Layer regrouping is to divide all the layers into several sets of production series according to the physical properties and recovery percent of layers at high water-cut stage, which is an important technique to impro...Layer regrouping is to divide all the layers into several sets of production series according to the physical properties and recovery percent of layers at high water-cut stage, which is an important technique to improve oil recovery for high water-cut multilayered reservoirs. Dif- ferent regroup scenarios may lead to different production performances. Based on unstable oil-water flow theory, a multilayer commingled reservoir simulator is established by modifying the production split method. Taking into account the differences of layer properties, including per- meability, oil viscosity, and remaining oil saturation, the pseudo flow resistance contrast is proposed to serve as a characteristic index of layer regrouping for high water-cut multilayered reservoirs. The production indices of multi- layered reservoirs with different pseudo flow resistances are predicted with the established model in which the data are taken from the Shengtuo Oilfield. Simulation results show that the pseudo flow resistance contrast should be less than 4 when the layer regrouping is implemented. The K-means clustering method, which is based on the objec- tive function, is used to automatically carry out the layer regrouping process according to pseudo flow resistances. The research result is applied to the IV-VI sand groups of the second member of the Shahejie Formation in the Shengtuo Oilfield, a favorable development performance is obtained, and the oil recovery is enhanced by 6.08 %.展开更多
This paper presents two systems for recognizing static signs (digits) from American Sign Language (ASL). These systems avoid the use color marks, or gloves, using instead, low-pass and high-pass filters in space and f...This paper presents two systems for recognizing static signs (digits) from American Sign Language (ASL). These systems avoid the use color marks, or gloves, using instead, low-pass and high-pass filters in space and frequency domains, and color space transformations. First system used rotational signatures based on a correlation operator;minimum distance was used for the classification task. Second system computed the seven Hu invariants from binary images;these descriptors fed to a Multi-Layer Perceptron (MLP) in order to recognize the 9 different classes. First system achieves 100% of recognition rate with leaving-one-out validation and second experiment performs 96.7% of recognition rate with Hu moments and 100% using 36 normalized moments and k-fold cross validation.展开更多
Deep Learning is a powerful technique that is widely applied to Image Recognition and Natural Language Processing tasks amongst many other tasks. In this work, we propose an efficient technique to utilize pre-trained ...Deep Learning is a powerful technique that is widely applied to Image Recognition and Natural Language Processing tasks amongst many other tasks. In this work, we propose an efficient technique to utilize pre-trained Convolutional Neural Network (CNN) architectures to extract powerful features from images for object recognition purposes. We have built on the existing concept of extending the learning from pre-trained CNNs to new databases through activations by proposing to consider multiple deep layers. We have exploited the progressive learning that happens at the various intermediate layers of the CNNs to construct Deep Multi-Layer (DM-L) based Feature Extraction vectors to achieve excellent object recognition performance. Two popular pre-trained CNN architecture models i.e. the VGG_16 and VGG_19 have been used in this work to extract the feature sets from 3 deep fully connected multiple layers namely “fc6”, “fc7” and “fc8” from inside the models for object recognition purposes. Using the Principal Component Analysis (PCA) technique, the Dimensionality of the DM-L feature vectors has been reduced to form powerful feature vectors that have been fed to an external Classifier Ensemble for classification instead of the Softmax based classification layers of the two original pre-trained CNN models. The proposed DM-L technique has been applied to the Benchmark Caltech-101 object recognition database. Conventional wisdom may suggest that feature extractions based on the deepest layer i.e. “fc8” compared to “fc6” will result in the best recognition performance but our results have proved it otherwise for the two considered models. Our experiments have revealed that for the two models under consideration, the “fc6” based feature vectors have achieved the best recognition performance. State-of-the-Art recognition performances of 91.17% and 91.35% have been achieved by utilizing the “fc6” based feature vectors for the VGG_16 and VGG_19 models respectively. The recognition performance has been achieved by considering 30 sample images per class whereas the proposed system is capable of achieving improved performance by considering all sample images per class. Our research shows that for feature extraction based on CNNs, multiple layers should be considered and then the best layer can be selected that maximizes the recognition performance.展开更多
基金supported by the Program for Changjiang Scholars and Innovative Research Team in University(IRT1294)the China National Science and Technology Major Projects(Grant No:2016ZX05011)
文摘Layer regrouping is to divide all the layers into several sets of production series according to the physical properties and recovery percent of layers at high water-cut stage, which is an important technique to improve oil recovery for high water-cut multilayered reservoirs. Dif- ferent regroup scenarios may lead to different production performances. Based on unstable oil-water flow theory, a multilayer commingled reservoir simulator is established by modifying the production split method. Taking into account the differences of layer properties, including per- meability, oil viscosity, and remaining oil saturation, the pseudo flow resistance contrast is proposed to serve as a characteristic index of layer regrouping for high water-cut multilayered reservoirs. The production indices of multi- layered reservoirs with different pseudo flow resistances are predicted with the established model in which the data are taken from the Shengtuo Oilfield. Simulation results show that the pseudo flow resistance contrast should be less than 4 when the layer regrouping is implemented. The K-means clustering method, which is based on the objec- tive function, is used to automatically carry out the layer regrouping process according to pseudo flow resistances. The research result is applied to the IV-VI sand groups of the second member of the Shahejie Formation in the Shengtuo Oilfield, a favorable development performance is obtained, and the oil recovery is enhanced by 6.08 %.
文摘This paper presents two systems for recognizing static signs (digits) from American Sign Language (ASL). These systems avoid the use color marks, or gloves, using instead, low-pass and high-pass filters in space and frequency domains, and color space transformations. First system used rotational signatures based on a correlation operator;minimum distance was used for the classification task. Second system computed the seven Hu invariants from binary images;these descriptors fed to a Multi-Layer Perceptron (MLP) in order to recognize the 9 different classes. First system achieves 100% of recognition rate with leaving-one-out validation and second experiment performs 96.7% of recognition rate with Hu moments and 100% using 36 normalized moments and k-fold cross validation.
文摘Deep Learning is a powerful technique that is widely applied to Image Recognition and Natural Language Processing tasks amongst many other tasks. In this work, we propose an efficient technique to utilize pre-trained Convolutional Neural Network (CNN) architectures to extract powerful features from images for object recognition purposes. We have built on the existing concept of extending the learning from pre-trained CNNs to new databases through activations by proposing to consider multiple deep layers. We have exploited the progressive learning that happens at the various intermediate layers of the CNNs to construct Deep Multi-Layer (DM-L) based Feature Extraction vectors to achieve excellent object recognition performance. Two popular pre-trained CNN architecture models i.e. the VGG_16 and VGG_19 have been used in this work to extract the feature sets from 3 deep fully connected multiple layers namely “fc6”, “fc7” and “fc8” from inside the models for object recognition purposes. Using the Principal Component Analysis (PCA) technique, the Dimensionality of the DM-L feature vectors has been reduced to form powerful feature vectors that have been fed to an external Classifier Ensemble for classification instead of the Softmax based classification layers of the two original pre-trained CNN models. The proposed DM-L technique has been applied to the Benchmark Caltech-101 object recognition database. Conventional wisdom may suggest that feature extractions based on the deepest layer i.e. “fc8” compared to “fc6” will result in the best recognition performance but our results have proved it otherwise for the two considered models. Our experiments have revealed that for the two models under consideration, the “fc6” based feature vectors have achieved the best recognition performance. State-of-the-Art recognition performances of 91.17% and 91.35% have been achieved by utilizing the “fc6” based feature vectors for the VGG_16 and VGG_19 models respectively. The recognition performance has been achieved by considering 30 sample images per class whereas the proposed system is capable of achieving improved performance by considering all sample images per class. Our research shows that for feature extraction based on CNNs, multiple layers should be considered and then the best layer can be selected that maximizes the recognition performance.
