Search

In this paper, we describe our solution to predict student STEM career choices during the 2017 ASSISTments Datamining Competition. We built a machine learning system that automatically reformats the data set, generates new features and prunes redundant ones, and performs model and feature selection. We designed the system to automatically find a model that optimizes prediction performance, yet the final model is a simple logistic regression that allows researchers to discover important features and study their effects on STEM career choices. We also compared our method to other methods, which revealed that the key to good prediction is proper feature enrichment in the beginning stage of the data analysis, while feature selection in a later stage allows a simpler final model.

The pomegranate fruit is valued for its nutritional and medicinal properties, and the composition and content of primary and secondary metabolites are the main factors impacting its nutritional and medicinal properties. However, a deep understanding of metabolites in different parts of fruit is still lacking. Here, the peel, aril, and seed of mature pomegranate fruits were analyzed separately to compare metabolic component differences using UPLC/MS–MS. A total of 858 metabolites belonging to 11 classes were identified, of which flavonoids, such as delphinidin‐3‐O‐glucoside and cyanidin‐3‐O‐glucoside; tannins, such as ellagic acid and punicalin; and terpenoids, such as corosolic acid and madasiatic acid, were upregulated in the peel. Lipids, such as punicic acid, methyl linolenate, and linoleic acid; alkaloids, such as indole and choline; nucleotides and derivatives mainly including 2‐deoxyribose‐1‐phosphate and 9‐(arabinosyl)‐hypoxanthine, were upregulated in seeds. Phenolic acids, such as 1‐O‐galloyl‐4,6‐(S)‐HHDP‐β‐D‐glucose and 1,7‐di‐O‐galloyl‐D‐sedoheptulose, and flavonoids, such as cyanidin‐3‐O‐glucoside, cyanidin‐3‐O‐(2″‐O‐xylosyl) galactoside, and delphinidin‐3‐O‐glucoside, were upregulated in aril. The flavone and flavonol biosynthesis (ko00944) pathways were significantly enriched between the peel and seed, as were the anthocyanin biosynthesis (ko00944) pathways between the aril and seed and the flavonoid biosynthesis (ko00941) pathways between the peel and aril. Additionally, functional antioxidants, such as 10,16‐dihydroxypalmitic acid, 3‐O‐methylellagic acid, and 3,3’‐O‐dimethylellagic acid, were first identified in pomegranate fruits. Our results revealed the composition and abundance of primary and secondary metabolites in pomegranate fruit, which can lay the foundation for further elucidation of its nutritional and medicinal properties. [ABSTRACT FROM AUTHOR]

For the current coal mine directional drilling MWD equipment and system are independent of each other, resulting in different forms of MWD data at the bottom of the hole, forming data islands; Based on the B/S system architecture mode, by comparing the measurement while drilling mode and measurement data format, the requirement module of data comprehensive acquisition system is analyzed; the background database of the integrated collection system is set up to develop the development of the integrated collection system of directional drilling while drilling data in coal mine. The verification shows that the data acquisition system can meet the unified collection and processing of various MWD data, the overall analysis and evaluation function, and achieve real-time data upload. It provides data network transmission guarantee for directional drilling data supervision platform in coal mine, and improves the intelligent level of coal mine drilling.

Fluorite and calcite have similar surface properties and natural floatability, so their flotation separation has always been a problem faced by the beneficiation industry. The key to flotation separation is the choice of depressants. Sodium hexametaphosphate (SHMP) has a good effect on fluorite calcite selective inhibition. In this paper, the effects of Zn2+ on the selective inhibition of SHMP in the flotation process of fluorite and calcite were studied through single mineral and artificial mixed mineral flotation experiments. Solution chemical calculation, X-ray photoelectron spectroscopy (XPS), Fourier Transform Infrared spectroscopy (FT-IR) and Time of Flight Secondary Ion Mass Spectrometry (ToF-SIMS) analyses investigated the mechanism of action of Zn2+, which had the most significant negative effect on the selective inhibition of SHMP. The results show that the main components of SHMP inhibiting minerals are HPO42- and H2PO4-, which can react with Ca active sites on the mineral surface to form hydrophilic Ca(H2PO4)2 and CaHPO4, while Zn2+ The presence of HPO42- in solution resulted in the formation of stable ZnHPO4 complexes, thereby weakening the inhibitory effect of SHMP on minerals. [ABSTRACT FROM AUTHOR]

Video highlight detection (VHD) has emerged as a pressing task due to the unprecedentedly increasing amount of video data, such as those from e-commerce live-broadcasting platforms. Many approaches focus on exploiting text data, in the form of video description or time-sync comments, to facilitate the VHD task. Despite the promising results, they have largely overlooked the noises inherent in the text data and have mostly relied on isolating the feature of text and video. In this paper, we introduce a novel model to handle VHD, termed Coevolution Network (CoEvo-Net), that allows us to account for joint learning of the language and video features explicitly via a coevolution paradigm, in which features from the two data modalities progressively refine each other. This is achieved by a dedicated CoEvo-Cell that takes language and video together as inputs, extracts cross-modality, and filters the undesired parts of the input, such as words in a sentence. Furthermore, we release a large-scale dataset of e-commerce for VHD, in which each video is coupled with a sentence for description, to benchmark the sentence-based VHD approaches. Extensive experiments on the released dataset demonstrate that CoEvo-Net achieves state-of-the-art performance. Our dataset and code will be made publicly available. [ABSTRACT FROM AUTHOR]

Existing wideband beampattern synthesis methods usually require multiple beamformers, each corresponding to one frequency bin, which results in excessive resource consumption in engineering practice. To alleviate the resource consumption of wideband array beamforming, we propose a novel time-domain wideband digital beamformer that can control the beam shape over the whole bandwidth for interference mitigation by using only one set of amplitude–phase weights and integer time delay filters. To tackle the resultant optimization problem, two effective algorithms are introduced, and both can solve the problem within polynomial time. One is an alternating optimization algorithm that decomposes the original problem into multiple tractable subproblems iteratively. The other is the convex approximation algorithm that transforms the original problem into a series of second-order cone programming problems iteratively. The two algorithms exhibit their respective advantages in terms of convergence and computational complexity. Extensive numerical examples are presented to evaluate the proposed time-domain wideband beamforming strategy, highlighting that it can form a deep notch in any interested spatial–spectral region to suppress the strong interferences. [ABSTRACT FROM AUTHOR]