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.     

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.     

基准平面垂直断面法在爆破漏斗试验中的应用

系统阐述了基准平面垂直断面法在爆破漏斗试验中测量爆破漏斗体积的基本原理,并将隧道激光断面仪应用于金厂河矿1 750 m水平15^#采场底部切割巷道爆破漏斗试验爆破漏斗体积测量中。通过与传统体重法等计算法所得漏斗体积分析比较,结果表明基于隧道激光断面仪与3D Mine软件分析的基准平面垂直断面法实用性强、操作方便、结果直观可靠,达到试验预期目的。     

不同段数爆破地震波的反应谱分析

为了研究段数对反应谱特性的影响,基于某石方控制爆破工程爆破振动实测数据,对不同段数爆破振动信号进行了反应谱分析。首先,利用实测的爆破振动速度信号采用直接微分法获得了加速度信号,并利用EEMD分解对加速度信号进行低通滤波去噪处理,获得了准确清晰的加速度曲线。然后,利用精确法求得了不同段数下爆破振动信号的速度反应谱和标准速度反应谱。分析结果表明:不同段数的爆破振动质点峰值速度与速度反应谱的峰值速度并不存在对应关系,因此分段数的选择应综合考虑结构对爆破振动的动态响应。     

立柱加固型框架大楼的爆破拆除

采用定向控制爆破技术拆除立柱加固型7层框架大楼。为了彻底炸毁加固立柱,确保大楼顺利定向倾倒,通过多次爆破试验确定了炸药单耗、布孔参数和装药结构。为了控制大楼塌落时的触地震动,采取了秒差分区爆破、空中解体、铺垫缓冲层和开挖减震沟等技术措施。爆破过程中进行了震动监测。此外还介绍了起爆顺序、安全防护措施及爆破结果。     

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。     

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。     

An experiential account of phantom vibration syndrome

A small handful of recent studies have addressed a phenomenon known as “phantom vibration syndrome”. This refers to when phone users perceive their device to vibrate, indicating that a call or text is incoming, when in fact the phone did not vibrate at all. Though these studies show that most users do not find phantom vibration hallucinations to be very bothersome, they also find that a large majority of users experience this phenomenon. This paper explores what the striking prevalence of phantom vibration syndrome means for our contemporary relationships with technology. I begin with a review of the theories purporting to explain these data, which largely rely on particular understandings of the brain. Next I develop an alternative theory of phantom vibration syndrome based on insights from the philosophical tradition of phenomenology. This account considers the ways users develop bodily and perceptual habits regarding how the phone is understood and used. By critically contrasting these different theories, we can refine our questions about what the high prevalence of phantom vibration syndrome implies about our contemporary technological situation.     

Anti‐Sway Crane Control Considering Wind Disturbance and Container Mass

A method for estimating the sway angle using an observer has already been proposed. The state observer estimates the sway angle accurately and must use the detected sway angle value. However, the estimated sway angle has an error owing to rope length error, friction force, and wind. Moreover, the container mass cannot be determined, and therefore the observer parameter is not suitable. We already proposed robust antisway control for overcoming rope length error without adding a new sensor. Further, we designed a friction disturbance observer to cancel out the influence of the friction force. In this paper, we first propose a container mass estimation method when a crane system performs rolling up control. The observer parameter can be selected using the estimated mass value. Second, in crane parallel shift control, we propose a robust antisway control even when there is a wind disturbance. We design a wind disturbance observer and propose a wind disturbance estimator to separate the friction observer output from the wind disturbance observer output. We confirm through experiments that the proposed method can reduce vibration.