2113 results about "Study methods" patented technology

Disclosed is a base station of a wireless communications system including an adaptive antenna array and beam forming means for forming simultaneous multiple forward link beams. Preferably mobile stations are separated into groups of mobile stations corresponding to a maximum number of simultaneous forward link beams for determining which of said groups can be served by compatible simultaneous forward link beams. Preferably, if mobiles remain outside of a compatible group, the number of simultaneous forward link beams is increased and grouping of the mobile stations is repeated until all the mobile stations are included in compatible groups. Preferably simultaneous data beams are formed to mobiles of a said group during a time interval accorded to said group, such that every mobile station receives service data during a full cycle of said time intervals at a rate equal to or in excess of a target service data rate for that mobile.

The present invention provides a deep and reinforcement learning-based real-time online path planning method. According to the method, the high-level semantic information of an image is obtained through using a deep learning method, the path planning of the end-to-end real-time scenes of an environment can be completed through using a reinforcement learning method. In a training process, image information collected in the environment is brought into a scene analysis network as a current state, so that an analytical result can be obtained; the analytical result is inputted into a designed deep cyclic neural network; and the decision-making action of each step of an intelligent body in a specific scene can be obtained through training, so that an optimal complete path can be obtained. In an actual application process, image information collected by a camera is inputted into a trained deep and reinforcement learning network, so that the direction information of the walking of the intelligent body can be obtained. With the method of the invention, obtained image information can be utilized to the greatest extent under a premise that the robustness of the method is ensured and the method slightly depends on the environment, and real-time scene walking information path planning can be realized.

A dynamic learning method and an adaptive normal behavior profile (NBP) architecture for providing fast protection of enterprise applications are disclosed. The adaptive NBP architecture includes a plurality of profile items. Each profile item includes a plurality of profile properties holding the descriptive values of the respective item. An application-level security system can identify and prevent attacks targeted at enterprise applications by matching application events against at least a single profile item in the adaptive NBP.

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.

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.

Disclosed are systems, methods and computer-readable media for controlling a computing device to provide contextual responses to user inputs. The method comprises receiving a user input, generating a set of features characterizing an association between the user input and a conversation context based on at least a semantic and syntactic analysis of user inputs and system responses, determining with a data-driven machine learning approach whether the user input begins a new topic or is associated with a previous conversation context and if the received question is associated with the existing topic, then generating a response to the user input using information associated with the user input and any previous user input associated with the existing topic.

In various embodiments, the systems and methods described herein relate to generative models. The generative models may be trained using machine learning approaches, with training sets comprising chemical compounds and biological or chemical information that relate to the chemical compounds. Deep learning architectures may be used. In various embodiments, the generative models are used to generate chemical compounds that have desired characteristics, e.g. activity against a selected target. The generative models may be used to generate chemical compounds that satisfy multiple requirements.

A computer-implemented adaptive learning method is disclosed. The method is intended for performance within the context of a task being carried out by a user. At least one of a sequence of elements presented to the user as part of the task is designated as a learning item. A learning object is selected in dependence upon the designated learning item, information relating to previous performance of the learning method in relation to the user, and a predetermined scheme devised to manage an overall learning process for the user. Presentation of the selected learning object to the user is intended to advance the user's knowledge of the designated learning item in some way. Once the learning object has been presented to the user, the information is updated in dependence upon the presented learning object and/or how the user interacts with or responds to the presented learning object.

The present invention relates to the field of deep learning techniques, in particular to a deep convolution neural network training method and a device. The deep convolution neural network training method and the device comprise the steps of a, pretraining the DCNN on a large scale data set, and pruning the DCNN; b, performing the migration learning on the pruned DCNN; c, performing the model compression and the pruning on the migrated DCNN with the small-scale target data set, In the process of migrating learning of large-scale source data set to small-scale target data set, the model compression and the pruning are performed on the DCNN by the migration learning method and the advantages of model compression technology, so as to improve the migration learning ability to reduce the risk of overfitting and the deployment difficulty on the small-scale target data set and improve the prediction ability of the model on the target data set.

Providing methods and systems for a computer-aided group-learning environment, where a number of users can interact and work on a subject together. The system and method can monitor and analyze users' inputs. The analysis process can identify a user's performance on the subject, and can understand some of the user's traits, such as confidence level and learning attitude. The system can include an interaction controller, which sets a duration of time for the users to communicate in a dialogue environment. Working on the subject in a group and working alone can be intertwined. For example, the users first work on the materials generated individually, and then solve the problem together in a dialogue environment. During the dialogue session, the interaction controller can provide hints to the users. The system can also include a user registry, which restricts the users who can use the embodiment to work on the subject. The registry can receive potential user's characteristics to determine whether such user may be allowed to join the existing users to work on the subject. The registry can also access a summarized profile of the existing users to help the potential user make joining decisions. The system can also include a notepad for a user to take notes. The interaction controller can also guide the user to take notes.

Disclosed is a method of estimating repeatable runout (RRO) for a disk drive. The method includes: determining a plurality of position error signal (PES) values for a plurality of servo wedges of a track of a disk; and estimating repeatable runout (RRO) in the PES values for the servo wedges of the track by averaging determined PES values over a pre-determined number of revolutions of the disk of the disk drive and scaling the averaged PES values by a pre-determined ratio of the variance of non-repeatable runout (NRRO) to the variance of an optimal estimation of the RRO for the disk drive.

The present invention relates to ultrafiltration. In particular, the present invention provides nanoporous membranes having pores for generating in vitro and in vivo ultrafiltrate, devices and bioartificial organs utilizing such nanoporous membranes, and related methods (e.g., diagnostic methods, research methods, drug screening). The present invention further provides nanoporous membranes configured to avoid protein fouling with, for example, a polyethylene glycol surface coating.

Systems and methods are disclosed for automatically segmenting a heart chamber from medical images of a patient. The system may include one or more hardware processors configured to: obtain image data including at least a representation of the patient's heart; obtain a region of interest from the image data; organize the region of interest into an input vector; apply the input vector through a trained graph; obtain an output vector representing a refined region of interest corresponding to the heart based on the application of the input vector through the trained graph; apply a deformable model on the obtained output vector representing the refined region of interest; and identify a segment of a heart chamber from the application of the deformable model on the obtained output vector.

The present invention relates to biologically and behaviorally based methods of measuring audience response to a short stimulus.

Tomographic/tomosynthetic image reconstruction systems and methods in the framework of machine learning, such as deep learning, are provided. A machine learning algorithm can be used to obtain an improved tomographic image from raw data, processed data, or a preliminarily reconstructed intermediate image for biomedical imaging or any other imaging purpose. In certain cases, a single, conventional, non-deep-learning algorithm can be used on raw imaging data to obtain an initial image, and then a deep learning algorithm can be used on the initial image to obtain a final reconstructed image. All machine learning methods and systems for tomographic image reconstruction are covered, except for use of a single shallow network (three layers or less) for image reconstruction.

The invention belongs to the field of depth learning, and provides a rail surface defect detection method based on the depth learning network, aiming at solving various problems existing in the priorrail detection methods. The depth learning method first automatically resets the input rail image to 416*416, and then extracts and processes the image. Image extraction mainly by Darknet-53 model complete. The processing output is mainly accomplished by the FPN-like network model. Firstly, the rail image is divided into cells. According to the position of the defects in the cells, the width, height and coordinates of the center point of the defects are calculated by dimension clustering method, and the coordinates are normalized. At the same time, we use logistic regression to predict the fraction of boundary box object, use binary cross-entropy loss to predict the category contained in the boundary box, calculate the confidence level, and then process the convolution in the output, up-sampling, network feature fusion to get the prediction results. The invention can accurately identify defects and effectively improve the detection and identification rate of rail surface defects.

The invention relates to the technical field of traffic control and artificial intelligence and provides a traffic signal self-adaptive control method based on deep reinforcement learning. The method includes the following steps that 1, a traffic signal control agent, a state space S, a motion space A and a return function r are defined; 2, a deep neutral network is pre-trained; 3, the neutral network is trained through a deep reinforcement learning method; 4, traffic signal control is carried out according to the trained deep neutral network. By preprocessing traffic data acquired by magnetic induction, video, an RFID, vehicle internet and the like, low-layer expression of the traffic state containing vehicle position information is obtained; then the traffic state is perceived through a multilayer perceptron of deep learning, and high-layer abstract features of the current traffic state are obtained; on the basis, a proper timing plan is selected according to the high-layer abstract features of the current traffic state through the decision making capacity of reinforcement learning, self-adaptive control of traffic signals is achieved, the vehicle travel time is shortened accordingly, and safe, smooth, orderly and efficient operation of traffic is guaranteed.

A collaborative Web research method (and system), includes organizing a plurality of documents in a N-dimensional space according to a collection of subject words, and based on the organizing, retrieving, by a user, said documents organized in the N-dimensional space according to the collection of subject words.

The present invention discloses a deep learning method-based short-term traffic flow prediction method. The influence of the traffic flow rate change of the neighbor points of a prediction point, the time characteristic of the prediction point and the influence of the periodic characteristic of the prediction point on the traffic flow rate of the prediction point are considered simultaneously. According to the deep learning method-based short-term traffic flow prediction method of the invention, a convolutional neural network and a long and short-term memory (LSTM) recurrent neural network are combined to construct a Conv-LSTM deep neural network model; a two-way LSTM model is used to analyze the traffic flow historical data of the point and extract the periodic characteristic of the point; and a traffic flow trend and a periodic characteristic which are obtained through analysis are fused, so that the prediction of traffic flow can be realized. With the method of the invention adopted, the defect of the incapability of an existing method to make full use of time and space characteristics can be eliminated, the time and space characteristics of the traffic flow are fully extracted, and the periodic characteristic of the data of the traffic flow is fused with the time and space characteristics, and therefore, the accuracy of short-term traffic flow prediction results can be improved.

A machine learning device that learns an operation of a robot for picking up, by a hand unit, any of a plurality of workpieces placed in a random fashion, including a bulk-loaded state, includes a state variable observation unit that observes a state variable representing a state of the robot, including data output from a three-dimensional measuring device that obtains a three-dimensional map for each workpiece, an operation result obtaining unit that obtains a result of a picking operation of the robot for picking up the workpiece by the hand unit, and a learning unit that learns a manipulated variable including command data for commanding the robot to perform the picking operation of the workpiece, in association with the state variable of the robot and the result of the picking operation, upon receiving output from the state variable observation unit and output from the operation result obtaining unit.

Systems and methods create high quality audio-centric, image-centric, and integrated audio-visual summaries by seamlessly integrating image, audio, and text features extracted from input video. Integrated summarization may be employed when strict synchronization of audio and image content is not required. Video programming which requires synchronization of the audio content and the image content may be summarized using either an audio-centric or an image-centric approach. Both a machine learning-based approach and an alternative, heuristics-based approach are disclosed. Numerous probabilistic methods may be employed with the machine learning-based learning approach, such as naïve Bayes, decision tree, neural networks, and maximum entropy. To create an integrated audio-visual summary using the alternative, heuristics-based approach, a maximum-bipartite-matching approach is disclosed by way of example.

Disclosed herein are novel polypeptides and the nucleic acid sequences that encode them. Also disclosed are antibodies that immunospecifically bind to the polypeptide, as well as derivatives, variants, mutants, or fragments of the novel polypeptide, polynucleotide, or antibody specific to the polypeptide. Vectors, host cells, antibodies and recombinant methods for producing the polypeptides and polynucleotides, as well as methods for using same are also included. The invention further discloses therapeutic, diagnostic and research methods for diagnosis, treatment, and prevention of apoptosis associated disorders involving these novel human nucleic acids and proteins.

Methods of producing and/or analyzing spectroscopically labeled proteins, e.g., proteins site-specifically labeled with NMR active isotopes, spin-labels, chelators for paramagnetic metals, and the like, are provided. The labeled proteins are produced in translation systems including orthogonal aminoacyl tRNA synthetase/tRNA pairs. Methods for assigning NMR resonances, e.g., methods using isotopically labeled proteins, are also provided.

A teaching and learning method and system (143, 145, 147, 148, 152) communicates exercises, including URL's of Web pages and questions related thereto. Each exercise is distributed by the teacher's computer (143), synchronously, or downloaded by a student computer (147), asynchronously. An indicator (129) used on the Web page of one computer can be viewed on the same Web page displayed on the other computers. Responses are processed by the response server (145) and by comparison and evaluation logic, and displayed contemporaneously on the teacher's computer, together with scoring information (105, 106) and with URL's (107) associated with links used on each student computer. Scores are awarded automatically, or arbitrarily by clicking on the screen (105) of the teacher's computer. A feedback signal (80) may appear on the student computer with each keystroke to indicate its correctness. Responses selected on the teacher's computer may viewed on the student computers or on a Class Display (171).

The invention discloses a session emotion autoanalysis method based on depth learning and belongs to the natural language processing and data mining field. According to the method, voice and text expression is learned on the basis of a de-noising auto-encoder, further through a depth learning method, depth fusion of two types of expressions is realized to acquire unified high level expression, and emotion analysis is carried out on the basis of high level expression after fusion. Through the method, depth fusion of acoustic and text characteristics is realized, and emotion classification accuracy is improved.

Disclosed are an aberrant driving behavior monitoring and recognizing method and system based on a smart mobile terminal. Data are collected from a sensor, characteristic value data are extracted, then a characteristic value is trained through a machine learning method, a classifier model is set up, a driving behavior pattern is intercepted in the real-time monitoring process, and six kinds of aberrant driving behaviors are judged. Sidewinding driving, rapid turning, sideslipping, rapid U turning, sudden turning and sudden braking in the aberrant driving behaviors can be fast detected through the sensor of a smart phone. An experimental result shows that the mean total precision of the specific types of the aberrant driving behaviors recognized by the system is 96.20 percent.

The invention relates to the field of auxiliary medical diagnosis and aims to provide an auxiliary diagnosis system for interpreting medical image features based on the deep learning method. The system comprises the following steps of: reading medical image data of a lesion and preprocessing the medical image data; selecting an image, establishing a convolutional neural network architecture, automatically learning and segmenting a lesion area, and refining the shape of the lesion; constructing a CNN model of a convolutional neural network architecture to automatically interpret the characteristics of benign and malignant lesions, and acquiring an auxiliary diagnosis system for interpreting medical image features based on the depth learning method after training. The invention not only canautomatically divide the focus area by means of the depth convolution neural network, make up the deficiency that the weak boundary problem cannot be solved based on the active contour and the like, but also can automatically learn the characteristic combination extracted with the value, thereby avoiding the complex of manually selecting the feature.

The invention provides a deep question and answer method, which comprises the following steps of: 1, receiving question data; 2, carrying out a first retrieval in a knowledge base database, wherein the knowledge base database comprises factual information in encyclopedia; and 3, carrying out a third retrieval in a self-defining data set, wherein the third step comprises the steps of: 3.1, classifying the questions by a machine study method on the basis of a sentence pattern model set, and determining the sentence pattern mode of questions; and 3.2, obtaining second type keywords through the questions matched with the sentence pattern mode, and retrieving the self-defining data set through the second type keywords. Corresponding to the method, the invention also provides a medical retrieval system which comprises an input module, a first retrieval module and a third retrieval module, wherein the first retrieval module is used for retrieving the knowledge base database, the knowledge base database comprises the factual information in encyclopedia, and the third retrieval module is used for retrieving the self-defining data set.

A method and system for an internet-based online research solution through the comparison and contrasting of a potentially infinite number of subjects having defined attributes within predefined as well as dynamic subject contexts; a method and system for searching a potentially infinite number of subjects against a customized set of attribute-value configurations to arrive at an appropriate set of subjects for further research; a method and system for an online research solution by which the user efficiently researches online using a highly customized search, collation, and compilation of comparison-contrast information; a Universal Research Framework that may be embedded within any externally managed information system and which enables the above three methods to be performed within the specific system for research.

The invention relates to a content caching decision and resource allocation combined optimization method based on mobile edge computing in the Internet of Vehicles, and belongs to the technical fieldof mobile communication. The mobile edge calculation MEC is used as a foreground edge calculation, and has strong calculation capability and storage capability. The MEC server is deployed on the RSU side and can provide storage space and computing resources for vehicle users. Although the MEC provides services similar to cloud computing, the problems of caching, computing resource allocation, spectrum resource allocation and the like still exist. The method aims to maximize the network revenue under the condition of guaranteeing the time delay requirement. According to the method, a content caching decision, MEC server computing resource distribution and spectrum resource distribution are jointly modeled into a Markov decision process (MDP), a deep reinforcement learning method is used forsolving, and an optimal content caching decision, computing resource distribution and spectrum distribution are obtained.