3183results about How to "Improve learning efficiency" patented technology

The invention provides a simulation training device for manual arc welding rod-moving operation, and an arc welding rod-moving detection method, which is used for the introduction, improvement and enhancement training of welders in welding rod-moving operation. The device comprises a simulated welding torch, a simulated test plate, an image detection module, a dip-angle sensor, a master control computer and an evaluation system. Through the reasonable choice and layout of sensors and efficient data processing, high-precision detection and evaluation of real-time positions of simulated welding rods operated by the welders are realized. The device can record the arc striking, rod moving, ending and a series of operation of welding students during operation, and allows operation tracks to reappear after the operation is completed so as to improve learning efficiency and learning effects.

The invention provides an Internet teaching method and system for developing teaching activities through the Internet including a wireless communication network, and particularly discloses a method and system capable of recording the Internet teaching process in real time and accurately and efficiently storing the Internet teaching process in a cloud side. The method includes the step of evaluating educational document learning results by students to learn and distinguish learning situations of students of different levels, thereby achieving targeted differential teaching, tutoring, homework doing, exercising and the like and easily improving the learning efficiency and learning effect, especially continuously improving the students at different learning progresses. Furthermore, by means of a data return gateway, a data verification mechanism, a timestamp verification mechanism, an audio and video flow verification mechanism, a data complementary transmitting mechanism, a local fragmentation encrypting, storing and uploading mechanism and other means, recorded data is stored in the cloud side efficiently and accurately.

The invention provides an intelligent arrhythmia diagnosis method based on multiple-lead and a convolutional neural network. The method includes the steps that 1, data samples are selected; 2, arrhythmia types are labeled; 3, led heartbeat signals are intercepted; 4, a normalized heartbeat set is obtained; 5, a concealed layer and an output layer are constructed; 6, a target function is set; 7, sample training is conducted; 8, arrhythmias classification is applied. According to the intelligent arrhythmia diagnosis method, network learning efficiency and precision of automatic arrhythmia diagnosis can be improved by training the convolutional neural network (CNN) through multiple-lead electrocardiogram data, a universal frame and a specific method for training the CNN through the multiple-lead electrocardiogram data with arrhythmia type labels are achieved, the arrhythmia types of electrocardiosignals to be diagnosed can be accurately judged, and the arrhythmia types can serve as diagnosis results or as reference of doctors.

The invention provides a technical scheme for providing individualized learning for a user by using a learning system prestored with knowledge points of preset arrangement, corresponding knowledge contents and evaluation contents, and answers. The learning system provides the knowledge content and the evaluation content of each knowledge point for the user through the interaction with the user, analyzes the answer given by the user to the evaluation content through the preset answer, and determines the subsequent learning knowledge point for the user. The learning system provides different knowledge learning tracks and different learning contents for the users with different learning effects, thereby realizing the technical scheme of individualized learning. In addition, the learning system can record the whole learning procedure of each user, and helps the user effectively determine the knowledge points to be learned later. The recorded procedure information includes the error evaluation contents fed back by the user and can be convenient for providing the user to review at any moment, thereby improving the learning efficiency and the learning effect.

The invention discloses an interaction method based on a mobile classroom. Operation of a teacher end includes the steps that a teacher end logs into a system, selects a textbook, controls student ends, displays course content on a full screen, takes notes, underlines key points, records and uses an eraser on a page of the book needing to be explained, can add or delete labels on a certain page of the textbook, interacts with the student ends, evaluates students, releases knowledge points and finishes a class. Operation of the student ends includes the steps that the student ends log into the system, select the textbook and display the textbook on full screens, wherein the content displayed by the student ends and the content displayed by the teacher end are consistent; the student ends take notes and conduct other operation; the student ends check evaluation from a teacher after taking participation in interaction; the student ends resolve the knowledge points, and then the class is over. The teacher end can check online conditions of the students in real time and can control textbooks of the students, pages are turned according to the teaching process of the teacher, the concentration degree of the students in the class is improved, the students keep in step with the teacher, learning efficiency of the students is improved, and the teaching system has the teaching activity management function.

An online learning behavior analysis-based individualized learning recommending method comprises the following steps of 1 collecting the data, and obtaining the learner log data, the student score data and the student character data of an online learning platform; 2 extracting and mining the features; 3 preparing a dataset to train a BP neural network and testing the accuracy of a model; 4 utilizing the trained model to predict the scores of the new learners; 5 issuing the questionnaires to the learners, and collecting the questionnaire data; 6 carrying out the k-means clustering analysis on the questionnaire data; 7 combining the character features of the different learners to recommend the individualized learning methods. The present invention provides a BP neural network prediction method that is higher in prediction precision and can analyze the online learning time regularity of the learners more comprehensively. According to the present invention, the characters of the learners can be analyzed, and the individualized learning methods can be recommended to the learners.

The invention discloses an aircraft track prediction method based on a depth memory network. Firstly, the method extracts the historical aircraft track data and preprocesses the data to form an aircraft track information data sequence under a time sequence. On this basis, the input and output sample characteristics are constructed, and the samples are standardized to generate dimensionless training data set. Then, the attention mechanism model is integrated into the long-term and short-term memory network structure, and the structural parameters are initialized to construct the track prediction neural network. Finally, the track prediction network is trained and optimized, and the track prediction network model with high prediction accuracy is obtained.

The invention relates generally to a system and methodology for learning, and in particular for practicing for tests. The system and method employs algorithms for performing various analytics. A computerized system analyzes Meta-Data associated with the Tests, Questions and the learner / student response to those and provides information which helps the learner / student learn faster, get a deeper understanding of the subject area and helps them focus and practice for the subject area of needs. As the data for a student is collected the system can analyze the core strength and weakness of student for the subject, topic or subtopic etc. and in various other dimensions. Additionally as data from multiple students is aggregated the methodology defines the mechanism to analyze and quantify the outcome from three areas of learning namely, the learner effort, an instructor effort and the quality of learning contents. Such a meta-data based learning methodology greatly reduces the potential for guess and subjective analysis and improves the learning of an individual based on the quantifiable data, either at the user choice or being driven by the system recommendation.

The invention discloses a cloud data center load prediction method based on LSTM (Long Short-Term Memory), and aims to solve the problem that optimal utilization can not be obtained by the limited calculation resources of a cloud data center. The method comprises the following steps that: taking the mass historical records of the cloud data center as a basis to manufacture a training sample and atesting sample; in addition, constructing a neural network connected by LSTM units; continuously inputting training samples on batch to obtain an output value. A neural network optimization algorithmadopts a new adaptation moment estimation method, parameters in each unit are continuously updated through iterative training, and global optimum is realized after training is finished, only the testing sample needs to be input into the network to obtain the next prediction value of a sample sequence; and if an input sequence is continuously updated by the prediction value, a prediction value sequence in one future period of time can be obtained.

The invention discloses a Fast R-CNN-based pavement traffic sign identification method. The method comprises the following steps of: carrying out image acquisition and preprocessing, and making a sample set; inputting a training set and carrying out multi-task training on a Fast R-CNN network; enabling a to-be-identified picture to pass through a plurality of convolutional layers and pooling layers so as to obtain a feature map; obtaining a corresponding feature frame from candidate frames, and respectively obtaining two output vectors: a classification score and window regression, through an ROI pooling layer and a total connection layer; and carrying out non-maxima suppression processing on all the results to generate a final target detection and identification result, so as to identify traffic signs. According to the method, a Fast R-CNN deep learning method is adopted, so that a redundant feature extraction operation in a regional convolutional neural network R-CNN is avoided, multi-task training is realized, an extra feature storage space is not required, and the detection speed and precision are improved. Compared with shallow-layer learning classifiers, the method has higher learning efficiency and identification precision.

The invention relates to a three-dimensional model retrieval method based on multi-feature relevance feedback, comprising the following steps: a server processes each three-dimensional model in a three-dimensional model database to obtain color view arrays; three-dimensional model features are acquired and synthesized to generate a feature database; features of a two-dimensional sketch offered by a computer client are calculated and matched with feathers in the feature database, the distance between the two-dimensional sketch and each three-dimensional model is calculated, the three-dimensional models as a retrieval result are sorted and outputted according to the distance values; the client labels each retrieval result with 'relevance' or 'irrelevance', returns labeled three-dimensional model information to the server, the server learns the information, classifies the three-dimensional database by SVM fusion method, sorts and outputs the three-dimensional models as a retrieval result; the above steps are repeated until a satisfactory three-dimensional model retrieval result is outputted to a user.

The invention relates to a method and a system for network protocol recognition based on tri-classifier cooperative training learning. The method comprises the following steps: carrying out IP (Internet Protocol) regrouping and TCP (Transmission Control Protocol) traffic reduction on network original traffic, and stipulating the unit of network data from original packets to flow; extracting each message of unidirectional flow feature information and vectoring to build a feature matrix; building a tri-classifier cooperative training classifier with few identified samples; judging whether a classifying model of an analyzed protocol exists or not, and utilizing a tri-classifier cooperative training learning method to build a protocol classifier if the classifying model does not exist, otherwise, judging the protocol attributes of data packets; training by a tri-classifier cooperative training learning algorithm based on J48 and obtaining the classifying model of the analyzed protocol; carrying out protocol type judgment on network data packets not identified, and outputting two classes of results: one class refers to the network data packets belonging to the target protocol, and the other class refers to network data packets not belonging to the target protocol. High recognition accuracy and high recalling rate are ensured by the method.

A cable damage localizing method for a cable-stayed bridge on the basis of improved back-propagation neural network is disclosed. The invention has the method that a BP neural network can be improved effectively based on how to effectively perform, thus a cable damage localizing of a cable-stayed bridge is carried out, and therefore, the cable damage localizing method for the cable-stayed bridge with the improvement is established. The invention proposes to improve traditional BP algorithm jointly with Bold Driver technology, momentum item increase, simulated annealing algorithm and random hill-climbing algorithm. The cable damage localizing method has the advantages of accelerating convergence, improving learning-efficiency improvement and preventing the learning process from falling into local minimum and, in addition, the invention can reasonably determine network topologies.

The invention discloses a nutrient meal-following food and a producing method thereof. The nutrient meal-following food is characterized by comprising the following components in parts by weight: 0.5-1.5 parts of polished round-grained rice, 0.5-1.5 parts of white rice, 0.5-1.5 parts of black rice, 0.5-1.5 parts of barley, 1.5-2.5 parts of buckwheat, 0.5-1.5 parts of wheat, 1.5-2.5 parts of oats, 1.5-2.5 parts of coix seeds, 1.5-2.5 parts of millets, 1.5-2.5 parts of corns, 1.5-2.5 parts of broomcorn and 1.6-2.4 parts of sesames. The producing steps are as follows: (1) mixing and cleaning the raw materials, and then soaking the mixture for 8-12 hours (2) steaming the raw materials thoroughly and then airing the raw materials to 30 DEG C; (3) adding fermentation strains and the raw material soaking water in the step (1) into the raw materials in the former step and mixing uniformly; (4) fermenting at a constant temperature of 30 DEG C for 30-35 hours; (5) repeating the step (3); (6) fermenting at a constant temperature of 30 DEG C for 24-30 hours; (7) grinding the well-fermented raw materials into paste; (8) drying the paste into powder and packaging the powder in a sealing manner. The nutrient meal-following food has rational allocation, results in no digestion discomfortableness to the intestines and stomach as the surfaces of the coarse grains are softened through biological fermentation, and is better for the absorption of an organism as the plant cell walls are destroyed by enzymes under the action of microorganisms.

The invention belongs to the technical field of intelligent auxiliary driving for vehicles and vehicle safety and particularly relates to a learning cruise control system and method used for a drivingstyle and based on mode switching. By means of the system and method, self-adaption cruise control is conducted through mode switching of a special driver style and self-adaption learning for the carfollowing behavior. According to the system and method, the driving style is defined to be switch strategies of a cruise control mode, an acceleration approach mode, a steady-state car following modeand a quick braking mode of a driver under different car following conditions, the driving style of the driver is learned, and the driving characteristic of the driver is further learned through a learning method based on a continuous state under each driving mode. The system is suitable for automatic driving of an L2-level vehicle, the aim is to effectively learn the driving style characteristicof the driver, and the adaptability and acceptability of the specific driver for the self-adaption cruise system under different working conditions are improved.

System and method for a learner interaction process comprising receiving information regarding one or more learners, receiving information regarding the educational material that the one or more learners would like to learn, presenting more than one question regarding the educational material prior to presenting the educational material to the one or more learners, receiving answers to the more than one questions presented to the one or more learners, presenting the educational material to the one or more learners, identifying the amount of time the one or more learns reviewed the educational material, presenting and receiving answers to more than one question regarding the educational material that the one or more learners has reviewed after the educational material has been presented to the one or more learners, and determining whether the one or more learners learned the educational material presented based on the one or more learners answers to the questions.

The invention discloses a road surface traffic sign recognition method based on a convolution neural network, and the method comprises the following steps: image collection and preprocessing; and convolution neural network structure design and training. The method employs a V-parallax method to obtain a road surface area from an original image, can reduce the impact caused by non-road-surface interference, and improves the extraction precision of a road surface area. The invention employs a vertical view to reconstruct the road surface area, enables unparallel lines, presented in a visual image because of a view angle, to be reconstructed into approximately parallel lines, facilitates the recognition of a road surface traffic sign, and improves the capability of adapting to view angle inclination. The method the deep learning method (convolution neural network), can extract recessive characters reflecting the data essence from a large number of training samples. Compared with a shallow-layer learning classifier, the method is higher in learning efficiency and recognition precision.

The invention discloses a learning method and system based on wrong problem analysis. The method comprises the following steps: analyzing wrong problem information as the wrong problem information is received, so that an analysis result is obtained, wherein the analysis result includes wrong knowledge points and wrong type; generating a learning plan according to the analysis result; acquiring learning contents according to the learning plan; and pushing the learning contents. The learning method and the system disclosed by the invention, which generate the learning plan by analyzing the wrong problem information of a student and push the learning contents according to the learning plan, can promote the student to develop a good learning habit and to improve learning capacity and learning efficiency.

The invention relates to a personalized learning method and a personalized learning device which can be used for educational electronic products. The learning device comprises an answering unit, a matching unit and a recommending unit, wherein the answering unit is used for receiving question content and searching corresponding knowledge points in a preset database according to the question content, the matching unit is used for searching and providing corresponding exercise content in the preset database according to the knowledge points, and the recommending unit is used for receiving answering content that corresponds to the exercise content and performing statistical calculation on the knowledge points according to the answering content so that learning content can be recommended according to a statistical result. According to the personalized learning method and learning device, classroom learning content is divided into a plurality of knowledge points, a simplified, independent and personalized learning scheme can be recommended according to question conditions in allusion to each knowledge point, spare time of students can be fully utilized and learning questions are centralized and solved one by one, and the learning efficiency of the students is greatly increased.

The invention discloses a subject evaluation system and method based on a knowledge point system. The subject evaluation system and method based on a knowledge point system comprise a database module, a knowledge point selection module, a quiz evaluation module and a stage-passing grade module, wherein the database module comprises a quiz unit and a knowledge point unit; the quiz unit comprises a quiz sub unit, a quiz analysis sub unit and a quiz difficulty level sub unit, and is used for selecting questions for a test and automatically judging the test performance when a student submits the questions; each test question of the quiz sub unit is related with one or more knowledge points in the knowledge point unit; the knowledge point selection unit comprises a chapter selection unit, a blind test, a difficulty selection unit and a quiz generation unit; and the quiz evaluation module is used for evaluating the test paper completed by the student and the situation about mastering of knowledge points. The subject evaluation system and method based on a knowledge point system forms an objective and reasonable evaluation reference for learning and mastering of knowledge points for students, and provides an accurate basis for 'what to practice' for students so as to comprehensively improve the learning efficiency.

The invention discloses a pushing method and device for learning resources. The method includes the steps that through learning operation performed on a learning machine by a user, user learning information is collected, stored and analyzed, the learning speed and / or interest trend of the user is obtained, and according to the learning speed and / or interest trend, the matched learning resources are obtained and provided for the learning machine of the user. The learning resources can be pushed in a targeted mode according to learning progresses and characteristics of the user himself, so that the utilization rate of the learning resources and learning efficiency of the user are improved.

A car driver driving skill practice guiding an examination scoring device comprises a core plate and an interface baseplate connected with the core plate, wherein the core plate comprises a DSP digital processing unit, an embedded MCU micro-controller, a program storage, a data storage and interface connector plugins; the DSP digital processing unit and the embedded MCU micro-controller are taken as the center namely a hardware platform of the device; the DSP digital processing unit is responsible for processing digital audios and digital video so as to obtain state data required by movement locus of an examination vehicle and other information; the embedded MCU micro-controller provides an operation platform for an operating system; and in addition to the interface connector plugins, interfaces containing corresponding interface circuit devices are also arranged on the interface baseplate. A realization method for car driver driving skill practice guiding an examination scoring, by means of the device, can improve the reliability of measurement data of the actual position of the examination car. Therefore, the integration level of functions of the vehicle-mounted equipment is improved, and the purchase and the maintenance cost for the customer are lowered.

The invention discloses a hyper-spectral remote sensing image classifying method based on AdaBoost. A traditional mode identification method cannot meet the requirements of carrying out high-efficiency and high-precision classification on hyper-spectral data with high data dimensions and great data quantity; and although a neural network and a support vector machine can effectively classify remote sensing data, an ideal selection method of parameters does not exist. The hyper-spectral remote sensing image classifying method based on the AdaBoost comprises the following steps of: pre-processing the hyper-spectral data to remove abnormal wave bands influenced by factors including atmosphere absorption and the like; then utilizing MNF (Minimum Noise Fraction) conversion to carry out wave band preferential selection to achieve the aims of optimizing data, removing noises and reducing dimensions of the data; then, dividing a training sample and a test sample; selecting a decision stump as a weak classifier and utilizing an AdaBoost algorithm to train the weak classifier to obtain a strong classifier; selecting suitable iterations; and finally, utilizing a one-to-one method to establish a plurality of the classifiers. According to the hyper-spectral remote sensing image classifying method based on the AdaBoost, the convergence rate is enhanced and the classification performance of a hyper-spectral image is improved.

There is provided a remote data transmission system that includes a hand-held remote device including a camera, a camera button, a wireless communication device for transmitting data obtained by the camera, and a storing device having one or more operating programs; and a computer comprising a display device, wherein the hand-held remote device obtains image data of an object and transmits the image data to the computer when the camera button is pressed, wherein the computer receives data from the hand-held remote device and displays the data on the display device, and wherein the computer displays the image data on the display device upon receipt of the image data.

Disclosed in the present invention are an ultrasound-assisted scanning method and system. On the basis of generating a real-time ultrasound image, carrying out matching operations on the acquired real-time image and the library image in the image library, so that the correctness of the current scanning operations is immediately fed back to the user. The method can further output image-text help information according to a matching result. If the current real-time image is the standard section image of an tissue or an organ, the relevant image-text information of the standard section is automatically exported, thereby improving the ease of the operations. If failing to obtain the standard section image, prompting the user on how to adjust the position of the probe, thereby quickly and accurately obtaining the desired image. The method and system of the present invention improve the user interaction and user guidance, and can significantly improve the assisted scanning effect.

The invention discloses a multi-unmanned aerial vehicle task decision method based on MADDPG, which introduces an MADDPG algorithm into multi-unmanned aerial vehicle task allocation, and comprises thesteps of firstly establishing a two-dimensional combat environment model required by deep reinforcement learning according to the actual combat environment of multiple unmanned aerial vehicles, secondly establishing mathematical description of various threats such as air defense missiles in the combat environment of the multiple unmanned aerial vehicles, and finally, taking the tracks and distances of the multiple unmanned aerial vehicles and the defense threats of the battlefield as constraint conditions, and performing learning training to obtain a multi-unmanned aerial vehicle task decision model. According to the method, an experience pool and a double-network structure are adopted, so that the operation and convergence speed of the whole network is greatly improved, a result can be obtained more quickly in the high-speed flight process of the unmanned aerial vehicles, the purpose of autonomous decision making of the multiple unmanned aerial vehicles can be achieved, and the highefficiency of task decision making of the unmanned aerial vehicles can also be guaranteed in an unknown combat environment.

The invention discloses a knowledge-based electronic medical record quality control method. The method includes: by a closed loop type design structure, designing and making quality control semantic judgment rules and inputting time limit rules in an initial stage; allowing middle-stage data to enter a mobile terminal taking Raspberry Pi as a key design, wherein an analysis module combined with the NLP (natural language processing) natural language learning technology is embedded in the terminal; after quality control is finished, uploading synchronous data to a data center for storage and management; by the data center, acquiring common templates in medical record data by means of big data analysis, establishing an error correction knowledge base, and designing and constructing a database and an integrated environment to realize data sharing with internal modules of an error detection quality control terminal. By adoption of the knowledge-based electronic medical record quality control method, data of the data center are sampled and inspected regularly to further guarantee data correctness. Therefore, error detection, integration and analysis of structural medical record data can be realized, mass data and artificial intelligence processing technologies under an intelligent medical environment are utilized completely, medical record quality control cost is reduced, construction of the error correction knowledge base is realized, and quality control algorithm and rule quality is improved.

A learning system with reviewing function comprises databank of question bank, collection module, query module, processing module and statistic module. The said system is featured as enabling to classify and collect knowledge points relating to wrongly answered examination questions and providing these knowledge points to user as reference for raising efficiency of learning.