Gabor-CNN for object detection based on small samples

Object detection models based on convolutional neural networks(CNN)have achieved state-of-the-art performance by heavily rely on large-scale training samples.They are insufficient when used in specific applications,such as the detection of military objects,as in these instances,a large number of samples is hard to obtain.In order to solve this problem,this paper proposes the use of Gabor-CNN for object detection based on a small number of samples.First of all,a feature extraction convolution kernel library composed of multi-shape Gabor and color Gabor is constructed,and the optimal Gabor convolution kernel group is obtained by means of training and screening,which is convolved with the input image to obtain feature information of objects with strong auxiliary function.Then,the k-means clustering algorithm is adopted to construct several different sizes of anchor boxes,which improves the quality of the regional proposals.We call this regional proposal process the Gabor-assisted Region Proposal Network(Gabor-assisted RPN).Finally,the Deeply-Utilized Feature Pyramid Network(DU-FPN)method is proposed to strengthen the feature expression of objects in the image.A bottom-up and a topdown feature pyramid is constructed in ResNet-50 and feature information of objects is deeply utilized through the transverse connection and integration of features at various scales.Experimental results show that the method proposed in this paper achieves better results than the state-of-art contrast models on data sets with small samples in terms of accuracy and recall rate,and thus has a strong application prospect.

Damage and fracture model for eutectic composite ceramics

Study of damage and fracture models to analyze the fracture mechanism of eutectic composite ceramics is of considerable importance because no accurate fracture models are available for these materials. Eutectic composite ceramics are composed of microcells with random direction. We present herein a model that predicts the damage and fracture of eutectic composite ceramics based on analysis of defect stability and the damage localization band. Firstly, given the microstructure of eutectic composite ceramics, a mesodomain and a microcell model are constructed. The local stress field in the mesodomain is then analyzed based on the interaction direct derivative estimate. Secondly, the stability of a defect around particles in a microcell is analyzed, and the stress intensity factor of an annular defect under the applied stress field and the residual stress field in the particle are calculated. The stress intensity factor of a defect is controlled by the residual stress when the defect extension is small. However, it is controlled by the applied stress when the defect extension is large. Finally, a model for the damage localization band at the crack tip is constructed based on the Dugdale-Barenblatt model. The residual intensity is the important factor affecting the length of the damage localization band. When the damage variables reach their largest value, the residual in ten sity and the length of the damage localization band attain their minimum value. This work provides the theoretical basis for further study of the damage mechanics of eutectic composite ceramics and guides the engineering applications of these materials.

Bayesian inference for ammunition demand based on Gompertz distribution

Aiming at the problem that the consumption data of new ammunition is less and the demand is difficult to predict,combined with the law of ammunition consumption under different damage grades,a Bayesian inference method for ammunition demand based on Gompertz distribution is proposed.The Bayesian inference model based on Gompertz distribution is constructed,and the system contribution degree is introduced to determine the weight of the multi-source information.In the case where the prior distribution is known and the distribution of the field data is unknown,the consistency test is performed on the prior information,and the consistency test problem is transformed into the goodness of the fit test problem.Then the Bayesian inference is solved by the Markov chain-Monte Carlo(MCMC)method,and the ammunition demand under different damage grades is gained.The example verifies the accuracy of this method and solves the problem of ammunition demand prediction in the case of insufficient samples.

Effective and selective separation of perrhenate from acidic wastewater by super-stable,superhydrophobic,and recyclable biosorbent

The recovery of scattered metal ions such as perrhenate(Re(VII))from industrial effluents has enormous economic benefits and promotes resource reuse.Nanoscale-metal/biochar hybrid biosorbents are attractive for recovery but are limited by their insufficient stability and low selectivity in harsh environments.Herein,a superstable biochar-based biosorbent composed of ZnO nanoparticles with remarkable superhydrophobic features is fabricated,and its adsorption/desorption capabilities toward Re(VII)in strongly acidic aqueous solutions are investigated.The ZnO nanoparticle/biochar hybrid composite(ZBC)exhibits strong acid resistance and high chemical stability,which are attributable to strong C-O-Zn interactions between the biochar and ZnO nanoparticles.Due to the advantages of its hydrolytic stability,superhydrophobicity,and abundance of Zn-O sites,the ZBC proves suitable for the effective and selective separation of Re(VII)from single,binary and multiple ion systems(pH=1),with a maximum sorption capacity of 29.41 mg/g.More importantly,this material also shows good recyclability and reusability,with high adsorption efficiency after six adsorption-desorption cycles.The findings in this work demonstrate that a metal/biochar hybrid composite is a promising sorbent for Re(VII)separation.