1937 results about "Small sample" patented technology

An apparatus and method are disclosed for monitoring and / or detecting concentrations of a chemical precursor in a reaction chamber. The apparatus and method have an advantage of operating in a high temperature environment. An optical emissions spectrometer (OES) is coupled to a gas source, such as a solid source vessel, in order to monitor or detect an output of the chemical precursor to the reaction chamber. Alternatively, a small sample of precursor can be periodically monitored flowing into the OES and into a vacuum pump, thus bypassing the reaction chamber.

This invention provides a device for determining the concentration of an analyte like glucose, cholesterol, free fatty acids, triglycerides, proteins, ketones, phenylalanine or enzymes, in a physiological or aqueous fluid like blood, serum, plasma, saliva, urine, interstitial and / or intra-cellular fluid, the device having an integrated calibration and quality control system suitable for dry reagent test strips with a very small sample volume of about 0.5 μL based on to a new sample distribution system. The production of the inventive analyte test element involves only a small number of uncomplicated production steps enabling an inexpensive production of the strips.

Method and apparatus of spectroscopy or the like on extremely small samples in which a drop is held between two opposing surfaces by surface tension and one surface is controllably toward and away from the other. To provide and transmit exciting energy through the drop for measurement, optical fibers go through a surface and finish flush with the surface. One of the surfaces can be swung clear of the other for easy cleaning between tests. Means for determining wetted surface are provided.

A method of separating components having a given negative or positive charge and contained in a sample is disclosed. The method involves, in one embodiment, loading a microchannel with a sample, placed between a trailing-edge electrolyte having a selected concentration of a titratable species, and a leading-edge electrolyte. With the application of a voltage potential across the microchannel, charged components in the sample stack by isotachophoresis, and electrolytic hydroxyl or hydrogen ions formed by electrolysis at the upstream-end electrode migrate into the trailing-edge ion buffer, titrating the titratable species therein, where the concentration of the titratable species in the trailing-edge electrolyte is selected , in relation to the lengths of the upstream channel region and sample-loading volume, to permit the sample to stack into a relatively small sample volume before electrolytic-ion migration from the upstream electrode into and through the sample-volume region is effective to overtake the charge sample components. With continued application of an electric potential across the channel ends, charged sample components in the stacked sample volume separated by zone electrophoresis.

The present invention provides a sample tank having a window for introduction of electromagnetic energy into the sample tank for analyzing a formation fluid sample down hole or at the surface without disturbing the sample. Near infrared, mid infrared and visible light analysis is performed on the sample to provide a downhole in situ or surface on site analysis of sample properties and contamination level. The onsite analysis comprises determination of gas oil ratio, API gravity and various other parameters which can be estimated by a trained neural network or chemometric equation. A flexural mechanical resonator is also provided to measure fluid density and viscosity from which additional parameters can be estimated by a trained neural network or chemometric equation. The sample tank is pressurized to obviate adverse pressure drop or other effects of diverting a small sample.

The invention relates to the field of computer vision recognition and transfer learning, and provides a small sample and zero sample image classification method based on metric learning and meta-learning, which comprises the following steps of: constructing a training data set and a target task data set; selecting a support set and a test set from the training data set; respectively inputting samples of the test set and the support set into a feature extraction network to obtain feature vectors; sequentially inputting the feature vectors of the test set and the support set into a feature attention module and a distance measurement module, calculating the category similarity of the test set sample and the support set sample, and updating the parameters of each module by utilizing a loss function; repeating the above steps until the parameters of the networks of the modules converge, and completing the training of the modules; and enabling the to-be-tested picture and the training picture in the target task data set to sequentially pass through a feature extraction network, a feature attention module and a distance measurement module, and outputting a category label with the highestcategory similarity with the test set to obtain a classification result of the to-be-tested picture.

When utilized in a flow imaging instrument, calibration beads provide a known data source that can be employed in various self-diagnostic, calibration and quality metric applications for the both the optical system of the flow imaging instrument, as well as the flow cell of the flow imaging instrument. Such data can be used to determine point spread functions associated with an imaging system, to determine a sensitivity of an imaging system, and to determine a focal point of the imaging system. Imagery collected from calibration beads can be used to determine core size and stability and TDI / flow speed synchronization. Calibration beads can be beneficially employed to enable stable system operation, even when very low sample concentration, or very small sample sizes are to be analyzed.

The present invention provides an electrochemical biosensor test strip used for quantitative determination of an analyte in a liquid sample. Methods of fabricating the test strip and reagent formulas are also provided. Improvements in electrochemical test strips are required to detect the presence of a compound in a liquid mixture using a smaller sample size with increased accuracy. The present invention was developed to be user-friendly, decrease sample requirements and decrease analyzing time while increasing the reproducibility and accuracy of the electrochemical test strip.

A system for treating a blood sample (700) having an analyte of interest comprises a strip (200) having a membrane (218), respective portions (216, 220 and 222, or 300) which are provided for receiving the sample, for lysing cells of the sample to liberate hemoglobin, and for capturing glycated hemoglobin. The latter two portions (220 and 222, or 300) of the membrane are treated with lysing and capture agents, respectively. A portion of the strip (214 or 230 or 240) is provided for holding an eluting agent and for releasing the agent upon a release condition. A system for detecting analyte comprises an optical subsystem (550) that is aligned with the strip to provide a signal corresponding to an amount of analyte, and an electronic subsystem (650) for processing the signal (560) to provide a result, such as an amount or percentage of glycated hemoglobin. To use these systems, the user simply applies a small sample (700) to the membrane (218) and closes a door (10) of the detection system over the strip (200) such that the door triggers the release of the eluting agent. No sample pre-treatment is required. The preferably handheld system (100) is a simple and convenient monitoring tool for the user, such as a diabetic patient who must monitor blood glucose on an on-going basis. While the systems are useful in the monitoring of blood glucose, they may be used for treating a sample other than blood and detecting an analyte other than an analyte in blood.

A non-volatile memory chip having SLC blocks acting as a write cache for MLC blocks for high density storage requires constant copying or folding of SLC blocks into MLC blocks. To avoid the time-consuming toggling out and in of the pages of the entire SLC block for ECC checking by a controller chip, only a small sample is checked. An optimal read point for reading the memory cells in the sample of the SLC block is dynamically determined by trying different read points so that the data is read within an error budget. Once the optimal read point is determined, it is used to read the entire SLC block without further error checking. Then the SLC block can be copied (blind folded) to the MLC block with the confidence of being within the error budget.

The present invention generally relates to a system and method that co-locates in a small flexible, configurable system and multi-level substrate sampling, rapid analysis, bio-sample storage and delivery functions to be performed on living tissues or matter obtained from living organisms. The types of the sampling may include chemical, biochemical, biological, thermal, mechanical, electrical, magnetic and optical sampling. In general, the analysis performed at the point of sampling measures the sample taken and records its value. The bio-sample storage function encapsulates a small sample of analyte and preserves it for subsequent examination or analysis, either on the organism by the system or at a remote location by an independent analysis system. Once stored, the sample can provide a record of a biological state at the precise time of sampling. The delivery at the point of sampling can include chemical, biochemical, thermal, mechanical, electrical, magnetic and optical stimuli.

The invention discloses an attention mechanism relationship comparison network model method. An attention relationship comparison network model for small sample learning under a small amount of labeled sample data is constructed. Based on a relational network architecture, the model is divided into a feature coding part, a feature combination part and a relational coding part, the feature coding module is used for extracting image feature information, and the feature combination part is used for recombining the extracted query image feature information with the training image feature information of each group to form a new combined feature map. The relation encoding module performs nonlinear metric learning of the network; by introducing an attention mechanism and a spectrum normalizationmethod into an end-to-end deep convolutional neural network model, the model has higher classification accuracy under the condition of small sample learning, the stability of a final training result of the model is improved, and the image classification accuracy of an existing model in small sample learning is improved.

A coherent laser beam combining system wherein the output of a single master oscillator is split into a plurality of signals, the signals are electronically modulated at unique frequencies. One signal is designated a reference signal while the remaining signals are passed through phase adjusters. All signals are optically amplified, aligned and passed through a beam splitter to split off a small sample that is imaged onto a photodetector. The photodetector output is fed to a signal processor that produces phase error signals that drive the phase adjusters resulting in a high-powered optically coherent output signal.

The invention discloses an automatic fruit identification method of an apple picking robot on the basis of a support vector machine. An apple orchard colored image under natural illumination is collected, and a vector median filter is adopted to pretreat the apple colored image; after pretreatment, the image is cut with the method of combining region growing with color characteristics; the color characteristics and the geometry characteristics of the cut apple colored image are respectively extracted; apple fruits are indentified with the mode identification method of the support vector machine; and finally, the fruits are accurately positioned. The identification method of the support vector machine of the invention which integrates color characteristics and shape characteristics has higher apple fruit identification precision rate than the precision rate when only color characteristics or shape characteristics are adopted and has better identification effect; the algorithm is easy to realize, the operation time is short, and the identification performance is superior to a commonly used neural network method, so that the identification method shows advantages in small sample learning.

The present invention provides methods and apparatus that can manipulate, detect, and / or analyze single molecules, single small particles or single small samples of matter passing through a nanoscale gap within a nanofluidic channel of a detector.

The invention relates to a heterogeneous cloud wireless access network resource allocation method based on deep reinforcement learning, and belongs to the technical field of mobile communication. Themethod comprises the following steps: 1) taking queue stability as a constraint, combining congestion control, user association, subcarrier allocation and power allocation, and establishing a random optimization model for maximizing the total throughput of the network; 2) considering the complexity of the scheduling problem, the state space and the action space of the system are high-dimensional,and the DRL algorithm uses a neural network as a nonlinear approximation function to efficiently solve the problem of dimensionality disasters; and 3) aiming at the complexity and the dynamic variability of the wireless network environment, introducing a transfer learning algorithm, and utilizing the small sample learning characteristics of transfer learning to enable the DRL algorithm to obtain an optimal resource allocation strategy under the condition of a small number of samples. According to the method, the total throughput of the whole network can be maximized, and meanwhile, the requirement of service queue stability is met. And the method has a very high application value in a mobile communication system.

A method and apparatus for tuning and matching extremely small sample coils with very low inductance for use in magnetic resonance experiments conducted at low frequencies. A circuit is disclosed that is appropriate for performing measurements in fields where magnetic resonance is beneficially utilized. The circuit has a microcoil, an adjustable tuning capacitance, and added inductance in the form of a tuning inductor. The microcoil is an electrical coil having an inductance of about 25 nanohenries (nH) or less. Because additional inductance is purposefully added, the capacitance required for resonance and apparatus function is proportionally and helpfully reduced. The apparatus and method permit the resonant circuit and the magnet to be made extremely small, which is crucial for new applications in portable magnetic resonance imaging, for example.

The invention discloses a radar one-dimensional range profile target recognition method based on a depth convolution neural network, includes the following steps: a data set is collected, the collected data is preprocessed, features are extracted from the preprocessed data, the HRRP signal is divided into two parts: low SNR and high SNR, A feature enhancement algorithm based on robust Boltzmann isconstructed, and a HRRP target recognition model based on convolution neural network and bidirectional loop neural network based on LSTM is constructed. The parameters of the network model are fine-tuned by using gradient descent algorithm, and an effective target recognition model is obtained. A radar HRRP automatic target recognition technology with small sample robustness and noise robustnessconstructed by the invention has strong engineering practicability, and a radar one-dimensional range profile target recognition model based on a convolution neural network and a cyclic neural networkis proposed from the aspects of feature extraction and the design of a classifier.

In many areas, recent developments have generated very large datasets from which it is desired to extract meaningful relationships between the dataset elements. However, to date, the finding of such relationships using prior art methods has proved extremely difficult especially in the biomedical arts. Methods for local causal learning and Markov blanket discovery are important recent developments in pattern recognition and applied statistics, primarily because they offer a principled solution to the variable / feature selection problem and give insight about local causal structure. The present invention provides a generative method for learning local causal structure around target variables of interest in the form of direct causes / effects and Markov blankets applicable to very large datasets and relatively small samples. The method is readily applicable to real-world data, and the selected feature sets can be used for causal discovery and classification. The generative method GLL-PC can be instantiated in many ways, giving rise to novel method variants. In general, the inventive method transforms a dataset with many variables into either a minimal reduced dataset where all variables are needed for optimal prediction of the response variable or a dataset where all variables are direct causes and direct effects of the response variable. The power of the invention and significant advantages over the prior art were empirically demonstrated with datasets from a diversity of application domains (biology, medicine, economics, ecology, digit recognition, text categorization, and computational biology) and data generated by Bayesian networks.

The invention provides a small-sample face recognition method which relates to a method for face recognition by means of electronic equipment. According to the face recognition method, a single-layer multi-scale convolutional neural network structure is used for performing multi-characteristic fusion and classification. The method comprises the steps of preprocessing a face image; extracting a multi-characteristic graph of the face image; extracting a DWT low-frequency subband graph, an Sobel edge characteristic graph and an LBP pattern characteristic graph; performing multi-characteristic fusion by means of the single-layer multi-scale convolutional neural network structure; and predicating a classification result by means of a Softmax classifier, thereby realizing face recognition. The small-sample face recognition method overcomes a defect of low classification recognition rate caused by a classification method in settling a small-sample face recognition problem.

The invention provides a multi-direction ship target detection and identification method in a high-resolution remote sensing image. The method is characterized by designing and realizing a multi-direction ship target detection and identification network structure under a complex scene and in a large-scale environment; automatically exploring shallow-layer and deep-layer multidimensional features and the like of a ship target based on a convolutional neural network; and realizing quick and accurate detection and recognition of multi-directional, and different scales and kinds of ship targets inthe high-resolution remote sensing image under a small sample environment. Compared with a conventional target detection method, the method is faster in detection speed and more accurate in detectionresult.

The invention discloses a hyperspectral image classification method based on fusion of multi-scale and multi-dimensional spatial spectral characteristics. The method comprises the following steps: (1)inputting a hyperspectral image; (2) preprocessing the hyperspectral images to be classified; (3) tracking neighborhood blocks; (4) generating a training set and a test set; (5) constructing a multi-scale spatial spectrum feature and multi-dimensional feature fusion network; (6) training a multi-scale spatial spectrum feature and multi-dimensional feature fusion network; and (7) classifying the test samples. The method provided by the invention can effectively solve the problems of too single feature and too single scale of the convolutional neural network during training, can solve the problem of low average classification precision AA during hyperspectral classification, can maintain the recognition capability of small sample number categories while realizing high classification precision, and is good in classification performance.

The invention discloses a method for evaluating voltage dip sensitivity of sensitive equipment, belonging to the field of electric measurement. A voltage dip frequency of a power grid in a time section and depth and duration time of each voltage dip are monitored at a measurement point so as to establish a small sample set of practical voltage dips of the power grid in the time section, and a final evaluation result depends on equipment fault rate caused by measuring the voltage dip each time, so that influence degree of running conditions of the power grid in the time section on the sensitive equipment is really reflected, and influence of the voltage dips caused by various short-circuit faults in the power grids with different structures on the sensitive equipment can be reflected, so that related departments is guided to take more reasonable control measures or providing a basis for calculating economic loss caused by the voltage dips. Therefore, the method can be widely applied to the field of power supply quality control and management of the power grid.

The invention discloses a Chinese financial news text classification method based on a convolutional neural network. The method is mainly divided into four parts including word vector training, text preprocessing, neural network model training and news classification. Large-scale financial news corpora are used for training to obtain a broadly common financial-category word vector model through anunsupervised learning method, the word vector is effectively imported into the training of the convolutional neural network, and the statistical information of the model is increased through a methodof dynamically regulating the word vector. The adopted convolutional neural network has a simple structure, and can show excellent performances by aiming at a small sample set, so that a Chinese financial news text classification problem can be effectively solved, and effectiveness of the convolutional neural network in processing a text classification problem can be fully proved.

The invention discloses a life prediction method of accelerated life test based on grey RBF neural network. An original curve of reliability and failure time is constructed by collecting test data; class ratio test is conducted on failure time data; a curve of reliability and accumulated failure time is constructed; three layers of RBF artificial neural network are established; RBF artificial neural network is trained; the well-trained neural network is used for prediction; and finally the prediction value of the dummy accumulated failure time obtained by prediction is reduced so as to obtain the life information of the products under normal stress. The method has no need of establishing physical accelerator model and resolving complex multivariate likelihood equation set, thereby avoiding the introduction of system error in the life prediction, solving the problem of needing a large number of training samples for artificial neural network modeling in accelerated life test, also being applied to small sample test data, and facilitating the application in actual engineering. Compared with the existing BP neural network prediction method, the life prediction precision is obviously improved.

Method and apparatus of spectroscopy or the like on extremely small samples in which a drop is held between two opposing surfaces by surface tension and one surface is controllably toward and away from the other. To provide and transmit exciting energy through the drop for measurement, optical fibers go through a surface and finish flush with the surface. One of the surfaces can be swung clear of the other for easy cleaning between tests. Means for determining wetted surface are provided.

Device and technique using same for abrading a small sample of epidermis for bio-analytical processing and method of using same. The device removes small samples of epidermal tissue with efficiency, minimal discomfort, and no excess tissue removal. The device and method may be provided as part of a home-use kit for individualized analysis.

The invention relates to an iterative incremental dialogue intention category identification method based on small samples. The method is based on a small sample data set. Training starts from a preliminary classification model, and along with the use of a model, the number of the preliminary models is continuously increased. Model accuracy is also gradually improved, and a training mode that a large number of samples are needed by a previous deep learning model is abandoned. According to the method, in the iterative training process, only a small number of samples are needed to train a new preliminary classification model each time. The weights of other existing historical preliminary classification models are not changed. Results of all the preliminary classification models are input into the secondary classification model for training, the calculation speed of the model cannot decrease along with increase of the number of samples, the similarity screening model can screen and removethe existing preliminary classification model, the performance is maintained under the condition that the accuracy is guaranteed. Compared with the prior art, the method is advantaged in that the number of training samples is small, the calculation performance is stable, and the model is easy to update and expand.