YOLSO: You Only Look Small Object

Small object detection is challenging and far from satisfactory. Most general object detectors suffer from two critical issues with small objects: (1) Feature extractor based on classification network cannot express the characteristics of small objects reasonably due to insufficient appearance information of targets and a large amount of background interference around them. (2) The detector requires a much higher location accuracy for small objects than for general objects. This paper proposes an effective and efficient small object detector YOLSO to address the above problems. For feature representation, we analyze the drawbacks in previous backbones and present a Half-Space Shortcut(HSSC) module to build a background-aware backbone. Furthermore, a coarse-to-fine Feature Pyramid Enhancement(FPE) module is introduced for layer-wise aggregation at a granular level to enhance the semantic discriminability. For loss function, we propose an exponential L1 loss to promote the convergence of regression, and a focal IOU loss to focus on prime samples with high classification confidence and high IOU. Both of them significantly improves the location accuracy of small objects. The proposed YOLSO sets state-of-the-art results on two typical small object datasets, MOCOD and VeDAI, at a speed of over 200 FPS. In the meantime, it also outperforms the baseline YOLOv3 by a wide margin on the common COCO dataset.     

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.     

Feature selection methods for root-cause analysis among top-level product attributes

Manufacturing companies not only strive to deliver flawless products but also monitor product failures in the field to identify potential quality issues. When product failures occur, quality engineers must identify the root cause to improve any affected product and process. This root-cause analysis can be supported by feature selection methods that identify relevant product attributes, such as manufacturing dates with an increased number of product failures. In this paper, we present different methods for feature selection and evaluate their ability to identify relevant product attributes in a root-cause analysis. First, we compile a list of feature selection methods. Then, we summarize the properties of product attributes in warranty case data and discuss these properties regarding the challenges they pose for machine learning algorithms. Next, we simulate datasets of warranty cases, which emulate these product properties. Finally, we compare the feature selection methods based on these simulated datasets. In the end, the univariate filter information gain is determined to be a suitable method for a wide range of applications. The comparison based on simulated data provides a more general result than other publications, which only focus on a single use case. Due to the generic nature of the simulated datasets, the results can be applied to various root-cause analysis processes in different quality management applications and provide a guideline for readers who wish to explore machine learning methods for their analysis of quality data.     

Understanding the asymmetric perceptions of smartphone security from security feature perspective: A comparative study

Smartphones are being used and relied on by people more than ever before. The open connectivity brings with it great convenience and leads to a variety of risks that cannot be overlooked. Smartphone vendors, security policy designers, and security application providers have put a variety of practical efforts to secure smartphones, and researchers have conducted extensive research on threat sources, security techniques, and user security behaviors. Regrettably, smartphone users do not pay enough attention to mobile security, making many efforts futile. This study identifies this gap between technology affordance and user requirements, and attempts to investigate the asymmetric perceptions toward security features between developers and users, between users and users, as well as between different security features. These asymmetric perceptions include perceptions of quality, perceptions of importance, and perceptions of satisfaction. After scoping the range of smartphone security features, this study conducts an improved Kano-based method and exhaustively analyzes the 245 collected samples using correspondence analysis and importance satisfaction analysis. The 14 security features of the smartphone are divided into four Kano quality types and the perceived quality differences between developers and users are compared. Correspondence analysis is utilized to capture the relationship between the perceived importance of security features across different groups of respondents, and results of importance-satisfaction analysis provide the basis for the developmental path and resource reallocation strategy of security features. This article offers new insights for researchers as well as practitioners of smartphone security.     

基于学科竞赛的中医药类院校程序设计课程教学模式的探索

高素质人才培养是我国可持续发展战略、科教兴国战略以及人才强国战略等多项发展战略的一项基础性工程。本文针对中医药类院校程序设计类课程实践教学模式单一等教学实际，以“学科竞赛”为平台，“赛教结合”为理念，以《C语言程序设计》为例，从现存问题、赛教结合模式的引入、建立实施及其评价机制4个方面展开阐述，旨在提高学生学习积极性和能力。     

Multi-discharge EDM coring of single crystal SiC ingot by electrostatic induction feeding method

A new technique of EDM coring of single crystal silicon carbide (SiC) ingot was proposed in this paper. Currently single crystal SiC devices are still of high cost due to the high cost of bulk crystal SiC material and the difficulty in the fabrication process of SiC. In the manufacturing process of SiC ingot/wafer, localized cracks or defects occasionally occur due to thermal or mechanical causes resulted from fabrication processes which may waste the whole piece of material. To save the part of ingot without defects and maximize the material utilization, the authors proposed EDM coring method to cut out a no defect ingot from a larger diameter ingot which has localized defects. A special experimental setup was developed for EDM coring of SiC ingot in this study and its feasibility and machining performance were investigated. Meanwhile, in order to improve the machining rate, a novel multi-discharge EDM coring method by electrostatic induction feeding was established, which can realize multiple discharges in single pulse duration. Experimental results make it clear that EDM coring of SiC ingot can be carried out stably using the developed experimental setup. Taking advantage of the newly developed multi-discharge EDM method, both the machining speed and surface integrity can be improved.     

Affective matches of fabric and lighting chromaticity

This study investigates the impact of lighting colors on subjective judgments of fabric: in particular, whether the influence of lighting varies depending on fabric types and color combinations. We conducted two visual assessments. In Study 1 (N = 44), eight illuminants and six types of fabric were presented as cloth stimuli. Derived from the literature review, four sets of adjectives (humble-luxurious, cool-warm, old-new, and not preferred-preferred) were used as metrics. In Study 2 (N = 41), five sets of fabric color combination swatches were assessed under lighting conditions that were identical to those of Study 1. Three bipolar scales (ordinary-characterful, classic-modern, and soft-rigid), were employed from factor analysis along with three unipolar scales (luxurious, preferred, harmonious with lighting). The results showed that hue characteristics of lighting and cloth types influenced participants' perceptions of the fabric. Overall, white lighting with 4000 K was the most preferred and luxurious lighting across various types of clothes, while a pinkish white with 4700 K (duv = −0.0127) was the best matched in every color combination. In addition, there were interaction effects between lighting colors, clothes types, and fabric color combinations with regard to each of the perceptual qualities. This study provides empirical evidence for optimally match lighting colors with fabric in the presentation of fabric goods.     

基于梯度提升决策树的车轮轮缘厚度磨耗预测

轮对在列车走行过程中起着导向、承受以及传递载荷的作用，其踏面及轮缘磨耗对地铁列车运行安全性和钢轨的寿命都将产生重要影响。根据地铁列车车轮磨耗机理，分析车轮尺寸数据特点，针对轮缘厚度这一型面参数，基于梯度提升决策树算法构建轮缘厚度磨耗预测模型。在该模型的基础上，任意选取某轮对数据进行验证分析，结果表明：基于梯度提升决策树的轮对磨耗预测模型具有较好的预测精度，可预测出1~6个月的轮缘厚度变化趋势范围，预测时间范围较长，可为地铁维保部门对轮对的维修方式由状态修转为预防修提供指导性建议。     

极限工况下的管网“互联互通”改进方案

在全国天然气管道“主干互联、区域成网”(以下简称“互联互通”)基础格局逐渐形成的背景下,天然气管网规模日益扩大、管道分支和气源增加,并且分布不集中、输送方向可变,使得输气方案更加灵活,可以更好地解决某些地域的供气紧张问题;但受现有站场和设备的限制,暂不能满足某些多线组合极限工况,使得“互联互通”的初衷难以全部实现。为了使得现有的各输气干线在实现“互联互通”之后可以满足更多的多线组合工况,在分析“互联互通”背景下M管网工况变化的基础上,研发了可以进行水力仿真和压气站方案制订的计算软件,并对3种极限工况下的不同输气量情况进行了可行性试算,进而基于试算结果提出了相应的管网改进建议。研究结果表明:(1)经验证,软件计算误差满足要求;(2)在M管道某处增设压气站或在某些输气站场配置压缩机组;(3) M管网改进调整后,可以完成大部分的多线组合极限工况,真正实现“互联互通”的输气方案。结论认为,该研究成果有助于推进全国天然气管网早日实现“互联互通”。     

基于深度学习的秀丽隐杆线虫显微图像分割方法

利用计算机实现自动、准确的秀丽隐杆线虫(C.elegans)的各项形态学参数分析,至关重要的是从显微图像上分割出线虫体态,但由于显微镜下的图像噪声较多,线虫边缘像素与周围环境相似,而且线虫的体态具有鞭毛和其他附着物需要分离,多方面因素导致设计一个鲁棒性的C.elegans分割算法仍然面临着挑战。针对这些问题,提出了一种基于深度学习的线虫分割方法,通过训练掩模区域卷积神经网络(Mask R-CNN)学习线虫形态特征实现自动分割。首先,通过改进多级特征池化将高级语义特征与低级边缘特征融合,结合大幅度软最大损失(LMSL)损失算法改进损失计算;然后,改进非极大值抑制;最后,引入全连接融合分支等方法对分割结果进行进一步优化。实验结果表明,相比原始的Mask R-CNN,该方法平均精确率(AP)提升了4.3个百分点,平均交并比(mIOU)提升了4个百分点。表明所提出的深度学习分割方法能够有效提高分割准确率,在显微图像中更加精确地分割出线虫体。