Symmetric Learning Data Augmentation Model for Underwater Target Noise Data Expansion

An important issue for deep learning models is the acquisition of training of data.Without abundant data from a real production environment for training,deep learning models would not be as widely used as they are today.However,the cost of obtaining abundant real-world environment is high,especially for underwater environments.It is more straightforward to simulate data that is closed to that from real environment.In this paper,a simple and easy symmetric learning data augmentation model(SLDAM)is proposed for underwater target radiate-noise data expansion and generation.The SLDAM,taking the optimal classifier of an initial dataset as the discriminator,makes use of the structure of the classifier to construct a symmetric generator based on antagonistic generation.It generates data similar to the initial dataset that can be used to supplement training data sets.This model has taken into consideration feature loss and sample loss function in model training,and is able to reduce the dependence of the generation and expansion on the feature set.We verified that the SLDAM is able to data expansion with low calculation complexity.Our results showed that the SLDAM is able to generate new data without compromising data recognition accuracy,for practical application in a production environment.

Data augmentation method for insulators based on Cycle-GAN

Data augmentation is an important task of using existing data to expand data sets.Using generative countermeasure network technology to realize data augmentation has the advantages of high-quality generated samples,simple training,and fewer restrictions on the number of generated samples.However,in the field of transmission line insulator images,the freely synthesized samples are prone to produce fuzzy backgrounds and disordered samples of the main insulator features.To solve the above problems,this paper uses the cycle generative adversarial network(Cycle-GAN)used for domain conversion in the generation countermeasure network as the initial framework and uses the self-attention mechanism and channel attention mechanism to assist the conversion to realize the mutual conversion of different insulator samples.The attention module with prior knowledge is used to build the generation countermeasure network,and the generative adversarial network(GAN)model with local controllable generation is built to realize the directional generation of insulator belt defect samples.The experimental results show that the samples obtained by this method are improved in a number of quality indicators,and the quality effect of the samples obtained is excellent,which has a reference value for the data expansion of insulator images.

Evidences of the expanding Earth from space-geodetic data over solid land and sea level rise in recent two decades

According to the space-geodetic data recorded at globally distributed stations over solid land spanning a period of more than 20-years under the International Terrestrial Reference Frame 2008,our previous estimate of the average-weighted vertical variation of the Earth＇s solid surface suggests that the Earth＇s solid part is expanding at a rate of 0.24 ± 0.05 mm/a in recent two decades.In another aspect,the satellite altimetry observations spanning recent two decades demonstrate the sea level rise（SLR） rate 3.2 ± 0.4 mm/a,of which1.8 ± 0.5 mm/a is contributed by the ice melting over land.This study shows that the oceanic thermal expansion is 1.0 ± 0.1 mm/a due to the temperature increase in recent half century,which coincides with the estimate provided by previous authors.The SLR observation by altimetry is not balanced by the ice melting and thermal expansion,which is an open problem before this study.However,in this study we infer that the oceanic part of the Earth is expanding at a rate about 0.4 mm/a.Combining the expansion rates of land part and oceanic part,we conclude that the Earth is expanding at a rate of 0.35 ± 0.47 mm/a in recent two decades.If the Earth expands at this rate,then the altimetry-observed SLR can be well explained.

Rectal Cancer Stages T2 and T3 Identification Based on Asymptotic Hybrid Feature Maps

Many existing intelligent recognition technologies require huge datasets for model learning.However,it is not easy to collect rectal cancer images,so the performance is usually low with limited training samples.In addition,traditional rectal cancer staging is time-consuming,error-prone,and susceptible to physicians’subjective awareness as well as professional expertise.To settle these deficiencies,we propose a novel deep-learning model to classify the rectal cancer stages of T2 and T3.First,a novel deep learning model(RectalNet)is constructed based on residual learning,which combines the squeeze-excitation with the asymptotic output layer and new cross-convolution layer links in the residual block group.Furthermore,a two-stage data augmentation is designed to increase the number of images and reduce deep learning’s dependence on the volume of data.The experiment results demonstrate that the proposed method is superior to many existing ones,with an overall accuracy of 0.8583.Oppositely,other traditional techniques,such as VGG16,DenseNet121,EL,and DERNet,have an average accuracy of 0.6981,0.7032,0.7500,and 0.7685,respectively.

一种新型钻孔采样数据管理方案

论述了在进行工程勘察软件设计中实际存在的一些问题。针对这些问题在对钻孔采样数据管理时,通过进行科学的数据空间的划分和结构重组提出了一种新型的钻孔数据管理方案,并成功地利用了的维数据处理功能解决了实际存在的困难。文章就该方案实现MAPGIS2.5的数据模型以及模型中使用的关键性技术分别进行了阐述。最后讨论了该模型可能存在的问题以及相应的解决方法。

Classification and Research of Skin Lesions Based on Machine Learning

Classification of skin lesions is a complex identification challenge.Due to the wide variety of skin lesions,doctors need to spend a lot of time and effort to judge the lesion image which zoomed through the dermatoscopy.The diagnosis which the algorithm of identifying pathological images assists doctors gets more and more attention.With the development of deep learning,the field of image recognition has made long-term progress.The effect of recognizing images through convolutional neural network models is better than traditional image recognition technology.In this work,we try to classify seven kinds of lesion images by various models and methods of deep learning,common models of convolutional neural network in the field of image classification include ResNet,DenseNet and SENet,etc.We use a fine-tuning model with a multi-layer perceptron,by training the skin lesion model,in the validation set and test set we use data expansion based on multiple cropping,and use five models’ensemble as the final results.The experimental results show that the program has good results in improving the sensitivity of skin lesion diagnosis.

Discriminative explicit instance selection for implicit discourse relation classification

Discourse relation classification is a fundamental task for discourse analysis,which is essential for understanding the structure and connection of texts.Implicit discourse relation classification aims to determine the relationship between adjacent sentences and is very challenging because it lacks explicit discourse connectives as linguistic cues and sufficient annotated training data.In this paper,we propose a discriminative instance selection method to construct synthetic implicit discourse relation data from easy-to-collect explicit discourse relations.An expanded instance consists of an argument pair and its sense label.We introduce the argument pair type classification task,which aims to distinguish between implicit and explicit argument pairs and select the explicit argument pairs that are most similar to natural implicit argument pairs for data expansion.We also propose a simple label-smoothing technique to assign robust sense labels for the selected argument pairs.We evaluate our method on PDTB 2.0 and PDTB 3.0.The results show that our method can consistently improve the performance of the baseline model,and achieve competitive results with the state-of-the-art models.