Model of Failure Resolution of Software-Defined Configurable Data Network

The publication deals with the design and modeling of fault tolerance for secured software-defined data transmission networks. A technique for evaluating the parameters of fault tolerance of a software-defined data transmission network is proposed. An organizational model for building a software-configurable data transmission network based on the design of a configuration based on the principle of dynamic protection with the use of selective transformation, taking into account the probability of failures and allowing to ensure high specified parameters of fault tolerance.

2,2-Bis(phenylselanyl)-1-(p-tolyl)vinyl 2-Oxo-2-(p-tolyl)acetate

2,2-Bis(phenylselanyl)-1-(p-tolyl)vinyl 2-oxo-2-(p-tolyl)acetate was synthesized via the reaction of p-tolylacetylene with diphenyl diselenide and benzoyl peroxide in benzene under atmospheric conditions. The molecular structure of the synthesized compound was evaluated using single-crystal X-ray analysis and spectral analyses. The process reported here provides a rare example of the direct and selective transformation of a terminal alkyne to the corresponding geminal diseleno-substituted alkene.

A study on selective transformation of norbornadiene into fluorinated cyclopentane-fused isoxazolines

This work presents an examination of the selective functionalization of norbornadiene through nitrile oxide 1,3-dipolar cycloaddition/ring-opening metathesis (ROM)/cross-metathesis (CM) protocols. Functionalization of commercially available norbornadiene provided novel bicyclic scaffolds with multiple stereogenic centers. The synthesis involved selective cycloadditions, with subsequent ROM of the formed cycloalkene-fused isoxazoline scaffolds and selective CM by chemodifferentiation of the olefin bonds of the resulting alkenylated derivatives. Various experimental conditions were applied for the CM transformations with the goal of exploring substrate and steric effects, catalyst influence and chemodifferentiation of the olefin bonds furnishing the corresponding functionalized, fluorine-containing isoxazoline derivatives.

One-dimensional DCNN Feature Selective Transformation with LSTM-RDN for Image Classification

Feature selection and transformation are the important techniques in machine learning field. A good feature selection or transformation will greatly improve the performance of classification method. In this work, we proposed a simple but efficient image classification method which is based on two-stage processing strategy. In the first stage, the one-dimensional features are obtained from image by transfer learning with the pre-trained Deep Convolutional Neural Networks (DCNN). These one-dimensional DCNN features still have the shortcomings of information redundancy and weak distinguishing ability. Therefore, it is necessary to use feature transformation to further obtain more discriminative features. We propose a feature learning and selective transformation network based on Long Short-Term Memory (LSTM) combing ReLU and Dropout layers (called LSTM-RDN) to further process one-dimensional DCNN features. The verification experiments were conducted on three public object image datasets (Cifar10, Cifar100 and Fashion-MNIST), three fine-grained image datasets (CUB200-2011, Stanford-Cars, FGVC-Aircraft) and a COVID-19 dataset, and several backbone network models were used, including AlexNet, VGG16, ResNet18, ResNet101, InceptionV2 and EfficientNet-b0. Experimental results have shown that the recognition performance of the proposed method can significantly exceed the performance of existing state-of-the-art methods. The level of machine vision classification has reached the bottleneck, it is difficult to solve this problem by using a large-scale network model which has huge parameters that need to be optimized. We present an effective approach for breaking through the bottleneck of visual classification task by feature extraction with backbone DCNN and feature selective transformation with LSTM-RDN, separately. The code and pre-trained models are available from: https://github.com/lillllllll/LSTM-RDN

One-dimensional DCNN Feature Selective Transformation with LSTM-RDN for Image Classification

Feature selection and transformation are the important techniques in machine learning field. A good feature selection / transformation method will greatly improve the performance of classification algorithm. In this work, we proposed a simple but efficient image classification method which is based on two-stage processing strategy. In the first processing stage, the one-dimensional features are obtained from image by transfer learning with the pre-trained Deep Convolutional Neural Networks (DCNN). These one-dimensional DCNN features still have the shortcomings of information redundancy and weak distinguishing ability. Therefore, it is necessary to use feature transformation to continue to obtain more distinguishable features. We propose a feature learning and selective transformation network based on Long Short-Term Memory (LSTM) combing ReLU and Dropout layers (called LSTM-RDN) to further process DCNN one-dimensional features. . The verification experiments were conducted on three public object image datasets(Cifar10, Cifar100 and Fashion-MNIST), three fine-grained image datasets(CUB200-2011, Stanford-Cars, FGVC-Aircraft) and a COVID-19 dataset. In the experiments, we used several backbone network models, including AlexNet, VGG16, ResNet18, ResNet101, InceptionV2 and EfficientNet-b0. Experimental results have shown that through feature selective transformation, the recognition accuracy of these DCNN models can significantly exceed the classification accuracies of the state-of-the-art methods.

One-dimensional DCNN Feature Selective Transformation with LSTM-RDN for Image Classification

Feature selection and transformation are the important techniques in machine learning field. A good feature selection / transformation method will greatly improve the performance of classification algorithm. In this work, we proposed a simple but efficient image classification method which is based on two-stage processing strategy. In the first processing stage, the one-dimensional features are obtained from image by transfer learning with the pre-trained Deep Convolutional Neural Networks (DCNN). These one-dimensional DCNN features still have the shortcomings of information redundancy and weak distinguishing ability. Therefore, it is necessary to use feature transformation to continue to obtain more distinguishable features. We propose a feature learning and selective transformation network based on Long Short-Term Memory (LSTM) combing ReLU and Dropout layers (called LSTM-RDN) to further process DCNN one-dimensional features. . The verification experiments were conducted on three public object image datasets(Cifar10, Cifar100 and Fashion-MNIST), three fine-grained image datasets(CUB200-2011, Stanford-Cars, FGVC-Aircraft) and a COVID-19 dataset. In the experiments, we used several backbone network models, including AlexNet, VGG16, ResNet18, ResNet101, InceptionV2 and EfficientNet-b0. Experimental results have shown that through feature selective transformation, the recognition accuracy of these DCNN models can significantly exceed the classification accuracies of the state-of-the-art methods.