1168 results about "Ensemble learning" patented technology

A facial expression recognition system that uses a face detection apparatus realizing efficient learning and high-speed detection processing based on ensemble learning when detecting an area representing a detection target and that is robust against shifts of face position included in images and capable of highly accurate expression recognition, and a learning method for the system, are provided. When learning data to be used by the face detection apparatus by Adaboost, processing to select high-performance weak hypotheses from all weak hypotheses, then generate new weak hypotheses from these high-performance weak hypotheses on the basis of statistical characteristics, and select one weak hypothesis having the highest discrimination performance from these weak hypotheses, is repeated to sequentially generate a weak hypothesis, and a final hypothesis is thus acquired. In detection, using an abort threshold value that has been learned in advance, whether provided data can be obviously judged as a non-face is determined every time one weak hypothesis outputs the result of discrimination. If it can be judged so, processing is aborted. A predetermined Gabor filter is selected from the detected face image by an Adaboost technique, and a support vector for only a feature quantity extracted by the selected filter is learned, thus performing expression recognition.

A facial expression recognition system that uses a face detection apparatus realizing efficient learning and high-speed detection processing based on ensemble learning when detecting an area representing a detection target and that is robust against shifts of face position included in images and capable of highly accurate expression recognition, and a learning method for the system, are provided. When learning data to be used by the face detection apparatus by Adaboost, processing to select high-performance weak hypotheses from all weak hypotheses, then generate new weak hypotheses from these high-performance weak hypotheses on the basis of statistical characteristics, and select one weak hypothesis having the highest discrimination performance from these weak hypotheses, is repeated to sequentially generate a weak hypothesis, and a final hypothesis is thus acquired. In detection, using an abort threshold value that has been learned in advance, whether provided data can be obviously judged as a non-face is determined every time one weak hypothesis outputs the result of discrimination. If it can be judged so, processing is aborted. A predetermined Gabor filter is selected from the detected face image by an Adaboost technique, and a support vector for only a feature quantity extracted by the selected filter is learned, thus performing expression recognition.

The invention discloses a Chinese network review emotion classification method based on an integrated study frame. According to the method, a part-of-speech combination mode, an order-preserving sub-matrix mode and a frequent word sequence mode are adopted as input characteristics, in the level of characteristics, factors of the influence of Chinese word order information, interval phrase characteristics and the sentence length are considered, and the characteristic vector sparsity problem is solved through semantic similarities; the problem that many review text characteristics exist is solved, the inter-base-classifier independence is guaranteed, and the classification performance of base classifiers is improved as much as possible; a base classifier algorithm constructed based on product attributes is adopted to comprehensively review emotion information of each attribute in a text, and then the sentence-level emotional tendency of reviews is judged, so that a final classification result is more accurate. The Chinese network review emotion classification method based on the integrated study frame is applicable to e-commerce network review emotion classification in various fields, can make a potential consumer know evaluation information of a commodity before purchase and can also make a merchant better sufficiently know the consumer's opinion, and therefore the service quality is improved.

A fully or semi-automated, integrated learning, labeling and classification system and method have closed, self-sustaining pattern recognition, labeling and classification operation, wherein unclassified data sets are selected and converted to an assembly of graphic and text data forming compound data sets that are to be classified. By means of feature vectors, which can be automatically generated, a machine learning classifier is trained for improving the classification operation of the automated system during training as a measure of the classification performance if the automated labeling and classification system is applied to unlabeled and unclassified data sets, and wherein unclassified data sets are classified automatically by applying the machine learning classifier of the system to the compound data set of the unclassified data sets.

The invention, which belongs to the technical field of network intrusion detection, discloses an intrusion detection method and intrusion detection system based on sustainable ensemble learning. A multi-class regression model is constructed by using a class probability output and a classification confidence product of an individual learner as training data, so that the decision-making process of the ensemble learning has high adaptability to the attack type to improve the detection accuracy. At the model updating stage, parameters and decision results of historical models are added into the training process of a new model, thereby completing incremental learning of the model. According to the invention, on the basis of the ensemble learning fusion plan of the multi-regression model, the decision-making weights of the individual learner during the detection processes for different attack types are allocated in a fine granularity manner; and the parameters and results of the historical models are used for training the new model, so that the stability of the model is improved and the sustainability of the learning process is ensured. Besides, the experiment result is compared with theexisting MV and WMV plans, the accuracy, stability and sustainability of the intrusion detection method and intrusion detection system are verified.

The invention discloses a method for 3D reconstruction and texture generation from single-view face based on multi-task learning, belonging to the computer vision field. The method comprises the following steps of: selecting a special viewpoint for rendering a three-dimensional human face model; generating depth map and texture map as truth value data from special viewpoint; designing an integrated learning and coding network based on feature sharing of depth information and texture information; designing the branch decoding network to recover the depth map from the shared features, and recovering the depth map, designing the mutual information with shared features as latent variables to maximize the generation of antagonistic network, and restoring the texture unwrapping map, adjusting the proportion of each task loss function and training the model; interpolating the depth map and using texture map to reconstruct the 3D face mesh model with texture details. The invention utilizes multi-task learning to carry out single-view face three-dimensional reconstruction, texture generation and style migration, and has the advantages of high speed, low cost and the like.

A multi-level anomaly detection method based on exponential smoothing, sliding window distribution statistics and an integrated learning model comprises the following steps of a statistic detection stage, an integrated learning training stage and an integrated learning classification stage, wherein in the statistic detection stage, a, a key feature set is determined according to the application scene; b, for discrete characteristics, a model is built through a sliding window distribution histogram, and a model is built through exponential smoothing for continuous characteristics; c, the observation features of all key features are input periodically; d, the process is ended. In the integrated learning training stage, a, a training data set is formed by marked normal and abnormal examples; b, a random forest classification model is trained. The method provides a general framework for anomaly detection problems comprising time sequence characteristics and complex behavior patterns and is suitable for online permanent detection, the random forest model is used in the integrated learning stage to achieve the advantages of parallelization and high generalization ability, and the method can be applied to multiple scenes like business violation detection in the telecom industry, credit card fraud detection in the financial industry and network attack detection.

The invention discloses an NRIET fog forecasting method based on machine learning. The method comprises steps that historical and forecast data for model training and operational forecasting in and around the forecast area is collected; the collected data is analyzed and processed to be a sample set for training a machine learning model; for problems, an xgboost model algorithm based on a decisiontree is selected, key influence factors generated by the airport fog are screened, and a relationship model between the fog and the influence factors is established; a training set and a verificationset are trained; according to the parameter adjusting sequence, model parameters are repeatedly adjusted till a forecasting model with optimal performance is acquired; an integrated learning method is utilized, and intersect verification and iteration training are carried out for the model to further improve model forecasting performance; observed real-time data is inputted to the forecasting model to acquire the fog forecasting result.

The invention belongs to the data mining and machine learning field and relates to a non-invasive load identification algorithm based on a hybrid neural network and ensemble learning. According to the method, experimental data are processed, so that the format of the data conforms to the input formats of models; after the data are processed, a hybrid neural network model is established; the data are input into the model; the model is trained and tested, identification results are obtained; and voting is performed for the results of three different models based on the idea of ensemble learning, so that a final identification result is obtained. With the method adopted, the feature extraction effect and load identification effect of the hybrid neural network are better than the effects of a traditional neural network; an ensemble learning idea-based method is provided, a plurality of feature subsets are selected from a total feature set so as to train a plurality of base classifiers, and the base classifiers are combined, and therefore, variance can be decreased, and the identification effect of the final identification result can be improved, and the problem of adverse influence of the introduction of harmonic features on an identification effect can be solved.

The invention discloses an on-line transformer fault diagnosis method based on support vector machines (SVM) and dissolved gas analysis (DGA), which belongs to the field of transformer fault diagnosis. The method comprises the following steps of: acquiring the concentration of fault feature gases including H2, CH4, C2H2, C2H4 and C2H6 in transformer insulating oil by a gas chromatographic analysis method, normalizing the data through a preprocessing system, sending the data to a classification diagnosis system assembled by an integrative learning method and formed by six SVM classifiers according to a decision process, classifying the measurement data through calculation, judging the running state of the transformer, and at last outputting the diagnosis results. In the method, the support vector machines (SVM) of the artificial intelligence technology are adopted to analyze the gases in the oil, and the relation between gas components and the running state of the transformer can be objectively and essentially reflected, thereby the accuracy of fault diagnosis is effectively improved.

The invention provides a real-time voice conversion method under conditions of minimal amount of training data. The method utilizes an ensemble learning theory to carry out modeling of a Gaussian mixture model to the collected data and design a mapping function under the rule of minimum mean square error. The method solves the problem that a standard GMM easily leads to over-fitting in the case of very minimal amount of data, and increases the robustness of a voice conversion algorithm for amount of data issues. At the same time, the GMM with more standard computational complexity is low in the process of estimating GMM parameters by the method, so the method is suitable for real-time voice conversion.

The invention provides a power transmission line gallop risk early-warning method based on Adaboost. The method comprises the following steps that internal reasons of gallop of power transmission lines are classified, and statistics is carried out on meteorological feature factors in historical gallop accidents of the power transmission lines according to the classification result; according to the information of a power transmission line to be predicted, the class, in the classification result of the internal reasons of gallop, corresponding to the power transmission line is selected, the meteorological feature factors under the conditions of the historical gallop accidents of the class are recorded to form a training sample set, a classifier is formed with an Adaboost ensemble learning algorithm, forecast data of the meteorological feature factors of the gallop of the power transmission line serve as input, and a gallop early-warning result of the power transmission line is obtained through the classifier; according to the early-warning result, the early-warning level of the gallop of the power transmission line is obtained through judgment. According to the power transmission line gallop risk early-warning method based on Adaboost, the internal reasons and the external reasons influencing the gallop of the power transmission line are comprehensively considered, the historical gallop information and the weather forecast information of the power transmission line are made full use of, and the method meets the actual conditions better; the algorithm in use is high in generalization ability, easy to encode and high in early-warning result accuracy.

The invention relates to an abnormal intrusion detection ensemble learning method based on the Wiener process. The method comprises the following steps: selecting a network traffic data set; inputting each network traffic sample and sample probability distribution thereof to an uninitialized neural network classifier or a neural network weak classifier obtained through the previous training, judging whether the neural network weak classifier wrongly classifies each network traffic sample, and adjusting quantity and sample probability distribution of each network traffic sample; repeating the step 2 to obtain a plurality of neural network weak classifiers; determining the weight of each neural network weak classifier respectively; obtaining strong classifiers based on each weak classifier and the corresponding weight of each neural network weak classifier; inputting network data flow to be detected to the strong classifiers to obtain intrusion detection results; and repeating the step 6 until all the network data flow to be detected is detected. According to the method and apparatus in the invention, the problem of classification of the unbalanced data set can be solved, and an unbiased classifier with high classification correct rate can be obtained.

The invention discloses an unbalanced data classification method based on unbalanced classification indexes and integrated learning, and mainly solves the problem of low classification accuracy of the minority class of the unbalanced data in the prior art. The method comprises steps as follows: (1), a training set and a testing set are selected; (2), training sample weight is initialized; (3), part of training samples is selected according to the training sample weight for training a weak classifier, and the well trained weak classifier is used for classifying all training samples; (4), the classification error rate of the weak classifier on the training set is calculated, is compared with a set threshold value and is optimized; (5), voting weight of the weak classifier is calculated according to the error rate, and the training sample weight is updated; (6), whether the training of the weak classifier reaches the maximum number of iterations is judged, if the training of the weak classifier reaches the maximum number of iterations, a strong classifier is calculated according to the weak classifier and the voting weight of the weak classifier, and otherwise, the operation returns to the step (3). The classification accuracy of the minority class is improved, and the method can be applied to classification of the unbalanced data.

The invention discloses a short-term electric load prediction method based on ensemble learning in the technical field of short-term electric load prediction. The method provided in the invention comprises the following steps of: firstly carrying out data preprocessing on electric load, creating a training sample set and a testing sample set for load prediction, then finding out the optimal initial parameter value of a nuclear vector regression learning device by means of a memes optimization algorithm, training the training sample set to obtain a sub-learning device model, and then implementing weighted array of the sub-learning device model to obtain a prediction model, predicting the testing sample set through the prediction model, determining whether adding a new sub-learning device according to the accuracy and the relative error of root mean square which is a condition in judging the accuracy of prediction model, obtaining an actual prediction model which is in line with the requirements of accuracy, and finally predicting the load of the next one week according to the actual prediction model. The method provided in the invention has the advantages of simple model, high prediction accuracy, and fast prediction speed and the like.

The invention belongs to technical fields characterized by protocols and discloses an attack occurrence confidence-based network security situation assessment method and system. According to the attack occurrence confidence-based network security situation assessment method and system, a machine learning technology is adopted to analyze network stream data and calculate a probability that networkstreams belong to attack streams; a D-S evidence theory is used to fuse the information of multi-step attacks to obtain the confidence of attack occurrence; and a network security situation is calculated by means of situational factor integration on the basis of security vulnerability information, network service information and host protection strategies; and therefore, the accuracy of assessmentis effectively improved. Since the confidence information of detection equipment is added to the assessment system, the influence of false negatives and false positives can be effectively reduced. Anensemble learning method is adopted, so that the accuracy of confidence calculation can be improved. A network attack is regarded as a dynamic process, and merging processing is performed on the information of the multi-step attacks. Information fusion technology is adopted, so that network environment characteristics such as vulnerabilities, service information and protection strategies are comprehensively considered.

The invention discloses a Chinese-medicinal-material identification method based on deep neural networks. The method includes the following steps: using Chinese-medicinal-material pictures, which arecollected by a web crawler and artificial photographing, as input of a data set, and carrying out preprocessing; and adopting a Bagging method of ensemble learning for training and prediction processes, namely adopting a random sampling method to generate multiple sub-training-sets, utilizing classical convolutional neural network models and all the sub-training-sets to carry out fine-tuning training to generate multiple weak classifiers, wherein the adopted convolutional neural network models include AlexNet, SqueezeNet and GoogleNet, and finally cooperate with a Softmax classification algorithm, and using an ensemble-learning combination strategy to obtain a strong classifier to obtain a classification result, wherein a voting method is adopted for the ensemble-learning combination strategy. The method of the invention is used for auxiliary identification of Chinese medicinal materials, reduces amateur errors appearing in identification, and can analyze the Chinese medicinal materials in a manner of high accuracy, fast identification speed and stable performance.

The invention relates to a category weight combined integrated learning classifying method. The method comprises the steps of preprocessing original data; converting into data formats that can be processed by the classification method so as to obtain a training data set and a data set to be classified; initializing the training data set sample weight; re-iterating and training M base classifiers according to the training data set and the sample weight thereof; calculating the category weight; integrating all base classifies; classifying the data set to be classified through a determining classifier according to the category weight; storing the classifying result into a file to obtain classification predication reference. With the adoption of the method, the problem of unbalancing category training under multi-category and multi-classification condition of integrated learning can be solved, the excessive learning is inhibited well, and moreover, the model predication precision is improved, and reliable reference is provided for classification predication.

A method for configuring a neural network is provided. The method includes: selecting a neural network including a plurality of layers, each of the layers including a plurality of neurons for processing an input and providing an output; and, incorporating at least one switch configured to randomly select and disable at least a portion of the neurons in each layer. Another method in the computer program product is disclosed.

The invention discloses a relation extraction method in combination with clause-level remote supervision and semi-supervised ensemble learning. The method is specifically implemented by the following steps of 1, aligning a relation triple in a knowledge base to a corpus library through remote supervision, and establishing a relation instance set; 2, removing noise data in the relation instance set by using syntactic analysis-based clause identification; 3, extracting morphological features of relation instances, converting the morphological features into distributed representation vectors, and establishing a feature data set; and 4, selecting all positive example data and a small part of negative example data in the feature data set to form a labeled data set, forming an unlabelled data set by the rest of negative example data after label removal, and training a relation classifier by using a semi-supervised ensemble learning algorithm. According to the method, the relation extraction is carried out in combination with the clause identification, the remote supervision and the semi-supervised ensemble learning; and the method has wide application prospects in the fields of automatic question-answering system establishment, massive information processing, knowledge base automatic establishment, search engines, specific text mining and the like.

The present invention discloses a selective integrated learning-based rotating machinery fault diagnosis method. The method comprises the steps of pre-processing a known input signal to obtain a training sequence; based on the Bagging algorithm, processing the training sequence to generate a series of differentiation-based learning machines; through the selective integrated learning process, giving a preference on the series of differentiation-based learning machines to obtain a well trained PSOSEN model; by utilizing the trained PSOSEN model, diagnosing a rotating machinery fault. The method solves the problem in the prior art that a classifier with better performances is difficult to be selected out of a series of classifiers can be solved.

The invention provides a wireless sensor network intrusion detection method based on integrated learning, and belongs to the technical field of communication. The method comprises the steps of collecting data of each node in a wireless sensor network, preprocessing the data, extracting a feature set of each node, and converting symbol features into values; normalizing each feature value; using a feature selection algorithm to screen out the optimal feature set from the preprocessed feature sets; using an improved support vector machine (SVM) algorithm to serve as a weak classifier, and combingwith the screened out optimal feature training set for training; and using an Adaboost integrated learning algorithm to combine the trained weak classifiers together to form a strong classifier, thenusing the trained strong classifier to test actual data, and picking out normal nodes and abnormal nodes of the wireless sensor network. According to the method provided by the invention, the accuracy of detection on intrusion attacks occurring in the wireless sensor network can be improved, the certain cost of labeled samples is reduced, and intrusion detection and training time is reduced, andthe reliability of the intrusion detection system is enhanced.

Methods and systems of detecting tampering in a digital image includes using hybrid large feature mining to identify one or more regions of an image in which tampering has occurred. Detecting tampering in a digital image with hybrid large feature mining may include spatial derivative large feature mining and transform-domain large feature mining. In some embodiments, known ensemble learning techniques are employed to address high feature dimensionality. detecting inpainting forgery includes mining features of a digital image under scrutiny based on a spatial derivative, mining one or more features of the digital image in a transform-domain; and detecting inpainting forgery in the digital image under scrutiny at least in part by the features mined based on the spatial derivative and at least in part by the features mined in the transform-domain.

The invention discloses a computer intrusion detection method based on integrated study and a semi-supervised SVM. The method is mainly used for solving the problem that when the computer intrusion detection problem is processed in the prior art, on the condition that the number of marked samples is limited and datasets are seriously unbalanced, the classification accuracy for attacked samples is low. The method comprises the implementation steps of 1, normalizing intrusion detection datasets; 2, initializing marked sample sets and unmarked sample sets; 3, training an SVM classifier, and predicting the unmarked samples to obtain predicted marks; 4, training a semi-supervised SVM classifier, and updating the marks of the unmarked samples in an iteration mode; 5, removing sampling data corresponding to a support vector; 6, using T classification models for predicting the marks of the unmarked samples; 7, inputting the T marks into an integrated classifier based on the Dunne index to obtain and output a final detection result. As for data with few marked samples, the detection precision of attacked samples is improved, and the method can be used for computer intrusion detection with few training samples.

The invention provides an early death risk assessment model establishing method and device based on ensemble learning. The method and device are used for assessing the death risk of an old multi-organfailure patient during hospitalization based on diagnosis and treatment data of the first day when the old multi-organ failure patient enters an intensive care unit. The method comprises the steps ofdata set construction, data processing and model construction and evaluation. The method comprises the following steps: acquiring three pieces of demographic information, five pieces of vital sign information, five laboratory examination indexes and two clinical indexes of a patient on the first day during living in an intensive care unit; inputting the data into a risk assessment device, and carrying out internal data preprocessing, feature calculation and model operation. Finally, the risk of adverse outcomes in the hospital of the patient can be predicted early, and doctors are helped to treat the patient as soon as possible.

The present invention discloses a bearing fault classification diagnosis method based on sparse representation and ensemble learning. The method comprises the steps of acquiring the vibration acceleration signals of a rolling bearing at different working rotating speeds via an acceleration sensor under each working condition as the training samples; selecting m training samples to form m sets of training data, establishing a weak classifier-graph regularization sparse representation model, and carrying out T times iterative operation on the graph regularization sparse representation; obtaining a classification function sequence via a weak classifier, then giving a weight to each classification function, and finally obtaining a strong classification function F by weighting a weak classification function; acquiring the vibration acceleration signal data of the to-be-tested rolling bearing at the rotation work via the acceleration sensor as a test sample; taking the test sample as the input quantity of the strong classification function to introduce in the strong classification function to operate, thereby being able to obtain a fault classification result of the to-be-tested rolling bearing. The method of the present invention enables the accuracy and the validity of the rolling bearing fault diagnosis to be improved.

The invention relates to a single lead electroencephalogram sleep automatic staging method based on Stacking, and belongs to the field of machine learning algorithms. The method comprises the steps that S1: sleep electroencephalograms are preprocessed; S2: multi-feature extraction and screening are carried out on the sleep electroencephalograms; S3: machine learning classification is carried out;S4: sleep automatic staging is carried out. The method can acquire a filtering method combining a wavelet function of a self-adaption threshold value and an IIR filtering function to conduct noise reduction processing on the electroencephalograms and effectively improve the signal to noise ratio of the electroencephalograms; a feature algorithm can be optimized and screened to acquire a new feature parameter set so as to take the new feature parameter set as a feature of sleep staging; a new multi-feature and integrated learning algorithm composition with high accuracy can be acquired and taken as the sleep staging method.

The present invention discloses a lane line detection method based on an integrated learning cascade classifier. By the method, the accurate position and direction information of the lane lines in an image can be real-timely obtained on a single CPU or DSP, so that a lane line equation is obtained, at the same time, a certain robustness about the brightness change of the traffic scenes is realized. The detection method comprises the steps of firstly, erecting an image sensor to obtain color images of which the lane lines need to be extracted; then extracting an interested area according to a detection result of the previous frame; and then calculating an integration graph and the LBP characteristic of a single scale block; then adopting the integrated learning to traverse the interested area to obtain the patches of the lane lines; after the patches of the lane lines are obtained, finally using an optimization-based method to obtain the lane line equation.

The invention discloses a video object tracking method based on a feature optical flow and online ensemble learning. The technical problem that tracking results of a tracking method of a specified object in an existing digital video are poor is solved. According to the technical scheme, the method comprises steps of inputting a tracking portion into a video sequence, tracking characteristic points of every frame through an iterative pyramid optical flow method by using functions of OpenCV, and obtaining positions of characteristic points of the next frame; selecting a positive sample or a negative sample to be subjected to adaboost algorithm processing for a detection portion; and conducting machine learning for possible object positions obtained by the tracking portion and the detection portion. A tracking feature extraction mode and a detection feature extraction mode are separated, the filtering for possible object position limitation is conducted during detection, possible objects which are far away from objects are removed, after tracking results and detection results are obtained again, the fisher discrimination ratio of objects and the online model is calculated in a self-adapting mode, the corresponding weight is determined, a fixed value is not used for fusing two results, and then the tracking effect is good.

Provided is a text categorization method based on an Xgboost categorization algorithm. According to the text categorization method, a characteristic value is calculated by extracting a tagged word through Labeled-LDA, and then text categorization is conducted by using the Xgboost categorization algorithm. Compared with a method that the text categorization is conducted by using a common categorization algorithm and a common vector space modal is adopted as characteristic space, the method reduces required consumed memory, this is because the number of words contained in a Chinese text is several million, dimensionality is high, if the words are adopted as characteristics, the consumed memory is massive, even one machine cannot conduct processing, however, the number of common Chinese characters is no more than ten thousand, the number of frequent Chinese characters is even two to three thousand, the dimensionality is reduced greatly, and meanwhile Xgboost supports input in a dictionary mode rather than an array mode. Besides, the invention provides a novel feature selection algorithm Labeled-LDA algorithm with latent semantic and supervision, the Labeled-LDA is adopted to conduct feature selection, and thus not only can semantic information of massive linguistic data be dug by utilizing LDA, but also class information contained in the text can be utilized. Furthermore, preprocessing is easy, there is no need to extract the characteristics carefully, and accuracy and performance of categorization are improved with the addition of the strong ensemble learning algorithm Xgboost supporting a distributed mode.