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.     

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。     

A new reverse reduce-error ensemble pruning algorithm

Although greedy algorithms possess high efficiency, they often receive suboptimal solutions of the ensemble pruning problem, since their exploration areas are limited in large extent. And another marked defect of almost all the currently existing ensemble pruning algorithms, including greedy ones, consists in: they simply abandon all of the classifiers which fail in the competition of ensemble selection, causing a considerable waste of useful resources and information. Inspired by these observations, an interesting greedy Reverse Reduce-Error (RRE) pruning algorithm incorporated with the operation of subtraction is proposed in this work. The RRE algorithm makes the best of the defeated candidate networks in a way that, the Worst Single Model (WSM) is chosen, and then, its votes are subtracted from the votes made by those selected components within the pruned ensemble. The reason is because, for most cases, the WSM might make mistakes in its estimation for the test samples. And, different from the classical RE, the near-optimal solution is produced based on the pruned error of all the available sequential subensembles. Besides, the backfitting step of RE algorithm is replaced with the selection step of a WSM in RRE. Moreover, the problem of ties might be solved more naturally with RRE. Finally, soft voting approach is employed in the testing to RRE algorithm. The performances of RE and RRE algorithms, and two baseline methods, i.e., the method which selects the Best Single Model (BSM) in the initial ensemble, and the method which retains all member networks of the initial ensemble (ALL), are evaluated on seven benchmark classification tasks under different initial ensemble setups. The results of the empirical investigation show the superiority of RRE over the other three ensemble pruning algorithms.     

Chemical-Shift Perturbations Reflect Bile Acid Binding to Norovirus Coat Protein: Recognition Comes in Different Flavors

Bile acids have been reported as important cofactors promoting human and murine norovirus (NoV) infections in cell culture. The underlying mechanisms are not resolved. Through the use of chemical shift perturbation (CSP) NMR experiments, we identified a low-affinity bile acid binding site of a human GII.4 NoV strain. Long-timescale MD simulations reveal the formation of a ligand-accessible binding pocket of flexible shape, allowing the formation of stable viral coat protein–bile acid complexes in agreement with experimental CSP data. CSP NMR experiments also show that this mode of bile acid binding has a minor influence on the binding of histo-blood group antigens and vice versa. STD NMR experiments probing the binding of bile acids to virus-like particles of seven different strains suggest that low-affinity bile acid binding is a common feature of human NoV and should therefore be important for understanding the role of bile acids as cofactors in NoV infection.     

Expression of Main Toll-Like Receptors in Patients with Different Types of Colorectal Polyps and Their Relationship with Gut Microbiota

Abnormal activation of Toll-like receptor (TLRs) signaling can result in colon cancer development. The aim of this study was to investigate the expression of important TLRs in different histological types of colorectal polyps and evaluate their relationship with intestinal microbiota. The expression levels of TLR2, 3, 4, and 5 were analyzed in intestinal biopsy specimens of 21 hyperplastic polyp (HP), 16 sessile serrated adenoma (SSA), 29 tubular adenoma (TA), 21 villous/tubulovillous (VP/TVP) cases, and 31 normal controls. In addition, selected gut bacteria including Streptococcus bovis, Enterococcus faecalis, Enterotoxigenic Bacteroides fragilis (ETBF), Fusobacterium nucleatum, Porphyromonas spp., Lactobacillus spp., Roseburia spp., and Bifidobacterium spp. were quantified in fecal samples using absolute qRT PCR, and, finally, the association between TLRs and these gut microbiota- was evaluated by Spearman’s correlation coefficient. Higher expression of TLR2 and TLR4 in VP/TVP and TA, and lower expression levels of TLR3 and TLR5 in all type of polyps were observed. The differences in TLR expression patterns was not only dependent on the histology, location, size, and dysplasia grade of polyps but also related to the intestinal microbiota patterns. TLR2 and TLR4 expression was directly associated with the F. nucleatum, E. faecalis, S. bovis, Porphyromonas, and inversely to Bifidobacterium, Lactobacillus, and Roseburia quantity. Furthermore, TLR3 and TLR5 expression was directly associated with Bifidobacterium, Roseburia, and Lactobacillus quantity. Our results suggest a possible critical role of TLRs during colorectal polyp progression. An abnormal regulation of TLRs in relation to gut microbial quantity may contribute to carcinogenesis.     

Specific emitter identification for satellite communication using probabilistic neural networks

Electromagnetic signal emitted by satellite communication (satcom) transmitters are used to identify specific individual uplink satcom terminals sharing the common transponder in real environment, which is known as specific emitter identification (SEI) that allows for early indications and warning (I&W) of the targets carrying satcom furnishment and furthermore the real time electromagnetic situation awareness in military operations. In this paper, the authors are the first to propose the identification of specific transmitters of satcom by using probabilistic neural networks (PNN) to reach the goal of target recognition. We have been devoted to the examination by exploring the feasibility of utilizing the Hilbert transform to signal preprocessing, applying the discrete wavelet transform to feature extraction, and employing the PNN to perform the classification of stationary signals. There are a total of 1000 sampling time series with binary phase shift keying (BPSK) modulation originated by five types of satcom transmitters in the test. The established PNNs classifier implements the data testing and finally yields satisfactory accuracy at 8 dB(±1 dB) carrier to noise ratio, which indicates the feasibility of our method, and even the keen insight of its application in military.     

Supramolecular Zn(II)-Dipicolylamine-Azobenzene-Aminocyclodextrin-ATP Complex: Design and ATP Recognition in Water

Cyclodextrins (CyDs) are water-soluble host molecules possessing a nanosized hydrophobic cavity. In the realm of molecular recognition, this cavity is used not only as a recognition site but also as a reaction medium, where a hydrophobic sensor recognizes a guest molecule. Based on the latter concept, we have designed a novel supramolecular sensing system composed of Zn(II)-dipicolylamine metal complex-based azobenzene (1-Zn) and 3A-amino-3A-deoxy-(2AS,3AS)-γ-cyclodextrin (3-NH₂-γ-CyD) for sensing adenosine-5′-triphosphate (ATP). 1-Zn showed redshifts in the UV-Vis spectra and induced circular dichroism (ICD) only when both ATP and 3-NH₂-γ-CyD were present. Calculations of equilibrium constants indicated that the amino group of 3-NH₂-γ-CyD was involved in the formation of supramolecular 1-Zn/3-NH₂-γ-CyD/ATP. The Job plot of the ICD spectral response revealed that the stoichiometry of 1-Zn/3-NH₂-γ-CyD/ATP was 2:1:1. The pH effect was examined and 1-Zn/3-NH₂-γ-CyD/ATP was most stable in the neutral condition. The NOESY spectrum suggested the localization of 1-Zn in the 3-NH₂-γ-CyD cavity. Based on the obtained results, the metal coordination interaction of 1-Zn and the electrostatic interaction of 3-NH₂-γ-CyD were found to take place for ATP recognition. The “reaction medium approach” enabled us to develop a supramolecular sensing system that undergoes multi-point interactions in water. This study is the first step in the design of a selective sensing system based on a good understanding of supramolecular structures.