A real-time transmission system for color ultrasound data
Through real-time bandwidth monitoring and graph cutting theory, the color ultrasound data transmission path is optimized, and the problem of unreasonable bandwidth allocation and path selection in the existing technology is solved, efficient and stable transmission of color ultrasound data is achieved, and the speed and quality of remote diagnosis is improved.
Patent Information
- Application Number
- CN202411244695.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-06
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2044-09-06
AI Technical Summary
The existing real-time color ultrasound data transmission system faces the problems of unreasonable bandwidth allocation and unoptimized path selection during data transmission, resulting in delay in medical image transmission when the data volume is large or the network condition is unstable, affecting the timeliness and accuracy of diagnosis. sex.
The real-time bandwidth monitoring module is used to optimize bandwidth utilization based on time series analysis and support vector machine technology; the data transmission path optimization module uses graph cutting theory to dynamically adjust the transmission path; the real-time color ultrasound data transmission optimization module adjusts the network by evaluating network performance indicators in real time Configure and schedule policies to optimize network performance.
It improves the continuity and reliability of data transmission, reduces transmission delay, improves data transmission efficiency and network flexibility, and significantly improves the quality and speed of remote diagnosis.
Smart Images

Figure CN118764425B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of network data transmission, and in particular to a real-time transmission system for color ultrasound data. Background Art
[0002] The field of network data transmission technology involves the use of various communication protocols, network interfaces and transmission technologies to efficiently and securely transmit data in the network. The core of the field is to ensure the reliable transmission of data from the source to the destination, including data encoding, compression, encryption and error detection. Network data transmission not only supports wired and wireless communication environments, but also involves a variety of network architectures, such as local area networks (LANs), wide area networks (WANs) and more complex Internet environments. The development of this technology has promoted the widespread application of remote communications, cloud computing services and real-time data processing, which has an important impact on improving business efficiency, supporting remote work, and achieving the reliability and response speed of various network services.
[0003] Among them, the color ultrasound data real-time transmission system is a technical application specific to the medical field. It is mainly used to transmit color ultrasound image data in real time between medical facilities or from medical equipment to data processing centers. The main purpose of this system is to ensure that doctors and medical teams can obtain the results of color ultrasound examinations in real time, thereby improving the speed and accuracy of diagnosis. Through real-time data transmission, doctors can analyze images in real time at different locations, supporting remote diagnosis and collaboration, which is particularly important in emergency medical services and expert consultations. This system provides patients with more timely and effective medical services by optimizing data flow, reducing delays, and improving image quality transmission efficiency.
[0004] The existing real-time transmission system for color Doppler ultrasound data faces problems of unreasonable bandwidth allocation and non-optimal path selection during the data transmission process, which leads to unnecessary delays in the transmission of critical data such as medical images when the data volume is large or the network conditions are unstable. For example, the standard bandwidth allocation strategy ignores the dynamic changes in real-time network conditions and cannot effectively respond to the sudden increase in data flow demand, affecting the timeliness and accuracy of data processing. The data transmission path relies on the preset network routing and fails to respond to congestion or fault changes in the network in real time. This static path selection mechanism limits the efficiency of data transmission. In emergency medical services and remote diagnosis scenarios, technical limitations lead to delayed transmission of diagnostic information, affecting the speed and accuracy of medical decision-making, and thus affecting the patient's treatment outcomes. Summary of the invention
[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a real-time transmission system for color ultrasound data.
[0006] In order to achieve the above object, the present invention adopts the following technical scheme: A color Doppler ultrasound data real-time transmission system comprises:
[0007] The real-time bandwidth monitoring module is based on time series analysis and support vector machine technology to continuously monitor network bandwidth usage and node response time, generate network load conditions, adjust monitoring thresholds according to network load conditions, optimize monitoring accuracy and response speed, and obtain real-time results of monitoring adjustments;
[0008] The bandwidth dynamic configuration module uses linear programming to reallocate the current bandwidth based on the real-time results of the monitoring adjustment, optimizes the bandwidth utilization, generates a preliminary bandwidth adjustment plan, and adjusts the bandwidth allocation based on the preliminary bandwidth adjustment plan and the priority of the color Doppler ultrasound data to obtain a bandwidth optimization plan;
[0009] The data transmission path optimization module optimizes the data transmission path according to the bandwidth optimization scheme by using graph cut theory, reduces potential delays in data transmission, obtains an optimized transmission path, and dynamically adjusts the optimized transmission path according to changes in network load to generate a dynamic path adjustment result;
[0010] The real-time color ultrasound data transmission optimization module uses the dynamic path adjustment results to evaluate network performance indicators in real time, adjust the network configuration and match the color ultrasound data transmission characteristics, generate network configuration adjustment results, optimize the network scheduling strategy according to the network configuration adjustment results, and generate a color ultrasound image enhancement transmission plan.
[0011] As a further solution of the present invention, the step of acquiring the network load condition is specifically as follows:
[0012] Based on time series analysis and support vector machine technology, the network bandwidth usage rate is analyzed in time series, and the exponential smoothing model is combined with logarithmic transformation to predict the bandwidth change trend in the future time period. The formula is:
[0013] ,
[0014] The bandwidth usage model of the time variable is calculated to generate a bandwidth usage rate variation model, where: , and represents the model adjustment parameter, t represents the time, is the time decay constant, represents the bandwidth usage variation model;
[0015] Based on the bandwidth usage change model, support vector machine technology is used to build a prediction model based on node response time, and the weighted average root error of the application error is evaluated using the formula:
[0016] ,
[0017] Get the prediction model of node response time, where Tuning parameters for model sensitivity, represents the response time of the i-th real-time node, is the historical response time mean, n is the number of samples, It is a prediction model for node response time;
[0018] Combining the bandwidth usage rate change model and the node response time prediction error, weighted synthesis is performed by harmonic mean method, and the formula is adopted:
[0019] ,
[0020] Get the network load status, where: is the total adjustment factor, and are the weights of the bandwidth usage model and the node response time model, respectively. and They are respectively the bandwidth usage variation model and the node response time prediction model. is the error set, The network load condition.
[0021] As a further solution of the present invention, the step of obtaining the real-time result of the monitoring adjustment is specifically as follows:
[0022] Based on the network load condition, dynamic threshold adjustment is implemented, through the formula:
[0023] ,
[0024] Generate dynamic monitoring thresholds based on current load and volatility, where: and is the weight coefficient, is the nonlinear adjustment index, is the standard deviation of network load conditions, Represents the dynamic monitoring threshold. Indicates network load conditions;
[0025] The network data is monitored in real time according to the dynamic monitoring threshold. If the data exceeds the threshold, a response is triggered, using the formula:
[0026] ,
[0027] Get the monitoring adjustment signal, where: For response sensitivity, is a power, providing the ability of nonlinear response, To adjust the baseline, data represents the real-time network data monitored. Adjusting signals for monitoring;
[0028] The monitoring adjustment signal is used to adjust the network parameters in real time and optimize the network configuration, using the formula:
[0029] ,
[0030] Generate real-time results of monitoring adjustments, where and is the adjustment factor, Represents feedback data, To monitor the real-time results of adjustments, Condition the signal for monitoring.
[0031] As a further solution of the present invention, the step of obtaining the bandwidth optimization solution is specifically as follows:
[0032] Based on the real-time results of the monitoring adjustment, combined with the real-time network load monitoring results, a linear programming model is used to map the network load status to the bandwidth configuration, using the formula:
[0033] ,
[0034] Get the preliminary bandwidth adjustment plan, where represents the linear adjustment factor, represents the stability of logarithmic operations, Indicates the coefficient for smoothing the current load. It is the network load data obtained by real-time monitoring. It is a preliminary bandwidth adjustment plan;
[0035] Based on the preliminary bandwidth adjustment scheme, the bandwidth allocation is adjusted by weighted average method, using the formula:
[0036] ,
[0037] The priority of color Doppler ultrasound data is introduced to obtain the bandwidth allocation result, where: Adjust weights for bandwidth, is the influence coefficient of color Doppler ultrasound data priority, Indicates the priority coefficient of color Doppler ultrasound data. Represents the bandwidth allocation result after adjustment based on priority. It is a preliminary bandwidth adjustment plan;
[0038] Based on the bandwidth allocation result, bandwidth optimization is performed using the formula:
[0039] ,
[0040] Generate a bandwidth optimization plan, where and are bandwidth optimization coefficient and nonlinear adjustment index respectively, represents the standard deviation adjustment factor, Calculate the standard deviation of the priority sequence, For bandwidth optimization solutions, Indicates the bandwidth allocation result after adjustment based on priority.
[0041] As a further solution of the present invention, the step of obtaining the optimized transmission path is specifically:
[0042] Using the data obtained from the bandwidth optimization scheme, the nodes and edges of the network graph are initialized using the formula:
[0043] ,
[0044] Generate a preliminary network diagram where is the adjustment factor for graph construction, represents the positive definition of the logarithmic term, Smooth out changes in network load, is the output data of the bandwidth optimization solution, represents a preliminary network diagram;
[0045] Apply graph cut theory to the preliminary network graph to determine the optimal path for data transmission, using the formula:
[0046] ,
[0047] Get the optimized and adjusted graph cut results, where: represents the weight of the graph cut, Adjust the priority of data streams, Nonlinear tuning parameters, Represents a preliminary network diagram, is the optimized node cut set;
[0048] Based on the optimized and adjusted graph cut results, the data transmission path is reconstructed through the formula:
[0049] ,
[0050] Generate an optimized transmission path, where is the path reconstruction coefficient, calculate The standard deviation of is the optimized node cut set, Indicates the optimized transmission path.
[0051] As a further solution of the present invention, the step of obtaining the dynamic path adjustment result is specifically:
[0052] According to the optimized transmission path and real-time network load data, the path is initially dynamically adjusted using the formula:
[0053] ,
[0054] Generate a preliminary draft of the adjustment, where: Indicates the correlation between the regulation path and the load data, represents the logarithmic transformation of the load data, represents the domain of the logarithmic operation, Current network load data, Indicates adjustment of the first draft, represents the optimized transmission path;
[0055] Based on the draft of the adjustment, dynamic weight adjustment is applied to optimize the distribution of data flow, through the formula:
[0056] ,
[0057] Get the path optimization feedback result, where: represents the critical weight of the control path adjustment, Indicates the priority of the adjustment path. represents the adjustment of nonlinear effects, Indicates adjustment of the first draft, Indicates the feedback result of path optimization;
[0058] According to the feedback result of the path optimization, the optimization strategy is executed through the formula:
[0059] ,
[0060] Generate dynamic path adjustment results, where To optimize the adjustment coefficient, measure The variability of is the transmission path result after dynamic adjustment. Indicates the path optimization feedback result.
[0061] As a further solution of the present invention, the step of obtaining the network configuration adjustment result is specifically:
[0062] Based on the dynamic path adjustment result, the network performance evaluation index is calculated through the real-time monitoring data of network bandwidth and data traffic, and the formula is applied:
[0063] ,
[0064] Get the network performance index, where Indicates the real-time flow of color Doppler ultrasound data. Indicates the current available bandwidth. is a small amount used to avoid division by zero errors, Indicates network performance refers to the standard;
[0065] Based on the network performance indicators and the network's delayed response, the optimal network configuration is calculated using the formula:
[0066] ,
[0067] Get the adjusted network configuration parameters, where: is the time constant, Indicates the current delay of the network. is the adjusted network configuration parameter, Indicates network performance indicators;
[0068] Combining the adjusted network configuration parameters with the feedback of the current state, the formula is adopted:
[0069] ,
[0070] Generate network configuration adjustment results, where: is the adjustment factor that controls the impact of feedback data. is the data obtained from network feedback, It is the result of network configuration adjustment.
[0071] As a further solution of the present invention, the steps of obtaining the color ultrasound image enhancement transmission plan are specifically:
[0072] Based on the network configuration adjustment results, combined with the real-time available bandwidth and current data traffic, the scheduling optimization index is calculated using the formula:
[0073] ,
[0074] Generate scheduling optimization indicators, where Indicates the network configuration adjustment result. represents the network bandwidth, and the logarithmic term provides a nonlinear adjustment of the bandwidth effect. Indicates the current network traffic. represents the nonlinear coefficient affecting the flow rate adjustment, Represents the scheduling optimization index;
[0075] Based on the scheduling optimization index and combined with the characteristics of color Doppler ultrasound data, the matching degree between the network configuration and the color Doppler ultrasound data is calculated using the formula:
[0076] ,
[0077] Generate matching results, where represents the scheduling optimization index, Indicates the characteristic parameters of color Doppler ultrasound data transmission. Indicates the matching degree between network configuration and color Doppler ultrasound data transmission characteristics;
[0078] Using the matching result, combined with the feedback of the current transmission data status, the formula is applied:
[0079] ,
[0080] Generate a color Doppler ultrasound image enhancement transmission plan, where: Indicates the matching result. Indicates status feedback, represents the balance factor, represents the index of the adjustment plan, Indicates the color Doppler ultrasound image enhancement transmission plan.
[0081] Compared with the prior art, the advantages and positive effects of the present invention are:
[0082] In the present invention, the method of real-time monitoring of network bandwidth utilization and node response time through time series analysis and support vector machine technology improves monitoring accuracy and response speed. With this strategy, the network load can be predicted more accurately, thereby adjusting the monitoring threshold, capturing network status changes in real time, ensuring the continuity and reliability of data transmission, and applying linear programming to reallocate bandwidth based on real-time monitoring results, which not only improves bandwidth utilization, but also ensures the priority transmission of key data such as color ultrasound images and reduces the delay of key tasks. The optimization of data transmission path adopts graph cut theory, significantly reduces potential delays in the transmission process, improves the efficiency of data transmission, and further enhances the flexibility of the network and the ability to respond to emergencies by real-time evaluation of network performance indicators and dynamic adjustment, making the system more efficient and stable, including in situations where high-speed and precise medical image transmission is required, significantly improving the quality and speed of remote diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS
[0083] Figure 1 is a system flow chart of the present invention;
[0084] Figure 2 A flow chart showing the network load conditions in the present invention;
[0085] Figure 3 A flow chart of real-time results of monitoring and adjustment in the present invention;
[0086] Figure 4 It is a flow chart of the bandwidth optimization scheme in the present invention;
[0087] Figure 5 It is a flow chart of the optimized transmission path in the present invention;
[0088] Figure 6 A flow chart of the dynamic path adjustment result in the present invention;
[0089] Figure 7 A flow chart of the network configuration adjustment result in the present invention;
[0090] Figure 8 The figure is a flow chart of the color ultrasound image enhancement transmission plan in the present invention. DETAILED DESCRIPTION
[0091] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.
[0092] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.
[0093] See also Figure 1 , a color Doppler ultrasound data real-time transmission system comprises:
[0094] The real-time bandwidth monitoring module is based on time series analysis and support vector machine technology to continuously monitor network bandwidth usage and node response time, generate network load conditions, adjust monitoring thresholds according to network load conditions, optimize monitoring accuracy and response speed, and obtain real-time results of monitoring adjustments;
[0095] The bandwidth dynamic configuration module uses linear programming to reallocate the current bandwidth based on the real-time results of monitoring and adjustment, optimizes bandwidth utilization, generates a preliminary bandwidth adjustment plan, and adjusts bandwidth allocation based on the preliminary bandwidth adjustment plan and the priority of color Doppler ultrasound data to obtain a bandwidth optimization plan;
[0096] The data transmission path optimization module uses graph cut theory to optimize the data transmission path according to the bandwidth optimization plan, reduce the potential delay in data transmission, obtain the optimized transmission path, and dynamically adjust the optimized transmission path according to the change of network load to generate dynamic path adjustment results;
[0097] The real-time color ultrasound data transmission optimization module uses the dynamic path adjustment results to evaluate network performance indicators in real time, adjust the network configuration and match the color ultrasound data transmission characteristics, generate network configuration adjustment results, optimize the network scheduling strategy based on the network configuration adjustment results, and generate a color ultrasound image enhancement transmission plan.
[0098] The network load conditions include bandwidth utilization, data transmission speed, and response delay. The real-time results of monitoring and adjustment include adjusted thresholds, accuracy indicators, and response indicators. The preliminary bandwidth adjustment plan includes allocation parameters and utilization indicators. The bandwidth optimization plan includes priority classification and resource allocation results. The optimized transmission path includes path nodes, transmission efficiency, and delay indicators. The dynamic path adjustment results include path adjustment plans, adjustment frequency, and adjustment efficiency. The network configuration adjustment results include performance evaluation results and configuration update details. The color ultrasound image enhanced transmission plan includes scheduling optimization strategies and transmission performance improvement points.
[0099] See also Figure 2 , the specific steps for obtaining the network load situation are:
[0100] Based on time series analysis and support vector machine technology, the network bandwidth usage rate is analyzed in time series, and the exponential smoothing model is combined with logarithmic transformation to predict the bandwidth change trend in the future time period. The formula is:
[0101] ,
[0102] The bandwidth usage model of the time variable is calculated to generate a bandwidth usage rate variation model, where: , and represents the model adjustment parameter, t represents the time, is the time decay constant, represents the bandwidth usage variation model;
[0103] Based on the bandwidth usage change model, support vector machine technology is used to build a prediction model based on node response time, and the weighted average root error is used to evaluate the error size, using the formula:
[0104] ,
[0105] Get the prediction model of node response time, where Tuning parameters for model sensitivity, represents the response time of the i-th real-time node, is the historical response time mean, n is the number of samples, It is a prediction model for node response time;
[0106] Combining the bandwidth usage change model and the node response time prediction error, weighted synthesis is performed using the harmonic mean method, using the formula:
[0107] ,
[0108] Get the network load, where: is the total adjustment factor, and are the weights of the bandwidth usage model and the node response time model, respectively. and They are respectively the bandwidth usage variation model and the node response time prediction model. is the error set, The network load condition.
[0109] Bandwidth usage change model formula: ,
[0110] : Model adjustment parameter, affecting the scaling of the logarithmic term, set to 2; : Time decay constant adjustment parameter, set to 3; t: time variable, assuming the analysis time is 5 hours; : time decay constant, set to 10; : The coefficient of the linear term, set to 1.5;
[0111] First calculate The value of ,calculate ;
[0112] Then calculate ,Will and Bring in ;
[0113] calculate ,Will and Bring in ;
[0114] calculate ,Will Substituting t=5 into the equation, we get 1.5×5=7.5;
[0115] calculate have to .
[0116] When t=5, bandwidth utilization model The predicted value is 10.696, which indicates the bandwidth usage trend predicted by the model.
[0117] The prediction model formula for node response time is:
[0118] ,
[0119] : Model sensitivity adjustment parameter, set to 0.8; : Assume that the historical node response time data is ; n: sample size, set to 5 (i.e. The number of elements in ); : Calculate the average historical response time, ;
[0120] First calculate the sum of the squared errors:
[0121] ,
[0122] Calculate the square root of the mean error, ;
[0123] calculate have to ;
[0124] The value of is approximately 0.788, which represents the normalized value of the mean error estimate.
[0125] Network load condition formula:
[0126] ,
[0127] The total adjustment factor is set to 2; and : The weights of the bandwidth usage model and the node response time model are set to 0.5 and 0.3 respectively; : The error set value calculated previously is set to 0.788; and : The output values of the bandwidth utilization and node response time models calculated previously are 10.696 and 0.788 respectively;
[0128] First, the harmonic mean of the weights is calculated, ;
[0129] Calculate index adjustments, ;
[0130] calculate have to ;
[0131] calculate have to ;
[0132] The value of is approximately 2.962, which represents the comprehensive evaluation of the network load, which is specifically reflected in the weight adjustment and error consideration in the model calculation.
[0133] See also Figure 3 , the specific steps for obtaining the real-time results of monitoring adjustment are:
[0134] Based on the network load, dynamic threshold adjustment is implemented through the formula:
[0135] ,
[0136] Generate dynamic monitoring thresholds based on current load and volatility, where: and is the weight coefficient, is the nonlinear adjustment index, is the standard deviation of network load conditions, Represents the dynamic monitoring threshold. Indicates network load conditions;
[0137] Monitor network data in real time according to the dynamic monitoring threshold. If the data exceeds the threshold, a response is triggered using the formula:
[0138] ,
[0139] Get the monitoring adjustment signal, where: For response sensitivity, is a power, providing the ability of nonlinear response, To adjust the baseline, data represents the real-time network data monitored. Adjusting signals for monitoring;
[0140] Use monitoring adjustment signals to adjust network parameters in real time and optimize network configuration using the formula:
[0141] ,
[0142] Generate real-time results of monitoring adjustments, where and is the adjustment factor, Represents feedback data, To monitor the real-time results of adjustments, Condition the signal for monitoring.
[0143] The formula for dynamic monitoring threshold is: ,
[0144] and : weight coefficient, : Non-linear adjustment index, used to adjust the load The intensity of the impact; :yes The standard deviation of represents the volatility of the load; : Dynamic threshold adjusted according to current load;
[0145] Assumed parameter values: , , , (representing the network load level), (Standard deviation of load);
[0146] calculate : ,
[0147] calculate : ,
[0148] Apply the formula to calculate : ,
[0149] final The value is 9606, which is used to try a certain response based on the current network load situation and is used by the monitoring system to determine whether a certain response needs to be triggered.
[0150] Monitoring adjustment signal formula:
[0151] ,
[0152] : Response sensitivity; : Response sensitivity; : Adjust the baseline; data: the real-time network data currently monitored; : The calculated monitoring adjustment signal;
[0153] Assumed parameter values: , , , ;
[0154] calculate : ,
[0155] calculate : ,
[0156] Apply the formula to calculate :
[0157] ,
[0158] The value is 178237622.8, which indicates adjusting the signal strength and is used to further adjust the network parameters to cope with the current network conditions.
[0159] Real-time result formula for monitoring adjustment:
[0160] ,
[0161] and : adjustment coefficient, : Data fed back from the system; : The final real-time results of monitoring adjustments;
[0162] Assumed parameter values: , , (Example value of feedback data);
[0163] calculate : ,
[0164] calculate : ,
[0165] Apply the formula to calculate :
[0166] ,
[0167] The value is 17823764.78, which indicates the adjusted network parameters to respond to the current network load and performance.
[0168] See also Figure 4 , the specific steps for obtaining the bandwidth optimization solution are:
[0169] Based on the real-time results of monitoring and adjustment, combined with the real-time network load monitoring results, a linear programming model is used to map the network load status to the bandwidth configuration using the formula:
[0170] ,
[0171] Get the preliminary bandwidth adjustment plan, where represents the linear adjustment factor, represents the stability of logarithmic operations, Indicates the coefficient for smoothing the current load. It is the network load data obtained by real-time monitoring. It is a preliminary bandwidth adjustment plan;
[0172] Based on the preliminary bandwidth adjustment plan, the bandwidth allocation is adjusted by weighted average method, using the formula:
[0173] ,
[0174] The priority of color Doppler ultrasound data is introduced to obtain the bandwidth allocation result, where: Adjust weights for bandwidth, is the influence coefficient of color Doppler ultrasound data priority, Indicates the priority coefficient of color Doppler ultrasound data. Represents the bandwidth allocation result after adjustment based on priority. It is a preliminary bandwidth adjustment plan;
[0175] Bandwidth optimization is performed based on the bandwidth allocation results using the formula:
[0176] ,
[0177] Generate a bandwidth optimization plan, where and are bandwidth optimization coefficient and nonlinear adjustment index respectively, represents the standard deviation adjustment factor, Calculate the standard deviation of the priority sequence, For bandwidth optimization solutions, Indicates the bandwidth allocation result after adjustment based on priority.
[0178] Preliminary bandwidth adjustment solution formula: ,
[0179] : Linear adjustment factor. This value is usually derived from historical data analysis. Here it is assumed to be 1.2 to ensure that the logarithmic term has a greater impact.
[0180] : To ensure that there are no mathematical errors in logarithmic operations (the logarithm base is 0), set it to 1;
[0181] : Coefficient used to smooth the actual load data. A smaller coefficient can reduce the impact of outliers.
[0182] : Assume that the current network load data is 100;
[0183] Compute the logarithmic part: ;
[0184] Calculate the logarithmic term: ;
[0185] Calculate the square root part: ;
[0186] Calculate the square root term: ;
[0187] Combining the results of both parts: ;
[0188] : This represents the bandwidth configuration scheme after preliminary adjustment, providing the results of linear and nonlinear adjustments based on real-time load.
[0189] The bandwidth allocation formula after adjustment based on priority is: ,
[0190] : Bandwidth adjustment weight;
[0191] : The influence coefficient of color Doppler ultrasound data priority;
[0192] : Color Doppler ultrasound data priority coefficient sequence;
[0193] : The value obtained from the previous step;
[0194] Calculate the bandwidth adjustment weight part: ;
[0195] Calculate the priority weighted average: ;
[0196] Calculate the priority adjustment result: ;
[0197] Combining the results of both parts: ,
[0198] : Indicates the bandwidth allocation result after the priority of color Doppler ultrasound data is adjusted.
[0199] Bandwidth optimization solution formula:
[0200] ,
[0201] : Bandwidth optimization coefficient;
[0202] : Nonlinear adjustment index, increasing the sensitivity of adjustment;
[0203] : Standard deviation adjustment coefficient;
[0204] : The value obtained from the previous step;
[0205] : Standard deviation of the priority sequence of color Doppler ultrasound data.
[0206] Calculate the nonlinear adjustment result: ;
[0207] Calculate the nonlinear adjustment part: ;
[0208] Calculate the standard deviation adjustment result: ;
[0209] Combining the results of both parts: ;
[0210] The final bandwidth optimization solution is presented, which takes into account the priority of color Doppler ultrasound data and the volatility of the actual network load, and is the optimization result obtained through nonlinearity and standard deviation adjustment.
[0211] See also Figure 5 , the specific steps for obtaining the optimized transmission path are:
[0212] Using the data obtained from the bandwidth optimization solution, initialize the nodes and edges of the network graph, using the formula:
[0213] ,
[0214] Generate a preliminary network diagram where is the adjustment factor for graph construction, represents the positive definition of the logarithmic term, Smooth out changes in network load, is the output data of the bandwidth optimization solution, represents a preliminary network diagram;
[0215] Apply graph cut theory to the preliminary network graph to determine the optimal path for data transmission, using the formula:
[0216] ,
[0217] Get the optimized and adjusted graph cut results, where: represents the weight of the graph cut, Adjust the priority of data streams, Nonlinear tuning parameters, Represents a preliminary network diagram, is the optimized node cut set;
[0218] Based on the optimized and adjusted graph cut results, the data transmission path is reconstructed through the formula:
[0219] ,
[0220] Generate an optimized transmission path, where is the path reconstruction coefficient, calculate The standard deviation of is the optimized node cut set, Indicates the optimized transmission path.
[0221] Preliminary network diagram formula: ,
[0222] : Linear adjustment factor for graph construction;
[0223] : Ensure positive definition of logarithm calculation;
[0224] : Smooth out changes in network load;
[0225] : Output data of bandwidth optimization scheme;
[0226] Logarithmic term calculation: ;
[0227] Weighting of logarithmic terms: ;
[0228] Square root calculation: ;
[0229] Square root weighting: ;
[0230] Final result: ;
[0231] Represents the sum of weights of the initially constructed network graph.
[0232] Optimized node cut set formula: ,
[0233] : The weight of the graph cut;
[0234] : Influence coefficient of node optimization;
[0235] : nonlinear adjustment parameter;
[0236] : The value calculated in the previous step;
[0237] Assumptions and Same The value of
[0238] Calculation process:
[0239] Basic weighting: ;
[0240] Nonlinear term calculation: ;
[0241] Nonlinear terms weighted: ,
[0242] Final result: ;
[0243] Represents the total weight of the optimized graph cut.
[0244] The optimized transmission path formula is: ,
[0245] : Path reconstruction coefficient;
[0246] : The graph cut result calculated in the previous step;
[0247] Assumptions (standard deviation);
[0248] Power calculation: ;
[0249] Power Weighting: ;
[0250] Tangent calculation: ;
[0251] Final result: ;
[0252] Represents the total weight of the reconstructed data transmission path.
[0253] See also Figure 6 , the specific steps for obtaining the dynamic path adjustment results are:
[0254] According to the optimized transmission path and real-time network load data, the path is initially adjusted dynamically using the formula:
[0255] ,
[0256] Generate a preliminary draft of the adjustment, where: Indicates the correlation between the regulation path and the load data, represents the logarithmic transformation of the load data, represents the domain of the logarithmic operation, Current network load data, Indicates adjustment of the first draft, represents the optimized transmission path;
[0257] Based on the initial draft of the adjustment, dynamic weight adjustment is applied to optimize the distribution of data flow through the formula:
[0258] ,
[0259] Get the path optimization feedback result, where: represents the critical weight of the control path adjustment, Indicates the priority of the adjustment path. represents the adjustment of nonlinear effects, Indicates adjustment of the first draft, Indicates the feedback result of path optimization;
[0260] According to the feedback results of path optimization, the optimization strategy is executed through the formula:
[0261] ,
[0262] Generate dynamic path adjustment results, where To optimize the adjustment coefficient, measure The variability of is the transmission path result after dynamic adjustment. Indicates the path optimization feedback result.
[0263] Adjust the first draft formula: ,
[0264] : Linear coefficient of path adjustment; : Optimized transmission path; : Coefficient used to balance load impact; : Real-time network load data; : Avoid non-positive values in logarithmic operations;
[0265] Assumed parameter values: , (Transmission path optimization score), , (network load), ;
[0266] calculate :
[0267] ,
[0268] calculate :
[0269] ,
[0270] calculate :
[0271] ,
[0272] Apply the formula to get : ,
[0273] Represents the adjusted path score, which takes into account the impact of the current network load.
[0274] Path optimization feedback formula:
[0275] ,
[0276] : Path adjustment weight; : Path priority adjustment coefficient; : nonlinear adjustment parameter; : nonlinear adjustment parameter;
[0277] Assumed parameter values: , , ;
[0278] calculate : ,
[0279] Calculate weight adjustment: ,
[0280] Calculate the priority adjustment ratio:
[0281] ,
[0282] Calculate the final adjustment: ,
[0283] Indicates the path score after further optimization, taking into account the adjustment weight and priority of the path.
[0284] The formula for the transmission path after dynamic adjustment is:
[0285] ,
[0286] : Optimize adjustment coefficient; : The path optimization feedback result obtained from the previous step;
[0287] Assumed parameter values: ,calculate :
[0288] ,
[0289] Apply the adjustment factor:
[0290] ,
[0291] Assumptions Very small, close to 0:
[0292] ,
[0293] Calculate the final result: ,
[0294] It represents the final path score after dynamic adjustment, reflecting the final optimization of the path.
[0295] See also Figure 7 , the specific steps for obtaining the network configuration adjustment results are:
[0296] Based on the dynamic path adjustment results, the network performance evaluation index is calculated through real-time monitoring data of network bandwidth and data traffic, and the application formula is:
[0297] ,
[0298] Get the network performance index, where Indicates the real-time flow of color Doppler ultrasound data. Indicates the current available bandwidth. is a small amount used to avoid division by zero errors, Indicates network performance refers to the standard;
[0299] Based on network performance indicators and network latency response, the optimal network configuration is calculated using the formula:
[0300] ,
[0301] Get the adjusted network configuration parameters, where: is the time constant, Indicates the current delay of the network. is the adjusted network configuration parameter, Indicates network performance indicators;
[0302] Combining the adjusted network configuration parameters with the feedback of the current status, the formula is adopted:
[0303] ,
[0304] Generate network configuration adjustment results, where: is the adjustment factor that controls the impact of feedback data. is the data obtained from network feedback, It is the result of network configuration adjustment.
[0305] Network performance indicator formula: ,
[0306] Assumed parameter values: =300Mbps (real-time traffic of color Doppler ultrasound data), =1000Mbps (current available bandwidth), =10Mbps (excluding zero and small amount);
[0307] calculate : ,
[0308] Calculate the denominator: : ,
[0309] Apply the formula to calculate : ;
[0310] The value is about 89.11, which is a performance indicator that reflects the network load capacity under given bandwidth and data traffic.
[0311] Adjusted network configuration parameter formula: ,
[0312] Assume the parameters are: (calculated from the previous step), (time constant), (network delay parameter);
[0313] Calculate ratio : ,
[0314] Calculate the logarithmic term : ,
[0315] Apply the formula to calculate :
[0316] ,
[0317] The value of is approximately 1.807, which indicates the configuration parameters adjusted according to the network performance indicators and the current delay situation.
[0318] Network configuration adjustment result formula:
[0319] ,
[0320] Assumed parameter values: (calculated from the previous step), (network status feedback data), (Adjustment Factor);
[0321] Calculate the product : ,
[0322] Calculate the denominator : ,
[0323] Apply the formula to calculate :
[0324] ,
[0325] The value is approximately 82.14, which indicates the final network configuration adjustment result, which is used to ensure the optimized matching network performance of color Doppler ultrasound data transmission.
[0326] See also Figure 8 The specific steps for obtaining the color Doppler ultrasound image enhancement transmission plan are as follows:
[0327] Based on the network configuration adjustment results, combined with the real-time available bandwidth and current data traffic, the scheduling optimization index is calculated using the formula:
[0328] ,
[0329] Generate scheduling optimization indicators, where Indicates the network configuration adjustment result. represents the network bandwidth, and the logarithmic term provides a nonlinear adjustment of the bandwidth effect. Indicates the current network traffic. represents the nonlinear coefficient affecting the flow rate adjustment, Represents the scheduling optimization index;
[0330] Based on the scheduling optimization index and combined with the characteristics of color Doppler ultrasound data, the matching degree between the network configuration and the color Doppler ultrasound data is calculated using the formula:
[0331] ,
[0332] Generate matching results, where represents the scheduling optimization index, Indicates the characteristic parameters of color Doppler ultrasound data transmission. Indicates the matching degree between network configuration and color Doppler ultrasound data transmission characteristics;
[0333] Using the matching result, combined with the feedback of the current transmission data status, the formula is applied:
[0334] ,
[0335] Generate a color Doppler ultrasound image enhancement transmission plan, where: Indicates the matching result. Indicates status feedback, represents the balance factor, represents the index of the adjustment plan, Indicates the color Doppler ultrasound image enhancement transmission plan.
[0336] Scheduling optimization indicator formula: ,
[0337] : The network configuration adjustment result calculated in the previous step;
[0338] =1000Mbps: network bandwidth;
[0339] =500Mbps: current network traffic;
[0340] : nonlinear coefficient;
[0341] calculate : ,
[0342] calculate : ,
[0343] Apply the formula to calculate :
[0344] ,
[0345] The value of is 0.0000018, which represents the scheduling optimization index, taking into account the impact of network bandwidth and traffic.
[0346] The matching formula between network configuration and color Doppler ultrasound data transmission characteristics is as follows: ,
[0347] : The scheduling optimization index obtained from the previous step;
[0348] : Characteristic parameters of color Doppler ultrasound data transmission;
[0349] calculate : ,
[0350] calculate : ,
[0351] Apply the formula to calculate :
[0352] ,
[0353] The value is approximately 0.000012, which represents the matching degree between the color Doppler ultrasound data transmission characteristics and the network configuration.
[0354] Color Doppler ultrasound image enhancement transmission plan formula: ,
[0355] : The matching degree calculated from the previous step;
[0356] : System status feedback data;
[0357] : balance factor;
[0358] :index;
[0359] calculate :
[0360] ,
[0361] calculate :
[0362] ,
[0363] Apply the formula to calculate :
[0364] ,
[0365] The value of is approximately 0.00012, which represents the final generated color ultrasound image enhancement transmission plan.
[0366] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.
Claims
1. A color Doppler ultrasound data real-time transmission system, characterized in that: The system comprises: The real-time bandwidth monitoring module is based on time series analysis and support vector machine technology to continuously monitor network bandwidth usage and node response time, generate network load conditions, adjust monitoring thresholds according to network load conditions, optimize monitoring accuracy and response speed, and obtain real-time results of monitoring adjustments; The bandwidth dynamic configuration module uses linear programming to reallocate the current bandwidth based on the real-time results of the monitoring adjustment, optimizes the bandwidth utilization, generates a preliminary bandwidth adjustment plan, and adjusts the bandwidth allocation based on the preliminary bandwidth adjustment plan and the priority of the color Doppler ultrasound data to obtain a bandwidth optimization plan; The steps for obtaining the bandwidth optimization solution are specifically as follows: Based on the real-time results of the monitoring adjustment, combined with the real-time network load monitoring results, a linear programming model is used to map the network load status to the bandwidth configuration, using the formula: , Get the preliminary bandwidth adjustment plan, where represents the linear adjustment factor, represents the stability of logarithmic operations, Indicates the coefficient for smoothing the current load. It is the network load data obtained by real-time monitoring. It is a preliminary bandwidth adjustment plan; Based on the preliminary bandwidth adjustment scheme, the bandwidth allocation is adjusted by weighted average method, using the formula: , The priority of color Doppler ultrasound data is introduced to obtain the bandwidth allocation result, where: Adjust weights for bandwidth, is the influence coefficient of color Doppler ultrasound data priority, Indicates the priority coefficient of color Doppler ultrasound data. Represents the bandwidth allocation result after adjustment based on priority. It is a preliminary bandwidth adjustment plan; Based on the bandwidth allocation result, bandwidth optimization is performed using the formula: , Generate a bandwidth optimization plan, where and are bandwidth optimization coefficient and nonlinear adjustment index respectively, represents the standard deviation adjustment factor, Calculate the standard deviation of the priority sequence, For bandwidth optimization solutions, Represents the bandwidth allocation result adjusted according to the priority; The data transmission path optimization module optimizes the data transmission path according to the bandwidth optimization scheme by using graph cut theory, reduces potential delays in data transmission, obtains an optimized transmission path, and dynamically adjusts the optimized transmission path according to changes in network load to generate a dynamic path adjustment result; The steps for obtaining the optimized transmission path are specifically as follows: Using the data obtained from the bandwidth optimization scheme, the nodes and edges of the network graph are initialized using the formula: , Generate a preliminary network diagram where is the adjustment factor for graph construction, represents the positive definition of the logarithmic term, Smooth out changes in network load, is the output data of the bandwidth optimization solution, represents a preliminary network diagram; Apply graph cut theory to the preliminary network diagram to determine the optimal path for data transmission, using the formula: , Get the optimized and adjusted graph cut results, where: represents the weight of the graph cut, Adjust the priority of data streams, Nonlinear tuning parameters, Represents a preliminary network diagram, is the optimized node cut set; Based on the optimized and adjusted graph cut results, the data transmission path is reconstructed through the formula: , Generate an optimized transmission path, where is the path reconstruction coefficient, calculate The standard deviation of is the optimized node cut set, represents the optimized transmission path; The steps for obtaining the dynamic path adjustment result are specifically as follows: According to the optimized transmission path and real-time network load data, the path is initially dynamically adjusted using the formula: , Generate a preliminary draft of the adjustment, where: Indicates the correlation between the regulation path and the load data, represents the logarithmic transformation of the load data, represents the domain of the logarithmic operation, Current network load data, Indicates adjustment of the first draft, represents the optimized transmission path; Based on the draft of the adjustment, dynamic weight adjustment is applied to optimize the distribution of data flow, through the formula: , Get the path optimization feedback result, where: represents the critical weight of the control path adjustment, Indicates the priority of the adjustment path. represents the adjustment of nonlinear effects, Indicates adjustment of the first draft, Indicates the feedback result of path optimization; According to the feedback result of the path optimization, the optimization strategy is executed through the formula: , Generate dynamic path adjustment results, where To optimize the adjustment coefficient, measure The variability of is the transmission path result after dynamic adjustment. Indicates the feedback result of path optimization; The real-time color ultrasound data transmission optimization module uses the dynamic path adjustment results to evaluate network performance indicators in real time, adjust the network configuration and match the color ultrasound data transmission characteristics, generate network configuration adjustment results, optimize the network scheduling strategy according to the network configuration adjustment results, and generate a color ultrasound image enhancement transmission plan.
2. The color Doppler ultrasound data real-time transmission system according to claim 1, characterized in that: The steps for obtaining the network load condition are specifically as follows: Based on time series analysis and support vector machine technology, the network bandwidth usage rate is analyzed in time series, and the exponential smoothing model is combined with logarithmic transformation to predict the bandwidth change trend in the future time period. The formula is: , The bandwidth usage model of the time variable is calculated to generate a bandwidth usage rate variation model, where: , and represents the model adjustment parameter, t represents the time, is the time decay constant, represents the bandwidth usage variation model; Based on the bandwidth usage change model, support vector machine technology is used to build a prediction model based on node response time, and the weighted average root error of the application error is evaluated using the formula: , Get the prediction model of node response time, where Tuning parameters for model sensitivity, represents the response time of the i-th real-time node, is the historical response time mean, n is the number of samples, It is a prediction model for node response time; Combining the bandwidth usage rate change model and the node response time prediction error, weighted synthesis is performed by harmonic mean method, and the formula is adopted: , Get the network load, where: is the total adjustment factor, and are the weights of the bandwidth usage model and the node response time model, respectively. and They are respectively the bandwidth usage variation model and the node response time prediction model. is the error set, The network load condition.
3. The real-time transmission system for color Doppler ultrasound data according to claim 2, characterized in that: The steps for obtaining the real-time results of the monitoring adjustment are specifically as follows: Based on the network load condition, dynamic threshold adjustment is implemented, through the formula: , Generate dynamic monitoring thresholds based on current load and volatility, where: and is the weight coefficient, is the nonlinear adjustment index, is the standard deviation of network load conditions, Represents the dynamic monitoring threshold, Indicates network load conditions; The network data is monitored in real time according to the dynamic monitoring threshold. If the data exceeds the threshold, a response is triggered, using the formula: , Get the monitoring adjustment signal, where: For response sensitivity, is a power, providing the ability of nonlinear response, To adjust the baseline, data represents the real-time network data monitored. Adjusting signals for monitoring; The monitoring adjustment signal is used to adjust the network parameters in real time and optimize the network configuration, using the formula: , Generate real-time results of monitoring adjustments, where and is the adjustment factor, Represents feedback data, To monitor the real-time results of adjustments, Condition the signal for monitoring.
4. The real-time transmission system for color Doppler ultrasound data according to claim 1, characterized in that: The steps for obtaining the network configuration adjustment result are specifically as follows: Based on the dynamic path adjustment result, the network performance evaluation index is calculated through the real-time monitoring data of network bandwidth and data traffic, and the formula is applied: , Get the network performance index, where Indicates the real-time flow of color Doppler ultrasound data. Indicates the current available bandwidth. is a small amount used to avoid division by zero errors, Indicates network performance refers to the standard; Based on the network performance indicators and the network's delayed response, the optimal network configuration is calculated using the formula: , Get the adjusted network configuration parameters, where: is the time constant, Indicates the current network delay. is the adjusted network configuration parameter, Indicates network performance indicators; Combining the adjusted network configuration parameters with the feedback of the current state, the formula is adopted: , Generate network configuration adjustment results, where: is the adjustment factor that controls the impact of feedback data. is the data obtained from network feedback, It is the result of network configuration adjustment.
5. The color Doppler ultrasound data real-time transmission system according to claim 4, characterized in that: The steps for obtaining the color ultrasound image enhancement transmission plan are specifically as follows: Based on the network configuration adjustment results, combined with the real-time available bandwidth and current data traffic, the scheduling optimization index is calculated using the formula: , Generate scheduling optimization indicators, where Indicates the network configuration adjustment result. represents the network bandwidth, and the logarithmic term provides a nonlinear adjustment of the bandwidth effect. Indicates the current network traffic. represents the nonlinear coefficient affecting the flow rate adjustment, Represents the scheduling optimization index; Based on the scheduling optimization index and combined with the characteristics of color Doppler ultrasound data, the matching degree between the network configuration and the color Doppler ultrasound data is calculated using the formula: , Generate matching results, where represents the scheduling optimization index, Indicates the characteristic parameters of color Doppler ultrasound data transmission. Indicates the matching degree between network configuration and color Doppler ultrasound data transmission characteristics; Using the matching result, combined with the feedback of the current transmission data status, the formula is applied: , Generate a color Doppler ultrasound image enhancement transmission plan, where: Indicates the matching result. Indicates status feedback, represents the balance factor, represents the index of the adjustment plan, Indicates the color Doppler ultrasound image enhancement transmission plan.
