Tabular data: Deep learning is not all you need

A key element in solving real-life data science problems is selecting the types of models to use. Tree ensemble models (such as XGBoost) are usually recommended for classification and regression problems with tabular data. However, several deep learning models for tabular data have recently been proposed, claiming to outperform XGBoost for some use cases. This paper explores whether these deep models should be a recommended option for tabular data by rigorously comparing the new deep models to XGBoost on various datasets. In addition to systematically comparing their performance, we consider the tuning and computation they require. Our study shows that XGBoost outperforms these deep models across the datasets, including the datasets used in the papers that proposed the deep models. We also demonstrate that XGBoost requires much less tuning. On the positive side, we show that an ensemble of deep models and XGBoost performs better on these datasets than XGBoost alone.     

基于VMD和BSA-KELM的高陡边坡位移预测模型研究

边坡位移的时间序列曲线存在复杂的非线性特性,传统的预测模型精度不足以满足预测要求。为此提出了基于变分模态分解的鸟群优化-核极限学习机的预测模型,并用于河北省某水泥厂的边坡位移预测。该方法首先采用VMD把边坡位移序列分解为一系列的有限带宽的子序列,再对各子序列分别采用相空间重构并用核极限学习机预测,采用鸟群算法优化相空间重构的嵌入维度和KELM中惩罚系数和核参数三个数值,以取得最优预测模型。最后将各个子序列预测值叠加,得到边坡位移的最终预测值。结果表明：和KELM、BSA-KELM、EEMD-BSA-KELM模型相比,基于VMD的BSA-KELM预测精度更高,为边坡位移的预测提供一种有效的方法。     

基于机器视觉的轮胎表面缺陷检测系统的研究与应用

在传统的轮胎表面缺陷依靠人工检测,存在劳动强度高、受人的主观影响大以及效率低下的问题。针对这一现象,研究了一种基于机器视觉的轮胎表面缺陷3D检测系统。该系统依靠机器视觉系统获取检测轮胎的表面图像,然后创建3D模型、判定缺陷类型,最终实现实时自动预警,为轮胎生产商提供一种自动化检测方案。系统集成了先进的技术、软件和工具,配套的信息管控系统可以对轮胎型号和生产数据进行采集、存储、分析,以便在生产过程中实现更高效、更可靠的质量控制,具有较高的实际应用推广价值。     

Learn decision trees with deep visual primitives

In this paper, we strive to propose a self-interpretable framework, termed PrimitiveTree, that incorporates deep visual primitives condensed from deep features with a conventional decision tree, bridging the gap between deep features extracted from deep neural networks (DNNs) and trees’ transparent decision-making processes. Specifically, we utilize a codebook, which embeds the continuous deep features into a finite discrete space (deep visual primitives) to distill the most common semantic information. The decision tree adopts the spatial location information and the mapped primitives to present the decision-making process of the deep features in a tree hierarchy. Moreover, the trained interpretable PrimitiveTree can inversely explain the constituents of the deep features, highlighting the most critical and semantic-rich image patches attributing to the final predictions of the given DNN. Extensive experiments and visualization results validate the effectiveness and interpretability of our method.     

Enhanced wide-activated residual network for efficient and accurate image deblocking

To save bandwidth and storage space as well as speed up data transmission, people usually perform lossy compression on images. Although the JPEG standard is a simple and effective compression method, it usually introduces various visually unpleasing artifacts, especially the notorious blocking artifacts. In recent years, deep convolutional neural networks (CNNs) have seen remarkable development in compression artifacts reduction. Despite the excellent performance, most deep CNNs suffer from heavy computation due to very deep and wide architectures. In this paper, we propose an enhanced wide-activated residual network (EWARN) for efficient and accurate image deblocking. Specifically, we propose an enhanced wide-activated residual block (EWARB) as basic construction module. Our EWARB gives rise to larger activation width, better use of interdependencies among channels, and more informative and discriminative non-linearity activation features without more parameters than residual block (RB) and wide-activated residual block (WARB). Furthermore, we introduce an overlapping patches extraction and combination (OPEC) strategy into our network in a full convolution way, leading to large receptive field, enforced compatibility among adjacent blocks, and efficient deblocking. Extensive experiments demonstrate that our EWARN outperforms several state-of-the-art methods quantitatively and qualitatively with relatively small model size and less running time, achieving a good trade-off between performance and complexity.     

Learning shape and texture progression for young child face aging

Face aging (FA) for young faces refers to rendering the aging faces at target age for an individual, generally under 20s, which is an important topic of facial age analysis. Unlike traditional FA for adults, it is challenging to age children with one deep learning-based FA network, since there are deformations of facial shapes and variations of textural details. To alleviate the deficiency, a unified FA framework for young faces is proposed, which consists of two decoupled networks to apply aging image translation. It explicitly models transformations of geometry and appearance using two components: GD-GAN, which simulates the Geometric Deformation using Generative Adversarial Network; TV-GAN, which simulates the Textural Variations guided by the age-related saliency map. Extensive experiments demonstrate that our method has advantages over the state-of-the-art methods in terms of synthesizing visually plausible images for young faces, as well as preserving the personalized features.     

Structural Aspects and Prediction of Calmodulin-Binding Proteins

Calmodulin (CaM) is an important intracellular protein that binds Ca²⁺ and functions as a critical second messenger involved in numerous biological activities through extensive interactions with proteins and peptides. CaM’s ability to adapt to binding targets with different structures is related to the flexible central helix separating the N- and C-terminal lobes, which allows for conformational changes between extended and collapsed forms of the protein. CaM-binding targets are most often identified using prediction algorithms that utilize sequence and structural data to predict regions of peptides and proteins that can interact with CaM. In this review, we provide an overview of different CaM-binding proteins, the motifs through which they interact with CaM, and shared properties that make them good binding partners for CaM. Additionally, we discuss the historical and current methods for predicting CaM binding, and the similarities and differences between these methods and their relative success at prediction. As new CaM-binding proteins are identified and classified, we will gain a broader understanding of the biological processes regulated through changes in Ca²⁺ concentration through interactions with CaM.     

Generating Questions Based on Semi-Automated and End-to-End Neural Network

With the emergence of large-scale knowledge base, how to use triple information to generate natural questions is a key technology in question answering systems. The traditional way of generating questions require a lot of manual intervention and produce lots of noise. To solve these problems, we propose a joint model based on semi-automated model and End-to-End neural network to automatically generate questions. The semi-automated model can generate question templates and real questions combining the knowledge base and center graph. The End-to-End neural network directly sends the knowledge base and real questions to BiLSTM network. Meanwhile, the attention mechanism is utilized in the decoding layer, which makes the triples and generated questions more relevant. Finally, the experimental results on SimpleQuestions demonstrate the effectiveness of the proposed approach.     

Effects of Winding Attachment Positions on Output Characteristics of Flux‐Modulating Synchronous Machines

The flux‐modulating synchronous machine (FMSM) is a new type of multipole SM with nonoverlapping concentrated armature and field windings on the stator. This paper compares the output characteristics of two FMSMs through finite element analysis (FEA) and experiments. In both of the FMSMs, the attachment positions of the armature and field windings are swapped. To determine the reason for the discrepancies in their output characteristics, unsaturated inductances were calculated using a d‐‐q equivalent circuit. In addition, the calculated results of the inductances were confirmed through a visualization of the leakage fluxes using FEA. The results of the study show that the synchronous inductance can be reduced by attaching the armature winding to the air‐gap side of the stator teeth and that the reduction leads to an increase in output power.     

基于神经网络和遗传算法的锭子弹性管性能优化

为得到减振弹性管对下锭胆的支承弹性和锭子高速运动下的稳定性等性能的最优匹配效率,依据减振弹性管的等效抗弯刚度及底部等效刚度系数公式,利用MatLab数值分析软件构建弹性管抗弯刚度和底部挠度数学模型。首先,结合Isight优化软件基于径向基神经网络构建其近似模型,且使精度达到可接受水平,并以模型的关键结构参数弹性模量、螺距、槽宽、壁厚为设计变量,结合遗传算法对弹性管抗弯刚度和底部挠度进行多目标优化设计,得到Pareto最优解集和Pareto前沿图,确定出减振弹性管结构工艺参数的优化方案。通过对优化数据进行分析发现,该方案在保证减振弹性管弹性的同时,其底部振幅明显减弱。