EnGAN: Enhancement Generative Adversarial Network in Medical Image Segmentation

Deep learning has been widely used in medical image segmentation, although the accuracy is affected by the problems of small sample space, data imbalance, and cross-device differences. Aiming at such issues, a enhancement GAN network is proposed by using the domain transferring of the adversarial generation network to enhance the original medical images. Specifically, based on retaining the transferability of the original GAN network, a new optimizer is added to generate a sample space with a continuous distribution, which can be used as the target domain of the original image transferring. The optimizer back-propagates the labels of the supervised data set through the segmentation network and maps the discrete distribution of the labels to the continuous image distribution, which has a high similarity to the original image but improves the segmentation efficiency.On this basis, the optimized distribution is taken as the target domain, and the generator and discriminator of the GAN network are trained so that the generator can transfer the original image distribution to the target distribution. extensive experiments are conducted based on MRI, CT, and ultrasound data sets. The experimental results show that, the proposed method has a good generalization effect in medical image segmentation, even when the data set has limited sample space and data imbalance to a certain extent.

A Novel Optimization Method for Conventional Primary and Secondary School Classrooms in Southern China Considering Energy Demand, Thermal Comfort and Daylighting

The classroom environment is of great significance for the health of primary and secondary school students, but a comfortable indoor environment often requires higher energy consumption. This paper presents a multi-objective optimization method based on an artificial neural network (ANN) model, which can help designers efficiently optimize the design of primary and secondary school classrooms in southern China. In this optimization method, first, the optimization objectives and variables are determined according to building characteristics, and the physical model is established through simulation software (EnergyPlus) to generate the sample space. Second, sensitivity analysis is carried out for each optimization variable, and the physical model is modified according to the results to regenerate the sample space. Third, the ANN model is trained by using the regenerated sample space, and the Pareto optimal solution is generated through the use of the non-dominated sorting genetic algorithm II (NSGA-II). Finally, the effectiveness of the multi-objective optimization method is proven through a typical case of primary and secondary school classrooms in Nanjing, China. The results show that, compared with the benchmark scheme, TES decreased by 810.8 kWh at most, PT increased by 47.8% at most and DI increased by 4.2% at most.

Joint Feature-Space and Sample-Space Based Heterogeneous Feature Transfer Method for Object Recognition Using Remote Sensing Images with Different Spatial Resolutions

To improve the classification results of high-resolution remote sensing images (RSIs), it is necessary to use feature transfer methods to mine the relevant information between high-resolution RSIs and low-resolution RSIs to train the classifiers together. Most of the existing feature transfer methods can only handle homogeneous data (i.e., data with the same dimension) and are susceptible to the quality of the RSIs, while RSIs with different resolutions present different feature dimensions and samples obtained from illumination conditions. To obtain effective classification results, unlike existing methods that focus only on the projection transformation in feature space, a joint feature-space and sample-space heterogeneous feature transfer (JFSSS-HFT) method is proposed to simultaneously process heterogeneous multi-resolution images in feature space using projection matrices of different dimensions and reduce the impact of outliers by adaptive weight factors in the sample space simultaneously to reduce the occurrence of negative transfer. Moreover, the maximum interclass variance term is embedded to improve the discriminant ability of the transferred features. To solve the optimization problem of JFSSS-HFT, the alternating-direction method of multipliers (ADMM) is introduced to alternatively optimize the parameters of JFSSS-HFT. Using different types of ship patches and airplane patches with different resolutions, the experimental results show that the proposed JFSSS-HFT obtains better classification results than the typical feature transferred methods.

Optimization of a vacuum cleaner fan suction and shaft power using Kriging surrogate model and MIGA

Optimization of vacuum cleaner fan components is a low-cost and time-saving solution to satisfy the increasing requirement for compact energy-efficient cleaners. In this study, surrogate-based optimization technique is used and for the first time it is focused on maximization of Airwatt parameter, which describes the fan suction power, as an objective function (Case II). Besides, the shaft power is minimized (Case I) as another optimization target in order to reduce the power consumption of the vacuum cleaner. 11 geometrical variables of 3 fan components including impeller, diffuser and return channel are selected as the optimization design variables. 80 training points are distributed in the sample space using Advanced Latin Hypercube Sampling (ALHS) technique and the outputs of sample points are calculated by means of CFD simulations. Kriging and RSA surrogate models have been fitted to the outputs of the sample space. Through coupling of constructed Kriging models and Multi-Island Genetic Algorithm (MIGA), the optimal design for each of the optimization cases is presented and evaluated using numerical simulations. A 20.22% reduction in shaft power in Case I and an improvement of 27.73% in Airwatt in Case II have been achieved as the overall results of this study. Despite achieving goals in both optimization cases, a slight decrease in Airwatt in Case I (−6.20%) and a slight increase in shaft power in Case II (+4.82%) are observed relative to primary fan. Furthermore, the Analysis of Variance (ANOVA) determines the importance level of design variables and their 2-way interactions on the objective functions. It was concluded that geometrical parameters related to all of the fan components must be considered simultaneously to conduct a comprehensive optimization. The reasons of enhancement in optimal cases compared with the reference design have been further investigated by analysis of the fan internal flow field. Post-processing of the CFD results demonstrates that the applied geometrical modifications cause a more uniform flow through the flow passages of the optimal fan components.

Complete and competitive financial markets in a complex world

We investigate the possibility of completing financial markets in a model with no exogenous probability measure, with market imperfections and with an arbitrary sample space. We also consider whether such an extension may be possible in a competitive environment. Our conclusions highlight the economic role of complexity.

On probabilistic argumentation and subargument-completeness

Probabilistic argumentation combines probability theory and formal models of argumentation. Given an argumentation graph where vertices are arguments and edges are attacks or supports between arguments, the approach of probabilistic labellings relies on a probability space where the sample space is any specific set of argument labellings of the graph, so that any labelling outcome can be associated with a probability value. Argument labellings can feature a label indicating that an argument is not expressed, and in previous work these labellings were constructed by exploiting the subargument-completeness postulate according to which if an argument is expressed then its subarguments are expressed and through the use of the concept of ‘subargument-complete subgraphs’. While the use of such subgraphs is interesting to compare probabilistic labellings with other works in the literature, it may also hinder the comprehension of a relatively simple framework. In this short communication, we revisit the construction of probabilistic labellings and demonstrate how labellings can be specified without reference to the concept of subargument-complete subgraphs. By doing so, the framework is simplified and yields a more natural model of argumentation.

Unsupervised drill core pseudo-log generation in raw and filtered data, a case study in the Rio Salitre greenstone belt, São Francisco Craton, Brazil

We use in situ portable X-Ray Fluorescence data acquired in sawn drill core samples of rocks from the Sabiá prospect, at the Rio Salitre greenstone belt, São Francisco Craton Brazil, for pseudo-log automatic generation through running unsupervised learning models to group distinct lithotypes. We tested the K-means and Model-Based Cluster (MBC) algorithms and compared their performance in the raw and filtered data with a manual macroscopic log description. From the initial 47 available elements, 20 variables were selected for modeling following the criteria of presenting at least 95% of uncensored values. Additionally, we performed a Shapiro-Wilk test that confirmed a non-parametric distribution by verifying the P-value attribute less than the 5% significance level. We also checked if the dataset's distribution was statistically equivalent to the duplicates with the assistance of a Kruskal-Walis test, which would confirm the representativity power of the measurements at the same 5% significance level. After this step, the pseudo-log models were created based on reduced dimension data, compressed by a centered Principal Component Analysis with data rescaled by its range. Concerning to reduce the high-frequency noise in the selected features, we employed an exponential weighted moving average filter with a window of five samples. By the analysis of the Average Silhouette Width on sample space, the optimum number for K-means was fixed in two, and then the first models were generated for raw and filtered data. From the MBC perspective, the sample space is interpreted as a finite mixture of groups with distinct Gaussian probability distribution. The number of clusters is defined by the analysis of the Bayesian Information Criteria (BIC), where several models are tested, and the one in the first local maximum defines the number of groups and the type of probabilistic model in the simulation. For the data used in this work, the optimum group number for MBC is four, and the probabilistic model type determined by the BIC is elliptical with equal volume, shape, and orientation. Thus, Model-Based Cluster has detected four different cluster groups with almost the same representativity for the two drill cores' samples. All K-means and MBC models were able to detect changes in lithotypes not described in the manual log. On the other hand, one lithotype described by the experts was not detected by this methodology in any attempt. It was needed a detailed investigation with thin section descriptions to determine the cause of this response. Finally, compared with the manual log description, it is notable that the models built on filtered data have better performance than those generated on raw data, and the MBC filtered model had better performance than the others. Hence, this multivariate approach allied to filtering the data with a moving average transformation can be a tool of great help during several stages of mineral exploration, either in the creation of pseudo-log models prior the description of the drill core samples or in the data validation stage, when it is necessary to standardize several descriptions made by different professionals.