85results about How to "Reduce training difficulty" patented technology

The invention provides an intelligent power distribution cabinet safety early warning method, system and device and a storage medium, and relates to the field of electric power. The method comprises the steps of obtaining multi-source heterogeneous operation parameters of the intelligent power distribution cabinet, and performing feature extraction on the multi-source heterogeneous operation parameters to obtain operation feature parameters; performing parameter fusion on the operation characteristic parameters to obtain fused characteristic parameters, and inputting the fused characteristic parameters into a preset fault early warning model to obtain fault early warning data; and inputting the fault early warning data into a preset rule matching engine for rule matching to obtain a matching result, and generating an early warning signal according to the matching result. According to the method, the accuracy and timeliness of safety early warning of the intelligent power distribution cabinet are improved.

The invention provides a tunnel blasting effect small sample regression prediction method. The tunnel blasting effect small sample regression prediction method specifically comprises the following steps that feature data before blasting and blasting effect data after blasting are obtained and sorted; performing data normalization processing on the data, and selecting input features of a regression prediction model by using grey correlation analysis; establishing a generative adversarial network model, and augmenting and expanding the training data set; establishing a blasting effect multi-kernel Gaussian process regression prediction model; searching and predicting model hyper-parameters based on a multi-strategy integrated optimization sparrow algorithm; and predicting the new blasting effect based on the prediction model under the optimal parameter. According to the method, the unbalanced problems that blasting engineering data are difficult to collect, the number of samples is small, and meanwhile the number of samples with the excellent effect is large and the number of samples with the poor effect is small are effectively solved. The prediction precision and prediction efficiency of the blasting effect are improved, the generalization ability of blasting effect prediction is improved to the greatest extent, and the construction safety and efficiency of an engineering project are guaranteed.

The invention discloses an ultra-short-term photovoltaic power generation power prediction method and system based on a mixed correlation coefficient and a multi-scale TCN-transformer, and the method comprises the steps: obtaining ultra-short-term photovoltaic power generation power historical data and corresponding meteorological data, and carrying out the feature selection of the photovoltaic power generation power historical data and the meteorological data through the mixed correlation coefficient, screening out characteristic variables which have great influence on the photovoltaic power; dividing into a training set, a verification set and a test set; the method comprises the following steps of: improving a transform model so as to form a multi-scale CN-transform model; training is carried out on a multi-scale TCN-transform model by using the data of the training set; and verifying the trained multi-scale TCN-transformer model by using the verification set data, and checking whether the model is trained to an optimal state or not. And inputting the data of the test set into the trained multi-scale TCN-transformer model, and obtaining a final photovoltaic power prediction result. According to the method, the correlation between the photovoltaic power and the meteorological factors is comprehensively analyzed by combining two methods of the Pearson's correlation coefficient and the unified information coefficient, and the one-sidedness of a single correlation analysis method is avoided.

The invention discloses an article aspect-level preference decoupling recommendation method based on big language model enhancement. The method comprises the following steps: 1, constructing a user-article interaction matrix based on scores and comment data of users; 2, utilizing a large language model and combining Prompt to extract aspect preferences of a user to an article and a user intention from the comments; 3, constructing a preference prediction model, decoupling the user-article interaction matrix into a sub-intention interaction matrix, and performing convolution operation on the sub-intention interaction matrix by using GCN to obtain user and article embedding under each intention; 4, using an attention mechanism to obtain user and article embedding of weighted fusion of all intentions; 5, calculating a prediction score; 6, constructing and optimizing a loss function; and 7, sorting the prediction scores in a descending order, and taking the first X items as a recommendation list. According to the method, user intentions are deduced from user comments by using a large language model, and user and article embedding for weighting and fusing all intentions is obtained in combination with a GCN and an attention mechanism, so that the recommendation precision can be improved.

The invention discloses an audio signal processing method and device, computer equipment and a storage medium, and belongs to the technical field of artificial intelligence. The audio signal processing method is applied to a pre-built vocoder system, and the vocoder system is built based on a variational auto-encoder and comprises a prior encoder, a posterior encoder and a decoder. First, a loss function is constructed, including reconstruction loss and difference loss between encoders. And then, inputting the original audio signal into a posterior encoder to generate Gaussian distribution, sampling the distribution to generate an intermediate hidden variable, and inputting the hidden variable into a decoder for audio reconstruction to generate a restored audio signal. A pre-trained vocoder system is obtained by calculating loss and carrying out optimization and iterative training. And finally, processing the to-be-restored frequency spectrum by using the pre-trained vocoder system to generate a restored audio signal. According to the method, the stability of the model is effectively improved, the training difficulty is reduced, and the generalization ability of the model is enhanced.

The invention relates to the technical field of vehicle control, and discloses a vehicle-mounted semantic standardization method, device and equipment, a medium and a product, and the method comprises the steps: obtaining a pre-trained large language model; obtaining a target original vehicle control command; obtaining a format template used for representing the target standard vehicle control command; forming a cue word according to the target original vehicle control command and the format template; and inputting the target original vehicle control command and the cue word into the large language model, and outputting the converted target standard vehicle control command through the large language model. Based on the ability of the large language model to directly understand the text meaning, the original vehicle control command and the standard vehicle control command are directly paired to generate the training sample of the text style, so that the training sample is input into the large language model for training, the threshold of model training is reduced, and the training efficiency and the training accuracy are improved; and high accuracy and high automation degree of vehicle-mounted semantic standardization are considered.

The invention discloses a monocular depth estimation method and device based on a bidirectional state space model, and a medium, relates to an image processing technology, and solves the problems that an existing self-supervision method is insufficient in the aspects of long sequence modeling, training speed, reasoning speed and scene complex detail capturing, and the optimization effect of the model under sparse supervision is poor. The monocular depth estimation method comprises the following steps: constructing an encoder-decoder structure which comprises a continuous expansion convolution module and a bidirectional state space module, generating intermediate features of a training image by an encoder, modeling long-distance intermediate feature information, and generating output features by a decoder; constructing an attitude estimation model, performing joint reconstruction by using output features generated by a decoder and depth estimation of a training image, modeling a learning target, and designing a loss function of a target image and a reconstructed image to optimize a network; and training the constructed model by adopting a public KITTI data set to obtain a weight model, and evaluating the precision of monocular image depth estimation by the trained model. The method is used for image monocular depth estimation.

The invention provides a server testing system and method, electronic equipment and a computer readable storage medium, the server testing system comprises the electronic equipment, the electronic equipment is provided with a USB port, and the electronic equipment is in communication connection with a server through the USB port; the touch display screen is used for displaying a test item menu bar; the electronic equipment comprises an interaction module which responds to a selection operation of a user on a test item menu bar through a touch display screen so as to generate configuration parameters for a server; the configuration module is used for modifying a pre-stored test script according to the configuration parameters to obtain a modified test script; the sending module is used for sending the modified test script to the server through the USB port; and the test module is used for controlling the server to execute the modified test script and generate a test result. According to the method, the test process is packaged into the test script in advance, and one or more tests can be automatically executed by connecting the USB port of the electronic equipment with the server, so that the server test automation is realized.

The invention provides a diffusion-driven channel adaptive point cloud semantic communication method, which belongs to the technical field of wireless communication, and comprises the following steps: obtaining a training point cloud data set, constructing a point cloud feature extraction network based on a hypergraph convolutional neural network as a semantic encoder, and constructing a channel adaptive enhancement module as a channel decoder, a channel adaptive recovery module is constructed at a receiving end as a channel decoder, a diffusion reconstruction network is constructed as a semantic decoder, end-to-end joint training is performed on the point cloud feature extraction network, the channel adaptive enhancement module, the channel adaptive recovery module and the diffusion reconstruction network, the diffusion reconstruction network predicts original point cloud distribution, and the point cloud feature extraction network and the channel adaptive enhancement module are subjected to end-to-end joint training. And a loss function is constructed based on the chamfering distance between the predicted point cloud distribution and the original point cloud. In the communication process, the reconstructed semantic features are input into the diffusion reconstruction network to reconstruct an original point cloud structure. The high-order semantic features of the point cloud can be effectively extracted so as to improve the adaptive capacity of the method to the incomplete point cloud.

The invention relates to a new energy microgrid real-time energy management method based on near-end strategy optimization and Lightgbm. The new energy microgrid real-time energy management method comprises the following steps: S1, forming a training sample library of a Lightgbm model; s2, training a Lightgbm model, and predicting the power shortage of the new energy microgrid; s3, building a reinforcement learning environment required for training the intelligent agent, enabling the intelligent agent to interact with the environment, and forming a training sample library of deep reinforcement learning; s4, improving the reward function designed in S3; s5, training the intelligent agent by using a near-end strategy optimization algorithm, and storing model parameters; and S6, completing real-time energy management of the new energy microgrid. According to the invention, the training efficiency and training effect of the model can be obviously improved.

The invention belongs to the related technical field of intelligent fault diagnosis of equipment, and discloses an equipment fault diagnosis method and system based on a Gramb angle field and a VAE-GAN, and the method comprises the steps: an offline stage: collecting equipment vibration signals, and building an initial signal sample set; a GAF coding technology is used to code the signal sample into a Gramer angle field picture; establishing a sample augmentation model based on the GAN, and training by using the initial picture sample set; acquiring an extended picture sample set by using the trained sample augmentation model; establishing a picture classification model, and training based on the extended picture sample set; an on-line diagnosis stage: encoding a signal sample to be detected into a Gramer angle field picture; and inputting the trained picture classification model to obtain a fault mode classification result. According to the method, the equipment fault vibration signal is converted into the two-dimensional image, the advantages of the GAN in image generation can be fully played, and the problems of few fault samples and unbalanced sample distribution in the prior art are solved.

The invention belongs to the technical field of mobile phone display screen detection, and particularly discloses a defect detection method based on a smart mobile phone display screen. Graying and denoising the collected surface defect image of the original display screen; performing feature labeling and expansion on the preprocessed image; on the basis of the U-Net network, a residual block is inserted, common convolution is replaced by depth separable convolution, and an attention module is added; performing batch training on the cross entropy loss function by using a stochastic gradient descent method, continuously updating parameters of the network model, and optimizing the parameters of the network model by using an Adam method; when the output value of the loss function is reduced and does not change any more, iteration is stopped; and inputting a to-be-detected mobile phone display screen image into the trained network model for detection, if the mobile phone display screen is detected to have a defect, outputting a defect binary image of the mobile phone display screen, and calculating the real size of the defect. According to the invention, surface defects such as scratches and black spots of the mobile phone display screen can be rapidly and accurately detected.

The invention discloses a pineapple annona squamosa production and sightseeing cultivation method which comprises the following steps: S1, garden selection: S11, selecting a flat land suitable for tropical and subtropical regions, a gentle slope land below 5 degrees or a horizontal step to plant pineapple annona squamosa; s2, soil preparation and planting planning, including the following sub-steps: S21, clearing weeds, sundries, stones and the like hindering tillage in the garden 2-3 months before field planting, and then performing comprehensive deep tillage; and S22, harrowing soil blocks and leveling the land after exposing to the sun for one month, and determining the downwind direction as the planting row direction. According to the annona squamosa production and sightseeing cultivation method, the attractiveness of a sightseeing orchard is improved, the whole row of trees are connected into a whole through a grafting method, the whole row serves as a vegetative body, water and nutrients can circulate mutually, each single plant grows evenly, the pruning technical difficulty and the training difficulty for producers are greatly reduced, and the production cost is saved.

The present invention proposes an active gripping hand function training system based on multi-dimensional emotion recognition; it includes a rehabilitation training ball, a core processing module, a training interaction module and a multi-source data acquisition module. The core processing module performs emotion recognition on pulse wave data and electrocardiogram data respectively, and fuses the emotion recognition results corresponding to facial expression, pulse wave and electrocardiogram to obtain a comprehensive emotion recognition result. The rehabilitation training ball is used for the user to hold and detect the user's gripping force. The training interaction module is used to guide the user to perform hand gripping, rotation and movement training. The present invention comprehensively judges the user's emotional changes during hand training through facial expression, electrocardiogram and pulse wave signals, and when the user has negative emotions, reduces the training difficulty by reducing the required threshold of hand training gripping force and the threshold of rotation and movement amplitude, thereby alleviating the user's resistance and prompting the user to train more actively and proactively.

A training method, prediction method and device for an aftershock time-frequency spectrum prediction model, the method comprising: constructing an initial prediction model, the initial prediction model comprising an encoder and a decoder connected in sequence; acquiring a training data set and a test data set, wherein each piece of data comprises a time-frequency spectrum corresponding to a main earthquake acceleration time history, a main earthquake seismological parameter characteristic matrix and an aftershock seismological parameter characteristic matrix; training the decoder to obtain a trained decoder; training the encoder by using the training data set, the test data set and the trained decoder to obtain a trained prediction model; the prediction model is used for obtaining an aftershock time-frequency spectrum corresponding to the main shock based on the main and aftershock seismological parameters and the time-frequency spectrum corresponding to the main shock acceleration time history, and the aftershock time-frequency spectrum is used for obtaining an aftershock acceleration time history after phase recovery. According to the method, the decoder is trained first and then the decoder is trained, so that the model training difficulty can be reduced, the training efficiency can be improved, machine jamming can be avoided, and the computer performance can be improved.

The invention discloses a simulation test system for a control strategy of an application software layer of a range extender controller. The simulation test system comprises a virtual control system, a whole vehicle controlled object and a whole vehicle longitudinal dynamic model, the virtual control system comprises a virtual driver module, a virtual vehicle control unit, a virtual main drive motor controller, a range extender controller ASW, a virtual engine controller (ECU), a virtual generator controller (GCU), a virtual electric accessory controller and a virtual battery management system (BMS). The virtual whole vehicle controlled object comprises a virtual engine, a virtual generator, a virtual power battery, a virtual high-voltage electric accessory and a virtual chassis system. According to the invention, the test work which can only be carried out after hardware integration is completed in the past can be moved forward, the development period can be shortened, and the development cost is reduced.

The invention discloses a voice cloning model training method and device, and a voice cloning method and device, and the method comprises the steps: constructing a text alignment module, a first pitch extraction module, a second pitch extraction module and a rhythm extraction module, and carrying out the training of the modules, obtaining a trained text alignment module, a trained first pitch extraction module, a trained second pitch extraction module and a trained rhythm extraction module; combining the first training data set with a voice style diffusion module, a decoder and a random duration prediction module to construct a voice clone model, and training the voice clone model by adopting the first training data set to obtain a trained voice clone model; and performing fine tuning on the trained voice clone model by adopting the second training data set to obtain a fine-tuned voice clone model, and cloning high-quality voice close to the target tone only by providing reference voice of which the duration is at least the preset duration.

The application relates to the technical field of machine learning, and provides an animal sound classification method, system, device, medium and product. The application trains a classification model through a staged strategy, including pre-training the classification model based on a general audio dataset, end-to-end training the classification model based on an animal sound dataset, and deploying the trained classification model to an intelligent device; the intelligent device collects original audio signals in real time and extracts log-mel spectrum features as feature inputs of the classification model, and the model finally outputs prediction probabilities for each target sound category, so as to determine an animal sound classification result. The staged training method significantly reduces the model training difficulty, the log-mel spectrum features are used as inputs to improve the robustness of the model to background noise, and the generalization ability and overall accuracy of the classification model are effectively improved.

The invention discloses an occlusion facade perception method and system based on a feature distinguishing learning deep network. The method comprises the steps of 1, acquiring an occlusion facade image set; step 2, inputting the occlusion facade image set into a deep network to obtain first-stage enhanced image deep representation; 3, respectively sending the deep representation of the image enhanced in the first stage into two auxiliary processing modules for processing to obtain two multi-scale enhanced representations with distinguishing hidden layer features; 4, obtaining a difference dichotomy semantic prediction map of the attention rule component and the attention background, and obtaining semantic prediction maps of all classes; and step 5, training a deep network based on the dichotomy semantic prediction map and all category semantic prediction maps, and storing the trained deep network. According to the method, the technical problem of how to effectively process shielding and analyze the facade image is solved, and the method has good application value in the fields of computer vision, graphics, facade image processing and the like.

The method belongs to the technical field of panoramic monitoring of ultra-high voltage converter station, and aims to solve the problem that panoramic monitoring image data is directly uploaded to the cloud, occupying a large amount of cloud resources. By adopting multi-scale convolution blocks in the deep multi-scale residual network model to construct low-order and high-order features of images of various scales, the incomplete phenomenon of image detail extraction is avoided, and the residual learning mechanism is adopted to retain low-order rough features, thereby improving the reconstruction ability of the image. Topology optimization constructs the topology structure of the heterogeneous network, and the framework combining deep reinforcement learning and Monte Carlo tree search is used to construct the network according to the pre-defined topology rules. The search result of the Monte Carlo tree strengthens the learning of the deep convolutional neural network, so as to obtain more accurate prediction in the next iteration. After the data is processed in the edge side, it is transmitted to the cloud storage, saving the cloud storage space and transmission bandwidth.

The application provides a method and system for image data recognition model construction. The method comprises: obtaining an image data set comprising true value labels; based on the image data set and a teacher network model, using an FSP method to initialize the weights of each layer of a student network to obtain at least two student network models with the same network structure; based on the image data set comprising true value labels, using a DML distillation method to train each student network model, and when the trained student network models all meet preset conditions, taking the trained student network models as an image data recognition model. Through the method, at least two student network models with the same structure and completed weight initialization of each layer are obtained by transferring learning from a teacher network model, which can avoid problems such as the inability to well initialize a neural network due to insufficient data, and can reduce the training difficulty. The DML distillation method is used to obtain an image data recognition model with guaranteed recognition ability, and the training cycle is short, the speed is fast, the deployment is easy, and the applicability is wide.

This invention discloses a method for predicting the viewport of panoramic video streaming with viewer type estimation. This method, tailored to different viewer types, trains a corresponding neural network prediction model for the viewport position using a set of viewport position vector samples. This makes the neural network prediction model more viewer-type specific, ensuring that a particular viewport position prediction model is only applicable to a specific viewer type, reducing the training difficulty of the model and improving prediction accuracy. This method determines the viewer type based on the viewer's actual viewport position sequence before the current frame and selects the corresponding neural network prediction model to predict the viewport position of the current frame. This method ensures that for different types of viewers, a corresponding trained neural network prediction model is used to predict the viewport position of the current frame.

The application discloses a kind of based on multi-source fusion and reinforcement learning's composite material additive manufacturing adaptive control method, first in printing process Synchronous acquisition space position, infrared temperature, tension and compression force and multi-source sensor data such as visible light image;Through the lightweight perception module constructed to each road data is parallelly processed and feature extraction, to force data adopts second-order difference to carry out state discrimination, to temperature data adopts multistage threshold segmentation and extracts forming area statistical feature, and reward feature is generated in combination with image recognition and position mutation detection;The multi-dimensional state features after fusion are combined with reward function, and the agent is trained using reinforcement learning algorithm to learn the optimal printing parameter decision strategy;The trained agent is used for real-time control, and the best printing speed and layer thickness instruction are dynamically output to the mechanical arm according to the current state. The application realizes accurate description and real-time adaptive control of complex multi-physical field coupling process, effectively improves printing quality and process stability.

The invention relates to a data set decomposition-based large language model training method, which comprises the following steps of: performing token processing on an original document in a training data set to obtain a one-dimensional token sequence and calculating an original length; performing binary decomposition on the original length, splitting the token sequence into sub-token sequences, storing the sub-token sequences in buckets according to the length, and adding an original document traceability identifier; calculating a single sampling number of each effective bucket, and configuring a sampling probability; executing random sampling according to the sampling probability, and performing homologous constraint splicing to generate a training batch; and inputting the training batch into the to-be-trained large language model, and performing fine adjustment on the sampling probability adjustment rule and the training hyper-parameter according to the results of the conventional reference performance evaluation, the long context capability evaluation and the training efficiency evaluation. By means of the large language model training method based on data set decomposition, cross-document attention interference can be reduced, calculation waste can be reduced, and training efficiency can be improved.

The invention discloses a composite energy storage type high-speed forming device and a use method thereof, and aims to solve the technical problems of low striking efficiency and high maintenance difficulty of a high-speed forming device in the prior art. The composite energy storage type high-speed forming device comprises a combined machine body, an energy storage speed increasing mechanism, a pneumatic hammer lifting mechanism, an electromagnetic locking mechanism and a hammer head mechanism, by adopting a composite energy storage mode of high-pressure gas potential energy and hammer head gravitational potential energy, breakthrough on the impact speed of an existing traditional drop hammer is achieved, the metal forming capacity and quality are remarkably improved, and the forming efficiency is improved. And the requirement of high-performance material processing on high-speed impact is met. According to the using method, the high-speed forming device is used for machining and production, the consistency and repeatability of the forming process are ensured, the production efficiency and the product quality are improved, the production capacity is remarkably improved, and the requirement for large-scale production is met.

This invention discloses a method for displacement field recognition of cement-based materials based on a one-dimensional convolutional model. The method includes: S1: extracting the displacement field from a speckle image; using speckle image pairs as feature data, and using the lateral displacement field, longitudinal displacement field, and combined displacement field as label data, and normalizing the label data to obtain a sample dataset; S2: constructing a displacement field recognition model for cement-based materials based on a one-dimensional convolutional model; S3: constructing a model loss function containing the design parameters to be optimized by introducing physical loss, and training the displacement field recognition model based on the one-dimensional convolutional model for cement-based materials based on the sample dataset to obtain the optimal displacement field recognition model; and realizing the displacement field recognition of cement-based materials based on the optimal displacement field recognition model. This invention solves the problem of insufficient accuracy and efficiency in the displacement field recognition of cement-based materials by existing methods.

The present invention discloses a remote sensing SAR target detection method based on the combination of network pruning and parameter quantization, which mainly solves the defects of high model complexity and slow reasoning speed of existing remote sensing SAR target detection methods. Its implementation scheme is: obtain the divided training set and test set from the public remote sensing SAR target detection data set, and perform data expansion on the training set; perform data enhancement on the expanded training set; adjust the existing lightweight network to build a benchmark model; train the benchmark model and calculate its performance index; evaluate the importance of each feature extraction module in the adjusted network, prune unimportant modules, and then perform filter pruning; design a quantization search space, search for a mixed precision quantization scheme of the pruned model, obtain the final model, and use the model for SAR target detection. The present invention saves training costs while improving detection accuracy, and can be used in target recognition scenarios with limited computing resources and high real-time requirements.

The invention discloses a cross-hardware architecture operator adaptive generation method and device, equipment and a medium, and relates to the technical field of computers, and the method comprises the steps: extracting a first feature vector from operator description corresponding to an operator type of a to-be-generated operator; determining a weighted summation result of the target architecture configuration information and the first feature vector to obtain a first identifier, so as to screen a target calculation accelerator architecture adaptive network from each preset calculation accelerator architecture adaptive network corresponding to each calculation accelerator type; binarization is carried out on the first feature vector to obtain a second identifier, so that a target operator type adaptive network is screened from preset operator type adaptive networks corresponding to the operator types; and performing feature transformation on the first feature vector by using the target computing accelerator architecture adaptation network and the target operator type adaptation network, and generating an operator sequence of an operator to be generated based on a second feature vector and a third feature vector obtained after transformation. And the flexibility and simplicity of operator generation are improved.

The application discloses a multi-agent cooperative navigation optimization method, and the optimization method takes a multi-agent deep deterministic policy gradient algorithm as a basic framework; the following mechanism is introduced in the training stage: in the multi-agent cooperative navigation training stage, a joint priority experience extraction mechanism is introduced, joint experience samples are extracted and spliced according to the time difference error priority through cross-agent synchronization indexing; an information discarding and correction compensation mechanism is introduced at the input end of the centralized Critic network, information from other agents is divided into independent information blocks, the information blocks are randomly discarded with a preset probability, and a correction factor is applied to the retained information blocks to maintain the mathematical expectation of the input data unbiased, and the input of the reduced Critic network is obtained. The application provides a multi-agent cooperative navigation optimization method which can improve the key experience utilization rate, reduce the dependence of the model on high-dimensional global input, and enhance the robustness in a communication limited environment.

The invention discloses an occlusion attitude estimation method, system and device based on structured modeling and a medium, and the method comprises the following steps: obtaining an input image, and carrying out window division processing based on irregular expansion on the input image to obtain a divided image; sequentially performing down-sampling processing and feature classification quantization processing on the divided image based on a four-layer four-edge attention mechanism to obtain processed features; inputting the processed features into a decoder based on a multi-layer perceptron hybrid network for image attitude recovery; window expansion can be realized by adopting projection conversion, information loss caused by a square window is reduced, and the object information capturing capability is enhanced; a quadrilateral attention mechanism is adopted to perform down-sampling, feature extraction classification and quantification on the image, and huge calculation amount caused by window sliding is reduced; the multi-layer perceptron hybrid network is used as a decoder for attitude estimation and picture recovery, and the attitude estimation accuracy under the shielding condition is improved.