1624 results about "Training effect" patented technology

The invention discloses a track traffic simulation system. The track traffic simulation system comprises an ATC (Automatic Train Control) simulation system 11, a train driving simulation system 12 and a dispatching simulation system 13, wherein the ATC simulation system 11 is connected with the train driving simulation system 12 and is used for reappearing the control and the running rule of a real train according to a first mathematic model and carrying out driving training on a driver by combining the dynamic demonstration of a three-dimensional scene; the ATC simulation system 11 is connected with the dispatching simulation system 13 through a gateway computer and is used for reappearing the control and the running rule of a real ATS (Automatic Train Supervision) system according to a second mathematic model and carrying out dispatching training on a dispatcher by combining interactive operation of behavior simulation of the driver. According to the track traffic simulation system disclosed by the embodiment of the invention, the ATC simulation system, the train driving simulation system and the dispatching simulation system are integrated, the combination of the train driving training and the dispatching training is realized, the simulation degree is increased, and thus the training effect is enhanced.

The invention discloses an intensive learning based urban intersection passing method for a driverless vehicle. The method includes a step 1 of collecting vehicle continuous running state informationand position information through a photographing method, the vehicle continuous running state information and position information including speed, lateral speed and acceleration value, longitudinal speed and acceleration value, traveling track curvature value, accelerator opening degree and brake pedal pressure; a second step of obtaining characteristic motion track and the velocity quantity of actual data through clustering; a step 3 of processing original data by an exponential weighting moving average method; a step 4 of realizing the interaction passing method by utilizing an NQL algorithm. The NQL algorithm of the invention is obviously superior to a Q learning algorithm in learning ability when handling complex intersection scenes and a better training effect can be achieved in shorter training time with less training data.

The invention discloses a gas station virtual training system which comprises a three-dimensional drive engine module, a scene database module, a data glove drive module, a helmet-mounted display drive module, an accident three-dimensional rendering module and an exam estimation module. The gas station virtual training system based on hardware interaction, disclosed by the invention, virtualizes the real hardware equipment and the three-dimensional drive engine module by use of a pair of data gloves, a position tracker and the like to generate a vivid gas station virtual scene and a typical accident scene; and a trainee can actually finish standard operation simulation and accident emergency virtual training so as to improve the reality and training effect of virtual training of the gas station staff.

The invention relates to an assembly digital field based on a flexible array pressure sensor and a method for training gait. Parameters of an athlete including action time sequence, action frequency, position calibration, stress center point, stress time and flight time can be acquired through acquiring information including pressure of foot soles of the athlete contacted with the flexible array pressure sensor unit in the assembly digital field. The digital field and the method have the advantages that the requirement of real time can be met in longer distance; the module of the assembly digital field can be disassembled and assembled arbitrarily, and can extract gait characteristics on multiple sports training events; and the athlete can correctly recognize the training effect of the athlete self through a sports effect evaluation system and an expert system, and adjust the training plan in real time. The digital field and the method can also be applied in the field of mode recognition.

Featured is a method and device for increasing learning and effects of training. Such methods include locating a pair of electrodes on a head of a person in relation to a specific area of the brain, applying a desired DC current to the electrodes at a level sufficient to stimulate the brain tissue; and controlling the DC current application so the current is applied to the specific brain area at least one of before, during or after such a learning or training event. In this way, application of the DC current to the brain area improves a subject's ability to acquire one of motor skills or knowledge of the learning or training event or the ability to retain the motor skills or knowledge of the learning or training event. The person to which the electrodes are attached can be healthy or a patient after brain lesions.

The invention discloses a mine virtual reality training system based on immersion type input and output equipment. With the system, a trainee can be completely immersed in the virtual scene, and carries out man-machine interaction with the virtual training scene through natural methods including gestures, walking and running, and the like, so as to complete the preset training program. The system is composed of output equipment such as a head-wearing display, an omnidirectional running machine, output equipment such as a motion capturing device, a computer, and matched training software, wherein the head-wearing display can provide complete vision immersion experiences, and the omnidirectional running machine and the motion capturing device map the movements of the trainee in the reality on a virtual object in the virtual scene, and operate the system through the natural interaction method. Compared with the traditional training method, the training system provided by the invention enables the trainee to be immersed in the virtual mine environment close to the reality at any place, and obtain the training experiences the same as those obtained in the scene, and finally, the effect comparable with the on-site training effect is obtained.

The invention relates to a speech interactive training system and a speech interactive training method. The system comprises a user selection module, a speech interactive training module, a user feedback module, a speech evaluation module and a result feedback module, wherein the user selection module is used for acquiring training contents selected by a user; the speech interactive training module is used for displaying the training contents to the user in a multimode guiding mode to guide the user to perform a speech training; the user feedback module is used for collecting a fed-back speech and a lip video corresponding to the speech; the speech evaluation module is used for receiving the speech fed back by the user and the lip video corresponding to the speech, and automatically evaluating the speech training of the user and giving an evaluation result; and the result feedback module is used for feeding the evaluation result back to the user so that the user can correct and adjust the speech training. The speech interactive training system is used for automatically evaluating the speech training of the user, giving the evaluation result and feeding the evaluation result back to the user, and then the user finds out the level of the personal speech training according to the evaluation result and corrects and adjusts the personal speech training to further improve the speech level, so the rehabitation training effect of a speech impediment is greatly enhanced.

The invention relates to health monitoring sneakers based on flexible array pressure sensor and a health monitoring method thereof, which acquire parameters of a user including walking distance, pace, frequency and energy consumption through acquiring information of sole pressure in a walking process. The sole pressure information is transmitted to a multifunctional wristwatch through a wireless communication mode for processing, storing and displaying; the multifunctional wristwatch also has the functions of pulse detection, body temperature detection and children safety custody; data stored in the multifunctional wristwatch is transferred to a computer client through USB; software of the computer client can perform data exchange with software of a master server; and the user can obtain training effect evaluation and exercise planning. The sneakers and the method can carry out health monitoring on the user through information including pulse, body temperature and sports parameters.

A control system of exercise apparatuses for aid in group training includes a primary electronic control console and several secondary electronic control consoles. A control software program, a message transmitter and a message receiver are installed in each of the electronic control consoles of the same exercise apparatuses for controlling the exercise apparatuses and recording the operation status thereof. They are regarded as a basic electronic control equipment. The primary electronic control console can receive all exercise messages transmitted from all of the secondary electronic control consoles. Thereafter, the exercise messages can be clearly displayed on a data display zone of a display. At the same time, the control instructions will be transmitted to each of the secondary electronic control console by use of an external control keyboard, the message transmitter, and the message receiver. In this way, the exercise resistance level of the exercise apparatuses can be remote-controlled, thereby achieving the expected training effect and ensuring the training safety.

The invention discloses a detachable platform-type bicycle exercise trainer, which comprises a support frame of the trainer and a bicycle. The front tire holder and the rear tire holder are respectively provided with an arc structure. The front tire holder and the rear tire holder are respectively used to drive the tire to rotate and can be used to brake the wheel. The front and/or rear raised lifting drive mechanism is also provided with a turntable under the front tire holder, and a monitor, a central processing unit, a monitor and a VR worn by the trainer's eyes are arranged on the vertical direction of the L-shaped support frame. The output signal of the vision device is adapted. The detachable platform bicycle exercise trainer has the characteristics of simple structure, widely applicable to fitness exercises of various groups of people, good training effect, real simulation effect, economical and durable, and the like.

Disclosed is an inclination-adjustable golf training device capable of optionally changing the inclination of its platform, on which a player stands to practice his golf swing, in order to simulate the condition of a real golf course, thereby obtaining an enhanced training effect. The golf training device includes an upper plate assembly, to which a ball supply unit and a controller are internally mounted, the upper plate assembly including an upper plate, on which a player stands to practice his golf swing, a lower plate assembly adapted to support the upper plate while being spaced apart from the upper plate, a vertical reciprocating unit mounted on the lower plate assembly while including driving and driven parts operating to adjust the inclination of the upper plate with respect to the lower plate assembly in all radial directions. The vertical reciprocating unit has four operating points for reciprocation arranged on a circle about the center of the upper plate while being uniformly spaced from one another in a circumferential direction, the operating points being arranged in pairs so that the operating points of each operating point pair are opposite to each other while performing vertical movements of the upper plate in opposite directions by the same distance.

The invention relates to live working table type simulation training system and method. The system comprises a data server and a table type training machine which are connected by a WAN (Wide Area Network), wherein the data server is provided with a server management system; the server management system is provided with a plurality of management modules which are divided into a user information management module, a live working simulation working management module, a tool and project data management module, an examination and score management module and a database management module according to the managed content; the live working training is carried out on a training staff by applying the live working table type simulation training system, and the training form is divided into a stand-alone training form and a network training form; and the stand-alone training form is carried out by adopting a stand-alone table type training machine and the data server, and the network training form is carried out by adopting a plurality of table type training machines and data servers through WAN interconnection. The system has simplicity, practicability and convenient operation and can effectively reduce the training cost; and the method has strong pertinence, systematicness and good training effect.

The invention discloses a wheelchair device which can help a patient to perform lower limb rehabilitation training, can achieve adjustment of three postures, and can be applied to the field of medical rehabilitation apparatuses. The lower limb rehabilitation wheelchair includes a flexible adjustment mechanism arranged on a chair back, a three-posture adjustment mechanism which is arranged on a base and is fixedly connected to the chair back, a leg mechanism which is fixedly connected to a three-posture adjustment frame, and a leg auxiliary support system. A step function section is driven by a push rod, and bionics steps of human body natural walking are simulated through a preset program to achieve a training effect. The leg auxiliary support system can support legs in a seat posture through coordination of bevel gears, screw rods and support plates, and can automatically move backward in a stand posture and will not affect the legs. The chair back adjustment mechanism has the function of multi-dimension automatic flexible adjustment, and can adjust the chair back according to the demands of a user. The three-posture adjustment mechanism can adjust a stand posture, a seat posture and a lie posture. The lower limb rehabilitation wheelchair can provide various posture training manners.

The invention discloses a multi-pose lower-limb rehabilitation robot and a use method thereof, and belongs to the field of medical apparatuses. The rehabilitation robot comprises a pedestal, a liftingmechanism and a bed body which are arranged sequentially from bottom to top; a pair of thigh training mechanisms and a pair of leg training mechanisms are symmetrically arranged on the two sides of the bed body correspondingly; the thigh training mechanisms and the leg training mechanisms are used for performing lower-limb rehabilitation training on a patient whose lower limbs have dyskinesia; the patient is subjected to lower-limb rehabilitation training by multiple modes; furthermore, the bed body and a seat cushion are overturned, so that training of three poses of sitting, lying and standing can be realized, the training mode is comprehensive and the training effect is good. By the method adopting the multi-pose lower-limb rehabilitation robot, the training effect is excellent.

The invention provides a scene device for Chinese learning training based on artificial intelligence and virtual reality. The scene device comprises a virtual reality device, an expert system based on the artificial intelligence, a spoken language training module and a Chinese character training module. The virtual reality device comprises a pair of helmet type 3D glasses, a 3D displayer, a virtual electronic pen, a brain wave inductor, a touch screen, a camera and a computer host. According to the scene device, the mood state and the identity information of a trainer are obtained through a face recognition sub-module, whether the trainer focuses attention or not is judged through a brain wave recognition sub-module, guidance training is carried out on the trainer through the cooperation with the artificial intelligence algorithm, and intelligent evaluating and intelligent error correction are particularly carried out through the spoken language training module with the cooperation of the psychological states and the language environment moods of the trainer. Intelligent evaluating and intelligent error correction are carried out through the Chinese character training module with the cooperation of the psychological states and the language environment moods of the trainer, therefore, in the training interactivity is accordingly improved, a feedback type training mode is used in the scene device, and finally the training effect on the trainer is improved.

The invention provides a use method of a fire extinguishing training analog system of a naval vessel. The method includes the following steps: step A, setting fire information in a training process according to a training plan demand by group trainers; step B, designing the training plan according to the information collected in step A by the group trainer; step C, performing analog fire extinguishment training by trainee; step D, a center control host controlling a heater on the training clothes to heat according to the parameters set in the step B; step E, the center control host comparing fire extinguishment position image information corresponding to an analog extinguisher with the on-fire goods information set in the step B, and step F, the group trainer judging the training effect of the trainee. The invention provides the use method of the fire extinguishing training analog device. The fire extinguishing training analog system provided by the invention can be used for implementing special training which cannot be implemented in real naval vessel environments and a common simulator and has comprehensive training content.

The invention provides a wearable lower limb rehabilitation training device which comprises a base, a column, a waist bracket, knee-joint motion control units and hip joint motion control units, wherein the column is installed on the base, the waist bracket is installed at the top of the column and is provided with two protective frames, each protective frame is provided with the hip joint motion control unit and the knee-joint motion control unit, each hip joint motion control unit comprises a hip joint motor, a thigh rod, a thigh connecting rod, a thigh driving rod and a thigh layer board, and each knee-joint motion control unit comprises a knee-joint motor, a shank rod, a shank connecting rod, a shank driving rod and a pedal. The upper end of the shank rod is connected with the thigh rod through a thigh joint shaft. The device can realize lower limb rehabilitation training of patients or the old, improve a training effect, and further improve the comfort level of a user. Meanwhile, the device can be suitable for crowds in different body types by adopting a leg length, height and width adjusting mechanism.

The invention generally relates to a retrofit kit for a training device and to a training device. The training device includes a moving actuating element via which a training force produced by an individual who is training can be introduced into the training device. The training device also includes a force producing device via which a counterforce that works against the training force can be produced by a training weight. The training weight can be composed of one or more individual weights. In order to increase the training effect of the training device, an oscillation producing device is provided via which an oscillation can be produced that influences and modulates the counterforce. The oscillation producing device is provided in the form of an individual weight.

The invention discloses a target system based on actual combat countermeasure training. The target system comprises a commanding subsystem, an attack and defense training site control subsystem, an intelligent target subsystem, multiple single-soldier equipment subsystems and an observation subsystem. The intelligent target subsystem comprises multiple intelligent targets, and the commanding subsystem is connected with the intelligent target subsystem and the single-soldier equipment subsystems in a wireless communication mode. The invention further discloses an exercise method of the target system based on actual combat countermeasure training. Through setting the intelligent targets, actual combat of countermeasure training is achieved, the training effect of shooting exercise is effectively improved, and the tactics skill and combat capacity of troops are improved.

The invention provides a shooting training system and a shooting training method. The method includes the steps of obtaining the shooting point position and the aiming direction, detected by a first sensor, of a weapon and obtaining the shooting environmental condition detected by a second sensor; on the conditions of the shooting point position, the aiming direction and the shooting environmental condition, predicting an estimated shooting point position, located on a target, of a shot object shot by the weapon according to a shot article track model, established in advance, of the weapon; and reminding a shooter of the estimated shooting point position. According to the shooting training system and the shooting training method, the shooter, the weapon and the target do not need auxiliary devices such as sensors, the shooting training scene can be similar with the actual shooting scene, the shooting training procedure can be simplified, the shooter can use the system conveniently, the user experience of the shooter can be improved, and the training effect of the system can be improved. In addition, historical shooting data of the shooter can be used for assisting in shooting training of the shooter and providing personalized shooting training.

The invention discloses a multi-discriminator error back propagation confrontation network method, and belongs to the depth learning nerve network field; a model is built by the following steps: S1, constructing a formation confrontation network GAN model; S2, constructing a plurality of discriminators on the existing GAN model basis; S3, preparing a data set so as to train an improved multi-discriminator network; S4, recording all discriminator loss functions in each training process; S5, calculating the average value of all discriminator loss functions, and returning to a generator so as tocarry out follow up network training. A single discriminator may cause the network poor robustness problems in the network training process; the method can solve said problems, and can form the multi-discriminator formation confrontation network, thus evaluating the true and false of generator formed images from a more objective angle, and providing better training effect of the whole formation confrontation network.

The invention relates to a deep license plate detection method based on a thermodynamic diagram and key point regression. The method includes an off-line learning phase and a detection phase. The off-line learning phase includes the following four steps of: (1) designing network depth; (2) preparing a training sample set; (3) performing sample labeling; and (4) performing training. According to the step (1), a deep learning network structure is designed, inputted images are adjusted and unified, first-layer convolution and activation function operation are performed on the images, second-layerconvolution and activation function and pooling operation are performed, and third-layer convolution and activation function and pooling operation are performed, and a plurality of task branches areformed, one branch learns the coordinates of plate number plates through one convolutional layer, another branch learns the thermodynamic diagram of the license number plates through another convolutional layer. According to step (2), a batch of vehicle front or rear images is obtained and adopted as a sample set for offline learning, and the larger the total number of the classes of samples is, the better a training effect is, and the sizes of the samples are normalized. According to the method, the offline trained deep network is adopted to characterize a target, and therefore, license platedetection can be performed on the target quickly and steadily.

The invention discloses a method for detecting an abnormal user of a communication network based on a generated confrontation network. The method comprises the following steps: firstly regularizing the data of the abnormal user to obtain data with consistent same dimension and magnitude; training the generated confrontation network, that is, training a generator and a discriminator, to achieve oversampling of the abnormal user; and forming a training data set via the data generated by the generator and a normal user, classifying the training data set by using a deep fully connected neural network, and judging a user type. By adoption of the method disclosed by the invention, by means of a mutual game training mode between the neural networks in the generated confrontation network, the approximation of the data distribution of the abnormal user is achieved, the detection of the abnormal user is achieved, and the technical problem that the proportional imbalance of the training data setaffects the training effect of a classification model is solved.

Provided is a ground-air troop real-equipment confrontation training system. The system comprises an equipment data acquisition processing module, a simulation scheduling module, a director control module, a situation monitoring module, a decision assessment module, a data management module and a comprehensive guarantee module, the operation of a simulation training system is promoted through datatransmitted by a sensor connected with real equipment, and troop, real-equipment, and non-live-fire training effects are achieved. The training system is mainly used for development of base troop confrontation training of land forces and air defense forces, the equipment usage capability, the tactic application capability and the system combat capability of both warring parties are inspected andassessed, important bases and support can be provided for effective development of combat training in an informatization condition, and the problem of accurate assessment of the troop confrontation training is solved.

The invention discloses a pond dissolved oxygen prediction method based on data restoration. The prediction method comprises the steps of determining the prediction object, defining the meteorological composite index, data restoration, constructing a GRNN neural network model, initializing the GRNN neural network and training the neural network. Eleven index parameters of meteorological factors and aquaculture environment factors related to pond dissolved oxygen prediction are involved. The eleven index parameters act as the input quantity, and the lost and abnormal data in sensor acquisition are restored by using the meteorological composite index and linear interpolation based on short period of continuity of the meteorological environment data and the water quality data. The dissolved oxygen concentration acts as the output quantity, and a GRNN neural network prediction model is determined. Compared with the dissolved oxygen prediction training effect of the conventional BP model, the GRNN algorithm of the GRNN network model has higher accuracy in comparison with the BP model and can better reflect the basic trend of the change of the pond dissolved oxygen within a period of time.

The application presents a multi-posture lower limb rehabilitation robot, which includes a robot base and a training bed. The training bed comprises two sets of leg mechanisms, a seat, a seat width adjustment mechanism, a mechanism for adjusting the gravity center of human body, a back cushion, a weight support system and a mechanism for adjusting the back cushion angle. The robot base comprises a mechanism for adjusting the bed angle. The mechanisms for adjusting the angles of bed and back cushion can be used together to provide paralysis patients with multiple training modes of lying, sitting, and standing postures. Each leg mechanism comprises hip, knee, and ankle joints, which are driven by electric motors; angle and force sensors are installed on each joint, and can be used to identify patients' motion intention to provide patients with active and assistant training. The mechanism for adjusting the gravity center of human body, the leg mechanisms, and the weight support system can be used together to implement human natural walking gait to improve the training effect.

The invention relates to the field of artificial intelligence, and discloses a federal learning model training method and device, and the method comprises the steps that a server determines a first terminal and a second terminal according to the connection state of terminals participating in a federal learning model before issuing global parameters of a (k+1)th training period; wherein the first terminal is a terminal which cannot be connected; wherein the second terminal is a normally connected terminal; the server determines second local parameters of M network layers with contribution degrees meeting set conditions in the first terminal; according to the second local parameters of the M network layers of the first terminal in the kth training period and the first local parameters of the N network layers uploaded by the second terminal, the server sends the first local parameters to the kth training period, and determines the global parameters of the N network layers issued to the second terminal in the (k+1)th training period, so as to reduce the influence on the training effect of the model caused by offline of the terminal.

The invention relates to ball serving equipment, in particular to table tennis ball serving equipment for sports training and aims at achieving the technical purpose of providing the table tennis ballserving equipment for sports training with a good training effect and a higher training difficulty. The invention provides the table tennis ball serving equipment for sports training. The equipment comprises a box body, a feeding hopper, a feeding tube, a ball discharging tube, a buffering cushion, an intermittent feeding device and the like; the feeding hopper is installed on the left side of the top of the box body, the feeding tube is installed below the feeding hopper, the feeding hopper is communicated with the feeding tube, the feeding tube is communicated with the box body, the ball discharging tube is horizontally installed in the middle of the left side face of the inside of the box body, openings are formed in the left and right ends of the ball discharging tube, and the buffering cushion is installed in the middle of the bottom of the ball discharging tube. According to the equipment, balls are constantly fed to the ball discharging tube by the intermittent feeding device,an ejecting device is driven by a driving device to eject the balls out so that table tennis training of a user can be conducted to achieve the effects of good training effect and higher training difficulty.

The invention relates to an upper limb rehabilitation robot control system. An upper computer transmits instructions to an MCU (micro-programmed control unit) module through a Bluetooth/WIFI, the MCUmodule selects different training modes according to the instructions, a voice module identifies unspecific voice, voice signals are acquired and processed and transmitted to the MCU module by the aidof an SPI (serial peripheral interface) communication protocol, a driving module drives a motor to rotate in a controlled manner, so that training actions are completed, electromyography collection of a healthy side of a patient is implemented by an electromyography control module, electromyography signals are extracted, processed and analyzed, actions of the healthy side of the patient map a mechanical arm, movement intentions are identified, and functional compensation and control is achieved. By the aid of various man-machine interaction modes, targeted rehabilitation training effects canbe effectively achieved, joints of the upper limb of the patient can be accurately positioned when the system is used, and tissue damage and pulled muscle caused by misplaced training are avoided. Thecontrol system is small in size, convenient to use, good in training effect and low in manufacturing cost.

The invention relates to the technical field of medical rehabilitation instruments and specifically to an intelligent upper limb rehabilitation training device. The main structure comprises a controller, a detection module, a power driving device and a training device mechanism. The intelligent upper limb rehabilitation training device formed through the matching of the parts is suitable for rehabilitation training/training aiding of patients suffering from upper limb dyskinesia caused by hemiplegia and/or other factors, is especially suitable for the patients suffering from functional disorder of upper limbs, and can provide passive, active and/or resisting training according to the requirements of different patients and achieve an effect of targeted rehabilitation. During use, the device can guarantee accurate location and be attached to each joint of the upper limbs, thereby preventing the tissue damage and muscle strain caused by wrong practices. The intelligent upper limb rehabilitation training device is simple in structure, small in size, light in mass, convenient to use, good in training effect, high in training accuracy, low in manufacture cost and wide in application range.