3554 results about "Feature selection" patented technology

In a pre-processing step prior to training a learning machine, pre-processing includes reducing the quantity of features to be processed using feature selection methods selected from the group consisting of recursive feature elimination (RFE), minimizing the number of non-zero parameters of the system (l_o-norm minimization), evaluation of cost function to identify a subset of features that are compatible with constraints imposed by the learning set, unbalanced correlation score and transductive feature selection. The features remaining after feature selection are then used to train a learning machine for purposes of pattern classification, regression, clustering and/or novelty detection.

A system and method includes surgical instrumentation, implants, bone graft material, and measurement equipment to enable a spine fusion procedure to proceed more accurately, efficiently and safely by allowing precision measurement of the characteristics of the intervertebral space, selection of and provision of new implants, placement of an intervertebral implant, and to help overcome bone resorption all where improved healing thereafter takes place.

A monocular motion stereo-based automatic free parking space detection system is disclosed. The system acquires image sequences with a single rearview fisheye camera, three-dimensionally reconstructs the vehicle rearview by using point correspondences, and recovers metric information from a known camera height to estimate the positions of adjacent vehicles thereby detecting the free parking spaces. By using de-rotation-based feature selection and 3D structure mosaicking the degradation of the 3D structure near the epipole is solved and it is not necessary to use the unreliable odometry due to its accuracy depending on road conditions.

A data-centric data mining technique provides greater ease of use and flexibility, yet provides high quality data mining results by providing general methodologies for automatic data mining. A methodology for each major type of mining function is provided, including: supervised modeling (classification and regression), feature selection, and ranking, clustering, outlier detection, projection of the data to lower dimensionality, association discovery, and data source comparison. A method for data-centric data mining comprises invoking a data mining feature to perform data mining on a data source, performing data mining on data from the data source using the data mining feature, wherein the data mining feature uses data mining processes and objects internal to the data mining feature and does not use data mining processes and objects external to the data mining feature, outputting data mining results from the data mining feature, and removing all data mining processes and objects internal to the data mining feature that were used to process the data from the data source.

Systems and methods for defection classification in a semiconductor process are provided. The system includes a communication line configured to receive a defect image of a wafer from the semiconductor process and a deep-architecture neural network in electronic communication with the communication line. The neural network has a first convolution layer of neurons configured to convolve pixels from the defect image with a filter to generate a first feature map. The neural network also includes a first subsampling layer configured to reduce the size and variation of the first feature map. A classifier is provided for determining a defect classification based on the feature map. The system may include more than one convolution layers and/or subsampling layers. A method includes extracting one or more features from a defect image using a deep-architecture neural network, for example a convolutional neural network.

A method and system for dynamically configuring all or part of a casino floor to a theme targeted at a predetermined population of patrons. The configuration of the gaming machines may be controlled from a central system in accordance with a predetermined theme or alternatively the patrons may activate their favorite theme interactively at the gaming machine. The predetermined theme may be selected according to patron characteristics including, for example, nationality, ethnic origin, gender, racial identity, geographic origin, favorite hobby, political association, sexual orientation, preferred sport, musical idol or genre, age and/or faith of the patrons of the plurality of gaming machines. A hierarchical menu of authorized games may be dynamically generated from the patron characteristics and presented to the patron according to the patron's characteristics and associated theme is determined such that the patron is likely to quickly find his favorite game. The gaming system may include video cameras and microphones, at locations monitoring a group of gaming machines or fitted on each gaming machines, and recognition software for recognizing patrons' characteristics such as age group, clothing style, hair color, isolated person or a party of persons, language spoken, and ethnic origin in order to dynamically adapt the gaming machines' theme accordingly. Alternatively, contact-less player tracking cards supply characteristics as the patrons move around the casino premises.

he invention discloses a medical information extraction system and method based on depth learning and distributed semantic features. The system is composed of a pretreatment module, a linguistic-model-based word vector training module, a massive medical knowledge base reinforced learning module, and a depth-artificial-neural-network-based medical term entity identification module. With a depth learning method, generation of the probability of a linguistic model is used as an optimization objective; and a primary word vector is trained by using medical text big data; on the basis of the massive medical knowledge base, a second depth artificial neural network is trained, and the massive knowledge base is combined to the feature leaning process of depth learning based on depth reinforced learning, so that distributed semantic features for the medical field are obtained; and then Chinese medical term entity identification is carried out by using the depth learning method based on the optimized statement-level maximum likelihood probability. Therefore, the word vector is generated by using lots of unmarked linguistic data, so that the tedious feature selection and optimization adjustment process during medical natural language process can be avoided.

Support vector machines are used to classify data contained within a structured dataset such as a plurality of signals generated by a spectral analyzer. The signals are preprocessed to ensure alignment of peaks across the spectra. Similarity measures are constructed to provide a basis for comparison of pairs of samples of the signal. A support vector machine is trained to discriminate between different classes of the samples. to identify the most predictive features within the spectra. In a preferred embodiment feature selection is performed to reduce the number of features that must be considered.

The invention provides a method and a system for predicting cardiovascular and cerebrovascular disease risks. The method comprises the following steps: step 1, defining problems of cardiovascular and cerebrovascular disease prognosis risk prediction, step 2, collecting health medical data of cardiovascular and cerebrovascular disease patients; step 3, preprocessing data, including data integration, data cleaning, and processing missing data; step 4, constructing features and selecting features, identifying potential risk factors; step 5, the identified risk factors and rehabilitation outcomes forming an input-output sample set, inputting the input-output sample set to a random forest algorithm for model training, and evaluating prediction performance of a model. The method and the system can obtain health medical data of cardiovascular and cerebrovascular disease patients, the data being required by a clinician input model, and a predicted rehabilitation outcome of a patient in a certain time period in future is obtained through the model. The method and the system can preferably predict prognosis risks, so as to realize personalized accurate rehabilitation treatment.

The present invention is directed to a method for detecting unknown malicious code, such as a virus, a worm, a Trojan Horse or any combination thereof. Accordingly, a Data Set is created, which is a collection of files that includes a first subset with malicious code and a second subset with benign code files and malicious and benign files are identified by an antivirus program. All files are parsed using n-gram moving windows of several lengths and the TF representation is computed for each n-gram in each file. An initial set of top features (e.g., up to 5500) of all n-grams IS selected, based on the DF measure and the number of the top features is reduced to comply with the computation resources required for classifier training, by using features selection methods. The optimal number of features is then determined based on the evaluation of the detection accuracy of several sets of reduced top features and different data sets with different distributions of benign and malicious files are prepared, based on the optimal number, which will be used as training and test sets. For each classifier, the detection accuracy is iteratively evaluated for all combinations of training and test sets distributions, while in each iteration, training a classifier using a specific distribution and testing the trained classifier on all distributions. The optimal distribution that results with the highest detection accuracy is selected for that classifier.

The system described herein determines an input command profile for a dynamic system that can be modeled as a linear system, the input command profile for transitioning an output of the dynamic system from one point to another point. The system identifies characteristics of the dynamic system, and then selects a command profile which defines an input to the dynamic system based on the identified characteristics. The command profile comprises one or more pulses which rise and fall at switch times, and the command profile is useable with substantially any dynamic system that can be modeled as a linear system. The system then imposes a plurality of constraints on the dynamic system, at least one of the constraints being defined in terms of the switch times, and determines the switch times for the input to the dynamic system based on the command profile and the plurality of constraints.

A system and method that classify driver driving skill based on multiple types of maneuvers. An original features generation processor receives signals identifying driving characteristics of the driver of the vehicle and outputs original features from the signals. A features extraction processor extracts certain features from the original features and outputs transformed features. A features selection processor selects certain ones of the transformed features and outputs final features and a classifier classifies the final features to determine the skill level of the vehicle driver.

A two-class analysis system for summarizing features and determining features appropriate to use in training a classifier related to a data mining operation. Exemplary embodiments describe how to select features which will be suited to training a classifier used for a two-class text classification problem. Bi-Normal Separation methods are defined wherein there is a measure of inverse cumulative distribution function of a standard probability distribution and representative of a difference between occurrences of the feature between said each class. In addition to training a classifier, the system provides a means of summarizing differences between classes.

The invention includes a thermometer with a backlight and a method for lighting the backlight. The thermometer has temperature sensing tip, a processor taking temperature readings and determining a sensed temperature reading of the living being from the temperature sensing tip. The thermometer also includes a display and a backlight for lighting the display. The backlight is activated upon a command from the processor and the processor determines whether to activate the backlight based upon the temperature readings. The method embodiment can includes the steps of using the processor to monitor a temperature change indicated by a temperature sensing element. The processor then detects a temperature decrease and activates a first color light emitting element to backlight a display if the temperature decrease exceeds or equals a predetermined threshold. The thermometer is operable in one of a plurality of selectable operating modes, and the predetermined threshold is dependent upon the selected operating mode. For example, operating modes may depend on patient age range or measurement location. Age range may include infant, toddler and adult.

The invention relates to the artificial intelligence technical field, in particular to a text classification feature selection and weigh calculation method based on field knowledge. The method combines sample statistics and field glossaries to construct a filed classification feature space, utilizes internal knowledge relations in the field, calculates the similarity between the glossaries, and then adjusts the corresponding feature weight of classification feature vectors. Moreover, the method adopts a learning algorithm of a support vector machine to construct a field text classification model and then realize field text classification. As shown by text classification laboratory results of the Yunan tourist field and the non-tourist field, the classification accuracy of the method is improved by 4 percent compared with the text classification effect of the improved TFIDF feature weigh method.

The invention relates to auxiliary medical diagnoses, and aims to provide a method for automatically identifying whether a thyroid nodule is benign or malignant based on a deep convolutional neural network. The method for automatically identifying whether the thyroid nodule is benign or malignant based on the deep convolutional neural network comprises the following steps: reading B ultrasonic data of thyroid nodules; performing preprocessing for thyroid nodule images; selecting images, and obtaining nodule portions and non-nodule portions through segmentations; averagely dividing the extracted ROIs (regions of interest) into p groups, extracting characteristics of the ROIs by utilizing a CNN (convolutional neural network), and performing uniformization; taking p-1 groups of data as a training set, taking the remaining one group to make a test, and obtaining an identification model through training to make the test; and repeating cross validation for p times, and then obtaining an optimum parameter of the identification model. The method can obtain the thyroid nodules through the automatic segmentations by means of the deep convolutional neural network, and makes up for the deficiency that a weak boundary problem cannot be solved based on a movable contour and the like; and the method can automatically lean and extract valuable feature combinations, and prevent the complexity of an artificial feature selection.

The present invention relates generally to wireless, remote, physiological monitoring in the evaluation of health and disease state specifically with respect to cardiac and pulmonary pathologies, including heart failure and sleep apnea. Personalized thresholds are used to enhance performance of classification and prediction methods by utilizing patient clinical history and past empiric sensed data, such as through an initialization period, to learn the biological variation present in each sensed individual.

Data from an adherent patch undergoes disseminated processing as data is securely sent from a sensing device ultimately to a remote server. Monitoring, classification, and prediction results are hosted and made accessible through an authenticated system to members of the individual's healthcare team, family, or other caregivers.

Learning algorithms are used to characterize physiological attributes and to classify a health or disease state based on an aggregate of features. Classification models and feature selection are optimized with validation algorithms.

Methods for feature selection based on hierarchical local-region analysis of feature relationships in a data set are provided.

The invention provides a human body behavior identification method based on an inertial sensor. The method comprises the steps of acquiring human body behavior data of testees by means of the inertial sensor, conducting sliding window segmentation on the acquired human body behavior data, conducting feature extraction on a triaxial accelerated speed subsequence and a triaxial angular speed subsequence which are obtained after sliding window segmentation, conducting feature fusion on a feature vector to form a sample set of the human body behaviors of the testees, conducting feature selection on the sample set by means of the least correlated maximum redundant algorithm and the Bayes regularization sparse polynomial logistic regression algorithm, obtaining the classification feature vectors of all human body behaviors of all the testees, obtaining a classifier model of each human body behavior by means of a fuzzy least square support vector machine, and obtaining a human body behavior identification result after the human body behavior data are tested by means of the fuzzy least square support vector machine. By means of the human body behavior identification method, self-adaptation and identification efficiency can be improved.

A method and apparatus for combining a plurality of images is disclosed. In one embodiment, at least one signal component is determined from a plurality of source images using feature selective fusion. At least one color component is determined from the plurality of source images using color fusion. An output image is formed from the at least one signal component and the at least one color component. In another embodiment, at least one image component is determined from a plurality of source images using feature selective fusion. An output image is formed from the at least one image component using color fusion.