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.     

Volatile and non-volatile compound profiles of commercial sweet pickled mango and its correlation with consumer preference

Sweet pickled mango named Ma-Muang Bao Chae-Im is a traditional preserved mango from Hat Yai, Thailand. This study investigated (I) volatile and non-volatile compound profiles of commercial Ma-Muang Bao Chae-Im and (II) their relationship to consumer preference. Untargeted metabolomics profiling was performed by gas chromatography-mass quadrupole-time of flight analysis. There were 117 volatile and 44 non-volatile compounds annotated in six commercial brands of Ma-Muang Bao Chae-Im. Furthermore, 46 volatile and 19 non-volatile compounds’ discriminant markers were found by Partial least square discriminant analysis. Among those markers, sorbic and benzoic acid were observed in several brands; moreover, the combination of both compounds altered the volatile profile, especially the ester group. Partial least square regression revealed that overall consumer liking is correlated to 1-heptanol; 1-octanol; acetoin; acetic acid, 2-phenylethyl ester; D-manitol; terpenes and terpenoids, while firmness to sucrose and L-(-)-sorbofuranose. On the other hand, most ester compounds were not related to consumer preference.     

Data fusion and transfer learning empowered granular trust evaluation for Internet of Things

In the Internet of Things (IoT), a huge amount of valuable data is generated by various IoT applications. As the IoT technologies become more complex, the attack methods are more diversified and can cause serious damages. Thus, establishing a secure IoT network based on user trust evaluation to defend against security threats and ensure the reliability of data source of collected data have become urgent issues, in this paper, a Data Fusion and transfer learning empowered granular Trust Evaluation mechanism (DFTE) is proposed to address the above challenges. Specifically, to meet the granularity demands of trust evaluation, time–space empowered fine/coarse grained trust evaluation models are built utilizing deep transfer learning algorithms based on data fusion. Moreover, to prevent privacy leakage and task sabotage, a dynamic reward and punishment mechanism is developed to encourage honest users by dynamically adjusting the scale of reward or punishment and accurately evaluating users’ trusts. The extensive experiments show that: (i) the proposed DFTE achieves high accuracy of trust evaluation under different granular demands through efficient data fusion; (ii) DFTE performs excellently in participation rate and data reliability.     

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.     

Effect of cooking temperature on texture and flavour binding of braised sauce porcine skin

To investigate the effect of cooking temperature (55, 65, 75, 85 and 95 °C) on texture and flavour binding of braised sauce porcine skin (BSPS), sensory acceptance, microstructure and flavour-binding capacity were investigated during the processing of BSPS. Samples cooked at 85 and 95 °C showed better texture and aroma scores. Hardness and chewiness of BSPS were obviously improved at 85 and 95 °C than control group. Collagen structure was significantly destroyed over 85 °C. The porcine skin collagen heated at 85 and 95 °C showed relatively higher flavour-binding capacity than other samples. The improvement of texture of BSPS was mainly attributed to the degradation of collagen. Higher aroma scores of BSPS were related to intense binding abilities with aroma compounds at 85 and 95 °C. Cooking at 85 or 95 °C could be an optimal cooking temperature for BSPS.     

我国水-能源-粮食耦合关系及影响因素

为缓解我国水、能源和粮食资源紧张问题，促进资源可持续利用，构建水-能源-粮食系统，利用耦合协调度模型对我国的30个省（自治区、直辖市）进行测算,并利用空间杜宾模型分析主要影响因素。结果表明：2003—2017年，我国能源、粮食评价[JP]指数高于水资源评价指数，系统综合评价指数逐年递增；大部分省份耦合协调度处于初级协调水平且呈现逐年上升的态势，个别省份耦合协调度濒临失调；耦合协调度空间自相关性较强，虽有明显波动，但是呈现逐年加强的态势；影响耦合协调度的主要因素有从业人口数、固定资产投资额、人均生产总值、人口总数、[JP]文盲人口占比、工业污染排放、城镇化。     

Effect of heat treatment on structural,morphological, dielectric and magnetic properties of Mg–Zn ferrite nanoparticles

Green combustion was used to prepare a ferrite composition of Mg_0.4Zn_0.6Fe₂O₄ using a blend of fresh lemon juice as a natural fuel-reductant. Effect of heat treatment on phase, morphological, dielectric, and humidity sensor properties is discussed. The formation of a cubic spinel ferrite has been established by XRD-diffraction and vibrational spectroscopic studies. The experimental lattice parameter ranges from 8.3721 to 8.3631 Å. The broadening of octahedral band (υ₂) in the vibrational spectra is an identification for the existence of ferrite nanoparticles in various sizes. The typical crystallite size ranges from 10.2 to 36.9 nm. Using micrographs obtained from field-effect scanning electron microscopy (FESEM), researchers observed a spherical-shaped microstructure with agglomerated nanoparticles. Dielectric investigations have shown that the current ferrite composition has typical dielectric dispersion. The highest reported value for saturation magnetization (M_s) in the present study is 33 emu/g. Magnetic behaviour is primarily influenced by magnetocrystalline anisotropy, cation distribution, and crystallite size. The existence of void spaces in the sintered samples, as well as their porous nature, rendered them suitable for humidity sensor applications. Sintered samples have good sensing capability at 900 °C. The current findings are integrated in terms of cation distribution and magnetocrystalline anisotropy, assuming fine size effects of ferrite nanoparticles.     

自适应融合层级特征的混合退化图像复原算法

多种退化类型混合的图像比单一类型的退化图像降质更严重,很难建立精确模型对其复原,研究端到端的神经网络算法是复原的关键.现有的基于操作选择注意力网络的算法(operation-wiseattentionnetwork,OWAN)虽然有一定的性能提升,但是其网络过于复杂,运行较慢,复原图像缺乏高频细节,整体效果也有提升的空间.针对这些问题,提出一种基于层级特征融合的自适应复原算法.该算法直接融合不同感受野分支的特征,增强复原图像的结构;用注意力机制对不同层级的特征进行动态融合,增加模型的自适应性,降低了模型冗余;另外,结合L1损失和感知损失,增强了复原图像的视觉感知效果.在DIV2K,BSD500等数据集上的实验结果表明,该算法无论是在峰值信噪比和结构相似性上的定量分析,还是在主观视觉质量方面,均优于OWAN算法,充分证明了该算法的有效性.     

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.     

中国智能机械制造评价及发展研究

以中国规模以上工业企业数据库为基础，结合在智能制造主要区域调研的结果，筛选出15145家智能制造企业，经同行评议后，生成322家候选企业名单；再由资深产业专家从“开发式创新”和“探索式创新”两个方面去考察候选企业的能力，得到中国智能制造百强排行榜；随后根据行业分类，得到智能机械制造企业排行榜。在概述了智能机械制造上榜企业的基本情况后，着重分析了前20强企业，并提出了中国智能机械制造发展路径和未来的发展趋势。