1053 results about "Positive sample" patented technology

A system for increasing the accuracy in summarization techniques is disclosed. The system generates a set of summaries for text. The system determines a label for each summary based on a set of composite metrics. The label for the summary indicates the truthfulness and faithfulness of the summary with respect to the text. The system determines that more than a threshold number of the set of composite metrics indicate that a first summary is assigned with a first label. In response, the system adds the first summary paired with the text as a positive sample to a dataset. The system determines that more than a threshold number of composite metrics indicate that a second summary is assigned with a second label. In response, the system adds the second summary paired with the text as a negative sample to the dataset. The system trains a summarization algorithm with the dataset.

The invention discloses a method and system for evaluating the susceptibility of avalanches based on GIS and machine learning, and belongs to the technical field of avalanche susceptibility evaluation. The method comprises the following processes: determining the influencing factors causing avalanches in a target area according to the terrain data, meteorological data and avalanche data of the target area; performing correlation detection on the influencing factors causing avalanches preliminarily selected to determine the evaluation factors; constructing a positive sample set and a negative sample set according to the evaluation factors and avalanche point data information of the target area, training a machine learning model according to the positive sample set and the negative sample set, and obtaining an avalanche susceptibility evaluation model after training; producing an avalanche susceptibility zoning map according to the prediction results of the avalanche susceptibility evaluation model, and determining the avalanche susceptibility of each area; the method can improve the rationality and scientificity of the avalanche susceptibility evaluation results, and provide theoretical support and method guidance for the avalanche disaster prevention and control system.

The invention provides an information recommendation method and device based on collaborative sampling of a knowledge graph and an adjacent graph, and relates to the technical field of information recommendation. According to the method, the triple is constructed by obtaining the historical interaction data of the user, and the triple is fused with the project attribute graph to construct the collaborative knowledge graph; performing expression alignment through projection transformation to obtain initial embedding expression; performing multi-hop neighbor sampling through biased random walk to obtain a multi-hop neighbor set; determining a neighbor which is most similar to the embedding representation of the positive sample item as an anchor neighbor; then linear interpolation is carried out, and the embedding representation of the difficult negative sample is synthesized; on the basis of the multi-head graph attention network, training by adopting a positive sample and a synthesized difficult negative sample, and aggregating to obtain an updated embedded representation; and calculating an interaction probability based on the updated embedded representation, and generating a recommended item for the user. According to the method, the problems of user-project interaction sparsity and false negative example interference are effectively solved, and stronger semantic comprehension and generalization ability are provided for a recommendation system.

The invention relates to the technical field of recommendation algorithms, provides a graph collaborative filtering course recommendation method based on interactive attention and comparative learning, and aims to solve the problem that a traditional recommendation system is insufficient in modeling ability in a sparse interaction scene. The method comprises the following steps: firstly, constructing a user-course bipartite graph, and utilizing a dynamic attention mechanism guided by an interactive opposite-end node: carrying out vector dot product through original embedding of the opposite-end node (for example, course embedding is used during user aggregation) and current embedding of a neighbor node, and generating an attention coefficient in combination with temperature parameter normalization; and multi-level structure information aggregation is realized. Afterwards, local context features are fused through a multilayer graph convolutional network, random noise disturbance is introduced to generate a multi-view comparison sample, the consistency of positive samples is maximized in combination with an InfoNCE loss function, and the robustness of the model to noise and sparse data is enhanced; and finally, optimizing user-course embedding in combination with Bayesian personalized sorting loss and comparison loss, and generating a personalized recommendation list. According to the method, the key interaction relationship is screened through guided attention, the representation discrimination is improved in combination with comparative learning, and the recommendation precision in cold start and data sparse scenes can be improved.

The invention discloses a data construction and fine tuning method for a knowledge retrieval model in the field of energy and power, and the method comprises the steps: carrying out the preprocessing of document data in the field of energy and power, and segmenting the document data into document segments suitable for the input of a retrieval model; performing question generation based on a large language model, generating a question-document pair positive sample set according to document fragments, and sampling to generate a question-document pair negative sample set; and in combination with contrast learning of the positive sample set and the negative sample set and LoRA parameter fine tuning, training a retrieval model, and performing problem retrieval by using the trained retrieval model. According to the method, high-quality problem-document pairs and challenging negative samples are generated, a comparative learning technology is combined, the retrieval model is optimized, the retrieval accuracy of the vector model in the field is remarkably improved, specific retrieval requirements in the energy power field can be deeply understood, and retrieval suggestions which are highly reliable and conform to habits in the field are generated.

The invention discloses a consistent learning-oriented sample enhancement and optimization method, which comprises the following steps of: respectively performing knowledge extraction on professional knowledge data, professional vocabulary interpretation, historical practice data and an expert experience set in an unstructured text to obtain an original question and answer pair and a professional knowledge base; processing the original question and answer pairs through a diversified strategy to generate enhanced sample question and answer pairs with consistent semantics and various forms, and expanding or simplifying the enhanced sample question and answer pairs to obtain positive samples; introducing an interference expression or a fact error into the enhanced sample question and answer pair to obtain a negative sample; adjusting the positive and negative sample proportion according to the large model accuracy; and taking the positive sample and the negative sample as training data, and performing parameter fine tuning based on the pre-trained large model and the professional knowledge base to obtain a professional large model. According to the method, the adaptability and robustness of a large model in different scenes are improved, and the occurrence probability of irrelevant information and wrong answers is reduced.

The invention relates to the technical field of image classification and recognition, in particular to a semi-supervised classification method and a semi-supervised classification system for lumbar diseases based on semantic contrast fusion uncertain sensing, and adopts a semi-supervised classification network model as a semi-supervised classification framework for lumbar disease recognition. The cross entropy loss of the labeled samples and the consistency loss of the unlabeled samples are used as the loss of the model; selecting the labels with the prediction confidence greater than a threshold value and the prediction uncertainty less than the threshold value as pseudo labels; taking the labeled data with the same label and the unlabeled data with the false label as a positive sample pair, and training by adopting a supervised comparative learning method to obtain comparative learning loss of the model; semi-supervised model loss, uncertainty loss and comparative learning loss are used as total loss functions for joint training of the model. The problems that semantic information of annotated data is not utilized to constrain unannotated data, and a pseudo tag has confirmation deviation are solved, and the lumbar disease recognition accuracy is improved.

The invention relates to the field of image recognition, and provides a positive and negative sample algorithm combined power transmission line high-altitude anomaly detection method. The objective of the invention is to improve the accuracy and robustness of detection. By comprehensively utilizing the advantages of the positive sample algorithm and the negative sample algorithm, the method effectively solves the problems of background complexity and abnormal data collection. Firstly, a detection picture and a base picture are cut and masked and focused on a power transmission line area; next, a positive sample algorithm is used to identify an abnormal region, while a negative sample algorithm is focused on detecting a specific type of anomaly. Through a multi-stage filtering mechanism including target detection filtering and template matching filtering, false alarms are effectively reduced, and the detection effect is improved. According to the method, a memseg algorithm and a YOLO model are adopted in model training, and an anomaly filtering model is introduced to detect common misinformation targets such as birds and vegetation. Finally, by combining positive and negative sample results, high-precision and high-recall-rate detection performance is realized.

The invention discloses a watermark imperceptible embedding and recovering method based on a deep learning network structure. Firstly, a mask guide watermark embedding scheme is designed, a mask generation module is constructed by using a residual dense feature extraction module and an attention mask generation module, and a watermark is adaptively guided to be embedded into an image texture rich area so as to improve the invisibility of the watermark. And secondly, constructing a watermark decoding network based on comparative learning, and by comparing a loss function, taking the decoding features of the same watermark image under different noise conditions as positive samples and taking the decoding features of different watermark images as negative samples so as to enhance the consistency of the decoding features, thereby improving the robustness of the watermark. The deep learning network structure can improve the robustness of the watermark in a real screen shooting scene, and has a huge application value in copyright protection and traceability tracking.

The invention belongs to the technical field of industrial operation and maintenance term processing, and provides a big language model training method based on a knowledge graph, and the method comprises the steps: carrying out the cooperation with operation and maintenance personnel in advance to set a fault dictionary, collecting fault instances, carrying out the classification and preprocessing, extracting causal trigger words of the fault instances, and setting a text dependency relationship rule. Splitting and extracting a triple of the fault instance, and importing to form a knowledge graph; mapping the instance attribute into a node feature vector, outputting an embedded representation of a node, and fusing the embedded representation with the multi-modal feature vector to form a fused feature embedded representation; replacing semantic and degree words with fault instances in the knowledge graph to generate positive samples, randomly replacing subjects, objects and causal relationships to generate negative samples, inputting the negative samples into a semantic encoder, mapping the negative samples to the same metric space, and calculating similarity to obtain a comparison loss value to adjust graph convolutional network parameters; and after the fusion feature embedding representation retrieval of the fault instance is carried out and a subgraph is generated, maintenance suggestions are given step by step along a causal chain.

The invention discloses a small target detection method based on scale perception label distribution and context enhancement. The method comprises the following steps of: 1, organizing an image file and a corresponding annotation file to obtain image data, and dividing the image data into a training image and a test image to form a required data set; 2, preprocessing and training the image data through feature extraction and small target detection capability of an optimization model, and storing the weight; and step 3, testing the test image according to the weight stored by training, verifying the small target detection capability of the model in a real scene through evaluation on a test set by using the weight stored by training, and adjusting or optimizing model parameters. According to the invention, sufficient positive samples can be reasonably distributed for the targets of different scales for training according to the target scale change, so that the influence on the detection precision of the targets of other scales is reduced on the basis of improving the small target detection precision; the problem that a traditional multi-scale detection network fails to challenge small targets is effectively solved.

The invention discloses a protein generation model optimization method based on deep learning, and relates to the technical field of protein generation. The optimization method comprises the following steps: generating a candidate protein electron density distribution diagram based on the structural characteristics of a target spot by adopting a pre-trained diffusion model; converting the candidate protein electron density distribution diagram into a corresponding amino acid sequence; determining a functional index value corresponding to the amino acid sequence, and constructing a feedback data set; setting a reward threshold value, and marking the feedback data set as a positive sample data set and a negative sample data set according to the reward threshold value; constructing a utility function taking the reward threshold as a reference point, and respectively calculating utility values of the positive sample data set and the negative sample data set; and performing iterative optimization on the diffusion model according to the utility value. By adopting the technology provided by the invention, the dependence on preference paired data of large-scale and high-quality protein sequences can be avoided, and the performance of the protein generation model can be effectively and continuously improved.

The present disclosure provides a fault prediction method, a fault prediction model training method, a computing device, a storage medium, and a computer program product. The fault prediction method comprises: obtaining abnormal log data and unit attribute information of a service processing unit; determining an abnormal event sequence on the basis of the abnormal log data; and inputting the unit attribute information and the abnormal event sequence into a fault prediction model to obtain a fault prediction result of the service processing unit, wherein the fault prediction model is obtained by performing training on the basis of a positive sample, a first sample label corresponding to the positive sample, a negative sample, and a second sample label corresponding to the negative sample, the positive sample comprises a positive sample abnormal event sequence and sample unit attribute information, and the negative sample comprises a negative sample abnormal event sequence and sample unit attribute information. The training data of the fault prediction model is richer, so that the accuracy of prediction results of the fault prediction model during applications is improved.

The invention provides a cross-modal image-text retrieval method and system based on adaptive comparative learning. The method comprises the steps that two boundary parameters are introduced into probability distribution of each pair of positive samples, the probability of an image I corresponding to T is calculated, semantic consistency of each pair of positive samples is adjusted, and distribution characteristics of negative samples are distinguished and cloned; defining and calculating a saliency score of each batch of samples, and selecting negative sample sequences with the maximum saliency score and the minimum saliency score as an observation clone negative sample and a saliency negative sample; according to a Gaussian discriminant analysis method, predicting all potential clone negative samples of each batch of samples and generating anchor point samples; and iteratively updating the two boundary parameters according to the two boundary conditions of the similarity of the anchor point samples. According to the method, potential clone negative samples in each training batch are predicted by utilizing Gaussian discriminant analysis without additional training for clone negative samples easily appearing in an image-text data set. And a foundation is laid for subsequent further learning of potential high-dimensional key semantics of the cloned negative sample.

The invention provides a dense target detection method based on comparative learning characterization and reinforcement learning decision, which is suitable for dense animal individual detection in a livestock breeding scene. The method comprises the following steps: constructing a dense target detection model comprising a feature encoder, a reinforcement learning decision module and a detection head; the training process is divided into two stages: in the contrast learning characterization stage, an anchor sample, a positive sample and a negative sample are constructed, a first loss function is utilized to optimize a feature encoder, and an optimal feature encoder is obtained; in the reinforcement learning decision-making stage, the feature vector is used as an input state, a decision-making module dynamically selects a threshold lowering, maintaining or improving action, a detection head outputs a detection result in combination with the feature and the action, and parameters of the decision-making module are optimized through a reward function. During detection, after features of a to-be-detected image are extracted through the feature encoder, the optimized decision module selects the optimal action, and finally a detection result is output. The method has relatively high robustness and accuracy.

The invention provides a drug-disease association prediction method and system, computer equipment and a medium, and belongs to the technical field of computers. The method comprises the following steps: constructing a drug-protein-disease heterogeneous network, and extracting a plurality of element path sub-graphs; inputting the meta-path sub-graph into a multi-scale diffusion graph convolution module, executing learnable multi-step graph diffusion on the basis of graph convolution, synchronously capturing local adjacency and high-order topological information, and generating node embedding; and performing dynamic weighted fusion by utilizing meta-path attention to obtain unified representation. In order to relieve imbalance of positive and negative samples, implementing difficult negative sampling in the embedding space, and constructing a balance training set with the positive samples; medicine-disease features are spliced, a regularization XGBoost classifier is trained, and unknown correlation accurate prediction is achieved. By adopting the method, the drug-disease association prediction precision and efficiency are improved, multi-scale topology and priori knowledge are fused, and a powerful calculation tool is provided for drug relocation.

The invention provides an intention perception recommendation method based on knowledge graph and comparative learning fusion, relates to the technical field of artificial intelligence, and aims to optimize node representation by fusing knowledge graph and comparative learning technologies so as to improve the recommendation precision of a recommendation system for long-tail projects. Meanwhile, on the basis of data enhancement, positive sample selection in contrast learning is expanded in combination with user intentions, the ability of the model in the aspect of user intention modeling is further enhanced, and finally the accuracy and correlation of recommendation results are improved. The objective of the invention is to solve the problems of poor long-tail project representation quality, insufficient user intention modeling and limited recommendation precision caused by knowledge graph noise interference in the prior art.

The invention belongs to the technical field of intelligent dialogues, and provides a retrieval enhancement method and system for multi-round dialogue type questions and answers and application. A quaternion data set containing consultation questions, documents, answers and rewriting retrieval texts is constructed, and a retrieval result is obtained by combining dialogue state caching and a mixed retrieval strategy. The method comprises the following steps: generating a rewritten text taking a retrieval task as a main guide by utilizing a Rewriter model, dynamically mining a new difficult case according to the rewritten text, constructing a joint loss function by combining a generation loss function and a multi-positive sample comparison loss function, and jointly optimizing the Rewriter model. According to the method, a multi-positive sample comparison loss function is provided to make full use of supervision signals in a multi-round data set, and the ability of a rewriting model to understand the context is improved; a dynamic hard case mining method is provided, and dynamic mining is performed in real time according to a rewriting result in a training process, so that the problem that rewriting query cannot be optimized in real time according to retrieval feedback is solved.

The invention discloses a multi-modal large language model training method and system, and relates to the technical field of multi-modal large model data processing, and the method comprises the following steps: training a first large model through querying a question set, a positive sample and a hard negative sample; inputting the plurality of test samples into the trained first large model, and generating a plurality of second answers based on a first preset prompt; sorting each test sample based on the plurality of second answers, and retrieving to obtain a previous candidate multi-modal document related to the test question; and training the second large model through the test problem and the corresponding previous multi-modal document. According to the method, the positive samples and the hard negative samples are jointly used for training, the model is forced to capture the fine-grained semantic boundary of correlation judgment through a contrast learning mechanism, the distinguishing capacity of the model for difficult samples is remarkably improved, and the mistaken arrangement phenomenon is avoided.

The invention discloses a bacteriophage host prediction method based on a weighted integrated convolutional neural network. The method comprises the following steps: obtaining a joint feature vector for an input bacteriophage protein sequence and a host receptor protein sequence; taking the bacteriophage-host pair as a positive sample, randomly selecting non-host bacteria for each bacteriophage to generate a negative sample, dividing the negative sample into M subsets, and combining each subset with all the positive samples to form M balance training subsets; for each balance training subset, training an independent one-dimensional convolutional neural network model; independently training a one-dimensional convolutional neural network sub-model for each balance training subset to obtain a plurality of sub-models with different performances; and distributing weights based on the performance indexes of the sub-models on the verification set, performing weighted fusion on the prediction probabilities of the M sub-models, and outputting a final host interaction probability. The method realizes accurate prediction of phage-host interaction on the premise of only needing basic sequence information, and has the advantages of light weight, high efficiency and wide applicability.

The invention provides a model training method, mobile equipment, electronic equipment and a medium, and the model training method comprises the steps: executing a test task through a task execution model, and obtaining test data corresponding to a target time period in the process of executing the test task; inputting the test data into the initial state judgment model to obtain an initial state judgment result; under the condition that a test result corresponding to the test data meets a preset requirement and the initial state judgment result is inconsistent with the test result, storing the test data as positive sample data into a positive sample database; under the condition that the test result does not meet the preset requirement and the initial state judgment result is inconsistent with the test result, the test data serve as negative sample data to be stored in a negative sample database; and training the initial state judgment model by using the positive sample data in the positive sample database and the negative sample data in the negative sample database. According to the technical scheme, the whole training period of the model can be shortened, and the training efficiency is improved.

The invention discloses a malicious instruction detection method and system fusing self-supervised learning and a knowledge graph. The method comprises the steps of obtaining user instruction data and compliance labels, constructing an adversarial sample generation matrix, and generating an adversarial sample library through hierarchical variation and compliance correction; inputting the original instruction and the adversarial sample into a multi-modal detection model, wherein the model comprises a dual-channel encoder and a dynamic knowledge graph module; through a self-supervised comparison loss function optimization model, positive samples need to meet semantic and attack feature similarity threshold requirements, and negative samples are violation instructions; inputting a to-be-detected instruction into the trained model, extracting features, performing multi-hop reasoning on the features and the knowledge graph, and calculating a risk score; and when a malicious instruction is detected, generating a disposal strategy and updating the knowledge graph node. Through fusion of self-supervised learning and the dynamic knowledge graph, accurate detection is realized, the generalization ability and robustness of the model are enhanced, and the detection precision is improved.

The invention belongs to the technical field of artificial intelligence, and discloses a method for generating a migratable adversarial sample for a vision-language pre-training model based on comparative learning, and the method comprises the steps: carrying out the discrimination of an image-text pair set obtained through the data enhancement of the vision-language pre-training model, and obtaining a positive sample set and a negative sample set; in the positive sample guided adversarial sample generation process, negative samples are introduced to further enrich the diversity of the adversarial samples, so that cross-modal interaction is realized to the greatest extent; in the adversarial sample iteration generation process, through combination of three different types of learning modes of positive sample learning, negative sample learning and contrast learning, a transferable vision-language pre-training model adversarial sample is guided to be generated. Wherein the adversarial samples generated by fusing three learning methods show better mobility in different vision-language pre-training models and downstream tasks of the different vision-language pre-training models.

The invention discloses a mechanical fault diagnosis method based on a multi-source information self-integration neural network, and the method comprises the steps: sequentially selecting samples from each source domain, and calculating a point pair set distance set of the samples relative to a plurality of source domains, so as to construct a positive sample pair and a negative sample pair; establishing a first loss function for reducing the point pair set distance measure of the positive sample pair and increasing the point pair set distance measure of the negative sample pair, and training to obtain the point pair set distance measure; establishing a second loss function including multi-task learning loss and joint training loss, and training to obtain a hybrid expert network; establishing a third loss function for aligning the low-level features and the high-level features of the cross-domain through the multi-layer maximum mean value difference, and aligning the input and output features of the hybrid expert network; and training the aligned hybrid expert network to obtain a learnable distance measurement hybrid expert model for fault diagnosis. According to the method, specific feature output of multiple source domains can be integrated, gating output matching and independent task learning are balanced, and complex nonlinear domain drift can be processed.

The invention discloses a model training method and device, a storage medium and a computer program product, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining a weight positive sample training set and a weight negative sample training set, the weight positive sample training set and the weight negative sample training set are obtained by labeling and screening a preset unlabeled sample set; based on a preset unbiased positive sample and unmarked sample learning algorithm, according to the weight positive sample training set and the weight negative sample training set, training to obtain a dichotomy model; iterating the dichotomy model through a loss function and a regular function corresponding to the dichotomy model based on a preset expectation maximization algorithm until the dichotomy model converges, and obtaining a converged dichotomy model; and taking the converged dichotomy model as a prediction model. The problems that an existing method is poor in universality and generalization and needs to label samples manually are solved, and the universality and generalization of model training are improved.

A sample processing method includes: obtaining a positive sample image; obtaining, based on the positive sample image, an anomaly labeling mask map corresponding to the positive sample image; and generating a forged negative sample image based on the positive sample image and the anomaly labeling mask map, where an anomaly region in the forged negative sample image corresponds to an anomaly labeling region in the anomaly labeling mask map. In this way, a large quantity of forged negative sample images can be automatically generated, to provide sufficient sample datasets for task detection in a scenario with scarce samples.

The invention provides an operation decision-making method, device and system of an operation inspection robot and a medium. According to the implementation scheme, a plurality of positive sample pairs and a plurality of negative sample pairs are constructed; training a cross-modal semantic alignment model based on the plurality of positive sample pairs and the plurality of negative sample pairs, performing semantic alignment on each positive sample pair by adopting the trained cross-modal semantic alignment model to obtain a knowledge vector of semantic alignment, and storing the knowledge vector into a multi-modal operation inspection knowledge base; in response to an operation request text for the operation inspection robot, performing semantic alignment on the operation request text based on a cross-modal semantic alignment model to obtain a semantic-aligned operation request text vector; searching a target knowledge vector similar to the job request text vector in a multi-modal operation inspection knowledge base; and based on the target knowledge vector and the operation request text, generating an operation action instruction of the operation inspection robot. According to the embodiment of the invention, the operation decision accuracy of the operation inspection robot can be improved.

Embodiments described herein provide a method for training a neural network based language model (LM). The method includes receiving, via a data interface, a training dataset including pairs of user queries and ground-truth responses; generating, via the LM, a plurality of responses based on a query from the training dataset; identifying, from the plurality of responses, a first response having a first similarity metric value below a threshold, based on a similarity metric associated with a corresponding ground-truth response from the training dataset; training the LM using the first response as a negative sample and a second response as a positive sample such that the LM after training is more likely to generate the positive sample and less likely to generate the negative sample; receiving, via a user interface, a query; and generating a response to the query via the trained LM.

The invention relates to the technical field of biological detection, and discloses an underwater organism detection method, device and equipment, a storage medium and a program product.A big language model is used for processing the category name of an underwater organism to be detected to obtain category description, and the name, a picture and the description are input into a target multi-modal detection model together for processing; the dependence on manual annotation is reduced, and the data processing efficiency is improved. Meanwhile, data information of two modes of text and image is fully utilized, the limitation of single-mode data is avoided, and the detection accuracy is improved. Furthermore, by calculating the similarity between the visual features of the target and the false detection clustering center and performing result judgment according to a similarity threshold value, the target possibly causing false detection can be effectively identified, so that the omission ratio can be better balanced, the detection performance reduction caused by improper false detection processing measures is avoided, and the detection accuracy is improved. The problem that the recall rate of the positive sample is reduced is solved, and the reliability of underwater biological detection is improved.

The invention relates to the field of network security and the deep learning field, in particular to a satellite internet-oriented Tor website fingerprint identification method, which is implemented by constructing a self-supervised contrast learning framework and is implemented by generating a multi-view sample; extracting a feature matrix of the time sequence granularity; generating a synthesized negative sample based on linear insertion, and constructing a contrast with the positive sample; and track representation is extracted, and joint optimization is carried out in combination with cross entropy loss and mask reconstruction loss. Compared with a traditional website fingerprint identification method, the robustness of the model to satellite inherent noise caused by the Doppler effect can be enhanced. According to the method, multi-scale semantic features are provided for the weak enhancement view and the strong enhancement view, the inter-class distinction degree is improved by synthesizing negative samples, and the misjudgment rate is reduced; the joint loss optimization framework enables the model to give consideration to global statistical characteristics and local burst characteristics, and under the conditions of strong dynamic topology and limited labeling of satellite internet constellations, the accuracy and adaptability of website fingerprint recognition are remarkably improved.