The invention relates to a convolutional neural network prediction method based on a rotation region. The method comprises steps that step 1, a convolutional neural network characteristic graph and an area of interests based on a rotary rectangular frame are generated according to input images; step 2, a rotary area-of-interest pooling layer is utilized to acquire a characteristic mapping graph according to the convolutional neural network characteristic graph and the area of interests; step 3, the characteristic mapping graph is mapped to be a one-dimensional characteristic vector; step 4, the one-dimensional characteristic vector is classified to acquire a classification result; step 5, rotary rectangular frame regression prediction of the one-dimensional characteristic vector is carried out to acquire a regression prediction result; and step 6, a final prediction result is outputted according to the classification result and the regression prediction result. The method is advantaged in that a problem of positioning and identification difficulties caused by target rotation and an aggregation phenomenon of images is solved, and precise positioning is realized.

Convolutional neural network prediction method based on rotation region

The invention discloses a regional convolutional neural network-based method for gesture identification and interaction under egocentric vision. The method comprises the following steps of S1, obtaining training data; S2, designing a regional neural network which is used for gesture classification and fingertip detection while being used for hand detection, and ensuring that an input of the neural network is a three-channel RGB image and outputs of the neural network are top left corner coordinates and top right corner coordinates of an external connection matrix of a gesture region, gesture types and gesture skeleton key points; and S3, judging the gesture types, and outputting corresponding interactive results according to different interactive demands. The invention provides a complete method for gesture identification and interaction under egocentric vision. Through single model training and partial network sharing, the identification speed and accuracy of the gesture identification under the egocentric vision are increased and improved.

Regional convolutional neural network-based method for gesture identification and interaction under egocentric vision

The invention relates to a multi-sensor intelligent refrigerator control method based on deep learning and an intelligent refrigerator. The refrigerator is provided with a refrigerator body and a plurality of doors, and the refrigerator and each door form a refrigerator storage chamber. The control method includes the steps that a first image obtained before food is placed into the refrigerator storage chambers and a second image obtained after the food is placed into the refrigerator storage chambers are obtained, a visual detection method is adopted to obtain the image of the food to be detected based on the first image and the second image, a first trained convolved neural network model is adopted to recognize the above image of the food to be detected, and the varieties of the food to be detected in the refrigerator storage chambers are obtained; the first pressure of the storage chambers obtained before the food is placed into the refrigerator storage chambers and the second pressure of the storage chambers obtained after the food is placed into the refrigerator chambers are obtained, and the weight of the food to be measured is obtained based on the first pressure and the second pressure; and a voice door-opening or door-closing instruction is obtained, a second trained convolved neural network model is adopted to recognize the above voice door-opening or door-closing instruction to control the refrigerator doors to be opened and closed.

Multi-sensor intelligent refrigerator control method based on deep learning and intelligent refrigerator

The embodiment of the invention discloses a reservoir gas bearing recognition method, device and system. The method comprises the steps that the original seismic profile of a reservoir to be detectedis acquired; the original seismic profile is inputted to a pre-constructed gas bearing recognition model to be processed, wherein the gas bearing recognition model is obtained in a way that the selected deep learning initial model is trained through the acquired seismic profile sample data; and the gas bearing recognition result of the reservoir to be detected is determined according to the outputresult of the gas bearing recognition model. With application of the reservoir gas bearing recognition method, device and system, the information included in the original seismic data can be fully utilized so that the accuracy of gas bearing prediction can be enhanced.

Reservoir gas bearing recognition method, device and system

The invention discloses an earthquake oil and gas reservoir distribution-oriented convolutional neural network learning and prediction method. The method comprises the steps of firstly extracting earthquake attributes capable of representing oil and gas features based on original earthquake data; secondly designing a convolutional neural network model, taking the optimized earthquake attributes asinput layers of a network, extracting earthquake attribute values in a well position, taking the porosity, the permeability and the oiliness in the well position as training samples, and continuouslymodifying parameters such as a convolution kernel, a weight value w, a bias b and the like in a network structure through back propagation of a BP neural network, until model training is finished; and thirdly testing data of a no-well region, thereby realizing lateral prediction of reservoirs from a well region to the no-well region. The method directly performs convolutional neural network deeplearning on oil and gas sensitive attribute bodies, and can realize lateral prediction of earthquake information features of same-block and even cross-region unknown earthquake reservoir bodies.

Earthquake oil and gas reservoir distribution-oriented convolutional neural network learning and prediction method

The invention discloses a parallelization method of convolutional neural networks in a fuzzy region under a big-data environment. The parallelization method comprises the following steps: firstly, constructing the convolutional neural networks in the fuzzy region, putting a given target assumption region and object identification into the same network, carrying out convolutional calculation, and updating the weight of the whole network in a training process; and secondly, dividing an input log data set into a plurality of small data sets, introducing multiple workflows to pass through the convolutional neural networks in the fuzzy region in parallel for convolution and pooling, and independently training each small data set by virtue of gradient descent. By virtue of the parallelization method, a network structure and parameters are optimized, and relatively good analysis performance and precision are realized; furthermore, the number of FR-CNN obfuscation layers is adjusted aiming at different log data sets, so that the extracted features can well reflect the characters of oil-gas reservoirs, and the fuzzification problem of the log data can be solved; and the parallel training and execution of FR-CNN are carried out by virtue of multiple GPUs, so that the efficiency of the FR-CNN is improved.

Parallelization method of convolutional neural networks in fuzzy region under big-data environment

The present invention provides a logging facies identification and analysis method based on fuzzy depth learning in a big data environment. The method comprises: constructing a fuzzy area convolution nerve network, putting a given target hypothesis area and target identification into the same network to share the convolution calculation, and employing a training process to update the whole network weight; dividing input logging data to a plurality of small data sets, performing convolution and pooling operation steps of each small data set through the fuzzy area convolution nerve network; and employing classified features to construct a logging facies-sedimentary facies knowledge base which is configured to establish a corresponding knowledge base including the sedimentary facies, the sedimentary subfacies and the sedimentary microfacies based on the unambiguous logging data and the sedimentary facies fusion method to support the association analysis of the sedimentary facies and the logging facies so as to establish the logging facies-sedimentary facies knowledge base and determine the corresponding relation of the current logging data and the sedimentary facies.

Logging facies identification and analysis method based on fuzzy depth learning in big data environment

The invention provides a fuzzy theory and neural network-based well-log facies recognition method. The method comprises the steps of firstly, constructing a fuzzy area convolutional neural network, putting a given target hypothesis area and target recognition into the same network, sharing convolution calculation, and updating a weight of the whole network by a training process; and secondly, performing convolution and pooling operations on well-log data through the fuzzy area convolutional neural network, interacting a convolution layer with a pooling layer, performing fuzzy operation at the convolution layer and the pooling layer, gradually increasing a fuzzy layer number from a first layer of the fuzzy area convolutional neural network, adjusting the fuzzy layer number for different data sets, obtaining an eigenvector from a last layer of the fuzzy area convolutional neural network, mapping a feature of the eigenvector to a low-dimensional vector through a sliding window, and inputting the feature to two full connection layers, wherein one full connection layer is used for locating, and the other full connection layer is used for classification.

Fuzzy theory and neural network-based well-log facies recognition method

Microblog plays an important role in the dissemination of information now, especially on some sensitive topics. We established the propagation model of the microblog was constructed in this paper. The weak ties are used in the microblog network to obtain independent communities. We analyzed degree centrality, betweenness centrality and closeness centrality of microblog network. Various messages disseminate from different nodes with various feature which can be preset. The characteristics of some nodes in the information dissemination process become clearer according to the comparison among results after message dissemination. We analyzed the impacts of some nodes with information entropy during the information dissemination, which is so important to guide public opinion and maintain social stability.

Liu Xin

Papers

Parallelization method of convolutional neural networks in fuzzy region under big-data environment

Logging facies identification and analysis method based on fuzzy depth learning in big data environment

Fuzzy theory and neural network-based well-log facies recognition method

Feature Analysis of Important Nodes in Microblog