There is a universally accepted view that environmental pollution should be controlled while improving cement mortar natural abilities. The purpose of this study is to develop a green cement mortar that has better compressive strength and anti-chloride ion permeability. Two industrial wastes, lithium-slag and slag, were added to cement mortar, and the role of lithium-slag was to activate slag. In addition, to save economic and time costs, this paper also used the least-squares support vector machine (LS-SVM) method to predict the property changes of cementitious-based materials. Then multiple natural abilities of samples, including compressive strength, anti-chloride ion permeability, and fluidity, were tested. In addition, LS-SVM and traditional support vector machine (SVM) were used to train and forecast the performance, including compressive strength. The results show that lithium-slag can activate slag to improve the compressive strength, anti-chloride ion permeability of mortar, and LS-SVM sharpens accuracy by 11% compared to SVM.

No abstract

While deep models have proved successful in learning rich knowledge from massive well-annotated data, they may pose a privacy leakage risk in practical deployment. It is necessary to find an effective trade-off between high utility and strong privacy. In this work, we propose a discriminative-generative distillation approach to learn privacy-preserving deep models.Our key idea is taking models as bridge to distill knowledge from private data and then transfer it to learn a student network via two streams. First, discriminative stream trains a baseline classifier on private data and an ensemble of teachers on multiple disjoint private subsets, respectively. Then, generative stream takes the classifier as a fixed discriminator and trains a generator in a data-free manner. After that, the generator is used to generate massive synthetic data which are further applied to train a variational autoencoder (VAE). Among these synthetic data, a few of them are fed into the teacher ensemble to query labels via differentially private aggregation, while most of them are embedded to the trained VAE for reconstructing synthetic data. Finally, a semi-supervised student learning is performed to simultaneously handle two tasks: knowledge transfer from the teachers with distillation on few privately labeled synthetic data, and knowledge enhancement with tangent-normal adversarial regularization on many triples of reconstructed synthetic data. In this way, our approach can control query cost over private data and mitigate accuracy degradation in a unified manner, leading to a privacy-preserving student model. Extensive experiments and analysis clearly show the effectiveness of the proposed approach.

Content-based image retrieval is nowadays one of the possible and promising solutions to manage image databases effectively. However, with the large number of images, there still exists a great discrepancy between the users’ expectations (accuracy and efficiency) and the real performance in image retrieval. In this work, new optimization strategies are proposed on vocabulary tree building, retrieval, and matching methods. More precisely, a new clustering strategy combining classification and conventionalK-Means method is firstly redefined. Then a new matching technique is built to eliminate the error caused by large-scaled scale-invariant feature transform (SIFT). Additionally, a new unit mechanism is proposed to reduce the cost of indexing time. Finally, the numerical results show that excellent performances are obtained in both accuracy and efficiency based on the proposed improvements for image retrieval.