114 results about "Species identification" patented technology

Methods and systems for species identification are disclosed. The methods and systems include: obtaining first, second, and third trained artificial intelligence (AI) models; obtaining one or more runtime images including a subject; determining a first confidence level of a morphological group of the subject based on the first AI model; determining a second confidence level of a species of the subject based on the morphological group and the second AI model; in response to the second confidence level being lower than a predetermined confidence level; performing a genomic test for the subject based on the determined morphological group or the determined species of the subject; and identifying the species of the subject based on a test result of the genomic test based on the third AI model. Other aspects, embodiments, and features are also claimed and described.

The application discloses a biological individual species identification method based on a deep neural network, and relates to the technical field of zoology image recognition. Different direction image data of biological individual skull samples are collected as a data set, and the data set is divided into a "test set" and a "training set" according to a ratio of 8:2 based on a non-segmentation individual picture benchmark (the pictures of the same individual only exist in the same data set). Meanwhile, the training set images are subjected to data enhancement by using methods including but not limited to rotation, mirroring, changing brightness, blurring, random deletion and the like; the weight and value of the sample angle image data in a specific task are obtained through a corresponding algorithm, and the species identification result of the individual sample is obtained through a data fusion method.

This invention discloses a method, device, and storage medium for bird species identification based on bird calls. The method includes: (1) acquiring several segments of bird calls and preprocessing them; (2) filtering the power spectrum of the bird calls using two different filter banks, extracting the coefficients of the filtered signals, and then combining the two sets of coefficients, the short-time energy of the bird calls, and the short-time zero-crossing rate of the bird calls to form the feature vector of the current bird calls; (3) constructing a nonlinear classification model and using a prey optimization method to find the optimal kernel function in the nonlinear classification model; (4) inputting the extracted bird call feature vector into the nonlinear classification model for learning; and (5) extracting the feature vector of the bird call to be identified and inputting the feature vector into the learned nonlinear classification model to identify the bird species. This invention has low complexity and high accuracy.

The application discloses a kind of based on electronic nose's insect tea species identification method, belong to insect tea aroma detection technical field.The method includes: selecting training set and test set insect tea sample;Through the optimal parameter of single factor test screening carries out sample pretreatment and electronic nose detection, obtains sensor response characteristic value;Application principal component analysis (PCA) constructs category distribution model, obtains PCA distinction diagram;Application discriminant function analysis (DFA) constructs category discriminant model;Test set sample characteristic value is projected into PCA distinction diagram, and it is input DFA model to obtain discriminant result, and carries out visual verification.The method of the application is simple in operation, result is objective and reliable, can realize the accurate identification of different plant raw materials insect tea, and the overall accuracy reaches 91.84% by 49 unknown samples verification.

The invention discloses an algae species identification method and system based on a BEiT-CSA algorithm, and belongs to the technical field of computer vision. The method comprises the following steps: firstly, performing differential randomization adaptive enhancement on a microscopic image according to the form type of an algae body, calculating the comprehensive fidelity based on SSIM and normalized MSE, and only retaining samples with scores not lower than 0.7; the effective samples are input into a classification model with BEiT as a backbone, encoders of the fourth layer, the eighth layer and the twelfth layer are embedded into a cross-scale attention module, and hierarchical collaborative modeling of local details and global semantics is achieved through multi-scale feature generation, cross-scale cross attention calculation and a double fusion strategy. According to the method, the accuracy of 94.10% on a 214-type algae species data set is achieved, the capacity of distinguishing algae species with similar forms is remarkably improved, and meanwhile it is guaranteed that the biological authenticity of samples and the model robustness are enhanced.

The invention discloses a portable meat doping identification chip and a detection method, and the method comprises the following steps: placing a meat sample slice on a sample bearing layer of the chip, starting the chip to collect a terahertz time-domain spectral signal, and calculating optical parameters of a meat sample in a frequency band of 0.2-2.0 THz; performing principal component analysis on the high-dimensional data of the optical parameters in the whole frequency band to obtain feature vectors; and inputting the feature vector into a pre-trained artificial intelligence model, respectively performing qualitative identification of meat species and quantitative prediction of the doping content, and outputting an analysis report containing a species identification result and a doping ratio.

The invention relates to a specific real-time fluorescent PCR (polymerase chain reaction) amplification primer, a probe and a detection method for identifying lutjanus purpureus, and belongs to the technical field of molecular detection and species identification. According to the invention, the specific primer and the probe for lutjanus purpuratus are designed, and the real-time fluorescent PCR technology is combined, so that the lutjanus purpuratus can be quickly and accurately identified. The method has the advantages of high specificity, high sensitivity, simplicity and convenience in operation and the like, and a reliable molecular biological method is provided for species identification of lutjanus purpurea.

The invention discloses a DNA language model optimization method and system based on unsupervised noise contrast learning, and relates to the technical field of species identification by using DNA barcodes. The embedded vectors from the same sequence are used as positive samples, and the embedded vectors from different sequences are used as negative samples; in order to increase sample diversity, global and local feature noise layers are introduced, and positive sample embedded vectors are disturbed. And inputting the enhanced embedded vectors into an encoder, and mapping similar enhanced vectors to similar embedding spaces by integrating information and capturing really important modes in a sequence. By mixing positive and negative samples of an anchor point sample, a difficult negative sample with the characteristics of the two samples is constructed, so that the training difficulty is continuously increased, and the discrimination capability of the model is enhanced; the model is optimized by using an unsupervised comparative learning loss function with positive sample similarity penalty, so that the embedding space distribution of the model is effectively enhanced, and the accuracy of the model in DNA bar code species level classification is remarkably improved.

The present application relates to the technical field of biological fermentation detection, and discloses a kind of biological fermentation product kind identification method and system based on image recognition.The pixel offset of real-time image relative to background reference image is extracted to generate the first characteristic vector field;Response liquid level fluctuation obtains the time sequence image sequence of inner wall in preset boundary area, and the residual coverage rate decay rate constant is extracted to generate the first characteristic index;Based on real-time image gray information entropy, generate environment sampling operator.Three nonlinear weighted coupling generates species identification comprehensive index, realizes the dynamic weight inhibition of airspace scattering interference and the synchronous quantification of interface adhesion dynamics characteristics, guarantees the stability of species identification conclusion under complex fermentation conditions.

The invention relates to the technical field of plant ecological monitoring and computer vision, and discloses a grassland dominant species identification method based on unmanned aerial vehicle remote sensing and deep learning, and the method comprises the steps: carrying out the fusion processing of a to-be-identified unmanned aerial vehicle remote sensing image of a target grassland region, and obtaining a to-be-identified fusion image; inputting the fusion image to be identified into a trained species identification model to obtain a species classification result of the target grassland area; combining the species classification result with the space coordinates of the target grassland area to generate a species distribution diagram of the target grassland area; according to the method, the problem of insufficient species identification precision in a complex grassland environment can be solved, manual investigation cost and subjective deviation are reduced, grassland dominant species identification accuracy and spatial analysis capability are improved, and refined data support is provided for grassland ecological protection.

The utility model discloses a hold-down mechanism for identifying and screening down types, which comprises a frame, a bottom plate, a covering film, a reel and a compression roller, the bottom plate is horizontally and slidably connected with the frame, the reel is arranged on the frame through a winder, the covering film is wound on the reel and connected with the bottom plate, and the compression roller is rotatably arranged on the frame and compresses the covering film on the bottom plate; the down feather is placed between the bottom plate and the covering film. According to the down feather pressing device, the bottom plate and the covering film are matched, the covering film is automatically wound through the winding shaft, the bottom plate is pushed, meanwhile, the covering film covers the bottom plate through the pressing roller, through the structure, in the down feather pressing process, disturbance to down feather is greatly reduced, and it is guaranteed that the down feather is unfolded on the bottom plate and fixed through the covering film. And through the locking assembly, after the bottom plate moves in place, automatic locking is achieved, and operation is convenient.

The invention discloses a primer probe composition and a kit for group A streptococcus species identification and M1UK and M1global subtype typing and application of the primer probe composition and the kit. According to the primer probe composition, quadruple target amplification primers and probes are designed, so that specific amplification can be achieved in a single tube, and cross interference is avoided; the primer probe group forms a species-type-double SNP subtype three-stage detection system and is used for preparing detection kits for GAS species identification, em1 type confirmation, M1UK / M1global subtype typing and the like, interference of other em1 derived sublines is eliminated according to the double SNP co-occurrence requirement, and the M1UK typing accuracy is remarkably improved. The kit has the advantages of high specificity, high throughput, simplicity and convenience in operation and low cost, and is suitable for clinical diagnosis, high-virulence clone screening and public health emergency monitoring.

The invention relates to the technical field of ecological monitoring, in particular to a wild animal community state monitoring method and system based on an unmanned aerial vehicle, and the method comprises the steps: firstly controlling a visible light camera, a thermal imaging camera and a multispectral camera carried by the unmanned aerial vehicle to carry out hardware synchronous collection, and obtaining time-space aligned multi-modal data; preprocessing and lightweight AI preliminary identification are carried out at the unmanned aerial vehicle end; edge calculation and cross-modal fusion analysis are carried out on a ground control station to realize species identification, quantity statistics, behavior analysis and vegetation index calculation; multiple spatio-temporal data are integrated at the cloud end for deep modeling, distribution density fine calculation, behavior pattern semantic understanding and habitat suitability comprehensive evaluation are completed, and finally a comprehensive monitoring report and early warning are generated. The problems that a traditional monitoring method is single in data dimension, poor in analysis timeliness and lack of habitat association evaluation are solved, and efficient, all-weather and automatic comprehensive monitoring and evaluation of the wildlife community state are achieved.

This application relates to the field of computer vision technology, and in particular to a method for wildlife identification and tracing using infrared image enhancement and multi-scale fusion. The method includes: acquiring raw images from an infrared camera and enhancing the raw images using Retinex and contrast-limited adaptive histogram equalization; performing animal target detection, feature extraction, and feature fusion by optimizing the YOLOv8 model and using a multi-modal fusion Transformer to obtain multi-scale fused features; identifying species categories using a pre-defined primary species classification model and extracting and matching individual biometric features of key species using a pre-defined secondary individual identification model to generate individual identifiers for corresponding animals; and automatically associating the species identification results, individual identifiers, and multi-source forestry data to generate an intelligent decision-making report for wildlife population analysis and conservation management. This application contributes to achieving high-precision, automated wildlife identification and tracing.

The present invention relates to a chloroplast genome sequence-based SNP marker composition for distinguishing *Carex kobomugi* and its use. Since the SNP marker of the present invention can accurately distinguish *Carex kobomugi*, a plant of the sedge family, from similar species, it can improve the accuracy of species identification for sedge family plants that are difficult to distinguish morphologically, and can maintain a certain level of reliability as it is based on chloroplast genome information and is not affected by changes in the external environment.

The application discloses a bird chirp sound recognition method based on a combination of voiceprints and spatial distribution, and belongs to the technical field of intelligent sound classification and recognition. In view of the problems of ignoring geographical distribution prior knowledge and sample imbalance in the prior art, the application firstly constructs a voiceprint recognition model: a training data set is constructed by audio preprocessing, logarithmic mel spectrum and dynamic difference feature extraction, a model is trained based on DenseNet-121 by adopting a two-stage training strategy, and recognition confidence of each species is obtained; meanwhile, a spatial distribution model is constructed: based on public observation data, an average observer ability index is used to correct an original encounter rate, and spatial distribution probability of the species in a specific city is obtained; finally, a Sigmoid function is used to perform nonlinear fusion on the two, a joint recognition probability is calculated, and a classification result is output. The application introduces ecological spatial constraints into the recognition decision, effectively reduces false positive misjudgment, improves rare species monitoring capability, and makes the recognition result have ecological interpretability.

The invention relates to the technical field of molecular biology, and discloses a primer probe set for species identification of echinococcus granulosus, and the primer probe set comprises a first primer probe set for targeting echinococcus granulosus, a second primer probe set for targeting echinococcus multilocularis and / or a third primer probe set for targeting echinococcus stone. According to the primer probe group, synchronous, rapid and high-specificity identification and detection of three kinds of echinococcus, namely echinococcus granulosus (Eg), echinococcus multilocularis (Em) and echinococcus stone (Es), are realized. When the primer probe group is used for identifying and detecting the three kinds of echinococcus, the detection sensitivity reaches 200 copies / mL, and the positive coincidence rate reaches 100%. The primer probe group realizes synchronous and accurate identification of echinococcus species, and has a wide application prospect in molecular epidemiological investigation and port quarantine.

The application provides a microplastic species identification method based on concept constraint multi-task instance segmentation, comprising: performing instance-level labeling and concept label labeling on a microscopic image containing microplastic particles to obtain an input sample; constructing a concept constraint multi-task instance segmentation network with microplastic particle instance segmentation and polymer category identification as a main task and prediction of a concept label as a secondary task; the network processes the output result of the main task according to the output result of the secondary task to obtain a single-concept additional feature area, avoids missing detection, generates a minimum value result according to the output result of the secondary task and the output result of the main task, and further obtains a final identification result; training the network; and inputting a to-be-identified microscopic image into the trained network to obtain the final identification result. The method of the application completes microplastic particle instance segmentation and species identification under the condition of explicitly learning and utilizing the concept attributes of microplastics.

This invention discloses an intelligent identification system for benthic organisms. In the field of artificial intelligence technology, this system quantitatively groups benthic organisms according to their impact on water quality assessment based on the Hilsenhoff pollution tolerance system. Differentiated feature extraction priorities, counting weights, and confidence thresholds are set for different groups. After multi-module collaborative processing, the system combines the pollution tolerance values ​​to complete a standardized evaluation of water quality levels. The advantages of this invention are: it quantitatively groups benthic organisms according to their impact on water quality assessment based on the Hilsenhoff pollution tolerance system, abandoning the traditional method of indiscriminately optimizing the accuracy of all species identification. It implements targeted processing for different groups, including differentiated feature extraction priorities, differentiated counting weights, and differentiated confidence threshold verification. It focuses on core water quality indicator species to achieve key optimization of identification accuracy, directly preventing errors in species identification and counting from being transmitted to water quality evaluation results at the technological source.

The invention discloses an automatic algae identification method and system, and relates to the technical field of water environment monitoring. In the system, a multi-modal data acquisition module synchronously acquires a morphological image, characteristic spectrum data, characteristic fluorescence intensity and environmental parameter data of an algae sample through a microscope imaging unit, a spectrum detection unit, a fluorescence detection unit and an environmental parameter acquisition unit; the data preprocessing module is used for denoising, enhancing and normalizing the acquired multi-modal data; the feature extraction and fusion module extracts each modal feature through a preset network model, and performs weighted fusion by using an attention fusion algorithm; the classification and recognition module outputs an algae species recognition result based on the fusion features; and the cooperative control module coordinates the work of each module through a time sequence control signal to ensure the synchronism of data acquisition and processing.

The present application relates to the technical field of image processing, in particular to a pet body surface parasite species identification method based on multi-feature data fusion, first, through the cooperative triggering mechanism, the static image and short video stream of the pet body surface area are synchronously collected, then, three feature extraction channels are executed in parallel: the static morphological feature extraction channel based on deep learning, the dynamic behavior feature extraction channel based on motion trajectory analysis and the skin environment feature extraction channel based on semantic segmentation. Further, a two-level fusion strategy is adopted, and finally the recognition result is output through the classifier. The technical effect of the present application is that the introduction of dynamic behavior characteristics solves the misjudgment problem caused by angle and posture of static image; the combination of skin environment characteristics enhances the diagnosis ability for early or atypical infection, thereby realizing more accurate and reliable automatic parasite species identification.

This invention relates to the field of intelligent mosquito identification technology and discloses a mosquito identification and monitoring method based on convolutional neural networks. This method analyzes the statistical properties of feature maps at each level of the model and calculates feature stability scores to select robust levels. Primary and secondary features are extracted from the selected levels. First, highly correlated features are selected based on the correlation between primary features and species labels. These are then combined with secondary features, and redundancy is eliminated to obtain an optimized feature set. The model structure parameters are reorganized based on this set, and the final mosquito identification model is obtained through training. This method improves the model's feature discrimination ability and generalization performance by dynamically evaluating and optimizing internal feature representations, thereby enhancing the accuracy and robustness of mosquito species identification.

The invention discloses a design method and application of a universal primer for bird identification based on machine learning optimization, the method is based on a DNA bar code technology, and the method judges conservative bases through multiple comparison in combination with Shannon entropy, so that the accuracy of obtaining conservative sequences is improved; establishing a multi-dimensional primer scoring system covering a coverage degree, a Tm value, an interaction degree, a degenerate base number and a poly structure; training a random forest machine learning model by using known primer sequences and score data, and optimizing model parameters through grid search and cross validation; and finally, quickly evaluating and screening a large number of candidate primers by using the trained model to obtain a high-performance primer combination. Traditional manual screening is replaced with a machine learning algorithm, the primer design efficiency and screening precision are remarkably improved, the designed universal primer is wide in coverage, high in specificity and high in amplification stability and can be widely applied to bird species identification, and reliable technical support is provided for ecological monitoring, species protection and law enforcement detection.

The application discloses an insect radar body size parameter inversion method based on minimum polarization RCS. Firstly, the relationship between a polarization pattern shape and a scattering matrix eigenvalue is derived based on a symmetrical insect model, and on the basis, an analytic expression of minimum polarization RCS is derived, and finally, the relationship between the minimum polarization RCS and insect body length and weight is analyzed, and an empirical formula for inversing the insect body length and weight based on the minimum polarization RCS is given. The application provides an insect radar target body size parameter inversion method with good polarization error resistance and high precision, which is helpful to realize accurate species identification of migratory pests and improve the management ability of the migratory pests.

The invention belongs to the technical field of biological detection, and relates to a primer group, a kit and a method for identifying fungi based on RAA method targeted sequencing. The primer group comprises six primers of which the nucleotide sequences are shown as SEQ ID NO.1-6. The invention further discloses a kit for detecting the target gene. By utilizing the primer group, the kit and the method for identifying the fungi based on the RAA method targeted sequencing, the species identification of the fungi can be carried out after sequencing based on the amplification and capture of the SSU-ITS1-5. 8S-ITS2-LSU transcriptional unit of the rDNA of the fungi, so that the species identification resolution is improved.

The invention discloses a ganoderma species specific target sequence based on artificial intelligence screening, a primer pair, a kit, applications thereof and a species identification method. The target sequence is obtained by learning and screening sequence features through an artificial intelligence model based on disclosed genome data of ganoderma lucidum, the species specificity of the target sequence is further verified through two technical means of agarose gel electrophoresis and Sanger sequencing, the target sequence can be used for distinguishing ganoderma lucidum, ganoderma sinensis and related species thereof, and accurate judgment of a sample to be detected on the species level is achieved. The identification method constructed based on the target and primer system has the characteristics of high specificity, good sensitivity, stable result, simple and convenient detection process and the like, is suitable for identification of ganoderma lucidum sporocarp, hypha, spore powder, medicinal materials, decoction pieces and related products, and provides a basis for ensuring clinical medication safety and standardizing the ganoderma lucidum market.

This invention provides primers, a detection kit, and applications for identifying tilapia, belonging to the field of molecular biology. The invention provides primers for identifying tilapia species, enabling rapid, efficient, and accurate identification of Nile tilapia (Oreochromis niloticus), Oreochromis aureus, and Oreochromis spp., providing a scientific basis for tilapia germplasm resource conservation and species identification.

The application discloses a pangolin species identification method based on nail piece element characteristics, which comprises the following steps: step S1: collecting nail piece samples covering existing 10 kinds of pangolin species, and obtaining initial data of multi-element characteristics of the nail piece samples; step S2: identifying the species of the nail piece samples by a molecular biology method, and obtaining the species labels of each nail piece sample; step S3: constructing an "element characteristic-species label" standard data set; step S4: selecting a table prior fitting network as a core machine learning algorithm, training a model by using training set data, and constructing the model; and step S5: identifying whether a to-be-detected sample belongs to a pangolin nail piece according to morphological judgment. The method has a single sample data collection time of less than 60 seconds, does not need to damage the sample, is used for nail piece identification of samples without prior clues, and the overall accuracy of a global ten-species classification model reaches 0.93.

The invention discloses a femur species identification system and method based on a scanning electron microscope and artificial intelligence, and the system comprises a data module which is used for obtaining a data set and carrying out the data preprocessing; the model construction module is used for constructing an identification model for species identification; the recognition model carries out learning training based on a ResNet50 network and the preprocessed bone slice image data; the identification model comprises a two-category image identification model for preliminary classification and a multi-category image identification model for further subdivision, and the two models are independently trained; the species identification module is used for inputting femur image data needing to be identified into the identification model for two-stage cascade prediction after training is completed, and an identification result corresponding to each image is obtained; the method has the beneficial effects that the SEM technology is combined with the AI image recognition, so that the defects of the traditional means are overcome, and the identification efficiency is greatly improved while the identification accuracy is improved.

The invention discloses a fish body size measuring method based on computer vision, and belongs to the technical field of computer vision. The method comprises the following steps: establishing and training an image segmentation model; obtaining a fish body image by using a binocular camera and calibrating the fish body image; performing variety identification and key region segmentation on the image by using the trained model to generate a three-dimensional point cloud; denoising and coordinate transformation are carried out on the point cloud, and a fish body feature point set is extracted; and calculating phenotypic characters such as body length, body width, head length and body length. The device has the advantages of being non-contact, efficient, high in precision, high in adaptability and the like, is suitable for the fields of aquaculture, fishery resource investigation and the like, and can achieve rapid and automatic detection of the size and weight of the fish.