address the shortcomings mentioned in the background section, the present invention aims to provide a method and system for evaluating the collaborativeness of rural public spaces based on continuous trajectory EEG.

[0006] The system receives data related to rural public spaces, preprocesses the data to obtain processed data related to rural public spaces, including: real-time EEG data of walking tours, GPS trajectory data, and basic geospatial data of the environment.

[0007] Based on the processed data of rural public space, the walking brain perception coordination index is extracted. The walking brain perception coordination index is then input into a pre-established Gaussian process regression model based on the perception coordination decay kernel function, and the distribution results of the coordination degree of rural public space are output.

[0008] Hierarchical vector transfer data and weight data of environmental elements are obtained, and the hierarchical vector transfer data and weight data of environmental elements are projected onto rural public space grid units. Combined with the distribution results of rural public space synergy, the weighted synergy distribution results of rural public space environmental elements are obtained by overlaying, and the rural advantageous synergy space and weak synergy space are obtained by clustering.

[0009] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: the preprocessing of data related to rural public spaces includes noise cleaning and artifact removal of real-time EEG data from walking tours, and smoothing and anomaly filtering of continuous GPS trajectory data.

[0010] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: the process of noise cleaning and artifact processing of the real-time EEG data of the walking tour includes:

[0011] The raw EEG data underwent noise removal and artifact processing. The raw EEG data was real-time EEG data from a walking tour, and was a time series matrix S = [s1, s2, ... s2] containing M channels. M ], s m =[s m (1),s m (2),…,s m (N)] T Let m represent the signal of the m-th channel, where m = 1, 2, ..., M. High-pass and low-pass filters are applied to the original EEG data, and Bootstrap sample statistics are performed c times randomly, where c = 1, 2, ..., C, to obtain the three-dimensional matrix of the EEG resampled signal at the i-th time point.

[0012] Each channel signal s is transformed using the maximum overlap discrete wavelet transform.m The wavelet coefficients W = [w] of the m-th channel at the j-th decomposition level in a time series of length n are obtained. j,n [n], for each channel m and artifact substitution signal k = 0, 1, ..., K, generate a substitution time series. And the wavelet coefficients for each channel m, decomposition level j, and sample point n are obtained. Calculate the threshold Θ from the alternative distribution. j,m (n) and significance level α, to obtain the filtered wavelet coefficient w of the m-th channel at the j-th decomposition level. j,m,filtered (n) is:

[0013]

[0014] The filtered signal for each channel is reconstructed using inverse maximum overlap discrete wavelet transform, and the filtering results of all channels are combined into a filtered signal matrix S. filtered =[s 1,filtered ,s 1,filtered ,…,s M,filtered ];

[0015] The process of smoothing and filtering out anomalies in continuous GPS trajectory data:

[0016] Continuous GPS trajectory data is a matrix of timestamped geographic coordinate sequences, using two adjacent GPS points (x, y, z)... i ,y i ,z i ) and (x i+1 ,y i+1 ,z i+1 The walking speed v is obtained by calculating the horizontal distance and the time difference. i Calculate the walking acceleration a i ,for:

[0017]

[0018] Applying Savitzky-Golay polynomial fitting to digital filtering smoothing speed and acceleration Given a window of length 2k+1, fit the filter coefficients u using the least squares method and the sum of squared residuals (RSS). j ,for:

[0019]

[0020] In the formula, k represents the size of the sliding window. σ represents the average speed of continuous GPS travel. v The standard deviation of continuous GPS travel speed;

[0021] Calculate the smoothed velocity and acceleration The mean and standard deviation are used to detect and remove outliers by Z-score for each smoothed velocity and acceleration.

[0022] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: the process of extracting the walking brain perception coordination index based on the processed rural public space related data: constructing a two-dimensional feature vector of perception coordination and defining a discrete state set, combining the state transition probability matrix and the forward-backward probability algorithm to analyze the brain perception temporal dynamics, and realizing the standardized extraction of the rural public space walking brain perception coordination index.

[0023] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: the extraction process of the walking brain perception coordination index is as follows:

[0024] The power spectral densities of EEG rhythms α and β after cleaning are extracted. Based on the conversion of the power spectral density ratio into a two-dimensional vector of brain-sensory coordination features, the following is obtained:

[0025]

[0026] In the formula, PLE L-H Indicates a state of brain sensory activation; PLE N-P Represents the brain's perception of approach and avoidance states; n represents the number of EEG channels; PSD(α) and PSD(β) represent the power spectral density of EEG rhythms α and β, respectively. r_he and PSD l_he These represent the power spectral densities of the right and left cerebral cortex, respectively.

[0027] The pleasure feature is obtained by z-score normalization. and Perform K-means clustering on the standardized feature data, and set... There are two types: high wake-up and low wake-up. There are two types: positive valence and negative valence. Let the cluster center be... and The midpoint between two cluster centers is used as the threshold to determine the observation sequence O = (PLE) L-H PLE N-P The state of each point in );

[0028] Define walking brain perception coordination as a set of three discrete states H = {cooperative, neutral, non-cooperative}, and define a given system at time t in a cooperative state O. t The probability is:

[0029]

[0030] In the formula, O t This represents the observation sequence of walking brain perception coordination features at time t; and This represents the brain's sensory coordination characteristics at time t; TH L-H and TH N-P They represent PLE respectively L-H and PLE N-P Clustering threshold;

[0031] Establish the walking brain perception coordination state transition probability matrix A = [a ij ] and D = [d j (O t )], calculate the forward probability σ of random transitions in brain-sensory coordinated states over time series. t (j) and backward probability for:

[0032]

[0033] In the formula, σ t (j) represents the non-observed walking brain perception coordination state H at time t. j And the sequence O1, O2, ..., O was observed. t The joint probability; σ t-1 (i) indicates that the walking brain perception coordination state at time t-1 is H. i Forward probability; a ij The walking brain sensory coordination state is represented by H i Transfer to H j The probability of d; i (O t ) indicates the brain's sensory coordination state during walking. j O was observed below t The probability of; H represents the unobserved walking brain sensory coordination state at time t. i And sequence O was observed t+1 O t+2 ,…,O T The probability of; H represents the brain's sensory coordination state during walking at time t+1. j The backward probability; b j (O t+1 ) indicates the brain's sensory state during walking, H j O was observed below t+1 The probability of;

[0034] The probability of waking-brain sensory coordination at each time point is calculated as follows:

[0035]

[0036] Introduce weighting coefficients 1+τ·d based on equivalent distance adjustment e ,for:

[0037]

[0038] In the formula, (x i ,y i ,z i ) and (x i+1 ,y i+1 ,z i+1 ) represents the coordinates of two adjacent GPS points, ω is the Naismith constant; τ is the constant coefficient;

[0039] Calculate the characteristics of EEG static standing baseline state The standardized walking brain-sensory coordination index is obtained by subtracting the baseline value from the observed value. for:

[0040]

[0041] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: the pre-established Gaussian process regression model based on the perceptual co-decay kernel function is constructed based on the integration of the visual field of continuous walking trajectory in rural public space and the gridded geospatial model of brain perceptual co-location.

[0042] By identifying subject E m Continuous walking trajectory R in rural public spaces m Where m = 1, 2, ..., M, along the travel trajectory R m With the center point of the grid as the viewpoint G i Among them, G i ∈R m The visual field is generated by uniformly setting up a fine-grained hexagonal grid at intervals of n meters. The visual fields of all viewpoints along the subject's walking trajectory are superimposed to obtain the maximum accessible visual field VF of the rural public space. max And based on VF max Delineate the boundaries of perceptual collaboration in rural public spaces as follows:

[0043]

[0044] Computational viewpoint G i The current grid and the target grid G j The actual distance of the center to the DAC ij and perceived distance DAW ijThe inverse square law equation is used to obtain the distance decay index of walking brain perception coordination, and the normalized multiplier U of walking brain perception coordination distance decay is defined accordingly. ij The judgment conditions are as follows:

[0045]

[0046] In the formula, the actual distance to the DAC is... ij The grid G ​​where the viewpoint is located i With target mesh G j Euclidean distance between centers; perceived distance DAW ij The grid G ​​where the viewpoint is located i With target mesh G j The visible distance between centers; It is the walking brain sensory coordination decay index;

[0047] The normalized multiplier U of the walking brain perception coordination decay surface ij Scaling is performed to generate the walking brain perception coordination decay result representing the target grid, as follows:

[0048]

[0049] In the formula, PA ij Indicates at viewpoint G i The contribution value of the perception coordination attenuation to the target grid j; (G i ) represents the viewpoint G i The walking brain perception coordination value at the location;

[0050] Obtain all subjects E m On the trajectory R m Where m = 1, 2, ..., M, and the viewpoint G is on top. i The two-dimensional spatial location index of the grid and its walking brain perception coordination value, based on the maximum visual field (VF) max Use a double loop to traverse the hexagonal grid space, ensuring the viewpoint is within the corresponding hexagonal cell, until the entire rural public space CAD base map is covered. Record the center position of each grid as x. j The radial basis function (RBF) is chosen to train the Gaussian process regression, as follows:

[0051]

[0052] In the formula, ε f The value represents the signal variance; l represents the length scale parameter.

[0053] The normalized multiplier U of the walking brain perception coordination decay was used. ij Construct a prior kernel function for viewpoint G.i Grid position x i Using the corresponding walking brain perception coordination scores as training data, VF max The walking brain perception coordination within the range is smoothed and spatially interpolated, and then averaged to obtain the cumulative walking brain perception coordination of the target grid. for:

[0054]

[0055] In the formula, This represents the walking brain perception coordination value for subject m and each target grid j; This represents the number of viewpoints from which subject m influences target grid j along the walking path; M represents the total number of subjects.

[0056] Perform on all target meshes j The calculation generates a two-dimensional geographical distribution map of rural public space synergy within the perceived synergy boundary.

[0057] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: projecting the hierarchical vector transfer data and weight data of environmental elements onto rural public space grid cells and combining them with the distribution results of rural public space synergy, superimposing them to obtain the weighted synergy distribution results of rural public space environmental elements, and clustering them to obtain rural advantageous synergy spaces and weak synergy spaces.

[0058] The CAD data of rural public spaces is entered into the ArcGIS system, and basic drawings in Model Builder format are obtained through splicing, cropping, projection transformation, geometric correction and georegistration. Data links are also established for the two-dimensional geographic distribution of the coordination degree of rural public spaces.

[0059] Load the shape, spatial location, and attribute descriptions of rural public space environmental elements in shapefile format (shp format). Use the Analysis Tool to transfer and project the vector data of the environmental elements into spatial grid cells within the perceived synergy boundary of the rural public space. The environmental elements within the perceived synergy boundary of the rural public space include plants, facilities, and paving; the environmental elements adjacent to the perceived synergy boundary of the rural public space include fields, courtyards, and water bodies.

[0060] Based on the two-dimensional geographic distribution of rural public space synergy, the vector data of environmental elements such as plants, facilities, paving, fields, courtyards and water bodies are assigned values ​​and transformed into primary synergy raster data.

[0061] Obtain the weight coefficients of various environmental elements, and use the raster calculator to perform a weighted calculation on the primary synergy raster data of all environmental elements, resulting in:

[0062]

[0063] In the formula, Z represents the weighted synergy distribution result of rural public space environmental elements; EL i This is the primary synergy raster data for the i-th environmental element; HW i It is with EL i The corresponding weight coefficients, and satisfying If EL i If the value is null, replace it with 0; otherwise, retain the EL value. i The value;

[0064] Cluster analysis was performed on the weighted synergy distribution of rural public space environmental elements, and the results are as follows:

[0065]

[0066] Among them, HC i Let I and Z represent the local Moran's index of the i-th grid cell. i This represents the weighted synergy value of the i-th grid cell. S represents the average value of all grid cells. 2 w represents variance. ij This is the spatial weight matrix, calculated based on the distance between spatial grid cells i and j;

[0067] Extract the High-High clustering synergy space and its edges, and define them as the advantages of rural public space. Extract the low-low clustering synergy space and its edges, and define them as the vulnerable areas of rural public space.

[0068] Secondly, in order to achieve the above objectives, this invention discloses a rural public space collaboration assessment system based on continuous trajectory EEG, comprising:

[0069] The data processing module is used to receive data related to rural public spaces, preprocess the data to obtain processed data related to rural public spaces, wherein the data related to rural public spaces includes: real-time EEG data of walking tours, GPS trajectory data, and basic geospatial data of the environment.

[0070] The distribution determination module extracts the walking brain perception coordination index based on the processed rural public space related data, inputs the walking brain perception coordination index into a pre-established Gaussian process regression model based on the perception coordination decay kernel function, and outputs the distribution results of the rural public space coordination degree.

[0071] The spatial allocation module is used to acquire hierarchical vector transfer data and weight data of environmental elements, project the hierarchical vector transfer data and weight data of environmental elements onto rural public space grid cells, and combine them with the distribution results of rural public space synergy to obtain the weighted synergy distribution results of rural public space environmental elements, and cluster them to obtain rural advantageous synergy space and weak synergy space.

[0072] In another aspect of the present invention, in order to achieve the above-mentioned objective, a terminal device is disclosed, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor. The memory stores the computer program capable of running on the processor. When the processor loads and executes the computer program, it employs the rural public space coordination assessment method based on continuous trajectory EEG as described above.

[0073] In another aspect of the present invention, in order to achieve the above-mentioned objective, a computer-readable storage medium is disclosed, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is loaded and executed by a processor, it employs the rural public space coordination assessment method based on continuous trajectory EEG as described above.

[0074] The beneficial effects of this invention are:

[0075] This invention addresses the issues of arbitrary acquisition and subjective processing of continuous trajectory and brain perception data in rural public spaces. It combines an "activation-approach-avoidance" brain perception state induction experiment to collect continuous walking trajectory and EEG data in rural public spaces in real time, batch processing noise and artifacts in the continuous sample data. The EEG data is converted into a two-dimensional feature vector of "activation-approach-avoidance" perception coordination. A normalized walking brain perception coordination index is constructed in the continuous process using a stochastic state transition algorithm, calculating the probability set of the occurrence of the coordination state in the current time period, ensuring the timeliness and reliability of continuous trajectory EEG data in rural public spaces. Addressing the issues of sample data interception bias and the need to improve the resolution of spatial geographic pixels for coordination in rural public spaces, this invention converts walking brain perception coordination into hexagonal grid spatial geographic data in 1M units, uniformly segmenting and stacking the raster mapping data of the coordination state. The reachable range of the Isovist field of view in the direction of travel is set as the boundary of perception coordination in rural public spaces. A distance decay index for walking brain perception coordination is calculated, and Boolean operations are used to control the threshold conditions of the raster data, effectively improving the quantitative accuracy of coordination assessment in rural public spaces. To address the complex and cumbersome process of predicting and determining the distribution of synergy in rural public spaces, and the insufficient indicative power of decision-making for the renewal of rural synergy spaces, this invention uses a Gaussian process regression model based on a perceptual synergy decay kernel function to predict the geographical distribution of synergy in rural public spaces. It then weights and overlays raster data of environmental elements in rural public spaces and presents it visually. Furthermore, it utilizes hot and cold spot clustering results to determine the advantageous and disadvantageous synergy areas in rural spaces, improving the reliability and efficiency of decision-making for rural public spaces and providing an application approach for the quality improvement and renewal design of rural public spaces. Attached Figure Description

[0076] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0077] Figure 1 This is a schematic diagram of the method flow of the present invention;

[0078] Figure 2 This is a distribution map of the degree of synergy in rural public spaces according to the present invention;

[0079] Figure 3 This is a weighted synergy distribution map of rural public space environmental elements according to the present invention;

[0080] Figure 4 This is a schematic diagram of the rural collaborative spatial update decision-making of the present invention;

[0081] Figure 5 This is a schematic diagram of the system structure of the present invention. Detailed Implementation

[0082] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0083] Example 1:

[0084] like Figure 1 As shown, a method for assessing the collaborativeness of rural public spaces based on continuous trajectory EEG is presented. The method includes the following steps:

[0085] S101: Receive data related to rural public spaces, preprocess the data to obtain processed data related to rural public spaces, wherein the data related to rural public spaces includes: real-time EEG data of walking tours, GPS trajectory data, and basic geospatial data of the environment.

[0086] Specifically, the preprocessing process:

[0087] Processing of continuous trajectory EEG data.

[0088] Acquire basic CAD vector data of rural public spaces, including data on roads, buildings, courtyards, farmland, ponds, waterways, topography, boardwalks, and platforms. Record the participants' comfortable standing baseline, and then collect continuous GPS trajectory data and electroencephalogram (EEG) data in real time as the participants walk along selected routes in the rural public spaces.

[0089] The raw EEG data undergoes noise removal and artifact processing. The raw EEG data is a time series matrix S = [s1, s2, ... s2] containing M channels. M ], s m =[s m (1),s m (2),…,s m (N)] T Let m represent the signal of the m-th channel, where m = 1, 2, ..., M. High-pass and low-pass filters are applied to the original EEG data, and Bootstrap sample statistics are performed c times randomly, where c = 1, 2, ..., C, to obtain the three-dimensional matrix of the EEG resampled signal at the i-th time point.

[0090] Furthermore, the maximum overlap discrete wavelet transform is used for each channel signal s. mThe wavelet coefficients W = [w] of the m-th channel at the j-th decomposition level in a time series of length n are obtained. j,n [n], for each channel m and artifact substitution signal k = 0, 1, ..., K, generate a substitution time series. And the wavelet coefficients for each channel m, decomposition level j, and sample point n are obtained. Calculate the threshold Θ from the alternative distribution. j,m (n) and significance level α, to obtain the filtered wavelet coefficient w of the m-th channel at the j-th decomposition level. j,m,filtered (n), specifically:

[0091]

[0092] The filtered signal for each channel is reconstructed using inverse maximum overlap discrete wavelet transform, and the filtering results of all channels are combined into a filtered signal matrix S. filtered =[s 1,filtered ,s 1,filtered ,…,s M,filtered ].

[0093] The raw continuous GPS trajectory data undergoes smoothing and anomaly filtering. The continuous GPS trajectory data is a time-stamped geographic coordinate sequence matrix, using two adjacent GPS points (x... i ,y i ,z i ) and (x i+1 ,y i+1 ,z i+1 The walking speed v is obtained by calculating the horizontal distance and the time difference. i Calculate the walking acceleration a i ,for:

[0094]

[0095] Applying Savitzky-Golay polynomial fitting to digital filtering smoothing speed and acceleration data Given a window of length 2k+1, fit the filter coefficients u using the least squares method and the sum of squared residuals (RSS). j Specifically:

[0096]

[0097] In the formula, k represents the size of the sliding window. σ represents the average speed of continuous GPS travel. v This represents the standard deviation of continuous GPS travel speed.

[0098] Furthermore, calculate the smoothed velocity. and acceleration The mean and standard deviation are used to detect and remove outliers by Z-score for each smoothed velocity and acceleration.

[0099] In this embodiment, a 32-channel portable EEG system was used, with wet electrodes arranged in a 10-20 system configuration. The electrode impedance was maintained below 20kΩ. Data was transmitted to the host PC via a radio frequency wireless interface in its default operating frequency band. In EEGLAB, a 1Hz high-pass filter (order 826) and a 135Hz low-pass filter (order 56) were used to downsample the EEG data to 250Hz. The clean_rawdata toolbox was used to remove abnormal channels (flat channels lasting 5 seconds, channel correlation below 0.8, power frequency noise exceeding 4, and other parameters disabled). The EEG substitute signal was set to k=1000, the wavelet decomposition level to 5, and α to a 5% significance level. The EEG signal after artifact processing was verified by ROC curve analysis, and the AUC index of 28 channels reached 0.95, indicating that the EEG filtering process can effectively remove artifacts and retain useful EEG signal features.

[0100] Continuous GPS trajectory data of the subjects were recorded via Bluetooth using a mobile phone. The window size of the Savitzky-Golay filter was set to 7, and the polynomial order was set to 3. The absolute value of the Z-score threshold for outliers was >3. The error between the Fréchet distance and the root mean square error (RMSE) of the GPS trajectory after outlier filtering and smoothing and the actual CAD vector path was <0.5m, indicating that the GPS trajectory data processing was effective.

[0101] S102: Extract the walking brain perception coordination index based on the processed rural public space related data, input the walking brain perception coordination index into the pre-established Gaussian process regression model based on the perception coordination decay kernel function, and output the distribution results of the rural public space coordination degree.

[0102] The process of extracting the walking brain perception coordination index based on processed rural public space-related data involves: constructing a two-dimensional feature vector of perception coordination and defining a discrete state set; combining the state transition probability matrix and the forward-backward probability algorithm to analyze the temporal dynamics of brain perception; and realizing the standardized extraction of the walking brain perception coordination index in rural public spaces. Specifically, this includes:

[0103] The power spectral densities of EEG rhythms α and β after cleaning are extracted. The ratio of the power spectral densities is then converted into a two-dimensional vector of brain-sensory coordination features, specifically:

[0104]

[0105] In the formula, PLE L-HIndicates a state of brain sensory activation; PLE N-P Represents the brain's perception of approach and avoidance states; n represents the number of EEG channels; PSD(α) and PSD(β) represent the power spectral density of EEG rhythms α and β, respectively. r_he and PSD l_he These represent the power spectral density of the right and left cerebral cortex, respectively.

[0106] The brain perception coordination features were obtained by z-score normalization. and Perform K-means clustering on the standardized feature data, and set... There are two types: high activation and low activation. There are two types: approach tendency and avoidance tendency. Let the cluster center be... and The midpoint between two cluster centers is used as the threshold to determine the observation sequence O = (PLE) L-H PLE N-P The state of each point in ).

[0107] Furthermore, we define walking brain perception coordination as a set of three discrete states H = {cooperative, neutral, non-cooperative}, and define a given system in a cooperative state O at time t. t The probability is:

[0108]

[0109] In the formula, O t This represents the observation sequence of walking brain perception coordination features at time t; and This represents the brain's sensory coordination characteristics at time t; TH L-H and TH N-P They represent PLE respectively L-H and PLE N-P Clustering threshold.

[0110] Establish the walking brain perception coordination state transition probability matrix A = [a ij ] and D = [d j (O t )], calculate the forward probability σ of random transitions in brain-sensory coordinated states over time series. t (j) and backward probability Specifically:

[0111]

[0112] In the formula, σ t (j) represents the non-observed walking brain perception coordination state H at time t. jAnd the sequence O1, O2, ..., O was observed. t The joint probability; σ t-1 (i) indicates that the walking brain perception coordination state at time t-1 is H. i Forward probability; a ij The walking brain sensory coordination state is represented by H i Transfer to H j The probability of d; j (O t ) indicates the brain's sensory coordination state during walking. j O was observed below t The probability of; H represents the unobserved walking brain sensory coordination state at time t. i And sequence O was observed t+1 O t+2 ,…,O T The probability of; H represents the brain's sensory coordination state during walking at time t+1. j The backward probability; b j (O t+1 ) indicates the brain's sensory state during walking, H j O was observed below t+1 The probability of.

[0113] The probability of waking-brain sensory coordination at each time point is calculated as follows:

[0114]

[0115] To eliminate the influence of continuous walking difficulty and physical exertion on the walking brain-sensory coordination index, a weighting coefficient 1+τ·d based on equivalent distance adjustment is introduced. e Specifically:

[0116]

[0117] In the formula, (x i ,y i ,z i ) and (x i+1 ,y i+1 ,z i+1 ) represents the coordinates of two adjacent GPS points, ω is the Naismith constant used to quantify the extra effort required due to changes in altitude; τ is a constant coefficient obtained by minimizing the variance of brain-sensory synergy under different walking path conditions to eliminate the interference of different walking paths on the brain-sensory synergy index.

[0118] To further eliminate the influence of baseline differences, characteristics of the EEG static standing baseline state were calculated. The standardized walking brain-sensory coordination index is obtained by subtracting the baseline value from the observed value. To eliminate baseline differences among individual participants, specifically:

[0119]

[0120] In this embodiment, the additional effort constant coefficient is set to ω = 7.92. The selected rural public space case study includes three walking conditions: flat ground, uphill, and downhill. The corresponding unadjusted NPPIs are NPPI... flat NPPI up NPPI down Their equivalent distances are respectively Therefore, τ = 0.2 was chosen for calculating the walking brain perception coordination index.

[0121] The pre-established Gaussian process regression model based on the perception-co-decay kernel function was constructed by integrating the visual field of continuous walking trajectories in rural public spaces and the gridded geospatial model of brain perception co-coordination.

[0122] By identifying subject E m Continuous walking trajectory R in rural public spaces m Where m = 1, 2, ..., M, along the travel trajectory R m With the center point of the grid as the viewpoint G i Among them, G i ∈R m The visual field is generated by uniformly setting up a fine-grained hexagonal grid at intervals of n meters. The visual fields of all viewpoints along the subject's walking trajectory are superimposed to obtain the maximum accessible visual field VF of the rural public space. max And based on VF max Delineate the boundaries of perceptual collaboration in rural public spaces, specifically as follows:

[0123]

[0124] Computational viewpoint G i The current grid and the target grid G j The actual distance of the center to the DAC ij and perceived distance DAW ij The inverse square law equation is used to obtain the distance decay index of walking brain perception coordination, and the normalized multiplier U of walking brain perception coordination distance decay is defined accordingly. ij The judgment conditions are as follows:

[0125]

[0126] In the formula, the actual distance to the DAC is... ij The grid G ​​where the viewpoint is located iWith target mesh G j Euclidean distance between centers; perceived distance DAW ij The grid G ​​where the viewpoint is located i With target mesh G j The visible distance between centers; It is the walking brain perception coordination decay index.

[0127] The normalized multiplier U of the walking brain perception coordination decay surface ij Scaling is performed to generate the walking brain perception coordination decay result representing the target grid, as follows:

[0128]

[0129] In the formula, PA ij Indicates at viewpoint G i The contribution value of the perception coordination attenuation to the target grid j; (G i ) represents the viewpoint G i The walking brain perception coordination value at the location;

[0130] Obtain all subjects E m On the trajectory R m Where m = 1, 2, ..., M, and the viewpoint G is on top. i The two-dimensional spatial location index of the grid and its walking brain perception coordination value, based on the maximum visual field (VF) max Use a double loop to traverse the hexagonal grid space, ensuring the viewpoint is within the corresponding hexagonal cell, until the entire rural public space CAD base map is covered. Record the center position of each grid as x. j The radial basis function (RBF) is selected to train the Gaussian process regression, specifically as follows:

[0131]

[0132] In the formula, ε f represents the signal variance; l represents the length scale parameter, which controls the rate at which the walking brain's sensory coordination decays.

[0133] The normalized multiplier U of the walking brain perception coordination decay was used. ij Construct a prior kernel function for viewpoint G. i Grid position x i Using the corresponding walking brain perception coordination scores as training data, VF max The walking brain perception coordination within the range is smoothed and spatially interpolated, and then averaged to obtain the cumulative walking brain perception coordination of the target grid. Specifically:

[0134]

[0135] In the formula, This represents the walking brain perception coordination value for subject m and each target grid j; This represents the number of viewpoints from which subject m influences target grid j along the walking path; M represents the total number of subjects.

[0136] To obtain the cumulative walking brain perception synergy distribution within the rural public space perception synergy boundary, all target grids j were subjected to... The calculation generates a two-dimensional geographical distribution map of rural public space synergy within the perceived synergy boundary.

[0137] In this embodiment, 5912 viewpoints from 20 subjects were obtained. The public space red line was delineated in the rural public space CAD according to the rural land use plan. After importing the data into the Grasshopper platform, the Isovist battery pack was used to calculate the maximum reachable field of view using a hexagonal grid resolution of 1m. The rural public space perception collaboration boundary was then delineated by combining the public space red line and the maximum reachable field of view. The internal area of ​​the rural public space perception collaboration boundary is approximately 3370㎡, and the boundary length is approximately 1102m, resulting in a total of 4343 grid units (including complete and incomplete hexagonal grid units).

[0138] The attenuation index φ for gait perception coordination was set to -0.47. 65% of the grid cells with gait perception coordination values ​​were used as the training set, and the remaining 35% as the test set. When using the Python library Scikit-Learn for Gaussian process regression, hyperparameters were optimized with length_scale = 1.0, length_scale_bounds = (1e-2, 1e2), and n_restarts_optimizer = 10, allowing the optimizer to restart randomly multiple times to avoid getting trapped in local optima. The Gaussian process regression model was trained using the fit() method, allowing it to automatically adjust the hyperparameters of the kernel function to maximize the marginal likelihood. After model computation, the hyperparameter result was length_scale = 1.2, and the signal variance parameter ε... f =0.85; the marginal likelihood maximization converges at the 7th iteration with log-likelihood = -42.3.

[0139] The training and test sets, considering and not considering the walking brain perception synergy decay index, were used for modeling and prediction. The prediction errors of the model on the test set were statistically analyzed using mean absolute error (MAE), mean squared error (MSE), root mean squared error (RMSE), mean absolute percentage error (MAPE), silhouette coefficient (SC), and coefficient of determination (R²) (Table 1). Smaller MAE, MSE, RMSE, and MAPE, and larger R² and SC, indicate better model prediction performance. The model's performance improvement reached 50%-62%, and the effect size Cohen's d = 2.37, verifying the stability and superiority of the Gaussian process regression model based on the perception synergy decay kernel function of this invention. Furthermore, spatial interpolation of walking perception synergy was performed within the boundary of rural public space perception synergy, ultimately obtaining a two-dimensional geographical distribution map of rural public space synergy. Figure 2 ).

[0140] Table 1. Prediction results of Gaussian process regression model

[0141]

[0142] S103: Obtain the hierarchical vector transfer data and weight data of environmental elements, project the hierarchical vector transfer data and weight data of environmental elements onto the grid cells of rural public space, and combine them with the distribution results of the synergy degree of rural public space to obtain the weighted synergy degree distribution results of environmental elements in rural public space, and cluster them to obtain the rural advantageous synergy space and the weak synergy space.

[0143] Specifically, the following embodiments further illustrate the solution of the present invention: CAD data of rural public spaces are entered into the ArcGIS system, and basic drawings in Model Builder format are obtained through splicing, cropping, projection transformation, geometric correction, and georegistration. Data links are then established for the two-dimensional geographic distribution of the coordination degree of rural public spaces.

[0144] Furthermore, vector data of rural public space environmental elements in shapefile format with shape, spatial location and attribute descriptions are loaded. The Analysis Tool is used to transfer and project the vector data of environmental elements into spatial grid cells within the rural public space perception synergy boundary. The environmental elements within the rural public space perception synergy boundary include plants, facilities and paving; the environmental elements adjacent to the rural public space perception synergy boundary include fields, courtyards and water bodies.

[0145] Based on the two-dimensional geographic distribution of rural public space synergy, the vector data of environmental elements such as plants, facilities, paving, fields, courtyards and water bodies are assigned values ​​and transformed into primary synergy raster data.

[0146] Obtain the weight coefficients of various environmental elements, and use a raster calculator to perform a weighted calculation on the primary synergy raster data of all environmental elements, specifically:

[0147]

[0148] In the formula, Z represents the weighted synergy distribution result of rural public space environmental elements; EL i This is the primary synergy raster data for the i-th environmental element; HW i It is with EL i The corresponding weight coefficients, and satisfying If EL i If the value is null, replace it with 0; otherwise, retain the EL value. i The value of .

[0149] Cluster analysis was conducted on the weighted synergy distribution of rural public space environmental elements, specifically as follows:

[0150]

[0151] Among them, HC i Let I and Z represent the local Moran's index of the i-th grid cell. i This represents the weighted synergy value of the i-th grid cell. S represents the average value of all grid cells. 2 w represents variance. ij This is the spatial weight matrix, calculated based on the distance between spatial grid cells i and j.

[0152] Extract the High-High clustering synergy space and its edges, and define them as the advantages of rural public space. Extract the low-low clustering synergy space and its edges, and define them as the vulnerable areas of rural public space.

[0153] In this embodiment, rural public space environmental elements are classified based on aerial photographs, and a layered vector map layer is established, including groups of environmental elements such as plants, facilities, paving, fields, courtyards, and water bodies. In ArcGIS, the "Analysis Tool - Overlay Analysis - Spatial Module" function in the system toolbox is used, and the "JOIN_ONE_TO_ONE" connection operation is set. The "CLOSEST" matching option is selected to merge and transfer the vector data of field, courtyard, and water body environmental elements and connect them to the internal space of the rural public space perception synergy boundary. The "INTERSECT" matching option is selected to connect the vector data of plant, facility, and paving environmental elements to the internal space of the rural public space perception synergy boundary, respectively.

[0154] Activation and approach-avoidance sensory EEG data corresponding to environmental elements in rural public spaces were acquired. The Critic objective weighting method was used to comprehensively consider the variability and conflict of the activation and approach-avoidance sensory EEG data structure, calculating the weights of the environmental elements for plants, facilities, paving, fields, courtyards, and water bodies as 0.183434, 0.138201, 0.203683, 0.160249, 0.170956, and 0.143477, respectively. The weighted overlay of the brain-sensory synergy raster data for each environmental element yielded a weighted synergy distribution map of the rural public space environmental elements. Figure 3 ).

[0155] In ArcGIS, using the "Spatial Statistics Tools - Cluster Distribution Mapping" function in the system toolbox, the statistical value of the weighted synergy distribution of village public space environmental elements was input, and it was determined whether there were significant hotspots, cold spots, and spatial outliers. Based on the inverse distance weight between spatial grid cells i and j, a High-High clustering synergy spatial area of ​​679.729㎡ and a Low-Low clustering synergy spatial area of ​​878.701㎡ were calculated. The edge lines were extracted and a smoothing tolerance of 3m was set. The High-High clustering synergy spatial area was controlled as the rural public space to be updated area, and the Low-Low clustering synergy spatial area was controlled as the environmental quality maintenance area. Figure 4 ).

[0156] Example 2: For example Figure 5 As shown, in order to achieve the above objectives, this invention discloses a rural public space collaboration assessment system based on continuous trajectory EEG, comprising:

[0157] Data processing module 11 is used to receive data related to rural public spaces, preprocess the data related to rural public spaces, and obtain processed data related to rural public spaces. The data related to rural public spaces includes: real-time EEG data of walking tours, GPS trajectory data, and basic geospatial data of the environment.

[0158] The distribution determination module 12 is used to extract the walking brain perception coordination index based on the processed rural public space related data, input the walking brain perception coordination index into the pre-established Gaussian process regression model based on the perception coordination decay kernel function, and output the distribution result of the rural public space coordination degree.

[0159] The spatial allocation module 13 is used to acquire hierarchical vector transfer data and weight data of environmental elements, project the hierarchical vector transfer data and weight data of environmental elements onto rural public space grid cells, and combine them with the distribution results of rural public space synergy to obtain the weighted synergy distribution results of rural public space environmental elements, and cluster them to obtain rural advantageous synergy space and weak synergy space.

[0160] Based on the same inventive concept, the present invention also provides a computer device, comprising: one or more processors, and a memory for storing one or more computer programs; the program includes program instructions, and the processor is used to execute the program instructions stored in the memory. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., serving as the computing and control core of the terminal, and is used to implement one or more instructions, specifically for loading and executing one or more instructions stored in a computer storage medium to implement the aforementioned method.

[0161] It should be further explained that, based on the same inventive concept, the present invention also provides a computer storage medium storing a computer program, which, when executed by a processor, performs the above-described method. This storage medium can be any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In the present invention, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0162] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this disclosure. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0163] The foregoing has shown and described the basic principles, main features, and advantages of this disclosure. Those skilled in the art should understand that this disclosure is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of this disclosure. Various changes and modifications can be made to this disclosure without departing from its spirit and scope, and all such changes and modifications fall within the scope of this disclosure as claimed.

Claims

1. A method for evaluating the collaborativeness of rural public spaces based on continuous trajectory EEG, characterized in that, The method includes the following steps: The system receives data related to rural public spaces, preprocesses the data to obtain processed data related to rural public spaces, including: real-time EEG data of walking tours, GPS trajectory data, and basic geospatial data of the environment. Based on the processed data of rural public space, the walking brain perception coordination index is extracted. The walking brain perception coordination index is then input into a pre-established Gaussian process regression model based on the perception coordination decay kernel function, and the distribution results of the coordination degree of rural public space are output. Hierarchical vector transfer data and weight data of environmental elements are obtained, and the hierarchical vector transfer data and weight data of environmental elements are projected onto rural public space grid units. Combined with the distribution results of rural public space synergy, the weighted synergy distribution results of rural public space environmental elements are obtained by overlaying, and the rural advantageous synergy space and weak synergy space are obtained by clustering.

2. The method for evaluating the collaborativeness of rural public spaces based on continuous trajectory EEG according to claim 1, characterized in that, The preprocessing of data related to rural public spaces includes noise cleaning and artifact removal of real-time EEG data from walking tours, and smoothing and anomaly filtering of continuous GPS trajectory data.

3. The method for evaluating the collaborativeness of rural public spaces based on continuous trajectory EEG according to claim 2, characterized in that, The process of noise cleaning and artifact removal for real-time EEG data during walking tours includes: The raw EEG data underwent noise removal and artifact processing. The raw EEG data was real-time EEG data from a walking tour, and was a time series matrix S = [s1, s2, ... s2] containing M channels. M ], s m =[s m (1),s m (2),…,s m (N)] T Let m represent the signal of the m-th channel, where m = 1, 2, ..., M. High-pass and low-pass filters are applied to the original EEG data, and Bootstrap sample statistics are performed c times randomly, where c = 1, 2, ..., C, to obtain the three-dimensional matrix of the EEG resampled signal at the i-th time point. Each channel signal s is transformed using the maximum overlap discrete wavelet transform. m The wavelet coefficients W = [w] of the m-th channel at the j-th decomposition level in a time series of length n are obtained. j,n [n], for each channel m and artifact substitution signal k = 0, 1, ..., K, generate a substitution time series. And the wavelet coefficients for each channel m, decomposition level j, and sample point n are obtained. Calculate the threshold Θ from the alternative distribution. j,m (n) and significance level α, to obtain the filtered wavelet coefficient w of the m-th channel at the j-th decomposition level. j,m,filtered (n) is: The filtered signal for each channel is reconstructed using inverse maximum overlap discrete wavelet transform, and the filtering results of all channels are combined into a filtered signal matrix S. filtered =[s 1,filtered ,s 1,filtered ,…,s M,filtered ]; The process of smoothing and filtering out anomalies in continuous GPS trajectory data: Continuous GPS trajectory data is a matrix of timestamped geographic coordinate sequences, using two adjacent GPS points (x, y, z)... i ,y i ,z i ) and (x i+1 ,y i+1 ,z i+1 The walking speed v is obtained by calculating the horizontal distance and the time difference. i Calculate the walking acceleration a i ,for: Applying Savitzky-Golay polynomial fitting to digital filtering smoothing speed and acceleration Given a window of length 2k+1, fit the filter coefficients u using the least squares method and the sum of squared residuals (RSS). j ,for: In the formula, k represents the size of the sliding window. σ represents the average speed of continuous GPS travel. v The standard deviation of continuous GPS travel speed; Calculate the smoothed velocity and acceleration The mean and standard deviation are used to detect and remove outliers by Z-score for each smoothed velocity and acceleration.

4. The method for assessing the collaborativeness of rural public spaces based on continuous trajectory EEG according to claim 1, characterized in that, The process of extracting the walking brain perception coordination index based on the processed rural public space related data is as follows: construct a two-dimensional feature vector of perception coordination and define a discrete state set, combine the state transition probability matrix and the forward-backward probability algorithm to analyze the brain perception temporal dynamics, and realize the standardized extraction of the walking brain perception coordination index in rural public spaces.

5. The method for evaluating the collaborativeness of rural public spaces based on continuous trajectory EEG according to claim 4, characterized in that, The extraction process of the walking brain perception coordination index is as follows: The power spectral densities of EEG rhythms α and β after cleaning are extracted. Based on the conversion of the power spectral density ratio into a two-dimensional vector of brain-sensory coordination features, the following is obtained: In the formula, PLE L-H Indicates a state of brain sensory activation; PLE N-P Represents the brain's perception of approach and avoidance states; n represents the number of EEG channels; PSD(α) and PSD(β) represent the power spectral density of EEG rhythms α and β, respectively. r_he and PSD l_he These represent the power spectral densities of the right and left cerebral cortex, respectively. The brain perception coordination features were obtained by z-score normalization. and Perform K-means clustering on the standardized feature data, and set... There are two types: high activation and low activation. There are two types: approach tendency and avoidance tendency. Let the cluster center be... and The midpoint between two cluster centers is used as the threshold to determine the observation sequence O = (PLE) L-H PLE N-P The state of each point in ); Define walking brain perception coordination as a set of three discrete states H = {cooperative, neutral, non-cooperative}, and define a given system at time t in a cooperative state O. t The probability is: In the formula, O t This represents the observation sequence of walking brain perception coordination features at time t; and This represents the brain's sensory coordination characteristics at time t; TH L-H and TH N-P They represent PLE respectively L-H and PLE N-P Clustering threshold; Establish the walking brain perception coordination state transition probability matrix A = [a ij ] and D = [d j (O t )], calculate the forward probability σ of random transitions in brain-sensory co-state over time series. t (j) and backward probability for: In the formula, σ t (j) represents the non-observed walking brain perception coordination state at time t as H j And the sequence O1, O2, ..., O was observed. t The joint probability; σ t-1 (i) indicates that the walking brain perception coordination state at time t-1 is H. i Forward probability; α ij The walking brain sensory coordination state is represented by H i Transfer to H j The probability of d; j (O t ) indicates the brain's sensory coordination state during walking. j O was observed below t The probability of; H represents the unobserved walking brain sensory coordination state at time t. i And sequence O was observed t+1 O t+2 ,…,O T The probability of; H represents the brain's sensory coordination state during walking at time T+1. j The backward probability; b j (O t+1 ) indicates the brain's sensory state during walking, H j O was observed below t+1 The probability of; The probability of waking-brain sensory coordination at each time point is calculated as follows: Introduce weighting coefficients 1+τ·d based on equivalent distance adjustment e ,for: In the formula, (x i ,y i ,z i ) and (x i+1 ,y i+1 ,z i+1 ) represents the coordinates of two adjacent GPS points, ω is the Naismith constant; τ is the constant coefficient; Calculate the characteristics of EEG static standing baseline state The standardized walking brain-sensory coordination index is obtained by subtracting the baseline value from the observed value. for:

6. The method for evaluating the collaborativeness of rural public spaces based on continuous trajectory EEG according to claim 1, characterized in that, The pre-established Gaussian process regression model based on the perception-co-decay kernel function is constructed by integrating the visual field of continuous walking trajectories in rural public spaces and the gridded geospatial model of brain perception co-coordination. By identifying subject E m Continuous walking trajectory R in rural public spaces m Where m = 1, 2, ..., M, along the travel trajectory R m With the center point of the grid as the viewpoint G i Among them, G i ∈R m The visual field is generated by uniformly setting up a fine-grained hexagonal grid at intervals of n meters. The visual fields of all viewpoints along the subject's walking trajectory are superimposed to obtain the maximum accessible visual field VF of the rural public space. max And based on VF max Delineate the boundaries of perceptual collaboration in rural public spaces as follows: Computational viewpoint G i The current grid and the target grid G j The actual distance of the center to the DAC ij and perceived distance DAW ij The inverse square law equation is used to obtain the distance decay index of walking brain perception coordination, and the normalized multiplier U of walking brain perception coordination distance decay is defined accordingly. ij The judgment conditions are as follows: In the formula, the actual distance to the DAC is... ij The grid G ​​where the viewpoint is located i With target mesh G j Euclidean distance between centers; perceived distance DAW ij The grid G ​​where the viewpoint is located i With target mesh G j The visible distance between centers; It is the walking brain sensory coordination decay index; The normalized multiplier U of the walking brain perception coordination decay surface ij Scaling is performed to generate the walking brain perception coordination decay result representing the target grid, as follows: In the formula, PA ij Indicates at viewpoint G i The contribution value of the perception coordination attenuation to the target grid j; Representing viewpoint G i The walking brain perception coordination value at the location; Obtain all subjects E m On the trajectory R m Where m = 1, 2, ..., M, and the viewpoint G is on top. i The two-dimensional spatial location index of the grid and its walking brain perception coordination value, based on the maximum visual field (VF) max Use a double loop to traverse the hexagonal grid space, ensuring the viewpoint is within the corresponding hexagonal cell, until the entire rural public space CAD base map is covered. Record the center position of each grid as x. j The radial basis function (RBF) is chosen to train the Gaussian process regression, as follows: In the formula, ε f The variable represents the signal variance; l represents the length scale parameter. The normalized multiplier U of the walking brain perception coordination decay was used. ij Construct a prior kernel function for viewpoint G. i Grid position x i Using the corresponding walking brain perception coordination scores as training data, VF max The walking brain perception coordination within the range is smoothed and spatially interpolated, and then averaged to obtain the cumulative walking brain perception coordination of the target grid. for: In the formula, This represents the walking brain perception coordination value for subject m and each target grid j; This represents the number of viewpoints from which subject m influences target grid j along the walking path; M represents the total number of subjects. Perform on all target meshes j The calculation generates a two-dimensional geographical distribution map of rural public space synergy within the perceived synergy boundary.

7. The method for evaluating the collaborativeness of rural public spaces based on continuous trajectory EEG according to claim 1, characterized in that, The process of projecting hierarchical vector transfer data and weight data of environmental elements onto rural public space grid cells and combining them with the distribution results of rural public space synergy to obtain the weighted synergy distribution results of rural public space environmental elements, and then clustering them to obtain rural advantageous synergy spaces and weak synergy spaces: The CAD data of rural public spaces is entered into the ArcGIS system, and basic drawings in Model Builder format are obtained through splicing, cropping, projection transformation, geometric correction and georegistration. Data links are also established for the two-dimensional geographic distribution of the coordination degree of rural public spaces. Load the shape, spatial location, and attribute descriptions of rural public space environmental elements in shapefile format (shp format). Use the Analysis Tool to transfer and project the vector data of the environmental elements into spatial grid cells within the perceived synergy boundary of the rural public space. The environmental elements within the perceived synergy boundary of the rural public space include plants, facilities, and paving; the environmental elements adjacent to the perceived synergy boundary of the rural public space include fields, courtyards, and water bodies. Based on the two-dimensional geographic distribution of rural public space synergy, the vector data of environmental elements such as plants, facilities, paving, fields, courtyards and water bodies are assigned values ​​and transformed into primary synergy raster data. Obtain the weight coefficients of various environmental elements, and use the raster calculator to perform a weighted calculation on the primary synergy raster data of all environmental elements, resulting in: In the formula, Z represents the weighted synergy distribution result of rural public space environmental elements; EL i This is the primary synergy raster data for the i-th environmental element; HW i It is with EL i The corresponding weight coefficients, and satisfying If EL i If the value is null, replace it with 0; otherwise, retain the EL value. i The value; Cluster analysis was performed on the weighted synergy distribution of rural public space environmental elements, and the results are as follows: Among them, HC i Let I and Z represent the local Moran's index of the i-th grid cell. i This represents the weighted synergy value of the i-th 2-cell unit. S represents the average value of all grid cells. 2 w represents variance. ij This is the spatial weight matrix, calculated based on the distance between spatial grid cells i and j; Extract the High-High clustering synergy space and its edges, and set it as... Extract the Low-Low clustering synergy space and its edges, and set it as...

8. A rural public space collaboration assessment system based on continuous trajectory EEG, characterized in that, include: The data processing module is used to receive data related to rural public spaces, preprocess the data to obtain processed data related to rural public spaces, wherein the data related to rural public spaces includes: real-time EEG data of walking tours, GPS trajectory data, and basic geospatial data of the environment. The distribution determination module is used to extract the walking brain perception coordination index based on the processed rural public space related data. The walking brain perception coordination index is input into a pre-established Gaussian process regression model based on the perception coordination decay kernel function, and the distribution results of the rural public space coordination degree are output. The spatial allocation module is used to acquire hierarchical vector transfer data and weight data of environmental elements, project the hierarchical vector transfer data and weight data of environmental elements onto rural public space grid cells, and combine them with the distribution results of rural public space synergy to obtain the weighted synergy distribution results of rural public space environmental elements, and cluster them to obtain the rural advantage and disadvantage synergy space.

9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that, The memory stores a computer program that can run on a processor. When the processor loads and executes the computer program, it employs the rural public space collaboration assessment method based on continuous trajectory EEG as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is loaded and executed by the processor, it employs the rural public space collaboration assessment method based on continuous trajectory EEG as described in any one of claims 1 to 7.

Images