41results about How to "Overcome incompleteness" patented technology

The invention discloses a method for recovery treatment of a waste-and-old lithium battery electrolyte and treatment of electrolyte wastewater. Three treatment units are employed for treatment. Firstly, the waste-and-old electrolyte is treated. Then, waste gas resulting from the reaction of the electrolyte is pumped into the waste water for absorption, so that the waste gas can be removed during a waste water treatment process; the lithium battery waste water is treated by a Fenton agent through oxidation to obtain improved biodegradability of the waste water; and reaction precipitates are removed through flocculent sedimentation and the obtained water is treated through combination of A2/O and MBR membrane separation. Finally, the outlet water goes through a RO reverse osmosis unit to ensure the quality of the outlet water. Combination technology of active carbon powder adsorption and ultra-filtration is employed to remove organic pollutants of the concentrated water resulting from the RO unit, so that the water after treatment can meet the requirements of RO high-quality reuse water. According to the invention, imperfection of an existing technical method of waste-and-old lithium battery recovery and treatment is overcome, and quantitative reduction, harmlessness, and reutilization of waste water treatment of the waste-and-old electrolyte are realized.

The invention relates to the technical field of medical image processing, and aims to provide a dynamic ultrasonic breast nodule real-time segmentation and recognition method based on deep learning. The method comprises the following steps: collecting ultrasonic mammary gland images and videos with nodules and case data with operative pathology results, constructing a data set, constructing a static image nodule segmentation network, and training the static image nodule segmentation model on an original image; predicting an intermediate frame nodule probability by using an LSTM layer, constructing a video dynamic segmentation network, and training a dynamic segmentation model; constructing a benign and malignant identification network structure by using a basic network, and training a benign and malignant identification model; and outputting nodule position information in real time, using the benign and malignant recognition model for recognizing benign and malignant nodules of each frame, and outputting the number of output nodules and the comprehensive benign and malignant probability after examination is finished. Information incompleteness of a single image can be avoided, error detection is reduced, missing small nodules are reduced, and the nodule benign and malignant identification accuracy is improved.

The invention relates to a method for predicting power load and provides the power load prediction method which can better solve the problem of low accuracy. The invention provides application thereof in load prediction based on CURE algorithm. Application of the CURE algorithm in the load prediction comprises the following steps: (1) extracting data sample from a historical database of load prediction; (2) adopting hierarchical algorithm to cluster each sub-region of the data sample; and (3) clustering all the data in the sample and inputting representative points only including clusters found when all sub-regions cluster independently.

The invention discloses a method for testing road damage based on post-disaster high-resolution remote sensing image, which belongs to the technical field of road damage detection and evaluation. The method comprises the steps as follows: high-resolution remote sensing image of a damaged road is preprocessed, and spatial registration is carried out on the image data and the data in a GIS road database; then, by adopting the assistant of the information in the GIS road database, the road coverage area before the damage is extracted through analyzing the post-disaster high-resolution remote sensing image; simultaneously, the road coverage area after the damage in the high-resolution remote sensing image is extracted; and road damage information is obtained through comparing the road coverage areas before and after the damage. The method fully uses the GIS road database, realizes the object-level damage testing method by adopting the post-disaster high-resolution image only, improves the accuracy of the testing results, and reduces the level of manual intervention.

The invention relates to a method for fusing and integrating multi-source spatial data. The method specifically comprises the following steps that: a user sends a shared data request to an administrator; the administrator receives the shared data request and examines and approves whether the user is allowed to share data or not; if the examination and the approval are passed, the user organizes and uploads the data required to be shared to a server according to a complete element object and implements the step III; if the examination and the approval are not passed, the administrator returns the message which implies that the examination and the approval are not passed to the user; the administrator invokes a platform data conversion function, and an object-oriented approach is adopted in the platform data conversion to convert the data shared by the user to data adopting a GML (Geography Markup Language) format; the administrator distributes the data required by the user in the GML format according to the user demands. The method for fusing and integrating the multi-source spatial data has the benefits that the problems that element object information is incomplete when existing multi-source spatial data is subjected to format processing, and the access efficiency of the shared data in a Web service mode is low are solved.

The invention discloses a polarimetric SAR image classification method based on residual learning and a conditional GAN, and the method comprises the steps: (1), constructing a generator of the conditional GAN; (2), constructing a discriminator of the conditional GAN; (3), filtering a to-be-classified polarization SAR image; (4), performing pauli decomposition of a filtered scattering matrix; (5),normalizing a feature matrix; (6), generating a training data set and a test data set; (7), performing residual learning of deep and shallow features in the generator; (8), classifying features afterresidual learning; (9), obtaining a classification correctness rate; (10), training the generator of the conditional GAN; (11), classifying test data set. The method achieves the residual learning ofthe deep and shallow features of a polarimetric SAR image in the generator, achieves the extraction of the comprehensive feature information, achieves the good regional consistence of a classification result image, and is high in classification precision.

The invention relates to an agricultural material logistic anti-counterfeiting tracing system and method and belongs to the information service technology field. The system comprises an anti-counterfeiting label, an anti-counterfeiting reader, a server and a supplier card, wherein the anti-counterfeiting label is fixedly mounted at a sealing port of an agricultural material packaging bag, the anti-counterfeiting reader and the server realize network data transmission connection, the anti-counterfeiting reader reads the anti-counterfeiting label and the supplier card, and the supplier card is a portable information card. The system is advantaged in that the information industry and modern service industry technology is utilized, anti-counterfeiting and tracing problems of the agricultural material logistic field are solved, peasant households can be facilitated to simply and rapidly identify product authenticity, counterfeit control can be effectively carried out by enterprises, the government is facilitated to know about safe market operation conditions of agricultural materials, the agricultural material commodity information can be identified and traced, liability traceability can be realized, moreover, benefits of product manufacturers are taken as a core, logistics is taken as a main channel, real products can be guaranteed to smoothly arrive hands of consumers through various sale ways, and thereby peasant benefits are lastly guaranteed.

The invention discloses an image redirection quality evaluation method based on statistic similarity and bidirectional significance fidelity. The image redirection quality evaluation method is characterized in comprising the following steps of: 1) obtaining the natural scene statistical characteristics of the log-Gabor domains of an original image and a redirected image, and obtaining a difference value of the natural scene statistical characteristics of the log-Gabor domains of the original image and the redirected image as a natural scene difference value statistical characteristic; 2) obtaining a forward significance information missing value and a backward significance information missing value; 3) obtaining the significance structure fidelity value of the image; 4) forming redirection quality evaluation characteristics by the natural scene difference value statistical characteristic, the forward significance information missing value, the backward significance information missing value and the significance structure fidelity value; and 5) utilizing a support vector regression model to train and predict the redirection quality evaluation characteristics so as to obtain a quality evaluation model. By use of the image redirection quality evaluation method, the change of the natural scene statistical characteristics is considered, in addition, the significance fidelity of the image is measured from two directions, and the subjective visual quality of the redirected image can be more accurately predicted.

The invention discloses a spatial-semantic channel-based collaborative salient target detection method. The method comprises the steps of simulating human vision; according to a collaborative assistance rule among images, performing spatial collaboration and semantic collaboration dual-channel parallel processing on color images and image depth images in to-be-detected group images; by utilizing collaborative salient priori, obtaining two preliminary collaborative salient images; and fusing the two preliminary collaborative salient images to obtain a final collaborative salient image. The detection of a common salient target in the group images of a complex scene is realized; and the common salient target of the group images is effectively highlighted and complex background noises are suppressed, so that a relatively good detection result is obtained and the detection accuracy and recall rate are improved.

The invention discloses a game search method based on a defensive and offensive evaluation function of Einstein chess. The defensive and offensive evaluation function is used for simulating a game search in an expectation max-mini search. According to the game search method based on the defensive and offensive evaluation function of the Einstein chess, an expectation max-mini algorithm which is a variety of a max-mini algorithm is adopted, a probability layer is introduced into a process of search-down expansion, and the problem of incomplete game information caused by a dice is solved. According to the method, the designed defensive and offensive evaluation function is applied to the expectation search, the defensive and offensive expectation max-mini algorithm is designed, and the search efficiency and the game level of a system are improved.

The invention belongs to the technical field of land productivity enhancement and environment protection, and discloses a method for forming farmland ecosystem nutrient cycling integrity. The method comprises the following steps: 1) harvesting farmland crops, weighing crop grain yield; 2) detecting the nitrogen content of crop grain; 3) calculating total nitrogen amount of the crop grain; 4) detecting the nitrogen content of excrements of livestocks; 5) calculating application amount of the excrements of livestocks; 6) using the excrements of livestocks; and 7) totally crushing the crop straws for reclamation. The method forms the farmland ecosystem nutrient closed cycling, which solves the non integrity of the farmland ecosystem nutrient cycling due to man-made interference, continuous nutrient supply capability can be guaranteed for farmland soil, the law of nature can be perfected matched, cost is low, effect is high, and the method has environmental protection performance.

The present invention relates to a template-based safety case modeling method. The method comprises the following steps of performing field analysis on a safety case, and extracting concept, relation and constraint of the safety case; modeling the safety case, and establishing a safety case meta model and storing the safety case meta model into a database; establishing safety case templates according to the meta model and storing the safety case templates in the database, the safety case templates comprising a safety argument template, a system description template, a safety requirements template, a hazard analysis template and a risk management template; establishing constraint rules for the safety case templates and storing the constraint rules into the database; and calling the safety case templates from the database to write the safety case, and performing safety argument. According to the method, related personnel are directed to perform safety argument on a system and write a safety case; incompleteness generated by describing the safety case is prevented; and ambiguity caused by describing the safety case by natural language is reduced, and therefore the safety case is expressed completely and clearly.

The invention discloses an active power distribution network fault risk early warning method and system based on data mining, and belongs to the technical field of power distribution networks, and the method comprises the steps: obtaining fault features of an active power distribution network, and processing the fault features to obtain a fault data value; inputting the fault data value into a pre-established early warning model, and outputting an early warning index and a predicted value thereof; carrying out assignment on subjective weights and objective weights of the early warning indexes, and then calculating a comprehensive evaluation index value by adopting a combined algorithm of a triangular fuzzy number analytic hierarchy process and an entropy weight method; the comprehensive evaluation index value is compared with a preset risk grading standard threshold value, the obtained risk grade is an early warning result, and the relative error rate of the comprehensive evaluation index value and the early warning index prediction value is the early warning accuracy degree of the early warning model; the early warning speed is high, the early warning is more accurate, the incompleteness of a single assignment method is avoided, and the influence of coupling of various kinds of information is weakened.