CN117969774B - Automatic change bird's nest and detect and grading system - Google Patents
Automatic change bird's nest and detect and grading system Download PDFInfo
- Publication number
- CN117969774B CN117969774B CN202410394390.9A CN202410394390A CN117969774B CN 117969774 B CN117969774 B CN 117969774B CN 202410394390 A CN202410394390 A CN 202410394390A CN 117969774 B CN117969774 B CN 117969774B
- Authority
- CN
- China
- Prior art keywords
- sialic acid
- acid content
- data
- detection
- time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 244000000626 Daucus carota Species 0.000 title claims abstract description 80
- 235000005770 birds nest Nutrition 0.000 title claims abstract description 80
- 235000005765 wild carrot Nutrition 0.000 title claims abstract description 80
- 230000008859 change Effects 0.000 title claims description 61
- SQVRNKJHWKZAKO-UHFFFAOYSA-N beta-N-Acetyl-D-neuraminic acid Natural products CC(=O)NC1C(O)CC(O)(C(O)=O)OC1C(O)C(O)CO SQVRNKJHWKZAKO-UHFFFAOYSA-N 0.000 claims abstract description 174
- SQVRNKJHWKZAKO-OQPLDHBCSA-N sialic acid Chemical compound CC(=O)N[C@@H]1[C@@H](O)C[C@@](O)(C(O)=O)OC1[C@H](O)[C@H](O)CO SQVRNKJHWKZAKO-OQPLDHBCSA-N 0.000 claims abstract description 174
- 238000001514 detection method Methods 0.000 claims abstract description 149
- 238000004458 analytical method Methods 0.000 claims abstract description 125
- 230000007613 environmental effect Effects 0.000 claims abstract description 75
- 238000000034 method Methods 0.000 claims abstract description 64
- 230000008569 process Effects 0.000 claims abstract description 47
- 238000000611 regression analysis Methods 0.000 claims abstract description 6
- 230000002159 abnormal effect Effects 0.000 claims description 95
- 230000004044 response Effects 0.000 claims description 28
- 238000005457 optimization Methods 0.000 claims description 23
- 238000012549 training Methods 0.000 claims description 23
- 239000011159 matrix material Substances 0.000 claims description 22
- 238000012360 testing method Methods 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 16
- 238000004422 calculation algorithm Methods 0.000 claims description 15
- 238000012937 correction Methods 0.000 claims description 15
- 238000005070 sampling Methods 0.000 claims description 13
- 238000013441 quality evaluation Methods 0.000 claims description 12
- 230000035945 sensitivity Effects 0.000 claims description 12
- 230000007423 decrease Effects 0.000 claims description 10
- 238000011156 evaluation Methods 0.000 claims description 8
- 238000005259 measurement Methods 0.000 claims description 8
- 238000012300 Sequence Analysis Methods 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 claims description 6
- 238000013480 data collection Methods 0.000 claims description 5
- 238000007619 statistical method Methods 0.000 claims description 5
- 238000007418 data mining Methods 0.000 claims description 4
- 230000010354 integration Effects 0.000 claims description 4
- 238000012795 verification Methods 0.000 claims description 4
- 230000009467 reduction Effects 0.000 claims description 3
- 238000013450 outlier detection Methods 0.000 claims 1
- 230000006870 function Effects 0.000 description 11
- 230000005856 abnormality Effects 0.000 description 8
- 208000025174 PANDAS Diseases 0.000 description 7
- 208000021155 Paediatric autoimmune neuropsychiatric disorders associated with streptococcal infection Diseases 0.000 description 7
- 240000004718 Panda Species 0.000 description 7
- 235000016496 Panda oleosa Nutrition 0.000 description 7
- 238000003066 decision tree Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 239000000047 product Substances 0.000 description 4
- 238000004088 simulation Methods 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000010219 correlation analysis Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000001303 quality assessment method Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000012467 final product Substances 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000013077 scoring method Methods 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 238000000700 time series analysis Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Other Investigation Or Analysis Of Materials By Electrical Means (AREA)
Abstract
The invention relates to the technical field of bird's nest quality detection, in particular to an automatic bird's nest detection and classification system, which comprises: the sialic acid predictive analysis module collects sialic acid content data and environmental parameters of the bird's nest sample, processes the data set by regression analysis, builds a sialic acid content predictive model, and calculates to obtain a sialic acid content predictive value and a fluctuation index. In the invention, the sialic acid content prediction model is constructed by carrying out regression analysis on the data set by adopting a Gaussian process regression method through the sialic acid prediction analysis module, so that the scenes of small sample data and high variability data are effectively processed, the capturing capacity of the intrinsic complexity of the data is improved, and the accuracy and the reliability of the prediction result are enhanced. Through the differential analysis module, the variation trend of the sialic acid content of the bird's nest in continuous detection can be identified, the sustainable trend and the temporary trend of the sialic acid content of the bird's nest are effectively distinguished, and a basis is provided for accurately evaluating the quality of the bird's nest.
Description
Technical Field
The invention relates to the technical field of bird's nest quality detection, in particular to an automatic bird's nest detection and classification system.
Background
The technical field of bird's nest quality detection is a field which is focused on improving the detection efficiency and accuracy of bird's nest products. The method relates to various links from raw material collection, monitoring of the processing process, and inspection and evaluation of the final product. With the progress of science and technology, the field gradually changes from manual or semi-automatic detection to full-automatic detection and classification, the speed, accuracy and objectivity of detection are improved, the labor cost is reduced, and the consistency and reliability of product quality are ensured.
The automatic bird's nest detecting and classifying system is a system for detecting and classifying bird's nest quality by utilizing an automatic technology, and aims to reduce errors of manual operation, improve detection speed and realize quick and accurate evaluation of bird's nest quality through an automatic processing and analyzing flow. The system design considers the detection of key components such as sialic acid in the bird's nest, ensures that the quality of bird's nest products accords with industry standards, and meets consumer demands. Through automatic detection and classification, the quality of the market circulation bird's nest products is guaranteed.
Although the prior art has been automated in terms of nidus Collocaliae quality detection, improving detection speed and efficiency, in the scenario of processing small sample data and high variability data of sialic acid content of key components in nidus, due to complexity and uncertainty of the data, it is difficult for the system to fully capture the nonlinear relationship and pattern inherent in the data, for example, in a certain range, slight change of temperature may be difficult to significantly influence sialic acid content, but beyond a certain threshold, the change of sialic acid content may suddenly increase or decrease, thereby affecting accuracy and reliability of prediction results. In addition, although the automated system reduces errors of manual operation, it is difficult to effectively identify and reduce the influence of external interference factors on the result when continuous detection is performed, and thus problems of reduced accuracy and consistency of detection data are easily caused.
Disclosure of Invention
The application provides an automatic nidus Collocaliae detection and classification system, which solves the problems that although the prior art has realized automation in nidus Collocaliae quality detection, the detection speed and efficiency are improved, in the scene of processing small sample data and high variability data of sialic acid content of key components in nidus Collocaliae, the system is difficult to fully capture the inherent nonlinear relation and mode of the data due to complexity and uncertainty of the data, for example, slight change of temperature can hardly influence sialic acid content obviously in a certain range, but after a certain threshold value is exceeded, the change of sialic acid content can be suddenly increased or reduced, so that the accuracy and reliability of a prediction result are influenced. In addition, although the automated system reduces errors of manual operation, it is difficult to effectively identify and reduce the influence of external interference factors on the result when continuous detection is performed, and thus there is a problem that accuracy and consistency of detection data are degraded.
In view of the above, the present application provides an automated nidus Collocaliae detection and classification system.
The application provides an automatic bird's nest detection and classification system, wherein the system comprises;
The sialic acid predictive analysis module collects sialic acid content data and environmental parameters of the bird's nest sample, processes the data set by regression analysis, constructs a sialic acid content predictive model, and calculates to obtain a sialic acid content predictive value and a fluctuation index;
The differential analysis module carries out differential analysis on the sialic acid content predicted value and the fluctuation index, identifies the variation trend of the sialic acid content of the bird's nest in continuous detection, and obtains the analysis result of the variation trend;
The time matching optimization module corrects the data time stamp based on the change trend analysis result, and obtains a sequence time adjustment result by adjusting the time stamp in the data sequence;
The detection strategy adjustment module adjusts detection parameters according to characteristics of the bird's nest sample and environmental changes by using the sequence time adjustment result, and matches various test conditions to establish a detection parameter adjustment scheme;
the abnormal point detection module applies the detection parameter adjustment scheme to identify abnormal points in the data, marks sialic acid content data deviating from a normal range and obtains an abnormal cause analysis result;
The early warning feedback module starts an early warning mechanism according to the analysis result of the abnormal cause, sends an early warning signal, implements adjustment or re-detection measures and builds an early warning response record;
And the quality grade evaluation module integrates the sequence time adjustment result, the detection parameter adjustment scheme and the early warning response record, evaluates and grades the quality of the bird's nest sample, and generates a bird's nest quality grade list.
Preferably, the predicted value and the fluctuation index comprise an expected range of sialic acid concentration, and a predicted highest value and a predicted lowest value, the variation trend analysis result comprises an increase rate, a decrease rate and a stability analysis of sialic acid content, the sequence time adjustment result comprises an adjusted data acquisition time point and a time difference reduction index between sequences, the detection parameter adjustment scheme comprises an adjusted sampling frequency, detection sensitivity and a detection threshold value matched with environmental variation, the abnormality cause analysis result comprises a timestamp of the abnormality data, an abnormality level and a cause analysis, the early warning response record comprises early warning sending time, response measure content and conditions of early warning release, and the bird's nest quality level list comprises sialic acid content level of each sample, corresponding quality evaluation and recommended use range.
Preferably, the sialic acid predictive analysis module comprises:
The sample data acquisition submodule collects sialic acid content data and environmental parameters of the bird's nest sample, records sample numbers, sampling time, sialic acid content and environmental conditions, comprises various data of temperature and humidity, and acquires sample data and environmental information;
The environmental impact analysis submodule analyzes the influence of the environmental parameters including temperature and humidity on the sialic acid content based on the sample data and the environmental information, identifies key parameters affecting the sialic acid content, and acquires an environmental factor impact analysis result;
The sialic acid predictive modeling submodule processes the data set by using a Gaussian process regression method based on the environmental factor influence analysis result, constructs a sialic acid content predictive model, calculates a sialic acid content predictive value and a fluctuation range, and obtains a sialic acid content predictive value and a fluctuation index;
the Gaussian process regression method is according to an improved formula I:
Calculating the average value of the predicted values;
Wherein, Is the average of the predicted values,/>Is the covariance matrix between training points and test points,/>Is the covariance matrix between training points,/>For the current sialic acid content measurement value of the bird's nest sample in the training set,/>Representing the importance weight of each input feature for predicting sialic acid content, determined by feature selection algorithm or feature importance assessment method,/>Is a bias term, determined by an optimization process that minimizes the prediction error;
According to the modified formula II:
Calculating covariance of the predicted value, namely a predicted fluctuation range, and obtaining a sialic acid content predicted value and a fluctuation index;
Wherein, Covariance matrix of predicted value,/>For the covariance matrix between the new input data points,For covariance matrix between training data point and new input data point,/>For training covariance matrix between data points,/>And/>For covariance adjustment factors and bias terms,/>Determination by analysis of covariance relations between input features and target variables in training dataset,/>Determined by an optimization process that minimizes the prediction error.
Preferably, the differential analysis module includes:
The fluctuation detection submodule analyzes the difference between the sialic acid content predicted value and the measured value through a differential detection technology based on the sialic acid content predicted value and the fluctuation index, marks data points with the deviation exceeding a preset range, performs time sequence analysis on the data after differential analysis by using a dynamic time warping algorithm, optimizes a matching process, identifies the fluctuation of the data and obtains a fluctuation detection result;
the differential detection technique is according to the modified formula III:
Calculating the difference between the sialic acid content predicted value and the adjacent measured value to generate a deviation sequence;
Wherein, Time/>The adjusted difference between the predicted sialic acid content value and the measured value at the previous time,For time/>Predicted sialic acid content of/()For time/>Sialic acid content measurement,/>Is a weight coefficient of the importance of the difference between the reference predicted value and the current measured value in the differential detection, and is determined by carrying out statistical analysis on the difference between the predicted value and the current measured value of sialic acid content in the historical data set,/>Is an offset term in differential detection, and is determined by optimizing a model to minimize the overall error between the predicted value and the current measured value;
The dynamic time warping algorithm follows the modified formula IV:
Performing time sequence analysis based on the deviation sequence, optimizing a matching process, and identifying the fluctuation of the matching process to obtain a fluctuation detection result;
Wherein, Representation sequence/>And/>The minimum accumulated distance after weight adjustment and bias term correction is carried out between the two components,/>And/>Respectively represent the predicted value sequence and the current measured value sequence of sialic acid content after differential detection,/>And/>Sequences/>, respectivelyAnd/>Element at time/>，/>And/>Sequences/>, respectivelyAnd/>The weight coefficient of the element in the formula (I) is obtained by analyzing the sequence/>And/>The sensitivity of the change in data and the contribution to the final prediction result are determined for each time point,Is a bias term in DTW computation, determined by evaluating the average match error of time series pairings,/>Is the length of the sequence;
The trend change identification submodule distinguishes the continuous trend and the temporary trend of the sialic acid content of the bird's nest based on the fluctuation detection result, and the trend change identification result is obtained through analysis of the growth rate, the decline rate and the stability;
And the trend analysis result integration submodule is used for sorting and summarizing all the identified trend changes based on the trend change identification result, analyzing the overall change trend of the sialic acid content of the bird's nest, and generating a change trend analysis result by identifying key change points and stable periods.
Preferably, the time matching optimization module includes:
The time correction processing submodule is used for checking the consistency and accuracy of the data time stamp based on the change trend analysis result, correcting the time deviation in the data collection process and generating a time correction record;
The time mark adjustment submodule re-marks a time point in the data sequence by using the time correction record, adjusts the current time sequence of the time mark reflecting sialic acid content change, eliminates data dislocation caused by time mark errors and acquires a time mark adjustment table;
And the data alignment perfecting sub-module reorders and aligns all data points according to the time mark adjustment table to generate a sequence time adjustment result.
Preferably, the detection policy adjustment module includes:
The environmental adaptability analysis submodule analyzes the association of the environmental parameters and sialic acid content based on the sequence time adjustment result, identifies key environmental variables and generates an environmental factor influence analysis result;
The detection parameter optimization submodule utilizes the environmental factors to influence analysis results, adjusts the sensitivity or sampling frequency of the detection instrument to obtain various parameter settings, and matches various environmental conditions and sample characteristics to obtain adjusted parameter configuration;
and the adaptability test condition sub-module establishes test conditions matching with various environments and sample characteristics according to the adjusted parameter configuration, performs condition validity verification and constructs a detection parameter adjustment scheme.
Preferably, the abnormal point detection module includes:
The abnormal data mining sub-module analyzes sialic acid content data based on the detection parameter adjustment scheme, identifies data points deviating from a normal range, refers to variation coefficients and average deviations, identifies potential anomalies and generates an abnormal data list;
The abnormal point marking sub-module marks abnormal points at corresponding positions in the data sequence by using the abnormal data list, marks the abnormal points as abnormal data to be analyzed again and obtains an abnormal point marking index;
And the abnormal reason analysis submodule analyzes the marked abnormal points according to the abnormal point marking indexes, analyzes the abnormal reasons including various factors of environmental change or detection errors, and obtains an abnormal reason analysis result.
Preferably, the early warning feedback module includes:
the early warning triggering and notifying submodule sends early warning signals of abnormal data to detection personnel and administrators based on the abnormal cause analysis result to generate early warning notification records;
The adjustment measure recommending submodule makes targeted adjustment measures and recheck plans according to the identified abnormal reasons and generates an implementation adjustment scheme according to the early warning notification record;
And the early warning processing record submodule records the early warning response adopted according to the implementation adjustment scheme, wherein the early warning response comprises adjustment of operation parameters or redetection of various measures, processing procedures and results, and an early warning response record is constructed.
Preferably, the quality rating module includes:
The data comprehensive analysis submodule comprehensively refers to the sequence time adjustment result, the detection parameter adjustment scheme and the early warning response record, analyzes overall data trend and abnormal condition of sialic acid content of the bird's nest sample, performs quality analysis operation and generates a comprehensive analysis result;
The quality judgment flow submodule applies a quality evaluation standard according to the comprehensive analysis result to carry out quality judgment on sialic acid content of the bird's nest sample, and distinguishes quality grades to obtain a quality judgment result;
and the quality grade table generating sub-module sorts and files sialic acid content quality grade of each sample, corresponding quality evaluation and recommended use range according to the quality judging result, and builds a bird's nest quality grade list.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
The sialic acid predictive analysis module carries out regression analysis on the data set by adopting a Gaussian process regression method to construct a sialic acid content predictive model, effectively processes the scenes of small sample data and high variability data, improves the capture capacity of the intrinsic complexity of the data, and enhances the accuracy and reliability of the predictive result. Through the differential analysis module, the variation trend of the sialic acid content of the bird's nest in continuous detection can be identified, the sustainable trend and the temporary trend of the sialic acid content of the bird's nest are effectively distinguished, and a basis is provided for accurately evaluating the quality of the bird's nest. In addition, through the time matching optimization module, the accurate correction of the time stamp of the detection data and the optimization adjustment of the time sequence can be realized, and the problem that the influence of external interference factors is difficult to reduce in the continuous detection in the prior art is effectively solved. Error accumulation caused by external environment change is avoided, so that stability and reliability of the whole detection flow are guaranteed.
The foregoing description is only an overview of the present application, and is intended to provide a better understanding of the technical means of the present application, as it is embodied in the present specification, and is intended to provide a better understanding of the above and other objects, features and advantages of the present application, as it is embodied in the following description.
Drawings
FIG. 1 is a block diagram of an automated bird's nest detection and classification system according to the present invention;
FIG. 2 is a system frame diagram of an automated bird's nest detection and classification system according to the present invention;
FIG. 3 is a schematic diagram showing a specific flow of a sialic acid predictive analysis module in an automated bird's nest detection and classification system according to the present invention;
Fig. 4 is a schematic flow chart of a differential analysis module in an automatic nidus Collocaliae detection and classification system according to the present invention;
Fig. 5 is a schematic flow chart of a time matching optimization module in an automatic nidus Collocaliae detection and classification system according to the present invention;
fig. 6 is a schematic flow chart of a detection policy adjustment module in an automatic nidus Collocaliae detection and classification system according to the present invention;
Fig. 7 is a schematic flow chart of an abnormal point detection module in an automatic nidus Collocaliae detection and classification system according to the present invention;
fig. 8 is a schematic diagram of a specific flow chart of an early warning feedback module in an automatic nidus Collocaliae detection and classification system according to the present invention;
fig. 9 is a schematic flow chart of a quality grade evaluation module in an automatic nidus Collocaliae detection and classification system according to the present invention.
Detailed Description
As shown in fig. 1, the present application provides an automated bird's nest detecting and classifying system, wherein the system comprises:
The sialic acid predictive analysis module collects sialic acid content data and environmental parameters of the bird's nest sample, processes the data set by regression analysis, constructs a sialic acid content predictive model, and calculates to obtain a sialic acid content predictive value and a fluctuation index;
The differential analysis module carries out differential analysis on the sialic acid content predicted value and the fluctuation index, identifies the variation trend of the sialic acid content of the bird's nest in continuous detection, and obtains the analysis result of the variation trend;
The time matching optimization module corrects the data time stamp based on the change trend analysis result, and obtains a sequence time adjustment result by adjusting the time stamp in the data sequence;
The detection strategy adjustment module adjusts detection parameters according to characteristics of bird's nest samples and environmental changes by using a sequence time adjustment result, matches various test conditions, and establishes a detection parameter adjustment scheme;
the abnormal point detection module applies a detection parameter adjustment scheme to identify abnormal points in the data, marks sialic acid content data deviating from a normal range and obtains an abnormal cause analysis result;
The early warning feedback module starts an early warning mechanism according to the analysis result of the abnormal cause, sends an early warning signal, implements adjustment or re-detection measures and builds an early warning response record;
the quality grade evaluation module integrates the sequence time adjustment result, the detection parameter adjustment scheme and the early warning response record, and performs quality evaluation and grading on the bird's nest sample to generate a bird's nest quality grade list.
The predicted value and the fluctuation index comprise the expected range of sialic acid concentration, the highest value and the lowest value of prediction, the change trend analysis result comprises the increase rate, the decrease rate and the stability analysis of sialic acid content, the sequence time adjustment result comprises the adjusted data acquisition time point and the time difference reduction index between sequences, the detection parameter adjustment scheme comprises the adjusted sampling frequency, the detection sensitivity and the detection threshold value matched with the environmental change, the abnormal cause analysis result comprises the timestamp of abnormal data, the abnormal level and the cause analysis, the early warning response record comprises the early warning sending time, the response measure content and the early warning release condition, and the bird's nest quality grade list comprises the sialic acid content grade of each sample, the corresponding quality evaluation and the recommended use range.
As shown in fig. 2 and 3, the sialic acid predictive analysis module includes:
The sample data acquisition submodule collects sialic acid content data and environmental parameters of the bird's nest sample, records sample number, sampling time, sialic acid content and environmental conditions, comprises various data of temperature and humidity, and comprises the following specific processes of acquiring the sample data and the environmental information;
The sample data acquisition submodule adopts a data acquisition algorithm based on bird's nest sample characteristics, utilizes a sensor to collect sialic acid content data and environmental parameters such as temperature and humidity, sets a sensor reading interval to be once per hour, records the collected data together with a sample number and sampling time in a database, and each record comprises sialic acid content, temperature, humidity, sample number and sampling time to generate sample data and environmental information.
The environmental impact analysis submodule analyzes the influence of the environmental parameters including temperature and humidity on the sialic acid content based on the sample data and the environmental information, identifies key parameters affecting the sialic acid content, and obtains a concrete flow of an environmental factor impact analysis result;
The environmental impact analysis submodule adopts a linear regression analysis method based on sample data and environmental information, sets independent variables as temperature and humidity, sets the independent variables as sialic acid content, uses linregress functions in a SciPy library of Python to conduct data analysis, calculates correlation coefficients between the temperature and the humidity and the sialic acid content, determines statistical significance of influences of the temperature and the humidity on the sialic acid content, obtains a conclusion of the temperature and the humidity serving as key environmental parameters through analysis, and generates an environmental factor impact analysis result.
The sialic acid predictive modeling submodule processes the data set based on the environmental factor influence analysis result by using a Gaussian process regression method, builds a sialic acid content predictive model, calculates a sialic acid content predictive value and a fluctuation range, and obtains a sialic acid content predictive value and a fluctuation index, wherein the sialic acid content predictive value and the fluctuation index are specifically obtained by the steps of;
Based on environmental factor influence analysis results, the sialic acid predictive modeling submodule adopts a Gaussian process regression method, uses GaussianProcessRegressor types in scikit-learn libraries of Python, sets a kernel function as an RBF kernel, completes optimization parameters by maximizing an edge likelihood function, trains a dataset, constructs a sialic acid content predictive model, calculates a sialic acid content predictive value and a 95% confidence interval thereof through the model, represents a fluctuation range, and generates the sialic acid content predictive value and a fluctuation index.
The gaussian process regression method is according to the improved formula I:
Calculating the average value of the predicted values;
Wherein, Is the average of the predicted values,/>Is the covariance matrix between training points and test points,/>Is the covariance matrix between training points,/>For the current sialic acid content measurement value of the bird's nest sample in the training set,/>Representing importance weights of each input feature for predicting sialic acid content, and determining the importance weights by a feature selection algorithm or a feature importance assessment method for adjusting contribution degree of predicted value,/>Is a bias term for adjusting the overall predictor level, as determined by an optimization process that minimizes the prediction error.
According to the modified formula II:
Calculating covariance of the predicted value, namely a predicted fluctuation range, and obtaining a sialic acid content predicted value and a fluctuation index;
Wherein, The covariance matrix of the predicted value represents uncertainty or credibility of the predicted result. /(I)The covariance matrix between the new input data points reflects the similarity between the new inputs. /(I)Is the covariance matrix between the training data point and the new input data point. /(I)Is the covariance matrix between the training data points. /(I)And/>For covariance adjustment factors and bias terms, respectively, for adjusting uncertainty range of predicted values and providing additional adjustment to more accurately represent predicted uncertainty,/>Determination by analysis of covariance relations between input features and target variables in training dataset,/>Determined by an optimization process that minimizes the prediction error.
The execution process is as follows:
Calculating covariance matrix using training data points and new input data points Recalculating the covariance matrix/>, between the new input data pointsRepresenting the similarity of the new input points to each other, calculating a covariance matrix between the training data points。
Determining importance weights for each input feature by feature selection algorithm or feature importance assessment (e.g., feature importance scores for random forests)。
Analyzing training data sets, determining covariance adjustment factors using statistical testing or optimization algorithms (e.g., gradient descent)And bias term/>And bias term/>。
The mean of the sialic acid content predictions for the new input data points is calculated according to equation I. Includes the covariance matrixAnd training output/>Combining, adjusting the contribution/>, of each featureAnd add bias term/>。
Using equation II, the covariance of the predicted value, i.e., the uncertainty of the prediction, is calculated.
As shown in fig. 2 and 4, the variability analysis module includes:
The fluctuation detection submodule analyzes the difference between the sialic acid content predicted value and the measured value through a differential detection technology based on the sialic acid content predicted value and the fluctuation index, marks data points with deviation exceeding a preset range, performs time sequence analysis on the data after differential analysis by using a dynamic time warping algorithm, optimizes a matching process, and identifies the fluctuation of the data, and the specific flow for obtaining a fluctuation detection result is as follows;
The fluctuation detection submodule carries out differential detection technology application based on sialic acid content predicted values and fluctuation indexes, carries out differential operation through a NumPy library of Python, calculates differences between continuous measured values, is used for identifying the deviation between the predicted values and actual measured values, sets a threshold value of which the deviation exceeds a preset range as 10% of the predicted values and is used for marking abnormal data points, then applies a dynamic time warping algorithm, optimizes a time sequence matching process of sialic acid content data by using a fastdtw library of Python, and adjusts time sequence data to be aligned in an optimal mode by calculating fluctuation of minimum accumulated distance identification data, reduces the influence of time dislocation and generates a fluctuation detection result.
The differential detection technique is according to improved equation III:
Calculating the difference between the sialic acid content predicted value and the adjacent measured value to generate a deviation sequence;
Wherein, Time/>An adjusted difference between the predicted sialic acid content value and the measured value at a previous time.For time/>Predicted sialic acid content of (c). /(I)For time/>Is measured for sialic acid content of the sample. /(I)Is a weight coefficient of the importance of the difference between the reference predicted value and the current measured value in the differential detection, and is determined by carrying out statistical analysis on the difference between the predicted value of sialic acid content in the historical data set and the current measured value. /(I)Is an offset term in differential detection, determined by optimizing the model to minimize the overall error between the predicted value and the current measured value, for adjusting the baseline level of the differential result.
The dynamic time warping algorithm follows the modified formula IV:
performing time sequence analysis based on the deviation sequence, optimizing the matching process, and identifying the fluctuation of the matching process to obtain a fluctuation detection result;
Wherein, Representation sequence/>And/>The minimum accumulated distance is adjusted by the weight and corrected by the bias term. /(I)And/>Respectively representing the predicted value sequence and the current measured value sequence of sialic acid content after differential detection. /(I)And/>Sequences/>, respectivelyAnd/>Element at time/>。/>And/>Sequences/>, respectivelyAnd/>The weight coefficient of the element in the formula (I) is obtained by analyzing the sequence/>And/>The sensitivity of the change of each time point data and the contribution degree of the final prediction result are determined, and the weight refers to the importance of different time point data. /(I)Is a bias term in DTW calculation, and is determined by evaluating the average match error of different time series pairs, and is used for adjusting the level of the baseline distance in the time series matching process. /(I)Is the length of the sequence, representing the sequence/>And/>The total number of elements in (a).
The execution process is as follows:
and collecting the sialic acid content predicted value and the actual measured value sequence of the bird's nest sample.
For each time point, calculating the difference between the sialic acid content predicted value and the measured value at the previous time point by using a formula III, and determining the weight coefficient of the difference importance through statistical analysis or a machine learning modelAnd bias term/>。
Analyzing the historical dataset and determining the weight coefficient of each time point in the sequence by using a feature selection algorithm or an importance scoring methodAnd/>. Optimizing a model to minimize prediction error, determining bias term/>And/>。
Using the sequence adjusted by differential detection using formula IVAnd/>Time series analysis was performed. The matching process is optimized by calculating the minimum cumulative distance between the two sequences and identifying its volatility.
And identifying and marking abnormal data points exceeding a preset range according to the improved differential detection and DTW analysis results.
And analyzing the fluctuation of the time sequence data to determine the variation trend of sialic acid content of the bird's nest.
And integrating the results of the differential detection and the DTW analysis, and evaluating the sialic acid content fluctuation mode of the bird's nest sample.
The trend change identification submodule distinguishes the continuous trend and the temporary trend of the sialic acid content of the bird's nest based on the fluctuation detection result, wherein the trend change identification submodule comprises a specific flow for obtaining the trend change identification result through analysis of the growth rate, the decline rate and the stability;
The trend change identification submodule is used for distinguishing a continuous trend from a temporary trend based on a fluctuation detection result, carrying out data processing by using a Pandas library of Python, calculating the average increase rate and the decrease rate of sialic acid content in a window period by a sliding window calculation method, setting the window size to 7 days so as to capture Zhou Du trend, simultaneously, evaluating the stability of data by using a standard deviation function, identifying the stable period of data fluctuation, and distinguishing the change trend of sialic acid content of bird's nest as continuous or temporary by comparing the increase rate and the decrease rate in a continuous time period to generate a trend change identification result.
The trend analysis result integrating submodule is used for sorting and summarizing all the identified trend changes based on trend change identification results, analyzing the overall change trend of sialic acid content of the bird's nest, and comprises the specific processes of identifying key change points and stable periods and generating change trend analysis results, wherein the specific processes are as follows;
The trend analysis result integration submodule is used for carrying out arrangement and induction of trend change based on a trend change identification result, a Matplotlib library of Python is used for drawing a change trend chart of sialic acid content of the bird's nest, key change points and stable periods are identified in a graphical mode, data points in the chart are analyzed, obvious increase or decrease trend and stable periods with smaller fluctuation are identified, and the integral change trend of sialic acid content of the bird's nest is deeply understood through integration analysis, so that a change trend analysis result is generated.
As shown in fig. 2 and 5, the time matching optimization module includes:
The time correction processing submodule is used for checking the consistency and accuracy of the data time stamp based on the change trend analysis result, correcting the time deviation in the data collection process and generating a specific flow of time correction record, wherein the specific flow is as follows;
The time correction processing submodule carries out consistency and accuracy check of the data time stamp based on a change trend analysis result, uses the to_ datetime function in the pandas library of Python to convert the time stamp format, ensures uniformity, corrects the missing or wrong time stamp by comparing the corresponding relation between the sequence of the time sequence and the change trend of sialic acid content and adopting a linear interpolation method, sets the interpolation method as linear interpolation of the time sequence, predicts and fills the sialic acid content of the missing time point based on the sialic acid content of the adjacent time point, thereby correcting the time deviation in the data collection process and generating a time correction record.
The time mark adjusting submodule re-marks time points in the data sequence by utilizing time correction records, adjusts the current time sequence of the time mark reflecting sialic acid content change, eliminates data dislocation caused by time mark errors, and acquires a specific flow of a time mark adjusting table;
The time mark adjustment submodule uses time correction record to re-mark time points in the data sequence, adopts pandas library of Python to sequence the data sequence, adjusts the data sequence according to the corrected time mark, ensures that the time mark reflects the correct time sequence of sialic acid content change, uses the sort_value function to re-sequence the data sequence according to the corrected time mark, eliminates data dislocation caused by time mark error, and obtains a time mark adjustment table.
The data alignment perfecting submodule reorders and aligns all data points according to the time mark adjustment table, and the specific flow for generating a sequence time adjustment result is as follows;
The data alignment perfecting submodule reorders and aligns all data points according to a time mark adjustment table, approximately merges the data points by adopting a merge_ asof function of pandas libraries of Python, aligns the data according to time stamps in the time mark adjustment table, sets the merging direction as the latest past so as to ensure the sequency and continuity between the data points, optimizes the time sequence of a data sequence, ensures that the time mark of each data point accurately reflects the measurement time of sialic acid content, and generates a sequence time adjustment result.
As shown in fig. 2 and 6, the detection policy adjustment module includes:
The environmental adaptability analysis submodule analyzes the association of environmental parameters and sialic acid content based on the sequence time adjustment result, identifies key environmental variables, and generates a concrete flow of influencing the analysis result by environmental factors, wherein the concrete flow is as follows;
The environmental adaptability analysis submodule carries out correlation analysis of environmental parameters and sialic acid content based on a sequence time adjustment result, carries out nonparametric Spekerman grade correlation analysis by using spearmanr functions in SciPy libraries of Python, identifies key environmental variables with obvious influence on sialic acid content by calculating correlation coefficients between the environmental parameters such as temperature and humidity and sialic acid content, sets the significance level as 0.05, and is used for determining statistical significance of the relation between the environmental parameters and sialic acid content and generating environmental factor influence analysis results.
The detection parameter optimization submodule utilizes environmental factors to influence analysis results, adjusts various parameter settings of sensitivity or sampling frequency of a detection instrument, matches various environmental conditions and sample characteristics, and obtains the specific flow of the adjusted parameter configuration as follows;
The detection parameter optimization submodule utilizes environmental factors to influence analysis results, adjusts various parameter settings such as sensitivity or sampling frequency of a detection instrument, performs parameter optimization by adopting GRIDSEARCHCV functions in a sklearn library of Python, sets a parameter search range which comprises different levels from low sensitivity to high sensitivity, and selects parameter configurations which are best represented under various environmental conditions and sample characteristics based on optimization of cross-validation scores at different intervals from once per hour to once per day of sampling frequency, so as to obtain the adjusted parameter configurations.
The adaptive test condition submodule formulates test conditions matching various environments and sample characteristics according to the adjusted parameter configuration, and executes condition validity verification to construct a specific flow of a detection parameter adjustment scheme;
The adaptive test condition submodule prepares test conditions matching various environments and sample characteristics according to the adjusted parameter configuration, adopts a numpy library of Python to perform simulation test on the conditions, sets the simulation range of environment variables, such as the temperature between 15 and 30 ℃ and the humidity between 40% and 80%, executes sialic acid content measurement under a series of preset conditions through the simulation test, and utilizes predefined evaluation criteria, such as the stability and repeatability of measurement results to perform condition validity verification to construct a test parameter adjustment scheme.
As shown in fig. 2 and 7, the abnormal point detection module includes:
The abnormal data mining sub-module analyzes sialic acid content data based on a detection parameter adjustment scheme, identifies data points deviating from a normal range, refers to variation coefficients and average deviations, identifies potential anomalies, and generates an abnormal data list by the specific flow;
The abnormal data mining sub-module is used for analyzing sialic acid content data based on a detection parameter adjustment scheme, calculating variation coefficient and average deviation of the data by adopting NumPy library of Python, judging fluctuation of the data through the variation coefficient, setting a variation coefficient threshold value to be 0.5, setting the average deviation threshold value to be 10% of the sialic acid content average value for evaluating deviation degree of the data and the average value, identifying data points deviating from the threshold value as potential abnormalities, and generating an abnormal data list.
The abnormal point marking submodule marks abnormal points at corresponding positions in the data sequence by using an abnormal data list, marks the abnormal points as abnormal data to be analyzed again, and obtains the specific flow of the abnormal point marking index as follows;
The abnormal point marking sub-module marks abnormal points at corresponding positions in the data sequence by using an abnormal data list, adds a new column to mark abnormal data points by adopting a Pandas library of Python, allocates a specific mark for each data point identified as abnormal, for example, sets the mark value of the abnormal point as True, keeps the non-abnormal point as False, clearly identifies the abnormal data points needing further analysis, and obtains an abnormal point marking index.
The abnormal cause analysis submodule analyzes marked abnormal points according to the abnormal point marking indexes, analyzes abnormal causes including various factors of environmental change or detection errors, and obtains a specific flow of an abnormal cause analysis result as follows;
The abnormality cause analysis submodule analyzes the cause of the marked abnormal points according to the abnormal point marking index, adopts a decision tree classification algorithm, uses DecisionTreeClassifier functions in scikit-learn libraries of Python, sets the depth of a decision tree as 5, takes environmental change and detection errors as characteristic input, takes abnormality and non-abnormality as target output, and obtains an abnormality cause analysis result by training a decision tree model to identify main causes after abnormal data, such as sudden change of the environmental temperature or calibration deviation of a detection instrument.
As shown in fig. 2 and 8, the early warning feedback module includes:
the early warning triggering and notifying sub-module sends early warning signals of abnormal data to detection personnel and administrators based on the analysis result of the abnormal reasons, and the specific flow of generating early warning notification records is as follows;
The early warning triggering and notifying sub-module is used for sending early warning signals of abnormal data based on an abnormal reason analysis result, an email notification system is adopted, an SMTP server is configured by using smtplib library of Python, a sender mailbox address and a recipient mailbox list are set, the mailbox of a detector and a system manager is included, mail content is constructed, specific information and early warning level of the abnormal data are included, the sender is called to send the mail, the related personnel are ensured to receive early warning signals of the abnormal data in time, and an early warning notification record is generated.
The adjustment measure recommending submodule formulates targeted adjustment measures and recheck plans according to the identified abnormal reasons and the early warning notification records, and generates a specific flow for implementing an adjustment scheme;
The adjustment measure recommending submodule carries out the establishment of targeted adjustment measures and recheck plans according to the early warning notification record, a decision support system is used, the system provides a set of logic rules based on the identified abnormal reasons, such as environmental change or detection errors, for example, if the abnormal reasons are environmental change, the adjustment measure recommending submodule suggests to increase environmental stability control measures, if the abnormal reasons are detection errors, the adjustment measuring instrument is recommended to be calibrated, and the corresponding adjustment measures and recheck plans are matched for each abnormal reason through the set of logic rules, so that an implementation adjustment scheme is generated.
The early warning processing record submodule records the taken early warning response according to the implementation adjustment scheme, wherein the early warning response comprises adjustment of operation parameters or re-detection of various measures, and the specific flow of the processing process and the result to construct the early warning response record is as follows;
The early warning processing recording submodule records the taken early warning response according to the implementation adjustment scheme, comprises various measures such as adjustment of operation parameters or re-detection, uses project management software such as Jira to create task items, distributes the task items to responsible persons, sets the priority and the completion period of the tasks, records the execution process and the result of each task, comprises the implementation details of adjustment measures and the evaluation of the re-detection result, and ensures the effective implementation of the early warning response and constructs an early warning response record by periodically updating the task state and collecting feedback information.
As shown in fig. 2 and 9, the quality rating module includes:
the data comprehensive analysis submodule comprehensively refers to the sequence time adjustment result, the detection parameter adjustment scheme and the early warning response record, analyzes overall data trend and abnormal condition of sialic acid content of the bird's nest sample, performs quality analysis operation, and generates a specific flow of comprehensive analysis result as follows;
The data comprehensive analysis submodule comprehensively refers to sequence time adjustment results, detection parameter adjustment schemes and early warning response records, analyzes overall data trend and abnormal conditions of sialic acid content of the bird's nest sample, performs total statistical analysis on the data by adopting pandas and numpy libraries of Python, evaluates overall quality and stability of the sample by calculating average value, median, standard deviation and abnormal value proportion of the sialic acid content, compares analysis results with historical data, identifies quality fluctuation and trend change, and generates comprehensive analysis results.
The quality judgment flow submodule applies a quality evaluation standard according to the comprehensive analysis result to judge the quality of sialic acid content of the bird's nest sample, and distinguishes quality grades, so that the concrete flow of the quality judgment result is obtained;
The quality judgment flow submodule carries out quality judgment on sialic acid content of the bird's nest sample according to comprehensive analysis results by applying quality assessment standards, a decision tree algorithm is used, the depth of a decision tree is set to be 4 based on DecisionTreeClassifier types in a scikit-learn library of Python, input variables are statistical indexes of sialic acid content, such as average value, standard deviation and abnormal value proportion, output variables are quality grades, quality judgment results are obtained according to preset quality assessment standards, such as high quality of sialic acid content in a specific range and low quality of sialic acid content in an exceeding range, and a decision tree model automatically distinguishes the quality grades according to the values of the input variables.
The quality grade table generating submodule sorts and files sialic acid content quality grade of each sample, corresponding quality evaluation and recommended use range according to the quality judging result, and a specific flow for constructing the bird's nest quality grade table is as follows;
the quality grade table generating submodule sorts and files the sialic acid content quality grade, the corresponding quality evaluation and the recommended use range of each sample according to the quality judging result, creates a new DATAFRAME by using a pandas library of Python, adds the sialic acid content, the quality grade, the quality evaluation and the recommended use range of each sample into DATAFRAME as columns, exports DATAFRAME into a CSV file by utilizing a to_csv function, and is convenient to record and file, and a bird's nest quality grade list is constructed.
Although the application has been described in connection with specific features and embodiments thereof, it will be apparent that various modifications and combinations can be made without departing from the spirit and scope of the application. Accordingly, the specification and drawings are merely exemplary illustrations of the present application as defined in the appended claims and are considered to cover any and all modifications, variations, combinations, or equivalents that fall within the scope of the application. It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the scope of the application. Thus, it is intended that the present application cover the modifications and variations of this application provided they come within the scope of the appended claims and their equivalents.
Claims (6)
1. An automated bird's nest detection and classification system, the system comprising:
The sialic acid predictive analysis module collects sialic acid content data and environmental parameters of the bird's nest sample, processes the data set by regression analysis, constructs a sialic acid content predictive model, and calculates to obtain a sialic acid content predictive value and a fluctuation index;
the sialic acid predictive analysis module comprises:
The sample data acquisition submodule collects sialic acid content data and environmental parameters of the bird's nest sample, records sample numbers, sampling time, sialic acid content and environmental conditions, comprises various data of temperature and humidity, and acquires sample data and environmental information;
The environmental impact analysis submodule analyzes the influence of the environmental parameters including temperature and humidity on the sialic acid content based on the sample data and the environmental information, identifies key parameters affecting the sialic acid content, and acquires an environmental factor impact analysis result;
The sialic acid predictive modeling submodule processes the data set by using a Gaussian process regression method based on the environmental factor influence analysis result, constructs a sialic acid content predictive model, calculates a sialic acid content predictive value and a fluctuation range, and obtains a sialic acid content predictive value and a fluctuation index;
the Gaussian process regression method is according to an improved formula I:
Calculating the average value of the predicted values;
Wherein, Is the average of the predicted values,/>Is the covariance matrix between training points and test points,/>Is the covariance matrix between training points,/>For the current sialic acid content measurement value of the bird's nest sample in the training set,/>Representing the importance weight of each input feature for predicting sialic acid content, determined by feature selection algorithm or feature importance assessment method,/>Is a bias term, determined by an optimization process that minimizes the prediction error;
According to the modified formula II:
Calculating covariance of the predicted value, namely a predicted fluctuation range, and obtaining a sialic acid content predicted value and a fluctuation index;
Wherein, Covariance matrix of predicted value,/>For covariance matrix between new input data points,/>For covariance matrix between training data point and new input data point,/>For training covariance matrix between data points,/>And/>For covariance adjustment factors and bias terms,/>Determination by analysis of covariance relations between input features and target variables in training dataset,/>Determining by an optimization process that minimizes the prediction error;
the difference analysis module carries out difference analysis on the sialic acid content predicted value and the fluctuation index, identifies the change trend in continuous detection and acquires a change trend analysis result;
the differential analysis module comprises:
The fluctuation detection submodule analyzes the difference between the sialic acid content predicted value and the measured value through a differential detection technology based on the sialic acid content predicted value and the fluctuation index, marks data points with the deviation exceeding a preset range, performs time sequence analysis on the data after differential analysis by using a dynamic time warping algorithm, optimizes a matching process, identifies the fluctuation of the data and obtains a fluctuation detection result;
the differential detection technique is according to the modified formula III:
Calculating the difference between the sialic acid content predicted value and the adjacent measured value to generate a deviation sequence;
Wherein, Time/>Post-adjustment differences between predicted sialic acid content values and measured values at a previous time,/>For time/>Predicted sialic acid content of/()For time/>Sialic acid content measurement,/>Is a weight coefficient of the importance of the difference between the reference predicted value and the current measured value in the differential detection, and is determined by carrying out statistical analysis on the difference between the predicted value and the current measured value of sialic acid content in the historical data set,/>Is an offset term in differential detection, and is determined by optimizing a model to minimize the overall error between the predicted value and the current measured value;
The dynamic time warping algorithm follows the modified formula IV:
Performing time sequence analysis based on the deviation sequence, optimizing a matching process, and identifying the fluctuation of the matching process to obtain a fluctuation detection result;
Wherein, Representation sequence/>And/>The minimum accumulated distance after weight adjustment and bias term correction is carried out between the two components,/>And/>Respectively represent the predicted value sequence and the current measured value sequence of sialic acid content after differential detection,/>And/>Sequences/>, respectivelyAnd/>Element at time/>，/>And/>Sequences/>, respectivelyAnd/>The weight coefficient of the element in the formula (I) is obtained by analyzing the sequence/>And/>Sensitivity of variation of data and contribution degree determination of final prediction result at each time point,/>Is a bias term in DTW computation, determined by evaluating the average match error of time series pairings,/>Is the length of the sequence;
The trend change identification submodule distinguishes the continuous trend and the temporary trend of the sialic acid content of the bird's nest based on the fluctuation detection result, and the trend change identification result is obtained through analysis of the growth rate, the decline rate and the stability;
The trend analysis result integration submodule is used for sorting and summarizing all the identified trend changes based on the trend change identification result, analyzing the overall change trend of the sialic acid content of the bird's nest, and generating a change trend analysis result by identifying key change points and stable periods;
The time matching optimization module adjusts time marks in the data sequence based on the change trend analysis result to obtain a sequence time adjustment result;
The time matching optimization module comprises:
The time correction processing submodule is used for checking the consistency and accuracy of the data time stamp based on the change trend analysis result, correcting the time deviation in the data collection process and generating a time correction record;
The time mark adjustment submodule re-marks a time point in the data sequence by using the time correction record, adjusts the current time sequence of the time mark reflecting sialic acid content change, eliminates data dislocation caused by time mark errors and acquires a time mark adjustment table;
The data alignment perfecting sub-module reorders and aligns all data points according to the time mark adjustment table to generate a sequence time adjustment result;
The detection strategy adjustment module adjusts detection parameters according to characteristics of the bird's nest sample and environmental changes by using the sequence time adjustment result, and establishes a detection parameter adjustment scheme;
The abnormal point detection module applies the detection parameter adjustment scheme to mark sialic acid content data deviating from a normal range to obtain an abnormal cause analysis result;
the early warning feedback module sends an early warning signal according to the analysis result of the abnormal cause, implements adjustment or re-detection measures and builds an early warning response record;
And the quality grade evaluation module integrates the sequence time adjustment result, the detection parameter adjustment scheme and the early warning response record, evaluates and grades the quality of the bird's nest sample, and generates a bird's nest quality grade list.
2. The automated bird's nest detection and grading system according to claim 1, wherein the predicted value and volatility index includes an expected range of sialic acid concentration, and predicted highest and lowest values, the trend analysis result includes a growth rate, a decrease rate, and a stability analysis of sialic acid content, the sequence time adjustment result includes an adjusted data collection time point and a time difference reduction index between sequences, the detection parameter adjustment scheme includes an adjusted sampling frequency, a detection sensitivity, and a detection threshold value matching environmental changes, the anomaly cause analysis result includes a timestamp of anomaly data, an anomaly level, and a cause analysis, the early warning response record includes conditions of early warning issue time, response measure content, and early warning release, and the bird's nest quality level list includes sialic acid content level of each sample, a corresponding quality evaluation, and a recommended usage range.
3. The automated bird's nest detection and classification system of claim 1, wherein the detection policy adjustment module comprises:
The environmental adaptability analysis submodule analyzes the association of the environmental parameters and sialic acid content based on the sequence time adjustment result, identifies key environmental variables and generates an environmental factor influence analysis result;
The detection parameter optimization submodule utilizes the environmental factors to influence analysis results, adjusts the sensitivity or sampling frequency of the detection instrument to obtain various parameter settings, and matches various environmental conditions and sample characteristics to obtain adjusted parameter configuration;
and the adaptability test condition sub-module establishes test conditions matching with various environments and sample characteristics according to the adjusted parameter configuration, performs condition validity verification and constructs a detection parameter adjustment scheme.
4. The automated bird's nest detection and classification system of claim 1, wherein the outlier detection module comprises:
The abnormal data mining sub-module analyzes sialic acid content data based on the detection parameter adjustment scheme, identifies data points deviating from a normal range, refers to variation coefficients and average deviations, identifies potential anomalies and generates an abnormal data list;
The abnormal point marking sub-module marks abnormal points at corresponding positions in the data sequence by using the abnormal data list, marks the abnormal points as abnormal data to be analyzed again and obtains an abnormal point marking index;
And the abnormal reason analysis submodule analyzes the marked abnormal points according to the abnormal point marking indexes, analyzes the abnormal reasons including various factors of environmental change or detection errors, and obtains an abnormal reason analysis result.
5. The automated bird's nest detection and classification system of claim 1, wherein the early warning feedback module comprises:
the early warning triggering and notifying submodule sends early warning signals of abnormal data to detection personnel and administrators based on the abnormal cause analysis result to generate early warning notification records;
The adjustment measure recommending submodule makes targeted adjustment measures and recheck plans according to the identified abnormal reasons and generates an implementation adjustment scheme according to the early warning notification record;
And the early warning processing record submodule records the early warning response adopted according to the implementation adjustment scheme, wherein the early warning response comprises adjustment of operation parameters or redetection of various measures, processing procedures and results, and an early warning response record is constructed.
6. The automated bird's nest detection and grading system according to claim 1, wherein the quality rating module comprises:
The data comprehensive analysis submodule comprehensively refers to the sequence time adjustment result, the detection parameter adjustment scheme and the early warning response record, analyzes overall data trend and abnormal condition of sialic acid content of the bird's nest sample, performs quality analysis operation and generates a comprehensive analysis result;
The quality judgment flow submodule applies a quality evaluation standard according to the comprehensive analysis result to carry out quality judgment on sialic acid content of the bird's nest sample, and distinguishes quality grades to obtain a quality judgment result;
and the quality grade table generating sub-module sorts and files sialic acid content quality grade of each sample, corresponding quality evaluation and recommended use range according to the quality judging result, and builds a bird's nest quality grade list.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410394390.9A CN117969774B (en) | 2024-04-02 | 2024-04-02 | Automatic change bird's nest and detect and grading system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410394390.9A CN117969774B (en) | 2024-04-02 | 2024-04-02 | Automatic change bird's nest and detect and grading system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117969774A CN117969774A (en) | 2024-05-03 |
| CN117969774B true CN117969774B (en) | 2024-06-11 |
Family
ID=90866140
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410394390.9A Active CN117969774B (en) | 2024-04-02 | 2024-04-02 | Automatic change bird's nest and detect and grading system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117969774B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104271125A (en) * | 2012-01-18 | 2015-01-07 | 奥特吉尼克斯制药公司 | Method and formulation for treating sialic acid deficiencies |
| CN115046828A (en) * | 2022-06-21 | 2022-09-13 | 厦门市燕之屋丝浓食品有限公司 | Preparation method of cubilose standard substance for detection |
| CN116202988A (en) * | 2023-02-21 | 2023-06-02 | 厦门市燕之屋丝浓食品有限公司 | Method for constructing detection model and nondestructive detection of main component of dry bird's nest based on near infrared spectrum technology |
| CN117557299A (en) * | 2024-01-11 | 2024-02-13 | 天津慧聪科技有限公司 | Marketing planning method and system based on computer assistance |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210333288A1 (en) * | 2016-08-17 | 2021-10-28 | Momenta Pharmaceuticals, Inc. | Glycan oxonium ion profiling of glycosylated proteins |
-
2024
- 2024-04-02 CN CN202410394390.9A patent/CN117969774B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104271125A (en) * | 2012-01-18 | 2015-01-07 | 奥特吉尼克斯制药公司 | Method and formulation for treating sialic acid deficiencies |
| CN115046828A (en) * | 2022-06-21 | 2022-09-13 | 厦门市燕之屋丝浓食品有限公司 | Preparation method of cubilose standard substance for detection |
| CN116202988A (en) * | 2023-02-21 | 2023-06-02 | 厦门市燕之屋丝浓食品有限公司 | Method for constructing detection model and nondestructive detection of main component of dry bird's nest based on near infrared spectrum technology |
| CN117557299A (en) * | 2024-01-11 | 2024-02-13 | 天津慧聪科技有限公司 | Marketing planning method and system based on computer assistance |
Non-Patent Citations (5)
| Title |
|---|
| A comprehensive review of edible bird’s nest;Yuwei Dai et al.;Food Research International;20201103;全文 * |
| 东南亚食用燕窝研究现状;邵建宏;丁琦;王珊;赵福振;罗宝正;廖秀云;;食品安全质量检测学报;20180315(第05期);全文 * |
| 促红细胞生成素和人生长激素兴奋剂检测方法的研究进展;郭磊;张朝阳;唐吉军;谢剑炜;;色谱;20080730(第04期);全文 * |
| 基于健康指数相似的航空发动机剩余寿命预测;曹惠玲;梁佳旺;崔科璐;;科学技术与工程;20200108(第01期);全文 * |
| 微波辅助酶法提取燕窝唾液酸及其益智功能性的研究;范群艳;陈昕露;连建梅;陈玲;张怡;;热带农业科学;20151115(第11期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117969774A (en) | 2024-05-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107862338B (en) | Marine environment monitoring data quality management method and system based on double inspection method | |
| JP4911055B2 (en) | Batch process data analysis apparatus and abnormality detection / quality estimation apparatus using the same | |
| WO1999027466A2 (en) | System and method for intelligent quality control of a process | |
| CN108956111B (en) | Abnormal state detection method and detection system for mechanical part | |
| CN116985183B (en) | Quality monitoring and management method and system for near infrared spectrum analyzer | |
| CN114019139B (en) | Method for detecting heavy metal abnormal data of agricultural land soil | |
| CN113424119A (en) | Work efficiency evaluation method, work efficiency evaluation device, and program | |
| CN117969774B (en) | Automatic change bird's nest and detect and grading system | |
| CN116612820A (en) | Dairy product production intelligent management platform based on data analysis | |
| US11775512B2 (en) | Data analysis apparatus, method and system | |
| CN113984708B (en) | Maintenance method and device for chemical index detection model | |
| CN110956340A (en) | Engineering test detection data management early warning decision method | |
| CN114764550A (en) | Operation method and operation device of failure detection and classification model | |
| CN117556274B (en) | Temperature data anomaly analysis method for heat pipe backboard | |
| CN116759014B (en) | Random forest-based gas type and concentration prediction method, system and device | |
| US20230057972A1 (en) | System and method for classifying sensor readings | |
| CN117273553B (en) | Production anomaly monitoring system based on syrup concentration detection | |
| CN116559210B (en) | Mineral product phase detection method and system | |
| CN117607019B (en) | Intelligent detection method and detection system for electric power fitting surface | |
| CN117420811B (en) | Production line quality monitoring method and system for automatic production | |
| CN117556362B (en) | Measurement data abnormity supervision system and method based on data analysis | |
| CN117149584A (en) | Operation supervision system of multi-sample gauge length marking equipment based on big data | |
| Spieß | Atypical spectra screening: applications for monitoring infrared instruments and model predictions | |
| CN105259135A (en) | Near-infrared measurement method applicable to real-time on-line measuring-point-free temperature compensation | |
| TW202411648A (en) | A system for diagnosing system problems |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |