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.     

用于电弧检测的电力专用SoC设计

针对传统的电弧电路故障检测结果不准确的问题,设计用于电弧检测的SoC系统,并且在55nm工艺下进行流片验证。采用包含两种结构的模数转换器的片上电压源,设计了锁相环以及复位电路,精度最高可达8.67 bit。验证结果表明,本设计可提高电弧检测的准确性。     

Machine learning algorithm selection for windage alteration fault diagnosis of mine ventilation system

Machine learning algorithms have been widely used in mine fault diagnosis. The correct selection of the suitable algorithms is the key factor that affects the fault diagnosis. However, the impact of machine learning algorithms on the prediction performance of mine fault diagnosis models has not been fully evaluated. In this study, the windage alteration faults (WAFs) diagnosis models, which are based on K-nearest neighbor algorithm (KNN), multi-layer perceptron (MLP), support vector machine (SVM), and decision tree (DT), are constructed. Furthermore, the applicability of these four algorithms in the WAFs diagnosis is explored by a T-type ventilation network simulation experiment and the field empirical application research of Jinchuan No. 2 mine. The accuracy of the fault location diagnosis for the four models in both networks was 100%. In the simulation experiment, the mean absolute percentage error (MAPE) between the predicted values and the real values of the fault volume of the four models was 0.59%, 97.26%, 123.61%, and 8.78%, respectively. The MAPE for the field empirical application was 3.94%, 52.40%, 25.25%, and 7.15%, respectively. The results of the comprehensive evaluation of the fault location and fault volume diagnosis tests showed that the KNN model is the most suitable algorithm for the WAFs diagnosis, whereas the prediction performance of the DT model was the second-best. This study realizes the intelligent diagnosis of WAFs, and provides technical support for the realization of intelligent ventilation.     

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.     

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。     

Prediction of Flooding in Packed Liquid-Liquid and High-Pressure Extraction Columns Using a Gaussian Process

Reliable prediction of flooding conditions is needed for sizing and operating packed extraction columns. Due to the complex interplay of physicochemical properties, operational parameters and the packing-specific properties, it is challenging to develop accurate semi-empirical or rigorous models with a high validity range. State of the art models may therefore fail to predict flooding accurately. To overcome this problem, a data-driven model based on Gaussian processes is developed to predict flooding for packed liquid-liquid and high-pressure extraction columns. The optimized Gaussian process for the liquid-liquid extraction column results in an average absolute relative error (AARE) of 15.23 %, whereas the algorithm for the high-pressure extraction column results in an AARE of 13.68 %. Both algorithms can predict flooding curves for different packing geometries and chemical systems precisely.     

基于阶段注意力机制的电力线提取算法

电力系统维护是电力系统稳定运行的重要保障，应用智能算法的无人机电力巡检则为电力系统维护提供便捷。电力线提取是自主电力巡检以及保障飞行器低空飞行安全的关键技术，结合深度学习理论进行电力线提取是电力巡检的重要突破点。本文将深度学习方法用于电力线提取任务，结合电力线图像特点嵌入改进的图像输入策略和注意力模块，提出一种基于阶段注意力机制的电力线提取模型（SA-Unet）。本文提出的SA-Unet模型编码阶段采用阶段输入融合策略（Stage input fusion strategy， SIFS），充分利用图像的多尺度信息减少空间位置信息丢失。解码阶段通过嵌入阶段注意力模块（Stage attention module，SAM）聚焦电力线特征，从大量信息中快速筛选出高价值信息。实验结果表明，该方法在复杂背景的多场景中具有良好的性能。