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.     

Bovidae-based gelatin: Extractions method,physicochemical and functional properties,applications, and future trends

Gelatin is one of the most important multifunctional biopolymers and is widely used as an essential ingredient in food, pharmaceutical, and cosmetics. Porcine gelatin is regarded as the leading source of gelatin globally then followed by bovine gelatin. Porcine sources are favored over other sources since they are less expensive. However, porcine gelatin is religiously prohibited to be consumed by Muslims and the Jewish community. It is predicted that the global demand for gelatin will increase significantly in the future. Therefore, a sustainable source of gelatin with efficient production and free of disease transmission must be developed. The highest quality of Bovidae-based gelatin (BG) was acquired through alkaline pretreatment, which displayed excellent physicochemical and rheological properties. The utilization of mammalian- and plant-based enzyme significantly increased the gelatin yield. The emulsifying and foaming properties of BG also showed good stability when incorporated into food and pharmaceutical products. Manipulation of extraction conditions has enabled the development of custom-made gelatin with desired properties. This review highlighted the various modifications of extraction and processing methods to improve the physicochemical and functional properties of Bovidae-based gelatin. An in-depth analysis of the crucial stage of collagen breakdown is also discussed, which involved acid, alkaline, and enzyme pretreatment, respectively. In addition, the unique characteristics and primary qualities of BG including protein content, amphoteric property, gel strength, emulsifying and viscosity properties, and foaming ability were presented. Finally, the applications and prospects of BG as the preferred gelatin source globally were outlined.     

Noncentrosymmetric Tetrel Pnictides RuSi4P4 and IrSi3P3: Nonlinear Optical Materials with Outstanding Laser Damage Threshold

Noncentrosymmetric (NCS) tetrel pnictides have recently generated interest as nonlinear optical (NLO) materials due to their second harmonic generation (SHG) activity and large laser damage threshold (LDT). Herein nonmetal-rich silicon phosphides RuSi₄P₄ and IrSi₃P₃ are synthesized and characterized. Their crystal structures are reinvestigated using single crystal X-ray diffraction and ²⁹Si and ³¹P magic angle spinning NMR. In agreement with previous report RuSi₄P₄ crystallizes in NCS space group P1, while IrSi₃P₃ is found to crystallize in NCS space group Cm, in contrast with the previously reported space group C2. A combination of DFT calculations and diffuse reflectance measurements reveals RuSi₄P₄ and IrSi₃P₃ to be wide bandgap (E_g) semiconductors, E_g = 1.9 and 1.8 eV, respectively. RuSi₄P₄ and IrSi₃P₃ outperform the current state-of-the-art infrared SHG material, AgGaS₂, both in SHG activity and laser inducer damage threshold. Due to the combination of high thermal stabilities (up to 1373 K), wide bandgaps (≈2 eV), NCS crystal structures, strong SHG responses, and large LDT values, RuSi₄P₄ and IrSi₃P₃ are promising candidates for longer wavelength NLO materials.     

Systemic Inflammation and the Breakdown of Intestinal Homeostasis Are Key Events in Chronic Spinal Cord Injury Patients

Our aim was to investigate the subset distribution and function of circulating monocytes, proinflammatory cytokine levels, gut barrier damage, and bacterial translocation in chronic spinal cord injury (SCI) patients. Thus, 56 SCI patients and 28 healthy donors were studied. The levels of circulating CD14^+highCD16⁻, CD14^+highCD16⁺, and CD14^+lowCD16⁺ monocytes, membrane TLR2, TLR4, and TLR9, phagocytic activity, ROS generation, and intracytoplasmic TNF-α, IL-1, IL-6, and IL-10 after lipopolysaccharide (LPS) stimulation were analyzed by polychromatic flow cytometry. Serum TNF-α, IL-1, IL-6 and IL-10 levels were measured by Luminex and LPS-binding protein (LBP), intestinal fatty acid-binding protein (I-FABP) and zonulin by ELISA. SCI patients had normal monocyte counts and subset distribution. CD14^+highCD16⁻ and CD14^+highCD16⁺ monocytes exhibited decreased TLR4, normal TLR2 and increased TLR9 expression. CD14^+highCD16⁻ monocytes had increased LPS-induced TNF-α but normal IL-1, IL-6, and IL-10 production. Monocytes exhibited defective phagocytosis but normal ROS production. Patients had enhanced serum TNF-α and IL-6 levels, normal IL-1 and IL-10 levels, and increased circulating LBP, I-FABP, and zonulin levels. Chronic SCI patients displayed impaired circulating monocyte function. These patients exhibited a systemic proinflammatory state characterized by enhanced serum TNF-α and IL-6 levels. These patients also had increased bacterial translocation and gut barrier damage.     

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.     

Centimeter-scale low-damage micromachining on single-crystal 4H–SiC substrates using a femtosecond laser with square-shaped Flat-Top focus spots

Femtosecond (fs) lasers have been proved to be reliable tools for high-precision and high-quality micromachining of ceramic materials. Nevertheless, fs laser processing using a single-mode beam with a Gaussian intensity distribution is difficult to obtain large-area flat and uniform processed surfaces. In this study, we utilize a customized diffractive optical element (DOE) to redistribute the laser pulse energy from Gaussian to square-shaped Flat-Top profile to realize centimeter-scale low-damage micromachining on single-crystal 4H–SiC substrates. We systematically investigated the effects of processing parameters on the changes in surface morphology and composition, and an optimal processing strategy was provided. Mechanisms of the formation of surface nanoparticles and the removal of surface micro-burrs were discussed. We also examined the distribution of subsurface defects caused by fs laser processing by removing a thin surface layer with a certain depth through chemical mechanical polishing (CMP). Our results show that laser-induced periodic surface structures (LIPSSs) covered by fine SiO₂ nanoparticles form on the fs laser-processed areas. Under optimal parameters, the redeposition of SiO₂ nanoparticles can be minimized, and the surface roughness Sa of processed areas reaches 120 ± 8 nm after the removal of a 10 μm thick surface layer. After the laser processing, micro-burrs on original surfaces are effectively removed, and thus the average profile roughness Rz of 2 mm long surface profiles decreases from 920 ± 120 nm to 286 ± 90 nm. No visible micro-pits can be found after removing ~1 μm thick surface layer from the laser-processed substrates.     

基于面元素重排的三维网格模型数据隐藏算法

目的 为了解决目前三维数据隐藏算法不能兼顾无失真和盲提取的问题，提出一种新的完全无失真的三维网格模型数据隐藏盲算法。方法 首先使用混沌逻辑映射选择嵌入与提取模式，保证数据的安全性。然后利用面元素重排，完全不会造成三维模型失真的性质，通过不同嵌入模式规则对三角面元素进行重排，以嵌入秘密数据。接收端则可根据相应的提取模式规则提取秘密数据。结果 仿真结果与分析表明，该算法不会对三维模型造成任何失真，嵌入容量为每顶点2比特，且能抵抗仿射变换攻击、噪声攻击和平滑攻击等。结论 这种三维数据隐藏盲算法无失真，容量大、安全性高、鲁棒性强，适用于三维载体不容修改的情形，如军事、医学、秘密通信和版权保护等。     

The Age-Sensitive Efficacy of Calorie Restriction on Mitochondrial Biogenesis and mtDNA Damage in Rat Liver

Calorie restriction (CR) is the most efficacious treatment to delay the onset of age-related changes such as mitochondrial dysfunction. However, the sensitivity of mitochondrial markers to CR and the age-related boundaries of CR efficacy are not fully elucidated. We used liver samples from ad libitum-fed (AL) rats divided in: 18-month-old (AL-18), 28-month-old (AL-28), and 32-month-old (AL-32) groups, and from CR-treated (CR) 28-month-old (CR-28) and 32-month-old (CR-32) counterparts to assay the effect of CR on several mitochondrial markers. The age-related decreases in citrate synthase activity, in TFAM, MFN2, and DRP1 protein amounts and in the mtDNA content in the AL-28 group were prevented in CR-28 counterparts. Accordingly, CR reduced oxidative mtDNA damage assessed through the incidence of oxidized purines at specific mtDNA regions in CR-28 animals. These findings support the anti-aging effect of CR up to 28 months. Conversely, the protein amounts of LonP1, Cyt c, OGG1, and APE1 and the 4.8 Kb mtDNA deletion content were not affected in CR-28 rats. The absence of significant differences between the AL-32 values and the CR-32 counterparts suggests an age-related boundary of CR efficacy at this age. However, this only partially curtails the CR benefits in counteracting the generalized aging decline and the related mitochondrial involvement.