2140 results about "Support vector machine" patented technology

A system and method for distinguishing human input events from malware-generated events includes one or more central processing units (CPUs), one or more input devices and memory. The memory includes program code that when executed by the CPU causes the CPU to obtain a first set of input events from a user utilizing the input device. The first input events are used to obtain or derive a feature indicative of the user, such as a multi-dimensional feature vector as provided by a support vector machine. Second input events are then obtained, and the second input events are classified against the feature to determine if either the user or malware initiated the second input events.

The invention provides a text emotion classification method based on the joint deep learning model which relates to the text emotion classification method. The method is designed with the object of solving the problems with the dimension disaster and sparse data incurred from the existing support vector machine and other shallow layer classification methods. The method comprises: 1) processing each word in the text data; using the word2vec tool to train each processed word in the text data so as to obtain a word vector dictionary; 2) obtaining the matrix M of each sentence; training the matrix M by the LSTM layer and converting it into vector with fixed dimensions; improving the input layer; generating d-dimensional h word vectors with context semantic relations; 3) using a CNN as a trainable characteristic detector to extract characteristics from the d-dimensional h word vectors with context semantic relations; and 4) connecting the extracted characteristics in order; outputting to obtain the probability of each classification wherein the classification with the maximal probability value is the predicated classification. The invention is applied to the natural language processing field.

An object detector, an object detecting method and a robot can reduce diction errors of detecting wrong objects without increasing the volume of the computational operation to be performed to detect the right object. A face detector 101 comprises a face detecting section 110 that operates like a conventional face detecting section and is adapted to roughly select face candidates from an input image by template matching and detect face candidates by means of a support vector machine for face recognition, a non-face judging section 120 that detects non-face candidates that are judged to be non-faces and removes them from the face candidates selected by the face detecting section 110 and a skin tracker section 114 for tracking a face region after the non-face judgment. When the assumed distance between the face detector and the face as computed from the input image and the measured distance as measured by a distance sensor show a large difference, when the color variance of the face candidate is small, when the occupancy ratio of the skin color region is large and when the change in the size of the face region is large after the elapse of a predetermined time, the non-face judging section 120 judges such face candidates as non-faces and removes them from the face candidates.

A robot includes a face extracting section for extracting features of a face included in an image captured by a CCD camera, and a face recognition section for recognizing the face based on a result of face extraction by the face extracting section. The face extracting section is implemented by Gabor filters that filter images using a plurality of filters that have orientation selectivity and that are associated with different frequency components. The face recognition section is implemented by a support vector machine that maps the result of face recognition to a non-linear space and that obtains a hyperplane that separates in that space to discriminate a face from a non-face. The robot is allowed to recognize a face of a user within a predetermined time under a dynamically changing environment.

Methods for training machines to categorize data, and/or recognize patterns in data, and machines and systems so trained. More specifically, variations of the invention relates to methods for training machines that include providing one or more training data samples encompassing one or more data classes, identifying patterns in the one or more training data samples, providing one or more data samples representing one or more unknown classes of data, identifying patterns in the one or more of the data samples of unknown class(es), and predicting one or more classes to which the data samples of unknown class(es) belong by comparing patterns identified in said one or more data samples of unknown class with patterns identified in said one or more training data samples. Also provided are tools, systems, and devices, such as support vector machines (SVMs) and other methods and features, software implementing the methods and features, and computers or other processing devices incorporating and/or running the software, where the methods and features, software, and processors utilize specialized methods to analyze data.

Characterization of carotid atherosclerosis and classification of plaque into symptomatic or asymptomatic along with the risk score estimation are key steps necessary for allowing the vascular surgeons to decide if the patient has to definitely undergo risky treatment procedures that are needed to unblock the stenosis. This application describes a statistical (a) Computer Aided Diagnostic (CAD) technique for symptomatic versus asymptomatic plaque automated classification of carotid ultrasound images and (b) presents a cardiovascular stroke risk score computation. We demonstrate this for longitudinal Ultrasound, CT, MR modalities and extendable to 3D carotid Ultrasound. The on-line system consists of Atherosclerotic Wall Region estimation using AtheroEdge™ for longitudinal Ultrasound or Athero-CTView™ for CT or Athero-MRView from MR. This greyscale Wall Region is then fed to a feature extraction processor which computes: (a) Higher Order Spectra; (b) Discrete Wavelet Transform (DWT); (c) Texture and (d) Wall Variability. The output of the Feature Processor is fed to the Classifier which is trained off-line from the Database of similar Atherosclerotic Wall Region images. The off-line Classifier is trained from the significant features from (a) Higher Order Spectra; (b) Discrete Wavelet Transform (DWT); (c) Texture and (d) Wall Variability, selected using t-test. Symptomatic ground truth information about the training patients is drawn from cross modality imaging such as CT or MR or 3D ultrasound in the form of 0 or 1. Support Vector Machine (SVM) supervised classifier of varying kernel functions is used off-line for training. The Atheromatic™ system is also demonstrated for Radial Basis Probabilistic Neural Network (RBPNN), or Nearest Neighbor (KNN) classifier or Decision Trees (DT) Classifier for symptomatic versus asymptomatic plaque automated classification. The obtained training parameters are then used to evaluate the test set. The system also yields the cardiovascular stroke risk score value on the basis of the four set of wall features.

A system and method for historical database training of a support vector machine (SVM). The SVM is trained with training sets from a stream of process data. The system detects availability of new training data, and constructs a training set from the corresponding input data. Over time, many training sets are presented to the SVM. When multiple presentations are needed to effectively train the SVM, a buffer of training sets is filled and updated as new training data becomes available. Once the buffer is full, a new training set bumps the oldest training set from the buffer. The training sets are presented one or more times each time a new training set is constructed. A historical database of time-stamped data may be used to construct training sets for the SVM. The SVM may be trained retrospectively by searching the historical database and constructing training sets based on the time-stamped data.

The invention discloses a pedestrian tracking method based on HOG-LBP, comprising the following steps of, A1, sample establishment; A2, feature extraction; A3, SVM model establishment; A4, classifier training; A5, video capture and pretreatment; A6, video pedestrian examination; A7, video pedestrian tracking: applying a particle filtering tracking method based on an HOG-LBP feature to track the pedestrian examined in step A6. The method firstly learns an image pedestrian mode through a support vector machine, and then classifies a moving area in a video sequence and inputs the result to a particle filtering machine to update the particle status, and finally realizes continuous tracking to pedestrian movement in the scene. Because the method collects pedestrian feature by adopting HOG-LBP and uses the particle filtering to track movement, it has good adaptability and stability to movement interleave and sheltering phenomenon in a scene and non-linear feature presented by the movement.

A system and method for detecting malicious executable software code. Benign and malicious executables are gathered; and each are encoded as a training example using n-grams of byte codes as features. After selecting the most relevant n-grams for prediction, a plurality of inductive methods, including naive Bayes, decision trees, support vector machines, and boosting, are evaluated.

The methods, systems and devices of the present invention comprise use of Support Vector Machines and RFE (Recursive Feature Elimination) for the identification of patterns that are useful for medical diagnosis, prognosis and treatment. SVM-RFE can be used with varied data sets.

An apparatus and method for automatically generating radiation treatment planning parameters are disclosed. In accordance with the illustrative embodiment, a database is constructed that stores: (i) patient data and past treatment plans by expert human planners for these patients, and (ii) optimal treatment plans that are generated using multi-objective optimization and Pareto front search and that represent the best tradeoff opportunities of the patient case, and a predictive model (e.g., a neural network, a decision tree, a support vector machine [SVM], etc.) is then trained via a learning algorithm on a plurality of input/output mappings derived from the contents of the database. During training, the predictive model is trained to identify and infer patterns in the treatment plan data through a process of generalization. Once trained, the predictive model can then be used to automatically generate radiation treatment planning parameters for new patients.

A method and system managing radio frequency identification (RFID) systems. The system monitors the performance of systems that use RFID tags and readers. It operates at multiple levels to ensure the optimal performance of readers, tags, antennae, and the information processing systems that acquire and convey tag data. The management system may employ artificial intelligence techniques such as genetic algorithms, fuzzy logic, neural networks, Bayesian networks, support vector machines or statistical methods to develop, maintain and exploit models of RFID system behavior. By comparing the actual performance of RFIDs and related components, the management system can detect and report failures and partial failures of components. The management system may also send signals to components to enhance performance of the overall RFID system.

The invention discloses an SVM classification model-based equipment fault diagnosing method. The method comprises the following steps: performing a preprocessing operation on equipment data; constructing a fault diagnosis case knowledge base; performing fault diagnosis on a support vector machine on the basis of an SVM classification model; acquiring fault information and performing maintenance guide. According to the support vector machine-based intelligent equipment fault diagnosis method, the fault features of equipment are highlighted to the maximum degree; the situations that the equipment data are incomplete and inaccurate are reduced; the possibility is provided for constructing an accurate and reliable fault diagnosis model; the problem that the diagnosis model ages along with the operating time of the equipment is solved; the misdiagnosis rate of the fault diagnosis is reduced; the accuracy and the speed of the equipment fault diagnosis are greatly improved.

The invention provides a finger-vein image quality evaluation method and system based on a convolutional neural network. The method includes: labeling the quality of finger-vein gray images, building a training sample set, and using the training sample set to train the convolutional neural network; inputting one optional gray image and a binary image into trained models, selecting the output of second full connection layers in two convolutional neural network models as the depth feature vectors of the input gray image and the binary image; connecting the two depth feature vectors to form a united expression vector, inputting the united expression vector into a support vector machine for training, and using a probability support vector machine to calculate the quality of a predicted finger-vein image. By the evaluation method and system, finger-vein image quality evaluation precision can be increased to a large extent, and the identification performance of a certification system can be improved.

To accurately classify a query as navigational, thousands of available features are explored, extracted from major commercial search engine results, user Web search click data, query log, and the whole Web's relational content. To obtain the most useful features for navigational query identification, a three level system is used which integrates feature generation, feature integration, and feature selection in a pipeline. Because feature selection plays a key role in classification methodologies, the best feature selection method is coupled with the best classification approach to achieve the best performance for identifying navigational queries. According to one embodiment, linear Support Vector Machine (SVM) is used to rank features and the top ranked features are fed into a Stochastic Gradient Boosting Tree (SGBT) classification method for identifying whether or not a particular query is a navigational query.

The present invention provides a fundus image classification method and device of retinopathy. The method comprises a step of obtaining the fundus image of an eye detection patient, a step of preprocessing the fundus image and obtaining a corresponding grey fundus image, a step of extracting a preset image characteristic in the grey fundus image, a step of analyzing the preset image characteristic according to the diabetic retinopathy classification model of the fundus image, and obtaining the classification result of the corresponding fundus image, a step of extracting the preset image characteristic in the preprocessed grey fundus image, and carrying out prediction classification on the above preset image characteristic through the diabetic retinopathy classification model established according to a support vector machine and a deep neural network so as to obtain a final classification result. The artificial participation is not needed in the whole process, the workload of doctors is reduced, the high standard requirement of the medical qualification level of the doctor is reduced, the accuracy of classification is improved, and the method and the device have great significance for specific applications and medical research.

The invention discloses a method for establishing virtual reality excavation dynamic smart load prediction models. The method includes the steps that the knowledge excavation technology is adopted so that a virtual reality analysis environment can be formed, the influence relation between fixed quantities is explored, and an input variable candidate set is determined; smart load prediction models of a support vector machine of a self-adaptive structure and an Elman neural network and the like are established, wherein input variables are determined by the support vector machine through the attribute screening technology and parameters are optimized by the support vector machine through a flora tendency differential evolutionary algorithm; a region load smart load prediction model based on data slice excavation is established; a load curve prediction model combined with dynamic electrovalence factors, user characteristics and the user response electric quantity is established, so that linked correcting prediction of loads, electrovalence and the response electric quantity is achieved. According to the method, the prediction models suitable for the actual condition of a smart power grid of China are established, the scale of construction of renewable energy sources is reasonably planned, more efficient power utilization of users is facilitated, and reasonable arrangement of power supply resources of power enterprises is facilitated.

A method classifies images of faces according to gender. Training images of male and female faces are supplied to a vector support machine. A small number of support vectors are determined from the training images. The support vectors identify a hyperplane. After training, a test image is supplied to the support vector machine. The test image is classified according to the gender of the test image with respect to the hyperplane.

The invention provides a magnetic tile surface defect feature extraction and defect classification method based on machine vision. A concrete algorithm comprises a first step of building a 5-scale and 8-direction Gabor filter bank suitable for magnetic tile surface defect feature extraction, conducting filtering to an original image and obtaining a 40-width component plot, a second step of respectively extracting a gray average and a variance feature of the component plot and forming a 80-dimension feature vector, a third step of conducting dimensionality reduction to the original 80-dimension feature vector through a principal component analysis (PCA) method and an independent component analysis (ICA) method, removing relevance and redundancy and obtaining a 20-dimension feature vector, a fourth step of conducting normalization pretreatment to feature vector data, wherein the original data are normalized between zero and one, and a fifth step of adopting a grid method and a K-CV method to achieve SVM parameter optimization at first and training an SVM model using training sample data offline, wherein pretreated testing sample data are input into a support vector machine during online testing, and automatic classification and identification of defects can be achieved. The feature extraction method can effectively filter interference and prominent defects of magnetic tile surface texture, extracted features can reflect defect information accurately, data values are small, and a classifier used for classifying the defects can achieve defect identification fast and accurately online.

The invention relates to a text sentiment analysis method and device, a storage medium and computer equipment. A sentence vector in a sentence in a test text is obtained and is formed in a way that the word vectors of words in the sentence are connected, and the sentence vector is independently input into two preset convolutional neural networks and one two-way long short-term memory neural network model to be preprocessed to obtain three sentence feature vectors of the sentence. Three sentence feature vectors are connected, the connected sentence feature vectors are classified through a classifier SVM (Support Vector Machine) to obtain the sentiment classification result of the sentence, and the emotional tendency of a test text can be obtained according to the sentiment classification result of the sentence. By use of the method, the convolutional neural network can be combined to effectively extract local features, the two-way long short-term memory neural network can effectively analyze the advantages of time sequence features, the test text is subjected to the sentiment analysis through the method to obtain robustness with higher emotional tendency and generalization ability,and efficiency is higher.

The invention relates to a device and a method for automatically monitoring a telephone call behavior of a driver when driving and belongs to the fields of intelligent traffic and aided driving. The device comprises an image acquisition device, a calculating device, a warning device and a wireless transmission device. The method comprises the following steps of firstly acquiring a head and nearby area image of the driver, secondly, obtaining the positions of the face and both hands of the driver in the image by skin color detection, and classifying by a support vector machine to determine whether the driver makes a telephone call or not; warning the driver if the driver makes the telephone call; uploading the image that the driver makes the telephone call to the monitoring center of the road transport bureau through a wireless network if the warning is useless to be used as an evidence that the driver breaks the law. According to the device and the method for automatically monitoring the telephone call behavior of the driver when driving disclosed by the invention, the unlawful act of the driver can be effectively monitored, the working strength of law enforcement personnel is relieved, the working efficiency is improved, and the occurrence rate of traffic accidents is reduced.

The invention discloses a multi-vision defect detecting equipment and a multi-vision defect detecting method for a large-size LCD glass substrate in a production line. For the equipment, a linear scanning imaging detection system is adopted for acquiring the high-definition gray image of an LCD glass substrate to be detected, and the equipment is simple in structure and convenient to operate; according to the method disclosed by the invention, the acquired image is processed, a kmeans clustering method is adopted to carry out defect existence judgment on the processed image of the LCD glass substrate, and by making the defect regions, the defect category is judged by a classification method of a support vector machine (SVM), and the defect quantity is counted. Processed image and detection results are transmitted to an office in real time by a filed bus control system for operators on duty to check, and the field production parameters are transmitted, so that remote monitoring of the system is realized.

Spectrogram extraction from DNA sequence has been known since 2001. A DNA spectrogram is generated by applying Fourier transform to convert a symbolic DNA sequence consisting of letters A, T, C, G into a visual representation that highlights periodicities of co-occurrence of DNA patterns. Given a DNA sequence or whole genomes, with this method it is easy to generate a large number of spectrogram images. However, the difficult part is to elucidate where are the repetitive patterns and to associate a biological and clinical meaning to them. The present disclosure provides systems and methods that facilitate the location and/or identification of repetitive DNA patterns, such as CpG islands, Alu repeats, tandem repeats and various types of satellite repeats. These repetitive elements can be found within a chromosome, within a genome or across genomes of various species. The disclosed systems and methods apply image processing operators to find prominent features in the vertical and horizontal direction of the DNA spectrograms. Systems and methods for fast, full scale analysis of the derived images using supervised machine learning methods are also disclosed. The disclosed systems and methods for detecting and/or classifying repetitive DNA patterns include: (a) comparative histogram method, (b) feature selection and classification using support vector machines and genetic algorithms, and (c) generation of spectrovideo from a plurality of spectral images.

The invention discloses a method for identifying local discharge signals of a switchboard based on a support vector machine model. The method comprises a model training process and an audio identifying process, and particularly comprises the following steps of: preprocessing audio signals; extracting effective audios according to short-time energy and a zero-crossing rate; segmenting the effective audios and extracting characteristic parameters such as Mel cepstrum coefficients, first order difference Mel cepstrum coefficients, high zero-crossing rate and the like of each segment of the audios; training a sample set by using a support vector machine tool, and establishing a corresponding support vector machine model; after preprocessing audio signals to be identified and extracting and segmenting the effective audios, classifying and identifying segment-characteristic-based samples to be tested according to the support vector machine model; and post-processing classification results, and judging whether partial discharge signals exist. By using the method, the existence of the partial discharge signals of the switchboard is accurately identified, the happening of major accidents involving electricity is prevented and avoided, economic losses caused by insulation accidents are reduced, and the power distribution reliability is improved.

The aesthetic quality of a picture is automatically inferred using visual content as a machine learning problem using, for example, a peer-rated, on-line photo sharing Website as data source. Certain visual features of images are extracted based on the intuition that they can discriminate between aesthetically pleasing and displeasing images. A one-dimensional support vector machine is used to identify features that have noticeable correlation with the community-based aesthetics ratings. Automated classifiers are constructed using the support vector machines and classification trees, with a simple feature selection heuristic being applied to eliminate irrelevant features. Linear regression on polynomial terms of the features is also applied to infer numerical aesthetics ratings.

Age-estimation of a face of an individual is represented in image data. In one embodiment, age-estimation techniques involves combining a Contourlet Appearance Model (CAM) for facial-age feature extraction and Support Vector Regression (SVR) for learning aging rules in order to improve the accuracy of age-estimation over the current techniques. In a particular example, characteristics of input facial images are converted to feature vectors by CAM, then these feature vectors are analyzed by an aging-mechanism-based classifier to estimate whether the images represent faces of younger or older people prior to age-estimation, the aging-mechanism-based classifier being generated in one embodiment by running Support Vector Machines (SVM) on training images. In an exemplary binary youth/adult classifier, faces classified as adults are passed to an adult age-estimation function and the others are passed to a youth age-estimation function.

A system and method for detecting and tracking humans, such as pedestrians, in low visibility conditions or otherwise. A night vision camera periodically captures a an infrared image of a road from a single perspective. A pedestrian detection module determines a position of a pedestrian in the frame by processing the captured image. The pedestrian detection module includes a support vector machine to compare information derived from the night vision camera to a training database. A pedestrian tracking module estimates pedestrian movement of the detected pedestrian from in subsequent frames by applying filters. The tracking module uses Kalman filtering to estimate pedestrian movement at periodic times and mean-shifting to adjust the estimation. An output display module interleaves detection frames and tracking frames in generating output video for the display.

The invention belongs to the field of data analysis, and in particular relates to a water environment monitoring and quality-control data analysis method. The method is characterized by comprising the following steps of: a, acquiring water environment quality-control data to be verified; b, establishing a support vector machine water environment quality-control data forecasting module; c, comparing the quality-control data output with quality-control data in historical data which is identical in analysis method and instrument type, to obtain a deviation; and d, determining whether the verification of the data passes or not by the following specific steps of: judging that the data is rational and the verification passes if the deviation is not high, and adding into a historical dataset; or if the deviation is excessively high, classifying the data as suspect data. According to analysis research method disclosed by the invention, in analysis of the water environment monitoring and quality-control data, the problem on processing, verification and analysis of various rapid increasing and nonlinear multivariable monitoring and quality-control data is solved, and the demand of scientific management is met.

A system for performing face registration and authentication using face information, and a method thereof. A set of readily distinguishable features for each user is selected at a registration step and only the set of features selected at the registration step is used at a face authentication step, whereby memory use according to unnecessary information and amount of data calculation for face authentication can be reduced. Thus, the present system has an advantage in that identity authentication through face authentication can be performed even under restricted environments of a USB token or smart card with limited resources. The present system further has advantages in that authentication performance is improved, as readily distinguishable feature information is used, and the time for face authentication is reduced, as face authentication is performed using the SVM built by using the optimal set of readily distinguishable features at a training step.

The invention provides a method for three-dimensional reconstruction of laser speckle structured light and depth information. The three-dimensional reconstruction technology is an important subject for machine vision research and refers to the content that a three-dimensional space geometrical shape of a three-dimensional body is restored through images of the three-dimensional body. Generally, three-dimensional reconstruction is conducted through the binocular parallax principle of a binocular camera or through a triangulation method or space codes are obtained through the structured light and the depth information is obtained through the triangulation method. The method aims at obtaining the depth information through the laser speckle structured light, a similar invention such as the kinect of the Microsoft Corporation also obtains the depth information (namely different depths are matched through a cross-correlation function of laser speckles) of an object through the method, and the difference is an algorithm for obtaining the depth information through the speckles. According to the method, parallel code number sorting is conducted on each pixel block one by one by a thinning window through multiple support vector machines, so that the depth of each pixel window is obtained, coordinates under a world coordinate system of the object are obtained by inversely solving a camera model through the depth information, and therefore the depth information with the higher accuracy can be obtained.